| 11 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 | #ifndef __LINUX_ERSPAN_H #define __LINUX_ERSPAN_H /* * GRE header for ERSPAN type I encapsulation (4 octets [34:37]) * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |0|0|0|0|0|00000|000000000|00000| Protocol Type for ERSPAN | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * The Type I ERSPAN frame format is based on the barebones IP + GRE * encapsulation (as described above) on top of the raw mirrored frame. * There is no extra ERSPAN header. * * * GRE header for ERSPAN type II and II encapsulation (8 octets [34:41]) * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |0|0|0|1|0|00000|000000000|00000| Protocol Type for ERSPAN | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Sequence Number (increments per packet per session) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Note that in the above GRE header [RFC1701] out of the C, R, K, S, * s, Recur, Flags, Version fields only S (bit 03) is set to 1. The * other fields are set to zero, so only a sequence number follows. * * ERSPAN Version 1 (Type II) header (8 octets [42:49]) * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Ver | VLAN | COS | En|T| Session ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Reserved | Index | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * * ERSPAN Version 2 (Type III) header (12 octets [42:49]) * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Ver | VLAN | COS |BSO|T| Session ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Timestamp | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | SGT |P| FT | Hw ID |D|Gra|O| * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Platform Specific SubHeader (8 octets, optional) * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Platf ID | Platform Specific Info | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Platform Specific Info | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * GRE proto ERSPAN type I/II = 0x88BE, type III = 0x22EB */ #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/skbuff.h> #include <uapi/linux/erspan.h> #define ERSPAN_VERSION 0x1 /* ERSPAN type II */ #define VER_MASK 0xf000 #define VLAN_MASK 0x0fff #define COS_MASK 0xe000 #define EN_MASK 0x1800 #define T_MASK 0x0400 #define ID_MASK 0x03ff #define INDEX_MASK 0xfffff #define ERSPAN_VERSION2 0x2 /* ERSPAN type III*/ #define BSO_MASK EN_MASK #define SGT_MASK 0xffff0000 #define P_MASK 0x8000 #define FT_MASK 0x7c00 #define HWID_MASK 0x03f0 #define DIR_MASK 0x0008 #define GRA_MASK 0x0006 #define O_MASK 0x0001 #define HWID_OFFSET 4 #define DIR_OFFSET 3 enum erspan_encap_type { ERSPAN_ENCAP_NOVLAN = 0x0, /* originally without VLAN tag */ ERSPAN_ENCAP_ISL = 0x1, /* originally ISL encapsulated */ ERSPAN_ENCAP_8021Q = 0x2, /* originally 802.1Q encapsulated */ ERSPAN_ENCAP_INFRAME = 0x3, /* VLAN tag perserved in frame */ }; #define ERSPAN_V1_MDSIZE 4 #define ERSPAN_V2_MDSIZE 8 struct erspan_base_hdr { #if defined(__LITTLE_ENDIAN_BITFIELD) __u8 vlan_upper:4, ver:4; __u8 vlan:8; __u8 session_id_upper:2, t:1, en:2, cos:3; __u8 session_id:8; #elif defined(__BIG_ENDIAN_BITFIELD) __u8 ver: 4, vlan_upper:4; __u8 vlan:8; __u8 cos:3, en:2, t:1, session_id_upper:2; __u8 session_id:8; #else #error "Please fix <asm/byteorder.h>" #endif }; static inline void set_session_id(struct erspan_base_hdr *ershdr, u16 id) { ershdr->session_id = id & 0xff; ershdr->session_id_upper = (id >> 8) & 0x3; } static inline u16 get_session_id(const struct erspan_base_hdr *ershdr) { return (ershdr->session_id_upper << 8) + ershdr->session_id; } static inline void set_vlan(struct erspan_base_hdr *ershdr, u16 vlan) { ershdr->vlan = vlan & 0xff; ershdr->vlan_upper = (vlan >> 8) & 0xf; } static inline u16 get_vlan(const struct erspan_base_hdr *ershdr) { return (ershdr->vlan_upper << 8) + ershdr->vlan; } static inline void set_hwid(struct erspan_md2 *md2, u8 hwid) { md2->hwid = hwid & 0xf; md2->hwid_upper = (hwid >> 4) & 0x3; } static inline u8 get_hwid(const struct erspan_md2 *md2) { return (md2->hwid_upper << 4) + md2->hwid; } static inline int erspan_hdr_len(int version) { if (version == 0) return 0; return sizeof(struct erspan_base_hdr) + (version == 1 ? ERSPAN_V1_MDSIZE : ERSPAN_V2_MDSIZE); } static inline u8 tos_to_cos(u8 tos) { u8 dscp, cos; dscp = tos >> 2; cos = dscp >> 3; return cos; } static inline void erspan_build_header(struct sk_buff *skb, u32 id, u32 index, bool truncate, bool is_ipv4) { struct ethhdr *eth = (struct ethhdr *)skb->data; enum erspan_encap_type enc_type; struct erspan_base_hdr *ershdr; struct qtag_prefix { __be16 eth_type; __be16 tci; } *qp; u16 vlan_tci = 0; u8 tos; __be32 *idx; tos = is_ipv4 ? ip_hdr(skb)->tos : (ipv6_hdr(skb)->priority << 4) + (ipv6_hdr(skb)->flow_lbl[0] >> 4); enc_type = ERSPAN_ENCAP_NOVLAN; /* If mirrored packet has vlan tag, extract tci and * perserve vlan header in the mirrored frame. */ if (eth->h_proto == htons(ETH_P_8021Q)) { qp = (struct qtag_prefix *)(skb->data + 2 * ETH_ALEN); vlan_tci = ntohs(qp->tci); enc_type = ERSPAN_ENCAP_INFRAME; } skb_push(skb, sizeof(*ershdr) + ERSPAN_V1_MDSIZE); ershdr = (struct erspan_base_hdr *)skb->data; memset(ershdr, 0, sizeof(*ershdr) + ERSPAN_V1_MDSIZE); /* Build base header */ ershdr->ver = ERSPAN_VERSION; ershdr->cos = tos_to_cos(tos); ershdr->en = enc_type; ershdr->t = truncate; set_vlan(ershdr, vlan_tci); set_session_id(ershdr, id); /* Build metadata */ idx = (__be32 *)(ershdr + 1); *idx = htonl(index & INDEX_MASK); } /* ERSPAN GRA: timestamp granularity * 00b --> granularity = 100 microseconds * 01b --> granularity = 100 nanoseconds * 10b --> granularity = IEEE 1588 * Here we only support 100 microseconds. */ static inline __be32 erspan_get_timestamp(void) { u64 h_usecs; ktime_t kt; kt = ktime_get_real(); h_usecs = ktime_divns(kt, 100 * NSEC_PER_USEC); /* ERSPAN base header only has 32-bit, * so it wraps around 4 days. */ return htonl((u32)h_usecs); } /* ERSPAN BSO (Bad/Short/Oversized), see RFC1757 * 00b --> Good frame with no error, or unknown integrity * 01b --> Payload is a Short Frame * 10b --> Payload is an Oversized Frame * 11b --> Payload is a Bad Frame with CRC or Alignment Error */ enum erspan_bso { BSO_NOERROR = 0x0, BSO_SHORT = 0x1, BSO_OVERSIZED = 0x2, BSO_BAD = 0x3, }; static inline u8 erspan_detect_bso(struct sk_buff *skb) { /* BSO_BAD is not handled because the frame CRC * or alignment error information is in FCS. */ if (skb->len < ETH_ZLEN) return BSO_SHORT; if (skb->len > ETH_FRAME_LEN) return BSO_OVERSIZED; return BSO_NOERROR; } static inline void erspan_build_header_v2(struct sk_buff *skb, u32 id, u8 direction, u16 hwid, bool truncate, bool is_ipv4) { struct ethhdr *eth = (struct ethhdr *)skb->data; struct erspan_base_hdr *ershdr; struct erspan_md2 *md2; struct qtag_prefix { __be16 eth_type; __be16 tci; } *qp; u16 vlan_tci = 0; u8 gra = 0; /* 100 usec */ u8 bso = 0; /* Bad/Short/Oversized */ u8 sgt = 0; u8 tos; tos = is_ipv4 ? ip_hdr(skb)->tos : (ipv6_hdr(skb)->priority << 4) + (ipv6_hdr(skb)->flow_lbl[0] >> 4); /* Unlike v1, v2 does not have En field, * so only extract vlan tci field. */ if (eth->h_proto == htons(ETH_P_8021Q)) { qp = (struct qtag_prefix *)(skb->data + 2 * ETH_ALEN); vlan_tci = ntohs(qp->tci); } bso = erspan_detect_bso(skb); skb_push(skb, sizeof(*ershdr) + ERSPAN_V2_MDSIZE); ershdr = (struct erspan_base_hdr *)skb->data; memset(ershdr, 0, sizeof(*ershdr) + ERSPAN_V2_MDSIZE); /* Build base header */ ershdr->ver = ERSPAN_VERSION2; ershdr->cos = tos_to_cos(tos); ershdr->en = bso; ershdr->t = truncate; set_vlan(ershdr, vlan_tci); set_session_id(ershdr, id); /* Build metadata */ md2 = (struct erspan_md2 *)(ershdr + 1); md2->timestamp = erspan_get_timestamp(); md2->sgt = htons(sgt); md2->p = 1; md2->ft = 0; md2->dir = direction; md2->gra = gra; md2->o = 0; set_hwid(md2, hwid); } #endif |
| 109 109 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * common UDP/RAW code * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> */ #include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/interrupt.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in6.h> #include <linux/ipv6.h> #include <linux/route.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/icmp.h> #include <net/ipv6.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/transp_v6.h> #include <net/ip6_route.h> #include <net/tcp_states.h> #include <net/dsfield.h> #include <net/sock_reuseport.h> #include <linux/errqueue.h> #include <linux/uaccess.h> static bool ipv6_mapped_addr_any(const struct in6_addr *a) { return ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0); } static void ip6_datagram_flow_key_init(struct flowi6 *fl6, struct sock *sk) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); int oif = sk->sk_bound_dev_if; memset(fl6, 0, sizeof(*fl6)); fl6->flowi6_proto = sk->sk_protocol; fl6->daddr = sk->sk_v6_daddr; fl6->saddr = np->saddr; fl6->flowi6_mark = sk->sk_mark; fl6->fl6_dport = inet->inet_dport; fl6->fl6_sport = inet->inet_sport; fl6->flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label); fl6->flowi6_uid = sk->sk_uid; if (!oif) oif = np->sticky_pktinfo.ipi6_ifindex; if (!oif) { if (ipv6_addr_is_multicast(&fl6->daddr)) oif = np->mcast_oif; else oif = np->ucast_oif; } fl6->flowi6_oif = oif; security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6)); } int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr) { struct ip6_flowlabel *flowlabel = NULL; struct in6_addr *final_p, final; struct ipv6_txoptions *opt; struct dst_entry *dst; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct flowi6 fl6; int err = 0; if (np->sndflow && (np->flow_label & IPV6_FLOWLABEL_MASK)) { flowlabel = fl6_sock_lookup(sk, np->flow_label); if (IS_ERR(flowlabel)) return -EINVAL; } ip6_datagram_flow_key_init(&fl6, sk); rcu_read_lock(); opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt); final_p = fl6_update_dst(&fl6, opt, &final); rcu_read_unlock(); dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; } if (fix_sk_saddr) { if (ipv6_addr_any(&np->saddr)) np->saddr = fl6.saddr; if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { sk->sk_v6_rcv_saddr = fl6.saddr; inet->inet_rcv_saddr = LOOPBACK4_IPV6; if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); } } ip6_sk_dst_store_flow(sk, dst, &fl6); out: fl6_sock_release(flowlabel); return err; } void ip6_datagram_release_cb(struct sock *sk) { struct dst_entry *dst; if (ipv6_addr_v4mapped(&sk->sk_v6_daddr)) return; rcu_read_lock(); dst = __sk_dst_get(sk); if (!dst || !dst->obsolete || dst->ops->check(dst, inet6_sk(sk)->dst_cookie)) { rcu_read_unlock(); return; } rcu_read_unlock(); ip6_datagram_dst_update(sk, false); } EXPORT_SYMBOL_GPL(ip6_datagram_release_cb); int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *daddr, old_daddr; __be32 fl6_flowlabel = 0; __be32 old_fl6_flowlabel; __be16 old_dport; int addr_type; int err; if (usin->sin6_family == AF_INET) { if (ipv6_only_sock(sk)) return -EAFNOSUPPORT; err = __ip4_datagram_connect(sk, uaddr, addr_len); goto ipv4_connected; } if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (usin->sin6_family != AF_INET6) return -EAFNOSUPPORT; if (np->sndflow) fl6_flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK; if (ipv6_addr_any(&usin->sin6_addr)) { /* * connect to self */ if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK), &usin->sin6_addr); else usin->sin6_addr = in6addr_loopback; } addr_type = ipv6_addr_type(&usin->sin6_addr); daddr = &usin->sin6_addr; if (addr_type & IPV6_ADDR_MAPPED) { struct sockaddr_in sin; if (ipv6_only_sock(sk)) { err = -ENETUNREACH; goto out; } sin.sin_family = AF_INET; sin.sin_addr.s_addr = daddr->s6_addr32[3]; sin.sin_port = usin->sin6_port; err = __ip4_datagram_connect(sk, (struct sockaddr *) &sin, sizeof(sin)); ipv4_connected: if (err) goto out; ipv6_addr_set_v4mapped(inet->inet_daddr, &sk->sk_v6_daddr); if (ipv6_addr_any(&np->saddr) || ipv6_mapped_addr_any(&np->saddr)) ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); if (ipv6_addr_any(&sk->sk_v6_rcv_saddr) || ipv6_mapped_addr_any(&sk->sk_v6_rcv_saddr)) { ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &sk->sk_v6_rcv_saddr); if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); } goto out; } if (__ipv6_addr_needs_scope_id(addr_type)) { if (addr_len >= sizeof(struct sockaddr_in6) && usin->sin6_scope_id) { if (!sk_dev_equal_l3scope(sk, usin->sin6_scope_id)) { err = -EINVAL; goto out; } WRITE_ONCE(sk->sk_bound_dev_if, usin->sin6_scope_id); } if (!sk->sk_bound_dev_if && (addr_type & IPV6_ADDR_MULTICAST)) WRITE_ONCE(sk->sk_bound_dev_if, np->mcast_oif); /* Connect to link-local address requires an interface */ if (!sk->sk_bound_dev_if) { err = -EINVAL; goto out; } } /* save the current peer information before updating it */ old_daddr = sk->sk_v6_daddr; old_fl6_flowlabel = np->flow_label; old_dport = inet->inet_dport; sk->sk_v6_daddr = *daddr; np->flow_label = fl6_flowlabel; inet->inet_dport = usin->sin6_port; /* * Check for a route to destination an obtain the * destination cache for it. */ err = ip6_datagram_dst_update(sk, true); if (err) { /* Restore the socket peer info, to keep it consistent with * the old socket state */ sk->sk_v6_daddr = old_daddr; np->flow_label = old_fl6_flowlabel; inet->inet_dport = old_dport; goto out; } reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); out: return err; } EXPORT_SYMBOL_GPL(__ip6_datagram_connect); int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { int res; lock_sock(sk); res = __ip6_datagram_connect(sk, uaddr, addr_len); release_sock(sk); return res; } EXPORT_SYMBOL_GPL(ip6_datagram_connect); int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *uaddr, int addr_len) { DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, uaddr); if (sin6->sin6_family != AF_INET6) return -EAFNOSUPPORT; return ip6_datagram_connect(sk, uaddr, addr_len); } EXPORT_SYMBOL_GPL(ip6_datagram_connect_v6_only); static void ipv6_icmp_error_rfc4884(const struct sk_buff *skb, struct sock_ee_data_rfc4884 *out) { switch (icmp6_hdr(skb)->icmp6_type) { case ICMPV6_TIME_EXCEED: case ICMPV6_DEST_UNREACH: ip_icmp_error_rfc4884(skb, out, sizeof(struct icmp6hdr), icmp6_hdr(skb)->icmp6_datagram_len * 8); } } void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload) { struct ipv6_pinfo *np = inet6_sk(sk); struct icmp6hdr *icmph = icmp6_hdr(skb); struct sock_exterr_skb *serr; if (!np->recverr) return; skb = skb_clone(skb, GFP_ATOMIC); if (!skb) return; skb->protocol = htons(ETH_P_IPV6); serr = SKB_EXT_ERR(skb); serr->ee.ee_errno = err; serr->ee.ee_origin = SO_EE_ORIGIN_ICMP6; serr->ee.ee_type = icmph->icmp6_type; serr->ee.ee_code = icmph->icmp6_code; serr->ee.ee_pad = 0; serr->ee.ee_info = info; serr->ee.ee_data = 0; serr->addr_offset = (u8 *)&(((struct ipv6hdr *)(icmph + 1))->daddr) - skb_network_header(skb); serr->port = port; __skb_pull(skb, payload - skb->data); if (inet6_sk(sk)->recverr_rfc4884) ipv6_icmp_error_rfc4884(skb, &serr->ee.ee_rfc4884); skb_reset_transport_header(skb); if (sock_queue_err_skb(sk, skb)) kfree_skb(skb); } void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info) { const struct ipv6_pinfo *np = inet6_sk(sk); struct sock_exterr_skb *serr; struct ipv6hdr *iph; struct sk_buff *skb; if (!np->recverr) return; skb = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC); if (!skb) return; skb->protocol = htons(ETH_P_IPV6); skb_put(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); iph = ipv6_hdr(skb); iph->daddr = fl6->daddr; ip6_flow_hdr(iph, 0, 0); serr = SKB_EXT_ERR(skb); serr->ee.ee_errno = err; serr->ee.ee_origin = SO_EE_ORIGIN_LOCAL; serr->ee.ee_type = 0; serr->ee.ee_code = 0; serr->ee.ee_pad = 0; serr->ee.ee_info = info; serr->ee.ee_data = 0; serr->addr_offset = (u8 *)&iph->daddr - skb_network_header(skb); serr->port = fl6->fl6_dport; __skb_pull(skb, skb_tail_pointer(skb) - skb->data); skb_reset_transport_header(skb); if (sock_queue_err_skb(sk, skb)) kfree_skb(skb); } void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6hdr *iph; struct sk_buff *skb; struct ip6_mtuinfo *mtu_info; if (!np->rxopt.bits.rxpmtu) return; skb = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC); if (!skb) return; skb_put(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); iph = ipv6_hdr(skb); iph->daddr = fl6->daddr; mtu_info = IP6CBMTU(skb); mtu_info->ip6m_mtu = mtu; mtu_info->ip6m_addr.sin6_family = AF_INET6; mtu_info->ip6m_addr.sin6_port = 0; mtu_info->ip6m_addr.sin6_flowinfo = 0; mtu_info->ip6m_addr.sin6_scope_id = fl6->flowi6_oif; mtu_info->ip6m_addr.sin6_addr = ipv6_hdr(skb)->daddr; __skb_pull(skb, skb_tail_pointer(skb) - skb->data); skb_reset_transport_header(skb); skb = xchg(&np->rxpmtu, skb); kfree_skb(skb); } /* For some errors we have valid addr_offset even with zero payload and * zero port. Also, addr_offset should be supported if port is set. */ static inline bool ipv6_datagram_support_addr(struct sock_exterr_skb *serr) { return serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6 || serr->ee.ee_origin == SO_EE_ORIGIN_ICMP || serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL || serr->port; } /* IPv6 supports cmsg on all origins aside from SO_EE_ORIGIN_LOCAL. * * At one point, excluding local errors was a quick test to identify icmp/icmp6 * errors. This is no longer true, but the test remained, so the v6 stack, * unlike v4, also honors cmsg requests on all wifi and timestamp errors. */ static bool ip6_datagram_support_cmsg(struct sk_buff *skb, struct sock_exterr_skb *serr) { if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP || serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6) return true; if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL) return false; if (!IP6CB(skb)->iif) return false; return true; } /* * Handle MSG_ERRQUEUE */ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct sock_exterr_skb *serr; struct sk_buff *skb; DECLARE_SOCKADDR(struct sockaddr_in6 *, sin, msg->msg_name); struct { struct sock_extended_err ee; struct sockaddr_in6 offender; } errhdr; int err; int copied; err = -EAGAIN; skb = sock_dequeue_err_skb(sk); if (!skb) goto out; copied = skb->len; if (copied > len) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (unlikely(err)) { kfree_skb(skb); return err; } sock_recv_timestamp(msg, sk, skb); serr = SKB_EXT_ERR(skb); if (sin && ipv6_datagram_support_addr(serr)) { const unsigned char *nh = skb_network_header(skb); sin->sin6_family = AF_INET6; sin->sin6_flowinfo = 0; sin->sin6_port = serr->port; if (skb->protocol == htons(ETH_P_IPV6)) { const struct ipv6hdr *ip6h = container_of((struct in6_addr *)(nh + serr->addr_offset), struct ipv6hdr, daddr); sin->sin6_addr = ip6h->daddr; if (np->sndflow) sin->sin6_flowinfo = ip6_flowinfo(ip6h); sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr, IP6CB(skb)->iif); } else { ipv6_addr_set_v4mapped(*(__be32 *)(nh + serr->addr_offset), &sin->sin6_addr); sin->sin6_scope_id = 0; } *addr_len = sizeof(*sin); } memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); sin = &errhdr.offender; memset(sin, 0, sizeof(*sin)); if (ip6_datagram_support_cmsg(skb, serr)) { sin->sin6_family = AF_INET6; if (np->rxopt.all) ip6_datagram_recv_common_ctl(sk, msg, skb); if (skb->protocol == htons(ETH_P_IPV6)) { sin->sin6_addr = ipv6_hdr(skb)->saddr; if (np->rxopt.all) ip6_datagram_recv_specific_ctl(sk, msg, skb); sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr, IP6CB(skb)->iif); } else { ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &sin->sin6_addr); if (inet_sk(sk)->cmsg_flags) ip_cmsg_recv(msg, skb); } } put_cmsg(msg, SOL_IPV6, IPV6_RECVERR, sizeof(errhdr), &errhdr); /* Now we could try to dump offended packet options */ msg->msg_flags |= MSG_ERRQUEUE; err = copied; consume_skb(skb); out: return err; } EXPORT_SYMBOL_GPL(ipv6_recv_error); /* * Handle IPV6_RECVPATHMTU */ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; struct ip6_mtuinfo mtu_info; DECLARE_SOCKADDR(struct sockaddr_in6 *, sin, msg->msg_name); int err; int copied; err = -EAGAIN; skb = xchg(&np->rxpmtu, NULL); if (!skb) goto out; copied = skb->len; if (copied > len) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto out_free_skb; sock_recv_timestamp(msg, sk, skb); memcpy(&mtu_info, IP6CBMTU(skb), sizeof(mtu_info)); if (sin) { sin->sin6_family = AF_INET6; sin->sin6_flowinfo = 0; sin->sin6_port = 0; sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id; sin->sin6_addr = mtu_info.ip6m_addr.sin6_addr; *addr_len = sizeof(*sin); } put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info); err = copied; out_free_skb: kfree_skb(skb); out: return err; } void ip6_datagram_recv_common_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); bool is_ipv6 = skb->protocol == htons(ETH_P_IPV6); if (np->rxopt.bits.rxinfo) { struct in6_pktinfo src_info; if (is_ipv6) { src_info.ipi6_ifindex = IP6CB(skb)->iif; src_info.ipi6_addr = ipv6_hdr(skb)->daddr; } else { src_info.ipi6_ifindex = PKTINFO_SKB_CB(skb)->ipi_ifindex; ipv6_addr_set_v4mapped(ip_hdr(skb)->daddr, &src_info.ipi6_addr); } if (src_info.ipi6_ifindex >= 0) put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info); } } void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); struct inet6_skb_parm *opt = IP6CB(skb); unsigned char *nh = skb_network_header(skb); if (np->rxopt.bits.rxhlim) { int hlim = ipv6_hdr(skb)->hop_limit; put_cmsg(msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim); } if (np->rxopt.bits.rxtclass) { int tclass = ipv6_get_dsfield(ipv6_hdr(skb)); put_cmsg(msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass); } if (np->rxopt.bits.rxflow) { __be32 flowinfo = ip6_flowinfo((struct ipv6hdr *)nh); if (flowinfo) put_cmsg(msg, SOL_IPV6, IPV6_FLOWINFO, sizeof(flowinfo), &flowinfo); } /* HbH is allowed only once */ if (np->rxopt.bits.hopopts && (opt->flags & IP6SKB_HOPBYHOP)) { u8 *ptr = nh + sizeof(struct ipv6hdr); put_cmsg(msg, SOL_IPV6, IPV6_HOPOPTS, (ptr[1]+1)<<3, ptr); } if (opt->lastopt && (np->rxopt.bits.dstopts || np->rxopt.bits.srcrt)) { /* * Silly enough, but we need to reparse in order to * report extension headers (except for HbH) * in order. * * Also note that IPV6_RECVRTHDRDSTOPTS is NOT * (and WILL NOT be) defined because * IPV6_RECVDSTOPTS is more generic. --yoshfuji */ unsigned int off = sizeof(struct ipv6hdr); u8 nexthdr = ipv6_hdr(skb)->nexthdr; while (off <= opt->lastopt) { unsigned int len; u8 *ptr = nh + off; switch (nexthdr) { case IPPROTO_DSTOPTS: nexthdr = ptr[0]; len = (ptr[1] + 1) << 3; if (np->rxopt.bits.dstopts) put_cmsg(msg, SOL_IPV6, IPV6_DSTOPTS, len, ptr); break; case IPPROTO_ROUTING: nexthdr = ptr[0]; len = (ptr[1] + 1) << 3; if (np->rxopt.bits.srcrt) put_cmsg(msg, SOL_IPV6, IPV6_RTHDR, len, ptr); break; case IPPROTO_AH: nexthdr = ptr[0]; len = (ptr[1] + 2) << 2; break; default: nexthdr = ptr[0]; len = (ptr[1] + 1) << 3; break; } off += len; } } /* socket options in old style */ if (np->rxopt.bits.rxoinfo) { struct in6_pktinfo src_info; src_info.ipi6_ifindex = opt->iif; src_info.ipi6_addr = ipv6_hdr(skb)->daddr; put_cmsg(msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info); } if (np->rxopt.bits.rxohlim) { int hlim = ipv6_hdr(skb)->hop_limit; put_cmsg(msg, SOL_IPV6, IPV6_2292HOPLIMIT, sizeof(hlim), &hlim); } if (np->rxopt.bits.ohopopts && (opt->flags & IP6SKB_HOPBYHOP)) { u8 *ptr = nh + sizeof(struct ipv6hdr); put_cmsg(msg, SOL_IPV6, IPV6_2292HOPOPTS, (ptr[1]+1)<<3, ptr); } if (np->rxopt.bits.odstopts && opt->dst0) { u8 *ptr = nh + opt->dst0; put_cmsg(msg, SOL_IPV6, IPV6_2292DSTOPTS, (ptr[1]+1)<<3, ptr); } if (np->rxopt.bits.osrcrt && opt->srcrt) { struct ipv6_rt_hdr *rthdr = (struct ipv6_rt_hdr *)(nh + opt->srcrt); put_cmsg(msg, SOL_IPV6, IPV6_2292RTHDR, (rthdr->hdrlen+1) << 3, rthdr); } if (np->rxopt.bits.odstopts && opt->dst1) { u8 *ptr = nh + opt->dst1; put_cmsg(msg, SOL_IPV6, IPV6_2292DSTOPTS, (ptr[1]+1)<<3, ptr); } if (np->rxopt.bits.rxorigdstaddr) { struct sockaddr_in6 sin6; __be16 _ports[2], *ports; ports = skb_header_pointer(skb, skb_transport_offset(skb), sizeof(_ports), &_ports); if (ports) { /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ sin6.sin6_family = AF_INET6; sin6.sin6_addr = ipv6_hdr(skb)->daddr; sin6.sin6_port = ports[1]; sin6.sin6_flowinfo = 0; sin6.sin6_scope_id = ipv6_iface_scope_id(&ipv6_hdr(skb)->daddr, opt->iif); put_cmsg(msg, SOL_IPV6, IPV6_ORIGDSTADDR, sizeof(sin6), &sin6); } } if (np->rxopt.bits.recvfragsize && opt->frag_max_size) { int val = opt->frag_max_size; put_cmsg(msg, SOL_IPV6, IPV6_RECVFRAGSIZE, sizeof(val), &val); } } void ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { ip6_datagram_recv_common_ctl(sk, msg, skb); ip6_datagram_recv_specific_ctl(sk, msg, skb); } EXPORT_SYMBOL_GPL(ip6_datagram_recv_ctl); int ip6_datagram_send_ctl(struct net *net, struct sock *sk, struct msghdr *msg, struct flowi6 *fl6, struct ipcm6_cookie *ipc6) { struct in6_pktinfo *src_info; struct cmsghdr *cmsg; struct ipv6_rt_hdr *rthdr; struct ipv6_opt_hdr *hdr; struct ipv6_txoptions *opt = ipc6->opt; int len; int err = 0; for_each_cmsghdr(cmsg, msg) { int addr_type; if (!CMSG_OK(msg, cmsg)) { err = -EINVAL; goto exit_f; } if (cmsg->cmsg_level == SOL_SOCKET) { err = __sock_cmsg_send(sk, msg, cmsg, &ipc6->sockc); if (err) return err; continue; } if (cmsg->cmsg_level != SOL_IPV6) continue; switch (cmsg->cmsg_type) { case IPV6_PKTINFO: case IPV6_2292PKTINFO: { struct net_device *dev = NULL; int src_idx; if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct in6_pktinfo))) { err = -EINVAL; goto exit_f; } src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg); src_idx = src_info->ipi6_ifindex; if (src_idx) { if (fl6->flowi6_oif && src_idx != fl6->flowi6_oif && (READ_ONCE(sk->sk_bound_dev_if) != fl6->flowi6_oif || !sk_dev_equal_l3scope(sk, src_idx))) return -EINVAL; fl6->flowi6_oif = src_idx; } addr_type = __ipv6_addr_type(&src_info->ipi6_addr); rcu_read_lock(); if (fl6->flowi6_oif) { dev = dev_get_by_index_rcu(net, fl6->flowi6_oif); if (!dev) { rcu_read_unlock(); return -ENODEV; } } else if (addr_type & IPV6_ADDR_LINKLOCAL) { rcu_read_unlock(); return -EINVAL; } if (addr_type != IPV6_ADDR_ANY) { int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL; if (!ipv6_can_nonlocal_bind(net, inet_sk(sk)) && !ipv6_chk_addr_and_flags(net, &src_info->ipi6_addr, dev, !strict, 0, IFA_F_TENTATIVE) && !ipv6_chk_acast_addr_src(net, dev, &src_info->ipi6_addr)) err = -EINVAL; else fl6->saddr = src_info->ipi6_addr; } rcu_read_unlock(); if (err) goto exit_f; break; } case IPV6_FLOWINFO: if (cmsg->cmsg_len < CMSG_LEN(4)) { err = -EINVAL; goto exit_f; } if (fl6->flowlabel&IPV6_FLOWINFO_MASK) { if ((fl6->flowlabel^*(__be32 *)CMSG_DATA(cmsg))&~IPV6_FLOWINFO_MASK) { err = -EINVAL; goto exit_f; } } fl6->flowlabel = IPV6_FLOWINFO_MASK & *(__be32 *)CMSG_DATA(cmsg); break; case IPV6_2292HOPOPTS: case IPV6_HOPOPTS: if (opt->hopopt || cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_opt_hdr))) { err = -EINVAL; goto exit_f; } hdr = (struct ipv6_opt_hdr *)CMSG_DATA(cmsg); len = ((hdr->hdrlen + 1) << 3); if (cmsg->cmsg_len < CMSG_LEN(len)) { err = -EINVAL; goto exit_f; } if (!ns_capable(net->user_ns, CAP_NET_RAW)) { err = -EPERM; goto exit_f; } opt->opt_nflen += len; opt->hopopt = hdr; break; case IPV6_2292DSTOPTS: if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_opt_hdr))) { err = -EINVAL; goto exit_f; } hdr = (struct ipv6_opt_hdr *)CMSG_DATA(cmsg); len = ((hdr->hdrlen + 1) << 3); if (cmsg->cmsg_len < CMSG_LEN(len)) { err = -EINVAL; goto exit_f; } if (!ns_capable(net->user_ns, CAP_NET_RAW)) { err = -EPERM; goto exit_f; } if (opt->dst1opt) { err = -EINVAL; goto exit_f; } opt->opt_flen += len; opt->dst1opt = hdr; break; case IPV6_DSTOPTS: case IPV6_RTHDRDSTOPTS: if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_opt_hdr))) { err = -EINVAL; goto exit_f; } hdr = (struct ipv6_opt_hdr *)CMSG_DATA(cmsg); len = ((hdr->hdrlen + 1) << 3); if (cmsg->cmsg_len < CMSG_LEN(len)) { err = -EINVAL; goto exit_f; } if (!ns_capable(net->user_ns, CAP_NET_RAW)) { err = -EPERM; goto exit_f; } if (cmsg->cmsg_type == IPV6_DSTOPTS) { opt->opt_flen += len; opt->dst1opt = hdr; } else { opt->opt_nflen += len; opt->dst0opt = hdr; } break; case IPV6_2292RTHDR: case IPV6_RTHDR: if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_rt_hdr))) { err = -EINVAL; goto exit_f; } rthdr = (struct ipv6_rt_hdr *)CMSG_DATA(cmsg); switch (rthdr->type) { #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: if (rthdr->hdrlen != 2 || rthdr->segments_left != 1) { err = -EINVAL; goto exit_f; } break; #endif default: err = -EINVAL; goto exit_f; } len = ((rthdr->hdrlen + 1) << 3); if (cmsg->cmsg_len < CMSG_LEN(len)) { err = -EINVAL; goto exit_f; } /* segments left must also match */ if ((rthdr->hdrlen >> 1) != rthdr->segments_left) { err = -EINVAL; goto exit_f; } opt->opt_nflen += len; opt->srcrt = rthdr; if (cmsg->cmsg_type == IPV6_2292RTHDR && opt->dst1opt) { int dsthdrlen = ((opt->dst1opt->hdrlen+1)<<3); opt->opt_nflen += dsthdrlen; opt->dst0opt = opt->dst1opt; opt->dst1opt = NULL; opt->opt_flen -= dsthdrlen; } break; case IPV6_2292HOPLIMIT: case IPV6_HOPLIMIT: if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) { err = -EINVAL; goto exit_f; } ipc6->hlimit = *(int *)CMSG_DATA(cmsg); if (ipc6->hlimit < -1 || ipc6->hlimit > 0xff) { err = -EINVAL; goto exit_f; } break; case IPV6_TCLASS: { int tc; err = -EINVAL; if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) goto exit_f; tc = *(int *)CMSG_DATA(cmsg); if (tc < -1 || tc > 0xff) goto exit_f; err = 0; ipc6->tclass = tc; break; } case IPV6_DONTFRAG: { int df; err = -EINVAL; if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) goto exit_f; df = *(int *)CMSG_DATA(cmsg); if (df < 0 || df > 1) goto exit_f; err = 0; ipc6->dontfrag = df; break; } default: net_dbg_ratelimited("invalid cmsg type: %d\n", cmsg->cmsg_type); err = -EINVAL; goto exit_f; } } exit_f: return err; } EXPORT_SYMBOL_GPL(ip6_datagram_send_ctl); void __ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp, __u16 srcp, __u16 destp, int rqueue, int bucket) { const struct in6_addr *dest, *src; dest = &sp->sk_v6_daddr; src = &sp->sk_v6_rcv_saddr; seq_printf(seq, "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %u\n", bucket, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, sp->sk_state, sk_wmem_alloc_get(sp), rqueue, 0, 0L, 0, from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), 0, sock_i_ino(sp), refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } |
| 249 249 249 249 74 74 74 74 43 43 43 43 43 43 43 43 30 30 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 | // SPDX-License-Identifier: GPL-2.0-only #define pr_fmt(fmt) "%s: " fmt, __func__ #include <linux/kernel.h> #include <linux/sched.h> #include <linux/wait.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/percpu-refcount.h> /* * Initially, a percpu refcount is just a set of percpu counters. Initially, we * don't try to detect the ref hitting 0 - which means that get/put can just * increment or decrement the local counter. Note that the counter on a * particular cpu can (and will) wrap - this is fine, when we go to shutdown the * percpu counters will all sum to the correct value * * (More precisely: because modular arithmetic is commutative the sum of all the * percpu_count vars will be equal to what it would have been if all the gets * and puts were done to a single integer, even if some of the percpu integers * overflow or underflow). * * The real trick to implementing percpu refcounts is shutdown. We can't detect * the ref hitting 0 on every put - this would require global synchronization * and defeat the whole purpose of using percpu refs. * * What we do is require the user to keep track of the initial refcount; we know * the ref can't hit 0 before the user drops the initial ref, so as long as we * convert to non percpu mode before the initial ref is dropped everything * works. * * Converting to non percpu mode is done with some RCUish stuff in * percpu_ref_kill. Additionally, we need a bias value so that the * atomic_long_t can't hit 0 before we've added up all the percpu refs. */ #define PERCPU_COUNT_BIAS (1LU << (BITS_PER_LONG - 1)) static DEFINE_SPINLOCK(percpu_ref_switch_lock); static DECLARE_WAIT_QUEUE_HEAD(percpu_ref_switch_waitq); static unsigned long __percpu *percpu_count_ptr(struct percpu_ref *ref) { return (unsigned long __percpu *) (ref->percpu_count_ptr & ~__PERCPU_REF_ATOMIC_DEAD); } /** * percpu_ref_init - initialize a percpu refcount * @ref: percpu_ref to initialize * @release: function which will be called when refcount hits 0 * @flags: PERCPU_REF_INIT_* flags * @gfp: allocation mask to use * * Initializes @ref. @ref starts out in percpu mode with a refcount of 1 unless * @flags contains PERCPU_REF_INIT_ATOMIC or PERCPU_REF_INIT_DEAD. These flags * change the start state to atomic with the latter setting the initial refcount * to 0. See the definitions of PERCPU_REF_INIT_* flags for flag behaviors. * * Note that @release must not sleep - it may potentially be called from RCU * callback context by percpu_ref_kill(). */ int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release, unsigned int flags, gfp_t gfp) { size_t align = max_t(size_t, 1 << __PERCPU_REF_FLAG_BITS, __alignof__(unsigned long)); unsigned long start_count = 0; struct percpu_ref_data *data; ref->percpu_count_ptr = (unsigned long) __alloc_percpu_gfp(sizeof(unsigned long), align, gfp); if (!ref->percpu_count_ptr) return -ENOMEM; data = kzalloc(sizeof(*ref->data), gfp); if (!data) { free_percpu((void __percpu *)ref->percpu_count_ptr); ref->percpu_count_ptr = 0; return -ENOMEM; } data->force_atomic = flags & PERCPU_REF_INIT_ATOMIC; data->allow_reinit = flags & PERCPU_REF_ALLOW_REINIT; if (flags & (PERCPU_REF_INIT_ATOMIC | PERCPU_REF_INIT_DEAD)) { ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC; data->allow_reinit = true; } else { start_count += PERCPU_COUNT_BIAS; } if (flags & PERCPU_REF_INIT_DEAD) ref->percpu_count_ptr |= __PERCPU_REF_DEAD; else start_count++; atomic_long_set(&data->count, start_count); data->release = release; data->confirm_switch = NULL; data->ref = ref; ref->data = data; return 0; } EXPORT_SYMBOL_GPL(percpu_ref_init); static void __percpu_ref_exit(struct percpu_ref *ref) { unsigned long __percpu *percpu_count = percpu_count_ptr(ref); if (percpu_count) { /* non-NULL confirm_switch indicates switching in progress */ WARN_ON_ONCE(ref->data && ref->data->confirm_switch); free_percpu(percpu_count); ref->percpu_count_ptr = __PERCPU_REF_ATOMIC_DEAD; } } /** * percpu_ref_exit - undo percpu_ref_init() * @ref: percpu_ref to exit * * This function exits @ref. The caller is responsible for ensuring that * @ref is no longer in active use. The usual places to invoke this * function from are the @ref->release() callback or in init failure path * where percpu_ref_init() succeeded but other parts of the initialization * of the embedding object failed. */ void percpu_ref_exit(struct percpu_ref *ref) { struct percpu_ref_data *data = ref->data; unsigned long flags; __percpu_ref_exit(ref); if (!data) return; spin_lock_irqsave(&percpu_ref_switch_lock, flags); ref->percpu_count_ptr |= atomic_long_read(&ref->data->count) << __PERCPU_REF_FLAG_BITS; ref->data = NULL; spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); kfree(data); } EXPORT_SYMBOL_GPL(percpu_ref_exit); static void percpu_ref_call_confirm_rcu(struct rcu_head *rcu) { struct percpu_ref_data *data = container_of(rcu, struct percpu_ref_data, rcu); struct percpu_ref *ref = data->ref; data->confirm_switch(ref); data->confirm_switch = NULL; wake_up_all(&percpu_ref_switch_waitq); if (!data->allow_reinit) __percpu_ref_exit(ref); /* drop ref from percpu_ref_switch_to_atomic() */ percpu_ref_put(ref); } static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu) { struct percpu_ref_data *data = container_of(rcu, struct percpu_ref_data, rcu); struct percpu_ref *ref = data->ref; unsigned long __percpu *percpu_count = percpu_count_ptr(ref); static atomic_t underflows; unsigned long count = 0; int cpu; for_each_possible_cpu(cpu) count += *per_cpu_ptr(percpu_count, cpu); pr_debug("global %lu percpu %lu\n", atomic_long_read(&data->count), count); /* * It's crucial that we sum the percpu counters _before_ adding the sum * to &ref->count; since gets could be happening on one cpu while puts * happen on another, adding a single cpu's count could cause * @ref->count to hit 0 before we've got a consistent value - but the * sum of all the counts will be consistent and correct. * * Subtracting the bias value then has to happen _after_ adding count to * &ref->count; we need the bias value to prevent &ref->count from * reaching 0 before we add the percpu counts. But doing it at the same * time is equivalent and saves us atomic operations: */ atomic_long_add((long)count - PERCPU_COUNT_BIAS, &data->count); if (WARN_ONCE(atomic_long_read(&data->count) <= 0, "percpu ref (%ps) <= 0 (%ld) after switching to atomic", data->release, atomic_long_read(&data->count)) && atomic_inc_return(&underflows) < 4) { pr_err("%s(): percpu_ref underflow", __func__); mem_dump_obj(data); } /* @ref is viewed as dead on all CPUs, send out switch confirmation */ percpu_ref_call_confirm_rcu(rcu); } static void percpu_ref_noop_confirm_switch(struct percpu_ref *ref) { } static void __percpu_ref_switch_to_atomic(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch) { if (ref->percpu_count_ptr & __PERCPU_REF_ATOMIC) { if (confirm_switch) confirm_switch(ref); return; } /* switching from percpu to atomic */ ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC; /* * Non-NULL ->confirm_switch is used to indicate that switching is * in progress. Use noop one if unspecified. */ ref->data->confirm_switch = confirm_switch ?: percpu_ref_noop_confirm_switch; percpu_ref_get(ref); /* put after confirmation */ call_rcu_hurry(&ref->data->rcu, percpu_ref_switch_to_atomic_rcu); } static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref) { unsigned long __percpu *percpu_count = percpu_count_ptr(ref); int cpu; BUG_ON(!percpu_count); if (!(ref->percpu_count_ptr & __PERCPU_REF_ATOMIC)) return; if (WARN_ON_ONCE(!ref->data->allow_reinit)) return; atomic_long_add(PERCPU_COUNT_BIAS, &ref->data->count); /* * Restore per-cpu operation. smp_store_release() is paired * with READ_ONCE() in __ref_is_percpu() and guarantees that the * zeroing is visible to all percpu accesses which can see the * following __PERCPU_REF_ATOMIC clearing. */ for_each_possible_cpu(cpu) *per_cpu_ptr(percpu_count, cpu) = 0; smp_store_release(&ref->percpu_count_ptr, ref->percpu_count_ptr & ~__PERCPU_REF_ATOMIC); } static void __percpu_ref_switch_mode(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch) { struct percpu_ref_data *data = ref->data; lockdep_assert_held(&percpu_ref_switch_lock); /* * If the previous ATOMIC switching hasn't finished yet, wait for * its completion. If the caller ensures that ATOMIC switching * isn't in progress, this function can be called from any context. */ wait_event_lock_irq(percpu_ref_switch_waitq, !data->confirm_switch, percpu_ref_switch_lock); if (data->force_atomic || percpu_ref_is_dying(ref)) __percpu_ref_switch_to_atomic(ref, confirm_switch); else __percpu_ref_switch_to_percpu(ref); } /** * percpu_ref_switch_to_atomic - switch a percpu_ref to atomic mode * @ref: percpu_ref to switch to atomic mode * @confirm_switch: optional confirmation callback * * There's no reason to use this function for the usual reference counting. * Use percpu_ref_kill[_and_confirm](). * * Schedule switching of @ref to atomic mode. All its percpu counts will * be collected to the main atomic counter. On completion, when all CPUs * are guaraneed to be in atomic mode, @confirm_switch, which may not * block, is invoked. This function may be invoked concurrently with all * the get/put operations and can safely be mixed with kill and reinit * operations. Note that @ref will stay in atomic mode across kill/reinit * cycles until percpu_ref_switch_to_percpu() is called. * * This function may block if @ref is in the process of switching to atomic * mode. If the caller ensures that @ref is not in the process of * switching to atomic mode, this function can be called from any context. */ void percpu_ref_switch_to_atomic(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch) { unsigned long flags; spin_lock_irqsave(&percpu_ref_switch_lock, flags); ref->data->force_atomic = true; __percpu_ref_switch_mode(ref, confirm_switch); spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); } EXPORT_SYMBOL_GPL(percpu_ref_switch_to_atomic); /** * percpu_ref_switch_to_atomic_sync - switch a percpu_ref to atomic mode * @ref: percpu_ref to switch to atomic mode * * Schedule switching the ref to atomic mode, and wait for the * switch to complete. Caller must ensure that no other thread * will switch back to percpu mode. */ void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref) { percpu_ref_switch_to_atomic(ref, NULL); wait_event(percpu_ref_switch_waitq, !ref->data->confirm_switch); } EXPORT_SYMBOL_GPL(percpu_ref_switch_to_atomic_sync); /** * percpu_ref_switch_to_percpu - switch a percpu_ref to percpu mode * @ref: percpu_ref to switch to percpu mode * * There's no reason to use this function for the usual reference counting. * To re-use an expired ref, use percpu_ref_reinit(). * * Switch @ref to percpu mode. This function may be invoked concurrently * with all the get/put operations and can safely be mixed with kill and * reinit operations. This function reverses the sticky atomic state set * by PERCPU_REF_INIT_ATOMIC or percpu_ref_switch_to_atomic(). If @ref is * dying or dead, the actual switching takes place on the following * percpu_ref_reinit(). * * This function may block if @ref is in the process of switching to atomic * mode. If the caller ensures that @ref is not in the process of * switching to atomic mode, this function can be called from any context. */ void percpu_ref_switch_to_percpu(struct percpu_ref *ref) { unsigned long flags; spin_lock_irqsave(&percpu_ref_switch_lock, flags); ref->data->force_atomic = false; __percpu_ref_switch_mode(ref, NULL); spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); } EXPORT_SYMBOL_GPL(percpu_ref_switch_to_percpu); /** * percpu_ref_kill_and_confirm - drop the initial ref and schedule confirmation * @ref: percpu_ref to kill * @confirm_kill: optional confirmation callback * * Equivalent to percpu_ref_kill() but also schedules kill confirmation if * @confirm_kill is not NULL. @confirm_kill, which may not block, will be * called after @ref is seen as dead from all CPUs at which point all * further invocations of percpu_ref_tryget_live() will fail. See * percpu_ref_tryget_live() for details. * * This function normally doesn't block and can be called from any context * but it may block if @confirm_kill is specified and @ref is in the * process of switching to atomic mode by percpu_ref_switch_to_atomic(). * * There are no implied RCU grace periods between kill and release. */ void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill) { unsigned long flags; spin_lock_irqsave(&percpu_ref_switch_lock, flags); WARN_ONCE(percpu_ref_is_dying(ref), "%s called more than once on %ps!", __func__, ref->data->release); ref->percpu_count_ptr |= __PERCPU_REF_DEAD; __percpu_ref_switch_mode(ref, confirm_kill); percpu_ref_put(ref); spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); } EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm); /** * percpu_ref_is_zero - test whether a percpu refcount reached zero * @ref: percpu_ref to test * * Returns %true if @ref reached zero. * * This function is safe to call as long as @ref is between init and exit. */ bool percpu_ref_is_zero(struct percpu_ref *ref) { unsigned long __percpu *percpu_count; unsigned long count, flags; if (__ref_is_percpu(ref, &percpu_count)) return false; /* protect us from being destroyed */ spin_lock_irqsave(&percpu_ref_switch_lock, flags); if (ref->data) count = atomic_long_read(&ref->data->count); else count = ref->percpu_count_ptr >> __PERCPU_REF_FLAG_BITS; spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); return count == 0; } EXPORT_SYMBOL_GPL(percpu_ref_is_zero); /** * percpu_ref_reinit - re-initialize a percpu refcount * @ref: perpcu_ref to re-initialize * * Re-initialize @ref so that it's in the same state as when it finished * percpu_ref_init() ignoring %PERCPU_REF_INIT_DEAD. @ref must have been * initialized successfully and reached 0 but not exited. * * Note that percpu_ref_tryget[_live]() are safe to perform on @ref while * this function is in progress. */ void percpu_ref_reinit(struct percpu_ref *ref) { WARN_ON_ONCE(!percpu_ref_is_zero(ref)); percpu_ref_resurrect(ref); } EXPORT_SYMBOL_GPL(percpu_ref_reinit); /** * percpu_ref_resurrect - modify a percpu refcount from dead to live * @ref: perpcu_ref to resurrect * * Modify @ref so that it's in the same state as before percpu_ref_kill() was * called. @ref must be dead but must not yet have exited. * * If @ref->release() frees @ref then the caller is responsible for * guaranteeing that @ref->release() does not get called while this * function is in progress. * * Note that percpu_ref_tryget[_live]() are safe to perform on @ref while * this function is in progress. */ void percpu_ref_resurrect(struct percpu_ref *ref) { unsigned long __percpu *percpu_count; unsigned long flags; spin_lock_irqsave(&percpu_ref_switch_lock, flags); WARN_ON_ONCE(!percpu_ref_is_dying(ref)); WARN_ON_ONCE(__ref_is_percpu(ref, &percpu_count)); ref->percpu_count_ptr &= ~__PERCPU_REF_DEAD; percpu_ref_get(ref); __percpu_ref_switch_mode(ref, NULL); spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); } EXPORT_SYMBOL_GPL(percpu_ref_resurrect); |
| 640 640 640 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * xt_hashlimit - Netfilter module to limit the number of packets per time * separately for each hashbucket (sourceip/sourceport/dstip/dstport) * * (C) 2003-2004 by Harald Welte <laforge@netfilter.org> * (C) 2006-2012 Patrick McHardy <kaber@trash.net> * Copyright © CC Computer Consultants GmbH, 2007 - 2008 * * Development of this code was funded by Astaro AG, http://www.astaro.com/ */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/spinlock.h> #include <linux/random.h> #include <linux/jhash.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/list.h> #include <linux/skbuff.h> #include <linux/mm.h> #include <linux/in.h> #include <linux/ip.h> #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) #include <linux/ipv6.h> #include <net/ipv6.h> #endif #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/mutex.h> #include <linux/kernel.h> #include <linux/refcount.h> #include <uapi/linux/netfilter/xt_hashlimit.h> #define XT_HASHLIMIT_ALL (XT_HASHLIMIT_HASH_DIP | XT_HASHLIMIT_HASH_DPT | \ XT_HASHLIMIT_HASH_SIP | XT_HASHLIMIT_HASH_SPT | \ XT_HASHLIMIT_INVERT | XT_HASHLIMIT_BYTES |\ XT_HASHLIMIT_RATE_MATCH) MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>"); MODULE_DESCRIPTION("Xtables: per hash-bucket rate-limit match"); MODULE_ALIAS("ipt_hashlimit"); MODULE_ALIAS("ip6t_hashlimit"); struct hashlimit_net { struct hlist_head htables; struct proc_dir_entry *ipt_hashlimit; struct proc_dir_entry *ip6t_hashlimit; }; static unsigned int hashlimit_net_id; static inline struct hashlimit_net *hashlimit_pernet(struct net *net) { return net_generic(net, hashlimit_net_id); } /* need to declare this at the top */ static const struct seq_operations dl_seq_ops_v2; static const struct seq_operations dl_seq_ops_v1; static const struct seq_operations dl_seq_ops; /* hash table crap */ struct dsthash_dst { union { struct { __be32 src; __be32 dst; } ip; #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) struct { __be32 src[4]; __be32 dst[4]; } ip6; #endif }; __be16 src_port; __be16 dst_port; }; struct dsthash_ent { /* static / read-only parts in the beginning */ struct hlist_node node; struct dsthash_dst dst; /* modified structure members in the end */ spinlock_t lock; unsigned long expires; /* precalculated expiry time */ struct { unsigned long prev; /* last modification */ union { struct { u_int64_t credit; u_int64_t credit_cap; u_int64_t cost; }; struct { u_int32_t interval, prev_window; u_int64_t current_rate; u_int64_t rate; int64_t burst; }; }; } rateinfo; struct rcu_head rcu; }; struct xt_hashlimit_htable { struct hlist_node node; /* global list of all htables */ refcount_t use; u_int8_t family; bool rnd_initialized; struct hashlimit_cfg3 cfg; /* config */ /* used internally */ spinlock_t lock; /* lock for list_head */ u_int32_t rnd; /* random seed for hash */ unsigned int count; /* number entries in table */ struct delayed_work gc_work; /* seq_file stuff */ struct proc_dir_entry *pde; const char *name; struct net *net; struct hlist_head hash[]; /* hashtable itself */ }; static int cfg_copy(struct hashlimit_cfg3 *to, const void *from, int revision) { if (revision == 1) { struct hashlimit_cfg1 *cfg = (struct hashlimit_cfg1 *)from; to->mode = cfg->mode; to->avg = cfg->avg; to->burst = cfg->burst; to->size = cfg->size; to->max = cfg->max; to->gc_interval = cfg->gc_interval; to->expire = cfg->expire; to->srcmask = cfg->srcmask; to->dstmask = cfg->dstmask; } else if (revision == 2) { struct hashlimit_cfg2 *cfg = (struct hashlimit_cfg2 *)from; to->mode = cfg->mode; to->avg = cfg->avg; to->burst = cfg->burst; to->size = cfg->size; to->max = cfg->max; to->gc_interval = cfg->gc_interval; to->expire = cfg->expire; to->srcmask = cfg->srcmask; to->dstmask = cfg->dstmask; } else if (revision == 3) { memcpy(to, from, sizeof(struct hashlimit_cfg3)); } else { return -EINVAL; } return 0; } static DEFINE_MUTEX(hashlimit_mutex); /* protects htables list */ static struct kmem_cache *hashlimit_cachep __read_mostly; static inline bool dst_cmp(const struct dsthash_ent *ent, const struct dsthash_dst *b) { return !memcmp(&ent->dst, b, sizeof(ent->dst)); } static u_int32_t hash_dst(const struct xt_hashlimit_htable *ht, const struct dsthash_dst *dst) { u_int32_t hash = jhash2((const u32 *)dst, sizeof(*dst)/sizeof(u32), ht->rnd); /* * Instead of returning hash % ht->cfg.size (implying a divide) * we return the high 32 bits of the (hash * ht->cfg.size) that will * give results between [0 and cfg.size-1] and same hash distribution, * but using a multiply, less expensive than a divide */ return reciprocal_scale(hash, ht->cfg.size); } static struct dsthash_ent * dsthash_find(const struct xt_hashlimit_htable *ht, const struct dsthash_dst *dst) { struct dsthash_ent *ent; u_int32_t hash = hash_dst(ht, dst); if (!hlist_empty(&ht->hash[hash])) { hlist_for_each_entry_rcu(ent, &ht->hash[hash], node) if (dst_cmp(ent, dst)) { spin_lock(&ent->lock); return ent; } } return NULL; } /* allocate dsthash_ent, initialize dst, put in htable and lock it */ static struct dsthash_ent * dsthash_alloc_init(struct xt_hashlimit_htable *ht, const struct dsthash_dst *dst, bool *race) { struct dsthash_ent *ent; spin_lock(&ht->lock); /* Two or more packets may race to create the same entry in the * hashtable, double check if this packet lost race. */ ent = dsthash_find(ht, dst); if (ent != NULL) { spin_unlock(&ht->lock); *race = true; return ent; } /* initialize hash with random val at the time we allocate * the first hashtable entry */ if (unlikely(!ht->rnd_initialized)) { get_random_bytes(&ht->rnd, sizeof(ht->rnd)); ht->rnd_initialized = true; } if (ht->cfg.max && ht->count >= ht->cfg.max) { /* FIXME: do something. question is what.. */ net_err_ratelimited("max count of %u reached\n", ht->cfg.max); ent = NULL; } else ent = kmem_cache_alloc(hashlimit_cachep, GFP_ATOMIC); if (ent) { memcpy(&ent->dst, dst, sizeof(ent->dst)); spin_lock_init(&ent->lock); spin_lock(&ent->lock); hlist_add_head_rcu(&ent->node, &ht->hash[hash_dst(ht, dst)]); ht->count++; } spin_unlock(&ht->lock); return ent; } static void dsthash_free_rcu(struct rcu_head *head) { struct dsthash_ent *ent = container_of(head, struct dsthash_ent, rcu); kmem_cache_free(hashlimit_cachep, ent); } static inline void dsthash_free(struct xt_hashlimit_htable *ht, struct dsthash_ent *ent) { hlist_del_rcu(&ent->node); call_rcu(&ent->rcu, dsthash_free_rcu); ht->count--; } static void htable_gc(struct work_struct *work); static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg, const char *name, u_int8_t family, struct xt_hashlimit_htable **out_hinfo, int revision) { struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); struct xt_hashlimit_htable *hinfo; const struct seq_operations *ops; unsigned int size, i; unsigned long nr_pages = totalram_pages(); int ret; if (cfg->size) { size = cfg->size; } else { size = (nr_pages << PAGE_SHIFT) / 16384 / sizeof(struct hlist_head); if (nr_pages > 1024 * 1024 * 1024 / PAGE_SIZE) size = 8192; if (size < 16) size = 16; } /* FIXME: don't use vmalloc() here or anywhere else -HW */ hinfo = vmalloc(struct_size(hinfo, hash, size)); if (hinfo == NULL) return -ENOMEM; *out_hinfo = hinfo; /* copy match config into hashtable config */ ret = cfg_copy(&hinfo->cfg, (void *)cfg, 3); if (ret) { vfree(hinfo); return ret; } hinfo->cfg.size = size; if (hinfo->cfg.max == 0) hinfo->cfg.max = 8 * hinfo->cfg.size; else if (hinfo->cfg.max < hinfo->cfg.size) hinfo->cfg.max = hinfo->cfg.size; for (i = 0; i < hinfo->cfg.size; i++) INIT_HLIST_HEAD(&hinfo->hash[i]); refcount_set(&hinfo->use, 1); hinfo->count = 0; hinfo->family = family; hinfo->rnd_initialized = false; hinfo->name = kstrdup(name, GFP_KERNEL); if (!hinfo->name) { vfree(hinfo); return -ENOMEM; } spin_lock_init(&hinfo->lock); switch (revision) { case 1: ops = &dl_seq_ops_v1; break; case 2: ops = &dl_seq_ops_v2; break; default: ops = &dl_seq_ops; } hinfo->pde = proc_create_seq_data(name, 0, (family == NFPROTO_IPV4) ? hashlimit_net->ipt_hashlimit : hashlimit_net->ip6t_hashlimit, ops, hinfo); if (hinfo->pde == NULL) { kfree(hinfo->name); vfree(hinfo); return -ENOMEM; } hinfo->net = net; INIT_DEFERRABLE_WORK(&hinfo->gc_work, htable_gc); queue_delayed_work(system_power_efficient_wq, &hinfo->gc_work, msecs_to_jiffies(hinfo->cfg.gc_interval)); hlist_add_head(&hinfo->node, &hashlimit_net->htables); return 0; } static void htable_selective_cleanup(struct xt_hashlimit_htable *ht, bool select_all) { unsigned int i; for (i = 0; i < ht->cfg.size; i++) { struct dsthash_ent *dh; struct hlist_node *n; spin_lock_bh(&ht->lock); hlist_for_each_entry_safe(dh, n, &ht->hash[i], node) { if (time_after_eq(jiffies, dh->expires) || select_all) dsthash_free(ht, dh); } spin_unlock_bh(&ht->lock); cond_resched(); } } static void htable_gc(struct work_struct *work) { struct xt_hashlimit_htable *ht; ht = container_of(work, struct xt_hashlimit_htable, gc_work.work); htable_selective_cleanup(ht, false); queue_delayed_work(system_power_efficient_wq, &ht->gc_work, msecs_to_jiffies(ht->cfg.gc_interval)); } static void htable_remove_proc_entry(struct xt_hashlimit_htable *hinfo) { struct hashlimit_net *hashlimit_net = hashlimit_pernet(hinfo->net); struct proc_dir_entry *parent; if (hinfo->family == NFPROTO_IPV4) parent = hashlimit_net->ipt_hashlimit; else parent = hashlimit_net->ip6t_hashlimit; if (parent != NULL) remove_proc_entry(hinfo->name, parent); } static struct xt_hashlimit_htable *htable_find_get(struct net *net, const char *name, u_int8_t family) { struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); struct xt_hashlimit_htable *hinfo; hlist_for_each_entry(hinfo, &hashlimit_net->htables, node) { if (!strcmp(name, hinfo->name) && hinfo->family == family) { refcount_inc(&hinfo->use); return hinfo; } } return NULL; } static void htable_put(struct xt_hashlimit_htable *hinfo) { if (refcount_dec_and_mutex_lock(&hinfo->use, &hashlimit_mutex)) { hlist_del(&hinfo->node); htable_remove_proc_entry(hinfo); mutex_unlock(&hashlimit_mutex); cancel_delayed_work_sync(&hinfo->gc_work); htable_selective_cleanup(hinfo, true); kfree(hinfo->name); vfree(hinfo); } } /* The algorithm used is the Simple Token Bucket Filter (TBF) * see net/sched/sch_tbf.c in the linux source tree */ /* Rusty: This is my (non-mathematically-inclined) understanding of this algorithm. The `average rate' in jiffies becomes your initial amount of credit `credit' and the most credit you can ever have `credit_cap'. The `peak rate' becomes the cost of passing the test, `cost'. `prev' tracks the last packet hit: you gain one credit per jiffy. If you get credit balance more than this, the extra credit is discarded. Every time the match passes, you lose `cost' credits; if you don't have that many, the test fails. See Alexey's formal explanation in net/sched/sch_tbf.c. To get the maximum range, we multiply by this factor (ie. you get N credits per jiffy). We want to allow a rate as low as 1 per day (slowest userspace tool allows), which means CREDITS_PER_JIFFY*HZ*60*60*24 < 2^32 ie. */ #define MAX_CPJ_v1 (0xFFFFFFFF / (HZ*60*60*24)) #define MAX_CPJ (0xFFFFFFFFFFFFFFFFULL / (HZ*60*60*24)) /* Repeated shift and or gives us all 1s, final shift and add 1 gives * us the power of 2 below the theoretical max, so GCC simply does a * shift. */ #define _POW2_BELOW2(x) ((x)|((x)>>1)) #define _POW2_BELOW4(x) (_POW2_BELOW2(x)|_POW2_BELOW2((x)>>2)) #define _POW2_BELOW8(x) (_POW2_BELOW4(x)|_POW2_BELOW4((x)>>4)) #define _POW2_BELOW16(x) (_POW2_BELOW8(x)|_POW2_BELOW8((x)>>8)) #define _POW2_BELOW32(x) (_POW2_BELOW16(x)|_POW2_BELOW16((x)>>16)) #define _POW2_BELOW64(x) (_POW2_BELOW32(x)|_POW2_BELOW32((x)>>32)) #define POW2_BELOW32(x) ((_POW2_BELOW32(x)>>1) + 1) #define POW2_BELOW64(x) ((_POW2_BELOW64(x)>>1) + 1) #define CREDITS_PER_JIFFY POW2_BELOW64(MAX_CPJ) #define CREDITS_PER_JIFFY_v1 POW2_BELOW32(MAX_CPJ_v1) /* in byte mode, the lowest possible rate is one packet/second. * credit_cap is used as a counter that tells us how many times we can * refill the "credits available" counter when it becomes empty. */ #define MAX_CPJ_BYTES (0xFFFFFFFF / HZ) #define CREDITS_PER_JIFFY_BYTES POW2_BELOW32(MAX_CPJ_BYTES) static u32 xt_hashlimit_len_to_chunks(u32 len) { return (len >> XT_HASHLIMIT_BYTE_SHIFT) + 1; } /* Precision saver. */ static u64 user2credits(u64 user, int revision) { u64 scale = (revision == 1) ? XT_HASHLIMIT_SCALE : XT_HASHLIMIT_SCALE_v2; u64 cpj = (revision == 1) ? CREDITS_PER_JIFFY_v1 : CREDITS_PER_JIFFY; /* Avoid overflow: divide the constant operands first */ if (scale >= HZ * cpj) return div64_u64(user, div64_u64(scale, HZ * cpj)); return user * div64_u64(HZ * cpj, scale); } static u32 user2credits_byte(u32 user) { u64 us = user; us *= HZ * CREDITS_PER_JIFFY_BYTES; return (u32) (us >> 32); } static u64 user2rate(u64 user) { if (user != 0) { return div64_u64(XT_HASHLIMIT_SCALE_v2, user); } else { pr_info_ratelimited("invalid rate from userspace: %llu\n", user); return 0; } } static u64 user2rate_bytes(u32 user) { u64 r; r = user ? U32_MAX / user : U32_MAX; return (r - 1) << XT_HASHLIMIT_BYTE_SHIFT; } static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now, u32 mode, int revision) { unsigned long delta = now - dh->rateinfo.prev; u64 cap, cpj; if (delta == 0) return; if (revision >= 3 && mode & XT_HASHLIMIT_RATE_MATCH) { u64 interval = dh->rateinfo.interval * HZ; if (delta < interval) return; dh->rateinfo.prev = now; dh->rateinfo.prev_window = ((dh->rateinfo.current_rate * interval) > (delta * dh->rateinfo.rate)); dh->rateinfo.current_rate = 0; return; } dh->rateinfo.prev = now; if (mode & XT_HASHLIMIT_BYTES) { u64 tmp = dh->rateinfo.credit; dh->rateinfo.credit += CREDITS_PER_JIFFY_BYTES * delta; cap = CREDITS_PER_JIFFY_BYTES * HZ; if (tmp >= dh->rateinfo.credit) {/* overflow */ dh->rateinfo.credit = cap; return; } } else { cpj = (revision == 1) ? CREDITS_PER_JIFFY_v1 : CREDITS_PER_JIFFY; dh->rateinfo.credit += delta * cpj; cap = dh->rateinfo.credit_cap; } if (dh->rateinfo.credit > cap) dh->rateinfo.credit = cap; } static void rateinfo_init(struct dsthash_ent *dh, struct xt_hashlimit_htable *hinfo, int revision) { dh->rateinfo.prev = jiffies; if (revision >= 3 && hinfo->cfg.mode & XT_HASHLIMIT_RATE_MATCH) { dh->rateinfo.prev_window = 0; dh->rateinfo.current_rate = 0; if (hinfo->cfg.mode & XT_HASHLIMIT_BYTES) { dh->rateinfo.rate = user2rate_bytes((u32)hinfo->cfg.avg); if (hinfo->cfg.burst) dh->rateinfo.burst = hinfo->cfg.burst * dh->rateinfo.rate; else dh->rateinfo.burst = dh->rateinfo.rate; } else { dh->rateinfo.rate = user2rate(hinfo->cfg.avg); dh->rateinfo.burst = hinfo->cfg.burst + dh->rateinfo.rate; } dh->rateinfo.interval = hinfo->cfg.interval; } else if (hinfo->cfg.mode & XT_HASHLIMIT_BYTES) { dh->rateinfo.credit = CREDITS_PER_JIFFY_BYTES * HZ; dh->rateinfo.cost = user2credits_byte(hinfo->cfg.avg); dh->rateinfo.credit_cap = hinfo->cfg.burst; } else { dh->rateinfo.credit = user2credits(hinfo->cfg.avg * hinfo->cfg.burst, revision); dh->rateinfo.cost = user2credits(hinfo->cfg.avg, revision); dh->rateinfo.credit_cap = dh->rateinfo.credit; } } static inline __be32 maskl(__be32 a, unsigned int l) { return l ? htonl(ntohl(a) & ~0 << (32 - l)) : 0; } #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) static void hashlimit_ipv6_mask(__be32 *i, unsigned int p) { switch (p) { case 0 ... 31: i[0] = maskl(i[0], p); i[1] = i[2] = i[3] = 0; break; case 32 ... 63: i[1] = maskl(i[1], p - 32); i[2] = i[3] = 0; break; case 64 ... 95: i[2] = maskl(i[2], p - 64); i[3] = 0; break; case 96 ... 127: i[3] = maskl(i[3], p - 96); break; case 128: break; } } #endif static int hashlimit_init_dst(const struct xt_hashlimit_htable *hinfo, struct dsthash_dst *dst, const struct sk_buff *skb, unsigned int protoff) { __be16 _ports[2], *ports; u8 nexthdr; int poff; memset(dst, 0, sizeof(*dst)); switch (hinfo->family) { case NFPROTO_IPV4: if (hinfo->cfg.mode & XT_HASHLIMIT_HASH_DIP) dst->ip.dst = maskl(ip_hdr(skb)->daddr, hinfo->cfg.dstmask); if (hinfo->cfg.mode & XT_HASHLIMIT_HASH_SIP) dst->ip.src = maskl(ip_hdr(skb)->saddr, hinfo->cfg.srcmask); if (!(hinfo->cfg.mode & (XT_HASHLIMIT_HASH_DPT | XT_HASHLIMIT_HASH_SPT))) return 0; nexthdr = ip_hdr(skb)->protocol; break; #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) case NFPROTO_IPV6: { __be16 frag_off; if (hinfo->cfg.mode & XT_HASHLIMIT_HASH_DIP) { memcpy(&dst->ip6.dst, &ipv6_hdr(skb)->daddr, sizeof(dst->ip6.dst)); hashlimit_ipv6_mask(dst->ip6.dst, hinfo->cfg.dstmask); } if (hinfo->cfg.mode & XT_HASHLIMIT_HASH_SIP) { memcpy(&dst->ip6.src, &ipv6_hdr(skb)->saddr, sizeof(dst->ip6.src)); hashlimit_ipv6_mask(dst->ip6.src, hinfo->cfg.srcmask); } if (!(hinfo->cfg.mode & (XT_HASHLIMIT_HASH_DPT | XT_HASHLIMIT_HASH_SPT))) return 0; nexthdr = ipv6_hdr(skb)->nexthdr; protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off); if ((int)protoff < 0) return -1; break; } #endif default: BUG(); return 0; } poff = proto_ports_offset(nexthdr); if (poff >= 0) { ports = skb_header_pointer(skb, protoff + poff, sizeof(_ports), &_ports); } else { _ports[0] = _ports[1] = 0; ports = _ports; } if (!ports) return -1; if (hinfo->cfg.mode & XT_HASHLIMIT_HASH_SPT) dst->src_port = ports[0]; if (hinfo->cfg.mode & XT_HASHLIMIT_HASH_DPT) dst->dst_port = ports[1]; return 0; } static u32 hashlimit_byte_cost(unsigned int len, struct dsthash_ent *dh) { u64 tmp = xt_hashlimit_len_to_chunks(len); tmp = tmp * dh->rateinfo.cost; if (unlikely(tmp > CREDITS_PER_JIFFY_BYTES * HZ)) tmp = CREDITS_PER_JIFFY_BYTES * HZ; if (dh->rateinfo.credit < tmp && dh->rateinfo.credit_cap) { dh->rateinfo.credit_cap--; dh->rateinfo.credit = CREDITS_PER_JIFFY_BYTES * HZ; } return (u32) tmp; } static bool hashlimit_mt_common(const struct sk_buff *skb, struct xt_action_param *par, struct xt_hashlimit_htable *hinfo, const struct hashlimit_cfg3 *cfg, int revision) { unsigned long now = jiffies; struct dsthash_ent *dh; struct dsthash_dst dst; bool race = false; u64 cost; if (hashlimit_init_dst(hinfo, &dst, skb, par->thoff) < 0) goto hotdrop; local_bh_disable(); dh = dsthash_find(hinfo, &dst); if (dh == NULL) { dh = dsthash_alloc_init(hinfo, &dst, &race); if (dh == NULL) { local_bh_enable(); goto hotdrop; } else if (race) { /* Already got an entry, update expiration timeout */ dh->expires = now + msecs_to_jiffies(hinfo->cfg.expire); rateinfo_recalc(dh, now, hinfo->cfg.mode, revision); } else { dh->expires = jiffies + msecs_to_jiffies(hinfo->cfg.expire); rateinfo_init(dh, hinfo, revision); } } else { /* update expiration timeout */ dh->expires = now + msecs_to_jiffies(hinfo->cfg.expire); rateinfo_recalc(dh, now, hinfo->cfg.mode, revision); } if (cfg->mode & XT_HASHLIMIT_RATE_MATCH) { cost = (cfg->mode & XT_HASHLIMIT_BYTES) ? skb->len : 1; dh->rateinfo.current_rate += cost; if (!dh->rateinfo.prev_window && (dh->rateinfo.current_rate <= dh->rateinfo.burst)) { spin_unlock(&dh->lock); local_bh_enable(); return !(cfg->mode & XT_HASHLIMIT_INVERT); } else { goto overlimit; } } if (cfg->mode & XT_HASHLIMIT_BYTES) cost = hashlimit_byte_cost(skb->len, dh); else cost = dh->rateinfo.cost; if (dh->rateinfo.credit >= cost) { /* below the limit */ dh->rateinfo.credit -= cost; spin_unlock(&dh->lock); local_bh_enable(); return !(cfg->mode & XT_HASHLIMIT_INVERT); } overlimit: spin_unlock(&dh->lock); local_bh_enable(); /* default match is underlimit - so over the limit, we need to invert */ return cfg->mode & XT_HASHLIMIT_INVERT; hotdrop: par->hotdrop = true; return false; } static bool hashlimit_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_hashlimit_mtinfo1 *info = par->matchinfo; struct xt_hashlimit_htable *hinfo = info->hinfo; struct hashlimit_cfg3 cfg = {}; int ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 1); if (ret) return ret; return hashlimit_mt_common(skb, par, hinfo, &cfg, 1); } static bool hashlimit_mt_v2(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_hashlimit_mtinfo2 *info = par->matchinfo; struct xt_hashlimit_htable *hinfo = info->hinfo; struct hashlimit_cfg3 cfg = {}; int ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 2); if (ret) return ret; return hashlimit_mt_common(skb, par, hinfo, &cfg, 2); } static bool hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_hashlimit_mtinfo3 *info = par->matchinfo; struct xt_hashlimit_htable *hinfo = info->hinfo; return hashlimit_mt_common(skb, par, hinfo, &info->cfg, 3); } #define HASHLIMIT_MAX_SIZE 1048576 static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, struct xt_hashlimit_htable **hinfo, struct hashlimit_cfg3 *cfg, const char *name, int revision) { struct net *net = par->net; int ret; if (cfg->gc_interval == 0 || cfg->expire == 0) return -EINVAL; if (cfg->size > HASHLIMIT_MAX_SIZE) { cfg->size = HASHLIMIT_MAX_SIZE; pr_info_ratelimited("size too large, truncated to %u\n", cfg->size); } if (cfg->max > HASHLIMIT_MAX_SIZE) { cfg->max = HASHLIMIT_MAX_SIZE; pr_info_ratelimited("max too large, truncated to %u\n", cfg->max); } if (par->family == NFPROTO_IPV4) { if (cfg->srcmask > 32 || cfg->dstmask > 32) return -EINVAL; } else { if (cfg->srcmask > 128 || cfg->dstmask > 128) return -EINVAL; } if (cfg->mode & ~XT_HASHLIMIT_ALL) { pr_info_ratelimited("Unknown mode mask %X, kernel too old?\n", cfg->mode); return -EINVAL; } /* Check for overflow. */ if (revision >= 3 && cfg->mode & XT_HASHLIMIT_RATE_MATCH) { if (cfg->avg == 0 || cfg->avg > U32_MAX) { pr_info_ratelimited("invalid rate\n"); return -ERANGE; } if (cfg->interval == 0) { pr_info_ratelimited("invalid interval\n"); return -EINVAL; } } else if (cfg->mode & XT_HASHLIMIT_BYTES) { if (user2credits_byte(cfg->avg) == 0) { pr_info_ratelimited("overflow, rate too high: %llu\n", cfg->avg); return -EINVAL; } } else if (cfg->burst == 0 || user2credits(cfg->avg * cfg->burst, revision) < user2credits(cfg->avg, revision)) { pr_info_ratelimited("overflow, try lower: %llu/%llu\n", cfg->avg, cfg->burst); return -ERANGE; } mutex_lock(&hashlimit_mutex); *hinfo = htable_find_get(net, name, par->family); if (*hinfo == NULL) { ret = htable_create(net, cfg, name, par->family, hinfo, revision); if (ret < 0) { mutex_unlock(&hashlimit_mutex); return ret; } } mutex_unlock(&hashlimit_mutex); return 0; } static int hashlimit_mt_check_v1(const struct xt_mtchk_param *par) { struct xt_hashlimit_mtinfo1 *info = par->matchinfo; struct hashlimit_cfg3 cfg = {}; int ret; ret = xt_check_proc_name(info->name, sizeof(info->name)); if (ret) return ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 1); if (ret) return ret; return hashlimit_mt_check_common(par, &info->hinfo, &cfg, info->name, 1); } static int hashlimit_mt_check_v2(const struct xt_mtchk_param *par) { struct xt_hashlimit_mtinfo2 *info = par->matchinfo; struct hashlimit_cfg3 cfg = {}; int ret; ret = xt_check_proc_name(info->name, sizeof(info->name)); if (ret) return ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 2); if (ret) return ret; return hashlimit_mt_check_common(par, &info->hinfo, &cfg, info->name, 2); } static int hashlimit_mt_check(const struct xt_mtchk_param *par) { struct xt_hashlimit_mtinfo3 *info = par->matchinfo; int ret; ret = xt_check_proc_name(info->name, sizeof(info->name)); if (ret) return ret; return hashlimit_mt_check_common(par, &info->hinfo, &info->cfg, info->name, 3); } static void hashlimit_mt_destroy_v2(const struct xt_mtdtor_param *par) { const struct xt_hashlimit_mtinfo2 *info = par->matchinfo; htable_put(info->hinfo); } static void hashlimit_mt_destroy_v1(const struct xt_mtdtor_param *par) { const struct xt_hashlimit_mtinfo1 *info = par->matchinfo; htable_put(info->hinfo); } static void hashlimit_mt_destroy(const struct xt_mtdtor_param *par) { const struct xt_hashlimit_mtinfo3 *info = par->matchinfo; htable_put(info->hinfo); } static struct xt_match hashlimit_mt_reg[] __read_mostly = { { .name = "hashlimit", .revision = 1, .family = NFPROTO_IPV4, .match = hashlimit_mt_v1, .matchsize = sizeof(struct xt_hashlimit_mtinfo1), .usersize = offsetof(struct xt_hashlimit_mtinfo1, hinfo), .checkentry = hashlimit_mt_check_v1, .destroy = hashlimit_mt_destroy_v1, .me = THIS_MODULE, }, { .name = "hashlimit", .revision = 2, .family = NFPROTO_IPV4, .match = hashlimit_mt_v2, .matchsize = sizeof(struct xt_hashlimit_mtinfo2), .usersize = offsetof(struct xt_hashlimit_mtinfo2, hinfo), .checkentry = hashlimit_mt_check_v2, .destroy = hashlimit_mt_destroy_v2, .me = THIS_MODULE, }, { .name = "hashlimit", .revision = 3, .family = NFPROTO_IPV4, .match = hashlimit_mt, .matchsize = sizeof(struct xt_hashlimit_mtinfo3), .usersize = offsetof(struct xt_hashlimit_mtinfo3, hinfo), .checkentry = hashlimit_mt_check, .destroy = hashlimit_mt_destroy, .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "hashlimit", .revision = 1, .family = NFPROTO_IPV6, .match = hashlimit_mt_v1, .matchsize = sizeof(struct xt_hashlimit_mtinfo1), .usersize = offsetof(struct xt_hashlimit_mtinfo1, hinfo), .checkentry = hashlimit_mt_check_v1, .destroy = hashlimit_mt_destroy_v1, .me = THIS_MODULE, }, { .name = "hashlimit", .revision = 2, .family = NFPROTO_IPV6, .match = hashlimit_mt_v2, .matchsize = sizeof(struct xt_hashlimit_mtinfo2), .usersize = offsetof(struct xt_hashlimit_mtinfo2, hinfo), .checkentry = hashlimit_mt_check_v2, .destroy = hashlimit_mt_destroy_v2, .me = THIS_MODULE, }, { .name = "hashlimit", .revision = 3, .family = NFPROTO_IPV6, .match = hashlimit_mt, .matchsize = sizeof(struct xt_hashlimit_mtinfo3), .usersize = offsetof(struct xt_hashlimit_mtinfo3, hinfo), .checkentry = hashlimit_mt_check, .destroy = hashlimit_mt_destroy, .me = THIS_MODULE, }, #endif }; /* PROC stuff */ static void *dl_seq_start(struct seq_file *s, loff_t *pos) __acquires(htable->lock) { struct xt_hashlimit_htable *htable = pde_data(file_inode(s->file)); unsigned int *bucket; spin_lock_bh(&htable->lock); if (*pos >= htable->cfg.size) return NULL; bucket = kmalloc(sizeof(unsigned int), GFP_ATOMIC); if (!bucket) return ERR_PTR(-ENOMEM); *bucket = *pos; return bucket; } static void *dl_seq_next(struct seq_file *s, void *v, loff_t *pos) { struct xt_hashlimit_htable *htable = pde_data(file_inode(s->file)); unsigned int *bucket = v; *pos = ++(*bucket); if (*pos >= htable->cfg.size) { kfree(v); return NULL; } return bucket; } static void dl_seq_stop(struct seq_file *s, void *v) __releases(htable->lock) { struct xt_hashlimit_htable *htable = pde_data(file_inode(s->file)); unsigned int *bucket = v; if (!IS_ERR(bucket)) kfree(bucket); spin_unlock_bh(&htable->lock); } static void dl_seq_print(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { switch (family) { case NFPROTO_IPV4: seq_printf(s, "%ld %pI4:%u->%pI4:%u %llu %llu %llu\n", (long)(ent->expires - jiffies)/HZ, &ent->dst.ip.src, ntohs(ent->dst.src_port), &ent->dst.ip.dst, ntohs(ent->dst.dst_port), ent->rateinfo.credit, ent->rateinfo.credit_cap, ent->rateinfo.cost); break; #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) case NFPROTO_IPV6: seq_printf(s, "%ld %pI6:%u->%pI6:%u %llu %llu %llu\n", (long)(ent->expires - jiffies)/HZ, &ent->dst.ip6.src, ntohs(ent->dst.src_port), &ent->dst.ip6.dst, ntohs(ent->dst.dst_port), ent->rateinfo.credit, ent->rateinfo.credit_cap, ent->rateinfo.cost); break; #endif default: BUG(); } } static int dl_seq_real_show_v2(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { struct xt_hashlimit_htable *ht = pde_data(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ rateinfo_recalc(ent, jiffies, ht->cfg.mode, 2); dl_seq_print(ent, family, s); spin_unlock(&ent->lock); return seq_has_overflowed(s); } static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { struct xt_hashlimit_htable *ht = pde_data(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ rateinfo_recalc(ent, jiffies, ht->cfg.mode, 1); dl_seq_print(ent, family, s); spin_unlock(&ent->lock); return seq_has_overflowed(s); } static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { struct xt_hashlimit_htable *ht = pde_data(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ rateinfo_recalc(ent, jiffies, ht->cfg.mode, 3); dl_seq_print(ent, family, s); spin_unlock(&ent->lock); return seq_has_overflowed(s); } static int dl_seq_show_v2(struct seq_file *s, void *v) { struct xt_hashlimit_htable *htable = pde_data(file_inode(s->file)); unsigned int *bucket = (unsigned int *)v; struct dsthash_ent *ent; if (!hlist_empty(&htable->hash[*bucket])) { hlist_for_each_entry(ent, &htable->hash[*bucket], node) if (dl_seq_real_show_v2(ent, htable->family, s)) return -1; } return 0; } static int dl_seq_show_v1(struct seq_file *s, void *v) { struct xt_hashlimit_htable *htable = pde_data(file_inode(s->file)); unsigned int *bucket = v; struct dsthash_ent *ent; if (!hlist_empty(&htable->hash[*bucket])) { hlist_for_each_entry(ent, &htable->hash[*bucket], node) if (dl_seq_real_show_v1(ent, htable->family, s)) return -1; } return 0; } static int dl_seq_show(struct seq_file *s, void *v) { struct xt_hashlimit_htable *htable = pde_data(file_inode(s->file)); unsigned int *bucket = v; struct dsthash_ent *ent; if (!hlist_empty(&htable->hash[*bucket])) { hlist_for_each_entry(ent, &htable->hash[*bucket], node) if (dl_seq_real_show(ent, htable->family, s)) return -1; } return 0; } static const struct seq_operations dl_seq_ops_v1 = { .start = dl_seq_start, .next = dl_seq_next, .stop = dl_seq_stop, .show = dl_seq_show_v1 }; static const struct seq_operations dl_seq_ops_v2 = { .start = dl_seq_start, .next = dl_seq_next, .stop = dl_seq_stop, .show = dl_seq_show_v2 }; static const struct seq_operations dl_seq_ops = { .start = dl_seq_start, .next = dl_seq_next, .stop = dl_seq_stop, .show = dl_seq_show }; static int __net_init hashlimit_proc_net_init(struct net *net) { struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); hashlimit_net->ipt_hashlimit = proc_mkdir("ipt_hashlimit", net->proc_net); if (!hashlimit_net->ipt_hashlimit) return -ENOMEM; #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) hashlimit_net->ip6t_hashlimit = proc_mkdir("ip6t_hashlimit", net->proc_net); if (!hashlimit_net->ip6t_hashlimit) { remove_proc_entry("ipt_hashlimit", net->proc_net); return -ENOMEM; } #endif return 0; } static void __net_exit hashlimit_proc_net_exit(struct net *net) { struct xt_hashlimit_htable *hinfo; struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); /* hashlimit_net_exit() is called before hashlimit_mt_destroy(). * Make sure that the parent ipt_hashlimit and ip6t_hashlimit proc * entries is empty before trying to remove it. */ mutex_lock(&hashlimit_mutex); hlist_for_each_entry(hinfo, &hashlimit_net->htables, node) htable_remove_proc_entry(hinfo); hashlimit_net->ipt_hashlimit = NULL; hashlimit_net->ip6t_hashlimit = NULL; mutex_unlock(&hashlimit_mutex); remove_proc_entry("ipt_hashlimit", net->proc_net); #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) remove_proc_entry("ip6t_hashlimit", net->proc_net); #endif } static int __net_init hashlimit_net_init(struct net *net) { struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); INIT_HLIST_HEAD(&hashlimit_net->htables); return hashlimit_proc_net_init(net); } static void __net_exit hashlimit_net_exit(struct net *net) { hashlimit_proc_net_exit(net); } static struct pernet_operations hashlimit_net_ops = { .init = hashlimit_net_init, .exit = hashlimit_net_exit, .id = &hashlimit_net_id, .size = sizeof(struct hashlimit_net), }; static int __init hashlimit_mt_init(void) { int err; err = register_pernet_subsys(&hashlimit_net_ops); if (err < 0) return err; err = xt_register_matches(hashlimit_mt_reg, ARRAY_SIZE(hashlimit_mt_reg)); if (err < 0) goto err1; err = -ENOMEM; hashlimit_cachep = kmem_cache_create("xt_hashlimit", sizeof(struct dsthash_ent), 0, 0, NULL); if (!hashlimit_cachep) { pr_warn("unable to create slab cache\n"); goto err2; } return 0; err2: xt_unregister_matches(hashlimit_mt_reg, ARRAY_SIZE(hashlimit_mt_reg)); err1: unregister_pernet_subsys(&hashlimit_net_ops); return err; } static void __exit hashlimit_mt_exit(void) { xt_unregister_matches(hashlimit_mt_reg, ARRAY_SIZE(hashlimit_mt_reg)); unregister_pernet_subsys(&hashlimit_net_ops); rcu_barrier(); kmem_cache_destroy(hashlimit_cachep); } module_init(hashlimit_mt_init); module_exit(hashlimit_mt_exit); |
| 1853 1623 1625 515 515 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Software nodes for the firmware node framework. * * Copyright (C) 2018, Intel Corporation * Author: Heikki Krogerus <heikki.krogerus@linux.intel.com> */ #include <linux/device.h> #include <linux/kernel.h> #include <linux/property.h> #include <linux/slab.h> #include "base.h" struct swnode { struct kobject kobj; struct fwnode_handle fwnode; const struct software_node *node; int id; /* hierarchy */ struct ida child_ids; struct list_head entry; struct list_head children; struct swnode *parent; unsigned int allocated:1; unsigned int managed:1; }; static DEFINE_IDA(swnode_root_ids); static struct kset *swnode_kset; #define kobj_to_swnode(_kobj_) container_of(_kobj_, struct swnode, kobj) static const struct fwnode_operations software_node_ops; bool is_software_node(const struct fwnode_handle *fwnode) { return !IS_ERR_OR_NULL(fwnode) && fwnode->ops == &software_node_ops; } EXPORT_SYMBOL_GPL(is_software_node); #define to_swnode(__fwnode) \ ({ \ typeof(__fwnode) __to_swnode_fwnode = __fwnode; \ \ is_software_node(__to_swnode_fwnode) ? \ container_of(__to_swnode_fwnode, \ struct swnode, fwnode) : NULL; \ }) static inline struct swnode *dev_to_swnode(struct device *dev) { struct fwnode_handle *fwnode = dev_fwnode(dev); if (!fwnode) return NULL; if (!is_software_node(fwnode)) fwnode = fwnode->secondary; return to_swnode(fwnode); } static struct swnode * software_node_to_swnode(const struct software_node *node) { struct swnode *swnode = NULL; struct kobject *k; if (!node) return NULL; spin_lock(&swnode_kset->list_lock); list_for_each_entry(k, &swnode_kset->list, entry) { swnode = kobj_to_swnode(k); if (swnode->node == node) break; swnode = NULL; } spin_unlock(&swnode_kset->list_lock); return swnode; } const struct software_node *to_software_node(const struct fwnode_handle *fwnode) { const struct swnode *swnode = to_swnode(fwnode); return swnode ? swnode->node : NULL; } EXPORT_SYMBOL_GPL(to_software_node); struct fwnode_handle *software_node_fwnode(const struct software_node *node) { struct swnode *swnode = software_node_to_swnode(node); return swnode ? &swnode->fwnode : NULL; } EXPORT_SYMBOL_GPL(software_node_fwnode); /* -------------------------------------------------------------------------- */ /* property_entry processing */ static const struct property_entry * property_entry_get(const struct property_entry *prop, const char *name) { if (!prop) return NULL; for (; prop->name; prop++) if (!strcmp(name, prop->name)) return prop; return NULL; } static const void *property_get_pointer(const struct property_entry *prop) { if (!prop->length) return NULL; return prop->is_inline ? &prop->value : prop->pointer; } static const void *property_entry_find(const struct property_entry *props, const char *propname, size_t length) { const struct property_entry *prop; const void *pointer; prop = property_entry_get(props, propname); if (!prop) return ERR_PTR(-EINVAL); pointer = property_get_pointer(prop); if (!pointer) return ERR_PTR(-ENODATA); if (length > prop->length) return ERR_PTR(-EOVERFLOW); return pointer; } static int property_entry_count_elems_of_size(const struct property_entry *props, const char *propname, size_t length) { const struct property_entry *prop; prop = property_entry_get(props, propname); if (!prop) return -EINVAL; return prop->length / length; } static int property_entry_read_int_array(const struct property_entry *props, const char *name, unsigned int elem_size, void *val, size_t nval) { const void *pointer; size_t length; if (!val) return property_entry_count_elems_of_size(props, name, elem_size); if (!is_power_of_2(elem_size) || elem_size > sizeof(u64)) return -ENXIO; length = nval * elem_size; pointer = property_entry_find(props, name, length); if (IS_ERR(pointer)) return PTR_ERR(pointer); memcpy(val, pointer, length); return 0; } static int property_entry_read_string_array(const struct property_entry *props, const char *propname, const char **strings, size_t nval) { const void *pointer; size_t length; int array_len; /* Find out the array length. */ array_len = property_entry_count_elems_of_size(props, propname, sizeof(const char *)); if (array_len < 0) return array_len; /* Return how many there are if strings is NULL. */ if (!strings) return array_len; array_len = min_t(size_t, nval, array_len); length = array_len * sizeof(*strings); pointer = property_entry_find(props, propname, length); if (IS_ERR(pointer)) return PTR_ERR(pointer); memcpy(strings, pointer, length); return array_len; } static void property_entry_free_data(const struct property_entry *p) { const char * const *src_str; size_t i, nval; if (p->type == DEV_PROP_STRING) { src_str = property_get_pointer(p); nval = p->length / sizeof(*src_str); for (i = 0; i < nval; i++) kfree(src_str[i]); } if (!p->is_inline) kfree(p->pointer); kfree(p->name); } static bool property_copy_string_array(const char **dst_ptr, const char * const *src_ptr, size_t nval) { int i; for (i = 0; i < nval; i++) { dst_ptr[i] = kstrdup(src_ptr[i], GFP_KERNEL); if (!dst_ptr[i] && src_ptr[i]) { while (--i >= 0) kfree(dst_ptr[i]); return false; } } return true; } static int property_entry_copy_data(struct property_entry *dst, const struct property_entry *src) { const void *pointer = property_get_pointer(src); void *dst_ptr; size_t nval; /* * Properties with no data should not be marked as stored * out of line. */ if (!src->is_inline && !src->length) return -ENODATA; /* * Reference properties are never stored inline as * they are too big. */ if (src->type == DEV_PROP_REF && src->is_inline) return -EINVAL; if (src->length <= sizeof(dst->value)) { dst_ptr = &dst->value; dst->is_inline = true; } else { dst_ptr = kmalloc(src->length, GFP_KERNEL); if (!dst_ptr) return -ENOMEM; dst->pointer = dst_ptr; } if (src->type == DEV_PROP_STRING) { nval = src->length / sizeof(const char *); if (!property_copy_string_array(dst_ptr, pointer, nval)) { if (!dst->is_inline) kfree(dst->pointer); return -ENOMEM; } } else { memcpy(dst_ptr, pointer, src->length); } dst->length = src->length; dst->type = src->type; dst->name = kstrdup(src->name, GFP_KERNEL); if (!dst->name) { property_entry_free_data(dst); return -ENOMEM; } return 0; } /** * property_entries_dup - duplicate array of properties * @properties: array of properties to copy * * This function creates a deep copy of the given NULL-terminated array * of property entries. */ struct property_entry * property_entries_dup(const struct property_entry *properties) { struct property_entry *p; int i, n = 0; int ret; if (!properties) return NULL; while (properties[n].name) n++; p = kcalloc(n + 1, sizeof(*p), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); for (i = 0; i < n; i++) { ret = property_entry_copy_data(&p[i], &properties[i]); if (ret) { while (--i >= 0) property_entry_free_data(&p[i]); kfree(p); return ERR_PTR(ret); } } return p; } EXPORT_SYMBOL_GPL(property_entries_dup); /** * property_entries_free - free previously allocated array of properties * @properties: array of properties to destroy * * This function frees given NULL-terminated array of property entries, * along with their data. */ void property_entries_free(const struct property_entry *properties) { const struct property_entry *p; if (!properties) return; for (p = properties; p->name; p++) property_entry_free_data(p); kfree(properties); } EXPORT_SYMBOL_GPL(property_entries_free); /* -------------------------------------------------------------------------- */ /* fwnode operations */ static struct fwnode_handle *software_node_get(struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); kobject_get(&swnode->kobj); return &swnode->fwnode; } static void software_node_put(struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); kobject_put(&swnode->kobj); } static bool software_node_property_present(const struct fwnode_handle *fwnode, const char *propname) { struct swnode *swnode = to_swnode(fwnode); return !!property_entry_get(swnode->node->properties, propname); } static int software_node_read_int_array(const struct fwnode_handle *fwnode, const char *propname, unsigned int elem_size, void *val, size_t nval) { struct swnode *swnode = to_swnode(fwnode); return property_entry_read_int_array(swnode->node->properties, propname, elem_size, val, nval); } static int software_node_read_string_array(const struct fwnode_handle *fwnode, const char *propname, const char **val, size_t nval) { struct swnode *swnode = to_swnode(fwnode); return property_entry_read_string_array(swnode->node->properties, propname, val, nval); } static const char * software_node_get_name(const struct fwnode_handle *fwnode) { const struct swnode *swnode = to_swnode(fwnode); return kobject_name(&swnode->kobj); } static const char * software_node_get_name_prefix(const struct fwnode_handle *fwnode) { struct fwnode_handle *parent; const char *prefix; parent = fwnode_get_parent(fwnode); if (!parent) return ""; /* Figure out the prefix from the parents. */ while (is_software_node(parent)) parent = fwnode_get_next_parent(parent); prefix = fwnode_get_name_prefix(parent); fwnode_handle_put(parent); /* Guess something if prefix was NULL. */ return prefix ?: "/"; } static struct fwnode_handle * software_node_get_parent(const struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); if (!swnode || !swnode->parent) return NULL; return fwnode_handle_get(&swnode->parent->fwnode); } static struct fwnode_handle * software_node_get_next_child(const struct fwnode_handle *fwnode, struct fwnode_handle *child) { struct swnode *p = to_swnode(fwnode); struct swnode *c = to_swnode(child); if (!p || list_empty(&p->children) || (c && list_is_last(&c->entry, &p->children))) { fwnode_handle_put(child); return NULL; } if (c) c = list_next_entry(c, entry); else c = list_first_entry(&p->children, struct swnode, entry); fwnode_handle_put(child); return fwnode_handle_get(&c->fwnode); } static struct fwnode_handle * software_node_get_named_child_node(const struct fwnode_handle *fwnode, const char *childname) { struct swnode *swnode = to_swnode(fwnode); struct swnode *child; if (!swnode || list_empty(&swnode->children)) return NULL; list_for_each_entry(child, &swnode->children, entry) { if (!strcmp(childname, kobject_name(&child->kobj))) { kobject_get(&child->kobj); return &child->fwnode; } } return NULL; } static int software_node_get_reference_args(const struct fwnode_handle *fwnode, const char *propname, const char *nargs_prop, unsigned int nargs, unsigned int index, struct fwnode_reference_args *args) { struct swnode *swnode = to_swnode(fwnode); const struct software_node_ref_args *ref_array; const struct software_node_ref_args *ref; const struct property_entry *prop; struct fwnode_handle *refnode; u32 nargs_prop_val; int error; int i; prop = property_entry_get(swnode->node->properties, propname); if (!prop) return -ENOENT; if (prop->type != DEV_PROP_REF) return -EINVAL; /* * We expect that references are never stored inline, even * single ones, as they are too big. */ if (prop->is_inline) return -EINVAL; if (index * sizeof(*ref) >= prop->length) return -ENOENT; ref_array = prop->pointer; ref = &ref_array[index]; refnode = software_node_fwnode(ref->node); if (!refnode) return -ENOENT; if (nargs_prop) { error = property_entry_read_int_array(ref->node->properties, nargs_prop, sizeof(u32), &nargs_prop_val, 1); if (error) return error; nargs = nargs_prop_val; } if (nargs > NR_FWNODE_REFERENCE_ARGS) return -EINVAL; if (!args) return 0; args->fwnode = software_node_get(refnode); args->nargs = nargs; for (i = 0; i < nargs; i++) args->args[i] = ref->args[i]; return 0; } static struct fwnode_handle * swnode_graph_find_next_port(const struct fwnode_handle *parent, struct fwnode_handle *port) { struct fwnode_handle *old = port; while ((port = software_node_get_next_child(parent, old))) { /* * fwnode ports have naming style "port@", so we search for any * children that follow that convention. */ if (!strncmp(to_swnode(port)->node->name, "port@", strlen("port@"))) return port; old = port; } return NULL; } static struct fwnode_handle * software_node_graph_get_next_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle *endpoint) { struct swnode *swnode = to_swnode(fwnode); struct fwnode_handle *parent; struct fwnode_handle *port; if (!swnode) return NULL; if (endpoint) { port = software_node_get_parent(endpoint); parent = software_node_get_parent(port); } else { parent = software_node_get_named_child_node(fwnode, "ports"); if (!parent) parent = software_node_get(&swnode->fwnode); port = swnode_graph_find_next_port(parent, NULL); } for (; port; port = swnode_graph_find_next_port(parent, port)) { endpoint = software_node_get_next_child(port, endpoint); if (endpoint) { fwnode_handle_put(port); break; } } fwnode_handle_put(parent); return endpoint; } static struct fwnode_handle * software_node_graph_get_remote_endpoint(const struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); const struct software_node_ref_args *ref; const struct property_entry *prop; if (!swnode) return NULL; prop = property_entry_get(swnode->node->properties, "remote-endpoint"); if (!prop || prop->type != DEV_PROP_REF || prop->is_inline) return NULL; ref = prop->pointer; return software_node_get(software_node_fwnode(ref[0].node)); } static struct fwnode_handle * software_node_graph_get_port_parent(struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); swnode = swnode->parent; if (swnode && !strcmp(swnode->node->name, "ports")) swnode = swnode->parent; return swnode ? software_node_get(&swnode->fwnode) : NULL; } static int software_node_graph_parse_endpoint(const struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint) { struct swnode *swnode = to_swnode(fwnode); const char *parent_name = swnode->parent->node->name; int ret; if (strlen("port@") >= strlen(parent_name) || strncmp(parent_name, "port@", strlen("port@"))) return -EINVAL; /* Ports have naming style "port@n", we need to select the n */ ret = kstrtou32(parent_name + strlen("port@"), 10, &endpoint->port); if (ret) return ret; endpoint->id = swnode->id; endpoint->local_fwnode = fwnode; return 0; } static const struct fwnode_operations software_node_ops = { .get = software_node_get, .put = software_node_put, .property_present = software_node_property_present, .property_read_int_array = software_node_read_int_array, .property_read_string_array = software_node_read_string_array, .get_name = software_node_get_name, .get_name_prefix = software_node_get_name_prefix, .get_parent = software_node_get_parent, .get_next_child_node = software_node_get_next_child, .get_named_child_node = software_node_get_named_child_node, .get_reference_args = software_node_get_reference_args, .graph_get_next_endpoint = software_node_graph_get_next_endpoint, .graph_get_remote_endpoint = software_node_graph_get_remote_endpoint, .graph_get_port_parent = software_node_graph_get_port_parent, .graph_parse_endpoint = software_node_graph_parse_endpoint, }; /* -------------------------------------------------------------------------- */ /** * software_node_find_by_name - Find software node by name * @parent: Parent of the software node * @name: Name of the software node * * The function will find a node that is child of @parent and that is named * @name. If no node is found, the function returns NULL. * * NOTE: you will need to drop the reference with fwnode_handle_put() after use. */ const struct software_node * software_node_find_by_name(const struct software_node *parent, const char *name) { struct swnode *swnode = NULL; struct kobject *k; if (!name) return NULL; spin_lock(&swnode_kset->list_lock); list_for_each_entry(k, &swnode_kset->list, entry) { swnode = kobj_to_swnode(k); if (parent == swnode->node->parent && swnode->node->name && !strcmp(name, swnode->node->name)) { kobject_get(&swnode->kobj); break; } swnode = NULL; } spin_unlock(&swnode_kset->list_lock); return swnode ? swnode->node : NULL; } EXPORT_SYMBOL_GPL(software_node_find_by_name); static struct software_node *software_node_alloc(const struct property_entry *properties) { struct property_entry *props; struct software_node *node; props = property_entries_dup(properties); if (IS_ERR(props)) return ERR_CAST(props); node = kzalloc(sizeof(*node), GFP_KERNEL); if (!node) { property_entries_free(props); return ERR_PTR(-ENOMEM); } node->properties = props; return node; } static void software_node_free(const struct software_node *node) { property_entries_free(node->properties); kfree(node); } static void software_node_release(struct kobject *kobj) { struct swnode *swnode = kobj_to_swnode(kobj); if (swnode->parent) { ida_simple_remove(&swnode->parent->child_ids, swnode->id); list_del(&swnode->entry); } else { ida_simple_remove(&swnode_root_ids, swnode->id); } if (swnode->allocated) software_node_free(swnode->node); ida_destroy(&swnode->child_ids); kfree(swnode); } static struct kobj_type software_node_type = { .release = software_node_release, .sysfs_ops = &kobj_sysfs_ops, }; static struct fwnode_handle * swnode_register(const struct software_node *node, struct swnode *parent, unsigned int allocated) { struct swnode *swnode; int ret; swnode = kzalloc(sizeof(*swnode), GFP_KERNEL); if (!swnode) return ERR_PTR(-ENOMEM); ret = ida_simple_get(parent ? &parent->child_ids : &swnode_root_ids, 0, 0, GFP_KERNEL); if (ret < 0) { kfree(swnode); return ERR_PTR(ret); } swnode->id = ret; swnode->node = node; swnode->parent = parent; swnode->kobj.kset = swnode_kset; fwnode_init(&swnode->fwnode, &software_node_ops); ida_init(&swnode->child_ids); INIT_LIST_HEAD(&swnode->entry); INIT_LIST_HEAD(&swnode->children); if (node->name) ret = kobject_init_and_add(&swnode->kobj, &software_node_type, parent ? &parent->kobj : NULL, "%s", node->name); else ret = kobject_init_and_add(&swnode->kobj, &software_node_type, parent ? &parent->kobj : NULL, "node%d", swnode->id); if (ret) { kobject_put(&swnode->kobj); return ERR_PTR(ret); } /* * Assign the flag only in the successful case, so * the above kobject_put() won't mess up with properties. */ swnode->allocated = allocated; if (parent) list_add_tail(&swnode->entry, &parent->children); kobject_uevent(&swnode->kobj, KOBJ_ADD); return &swnode->fwnode; } /** * software_node_register_nodes - Register an array of software nodes * @nodes: Zero terminated array of software nodes to be registered * * Register multiple software nodes at once. If any node in the array * has its .parent pointer set (which can only be to another software_node), * then its parent **must** have been registered before it is; either outside * of this function or by ordering the array such that parent comes before * child. */ int software_node_register_nodes(const struct software_node *nodes) { int ret; int i; for (i = 0; nodes[i].name; i++) { const struct software_node *parent = nodes[i].parent; if (parent && !software_node_to_swnode(parent)) { ret = -EINVAL; goto err_unregister_nodes; } ret = software_node_register(&nodes[i]); if (ret) goto err_unregister_nodes; } return 0; err_unregister_nodes: software_node_unregister_nodes(nodes); return ret; } EXPORT_SYMBOL_GPL(software_node_register_nodes); /** * software_node_unregister_nodes - Unregister an array of software nodes * @nodes: Zero terminated array of software nodes to be unregistered * * Unregister multiple software nodes at once. If parent pointers are set up * in any of the software nodes then the array **must** be ordered such that * parents come before their children. * * NOTE: If you are uncertain whether the array is ordered such that * parents will be unregistered before their children, it is wiser to * remove the nodes individually, in the correct order (child before * parent). */ void software_node_unregister_nodes(const struct software_node *nodes) { unsigned int i = 0; while (nodes[i].name) i++; while (i--) software_node_unregister(&nodes[i]); } EXPORT_SYMBOL_GPL(software_node_unregister_nodes); /** * software_node_register_node_group - Register a group of software nodes * @node_group: NULL terminated array of software node pointers to be registered * * Register multiple software nodes at once. If any node in the array * has its .parent pointer set (which can only be to another software_node), * then its parent **must** have been registered before it is; either outside * of this function or by ordering the array such that parent comes before * child. */ int software_node_register_node_group(const struct software_node **node_group) { unsigned int i; int ret; if (!node_group) return 0; for (i = 0; node_group[i]; i++) { ret = software_node_register(node_group[i]); if (ret) { software_node_unregister_node_group(node_group); return ret; } } return 0; } EXPORT_SYMBOL_GPL(software_node_register_node_group); /** * software_node_unregister_node_group - Unregister a group of software nodes * @node_group: NULL terminated array of software node pointers to be unregistered * * Unregister multiple software nodes at once. If parent pointers are set up * in any of the software nodes then the array **must** be ordered such that * parents come before their children. * * NOTE: If you are uncertain whether the array is ordered such that * parents will be unregistered before their children, it is wiser to * remove the nodes individually, in the correct order (child before * parent). */ void software_node_unregister_node_group( const struct software_node **node_group) { unsigned int i = 0; if (!node_group) return; while (node_group[i]) i++; while (i--) software_node_unregister(node_group[i]); } EXPORT_SYMBOL_GPL(software_node_unregister_node_group); /** * software_node_register - Register static software node * @node: The software node to be registered */ int software_node_register(const struct software_node *node) { struct swnode *parent = software_node_to_swnode(node->parent); if (software_node_to_swnode(node)) return -EEXIST; if (node->parent && !parent) return -EINVAL; return PTR_ERR_OR_ZERO(swnode_register(node, parent, 0)); } EXPORT_SYMBOL_GPL(software_node_register); /** * software_node_unregister - Unregister static software node * @node: The software node to be unregistered */ void software_node_unregister(const struct software_node *node) { struct swnode *swnode; swnode = software_node_to_swnode(node); if (swnode) fwnode_remove_software_node(&swnode->fwnode); } EXPORT_SYMBOL_GPL(software_node_unregister); struct fwnode_handle * fwnode_create_software_node(const struct property_entry *properties, const struct fwnode_handle *parent) { struct fwnode_handle *fwnode; struct software_node *node; struct swnode *p; if (IS_ERR(parent)) return ERR_CAST(parent); p = to_swnode(parent); if (parent && !p) return ERR_PTR(-EINVAL); node = software_node_alloc(properties); if (IS_ERR(node)) return ERR_CAST(node); node->parent = p ? p->node : NULL; fwnode = swnode_register(node, p, 1); if (IS_ERR(fwnode)) software_node_free(node); return fwnode; } EXPORT_SYMBOL_GPL(fwnode_create_software_node); void fwnode_remove_software_node(struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); if (!swnode) return; kobject_put(&swnode->kobj); } EXPORT_SYMBOL_GPL(fwnode_remove_software_node); /** * device_add_software_node - Assign software node to a device * @dev: The device the software node is meant for. * @node: The software node. * * This function will make @node the secondary firmware node pointer of @dev. If * @dev has no primary node, then @node will become the primary node. The * function will register @node automatically if it wasn't already registered. */ int device_add_software_node(struct device *dev, const struct software_node *node) { struct swnode *swnode; int ret; /* Only one software node per device. */ if (dev_to_swnode(dev)) return -EBUSY; swnode = software_node_to_swnode(node); if (swnode) { kobject_get(&swnode->kobj); } else { ret = software_node_register(node); if (ret) return ret; swnode = software_node_to_swnode(node); } set_secondary_fwnode(dev, &swnode->fwnode); /* * If the device has been fully registered by the time this function is * called, software_node_notify() must be called separately so that the * symlinks get created and the reference count of the node is kept in * balance. */ if (device_is_registered(dev)) software_node_notify(dev); return 0; } EXPORT_SYMBOL_GPL(device_add_software_node); /** * device_remove_software_node - Remove device's software node * @dev: The device with the software node. * * This function will unregister the software node of @dev. */ void device_remove_software_node(struct device *dev) { struct swnode *swnode; swnode = dev_to_swnode(dev); if (!swnode) return; if (device_is_registered(dev)) software_node_notify_remove(dev); set_secondary_fwnode(dev, NULL); kobject_put(&swnode->kobj); } EXPORT_SYMBOL_GPL(device_remove_software_node); /** * device_create_managed_software_node - Create a software node for a device * @dev: The device the software node is assigned to. * @properties: Device properties for the software node. * @parent: Parent of the software node. * * Creates a software node as a managed resource for @dev, which means the * lifetime of the newly created software node is tied to the lifetime of @dev. * Software nodes created with this function should not be reused or shared * because of that. The function takes a deep copy of @properties for the * software node. * * Since the new software node is assigned directly to @dev, and since it should * not be shared, it is not returned to the caller. The function returns 0 on * success, and errno in case of an error. */ int device_create_managed_software_node(struct device *dev, const struct property_entry *properties, const struct software_node *parent) { struct fwnode_handle *p = software_node_fwnode(parent); struct fwnode_handle *fwnode; if (parent && !p) return -EINVAL; fwnode = fwnode_create_software_node(properties, p); if (IS_ERR(fwnode)) return PTR_ERR(fwnode); to_swnode(fwnode)->managed = true; set_secondary_fwnode(dev, fwnode); if (device_is_registered(dev)) software_node_notify(dev); return 0; } EXPORT_SYMBOL_GPL(device_create_managed_software_node); void software_node_notify(struct device *dev) { struct swnode *swnode; int ret; swnode = dev_to_swnode(dev); if (!swnode) return; ret = sysfs_create_link(&dev->kobj, &swnode->kobj, "software_node"); if (ret) return; ret = sysfs_create_link(&swnode->kobj, &dev->kobj, dev_name(dev)); if (ret) { sysfs_remove_link(&dev->kobj, "software_node"); return; } kobject_get(&swnode->kobj); } void software_node_notify_remove(struct device *dev) { struct swnode *swnode; swnode = dev_to_swnode(dev); if (!swnode) return; sysfs_remove_link(&swnode->kobj, dev_name(dev)); sysfs_remove_link(&dev->kobj, "software_node"); kobject_put(&swnode->kobj); if (swnode->managed) { set_secondary_fwnode(dev, NULL); kobject_put(&swnode->kobj); } } static int __init software_node_init(void) { swnode_kset = kset_create_and_add("software_nodes", NULL, kernel_kobj); if (!swnode_kset) return -ENOMEM; return 0; } postcore_initcall(software_node_init); static void __exit software_node_exit(void) { ida_destroy(&swnode_root_ids); kset_unregister(swnode_kset); } __exitcall(software_node_exit); |
| 13899 14187 13899 480 72 72 72 1594 1594 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Common capabilities, needed by capability.o. */ #include <linux/capability.h> #include <linux/audit.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/lsm_hooks.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/ptrace.h> #include <linux/xattr.h> #include <linux/hugetlb.h> #include <linux/mount.h> #include <linux/sched.h> #include <linux/prctl.h> #include <linux/securebits.h> #include <linux/user_namespace.h> #include <linux/binfmts.h> #include <linux/personality.h> #include <linux/mnt_idmapping.h> /* * If a non-root user executes a setuid-root binary in * !secure(SECURE_NOROOT) mode, then we raise capabilities. * However if fE is also set, then the intent is for only * the file capabilities to be applied, and the setuid-root * bit is left on either to change the uid (plausible) or * to get full privilege on a kernel without file capabilities * support. So in that case we do not raise capabilities. * * Warn if that happens, once per boot. */ static void warn_setuid_and_fcaps_mixed(const char *fname) { static int warned; if (!warned) { printk(KERN_INFO "warning: `%s' has both setuid-root and" " effective capabilities. Therefore not raising all" " capabilities.\n", fname); warned = 1; } } /** * cap_capable - Determine whether a task has a particular effective capability * @cred: The credentials to use * @targ_ns: The user namespace in which we need the capability * @cap: The capability to check for * @opts: Bitmask of options defined in include/linux/security.h * * Determine whether the nominated task has the specified capability amongst * its effective set, returning 0 if it does, -ve if it does not. * * NOTE WELL: cap_has_capability() cannot be used like the kernel's capable() * and has_capability() functions. That is, it has the reverse semantics: * cap_has_capability() returns 0 when a task has a capability, but the * kernel's capable() and has_capability() returns 1 for this case. */ int cap_capable(const struct cred *cred, struct user_namespace *targ_ns, int cap, unsigned int opts) { struct user_namespace *ns = targ_ns; /* See if cred has the capability in the target user namespace * by examining the target user namespace and all of the target * user namespace's parents. */ for (;;) { /* Do we have the necessary capabilities? */ if (ns == cred->user_ns) return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM; /* * If we're already at a lower level than we're looking for, * we're done searching. */ if (ns->level <= cred->user_ns->level) return -EPERM; /* * The owner of the user namespace in the parent of the * user namespace has all caps. */ if ((ns->parent == cred->user_ns) && uid_eq(ns->owner, cred->euid)) return 0; /* * If you have a capability in a parent user ns, then you have * it over all children user namespaces as well. */ ns = ns->parent; } /* We never get here */ } /** * cap_settime - Determine whether the current process may set the system clock * @ts: The time to set * @tz: The timezone to set * * Determine whether the current process may set the system clock and timezone * information, returning 0 if permission granted, -ve if denied. */ int cap_settime(const struct timespec64 *ts, const struct timezone *tz) { if (!capable(CAP_SYS_TIME)) return -EPERM; return 0; } /** * cap_ptrace_access_check - Determine whether the current process may access * another * @child: The process to be accessed * @mode: The mode of attachment. * * If we are in the same or an ancestor user_ns and have all the target * task's capabilities, then ptrace access is allowed. * If we have the ptrace capability to the target user_ns, then ptrace * access is allowed. * Else denied. * * Determine whether a process may access another, returning 0 if permission * granted, -ve if denied. */ int cap_ptrace_access_check(struct task_struct *child, unsigned int mode) { int ret = 0; const struct cred *cred, *child_cred; const kernel_cap_t *caller_caps; rcu_read_lock(); cred = current_cred(); child_cred = __task_cred(child); if (mode & PTRACE_MODE_FSCREDS) caller_caps = &cred->cap_effective; else caller_caps = &cred->cap_permitted; if (cred->user_ns == child_cred->user_ns && cap_issubset(child_cred->cap_permitted, *caller_caps)) goto out; if (ns_capable(child_cred->user_ns, CAP_SYS_PTRACE)) goto out; ret = -EPERM; out: rcu_read_unlock(); return ret; } /** * cap_ptrace_traceme - Determine whether another process may trace the current * @parent: The task proposed to be the tracer * * If parent is in the same or an ancestor user_ns and has all current's * capabilities, then ptrace access is allowed. * If parent has the ptrace capability to current's user_ns, then ptrace * access is allowed. * Else denied. * * Determine whether the nominated task is permitted to trace the current * process, returning 0 if permission is granted, -ve if denied. */ int cap_ptrace_traceme(struct task_struct *parent) { int ret = 0; const struct cred *cred, *child_cred; rcu_read_lock(); cred = __task_cred(parent); child_cred = current_cred(); if (cred->user_ns == child_cred->user_ns && cap_issubset(child_cred->cap_permitted, cred->cap_permitted)) goto out; if (has_ns_capability(parent, child_cred->user_ns, CAP_SYS_PTRACE)) goto out; ret = -EPERM; out: rcu_read_unlock(); return ret; } /** * cap_capget - Retrieve a task's capability sets * @target: The task from which to retrieve the capability sets * @effective: The place to record the effective set * @inheritable: The place to record the inheritable set * @permitted: The place to record the permitted set * * This function retrieves the capabilities of the nominated task and returns * them to the caller. */ int cap_capget(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { const struct cred *cred; /* Derived from kernel/capability.c:sys_capget. */ rcu_read_lock(); cred = __task_cred(target); *effective = cred->cap_effective; *inheritable = cred->cap_inheritable; *permitted = cred->cap_permitted; rcu_read_unlock(); return 0; } /* * Determine whether the inheritable capabilities are limited to the old * permitted set. Returns 1 if they are limited, 0 if they are not. */ static inline int cap_inh_is_capped(void) { /* they are so limited unless the current task has the CAP_SETPCAP * capability */ if (cap_capable(current_cred(), current_cred()->user_ns, CAP_SETPCAP, CAP_OPT_NONE) == 0) return 0; return 1; } /** * cap_capset - Validate and apply proposed changes to current's capabilities * @new: The proposed new credentials; alterations should be made here * @old: The current task's current credentials * @effective: A pointer to the proposed new effective capabilities set * @inheritable: A pointer to the proposed new inheritable capabilities set * @permitted: A pointer to the proposed new permitted capabilities set * * This function validates and applies a proposed mass change to the current * process's capability sets. The changes are made to the proposed new * credentials, and assuming no error, will be committed by the caller of LSM. */ int cap_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { if (cap_inh_is_capped() && !cap_issubset(*inheritable, cap_combine(old->cap_inheritable, old->cap_permitted))) /* incapable of using this inheritable set */ return -EPERM; if (!cap_issubset(*inheritable, cap_combine(old->cap_inheritable, old->cap_bset))) /* no new pI capabilities outside bounding set */ return -EPERM; /* verify restrictions on target's new Permitted set */ if (!cap_issubset(*permitted, old->cap_permitted)) return -EPERM; /* verify the _new_Effective_ is a subset of the _new_Permitted_ */ if (!cap_issubset(*effective, *permitted)) return -EPERM; new->cap_effective = *effective; new->cap_inheritable = *inheritable; new->cap_permitted = *permitted; /* * Mask off ambient bits that are no longer both permitted and * inheritable. */ new->cap_ambient = cap_intersect(new->cap_ambient, cap_intersect(*permitted, *inheritable)); if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EINVAL; return 0; } /** * cap_inode_need_killpriv - Determine if inode change affects privileges * @dentry: The inode/dentry in being changed with change marked ATTR_KILL_PRIV * * Determine if an inode having a change applied that's marked ATTR_KILL_PRIV * affects the security markings on that inode, and if it is, should * inode_killpriv() be invoked or the change rejected. * * Return: 1 if security.capability has a value, meaning inode_killpriv() * is required, 0 otherwise, meaning inode_killpriv() is not required. */ int cap_inode_need_killpriv(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); int error; error = __vfs_getxattr(dentry, inode, XATTR_NAME_CAPS, NULL, 0); return error > 0; } /** * cap_inode_killpriv - Erase the security markings on an inode * * @mnt_userns: user namespace of the mount the inode was found from * @dentry: The inode/dentry to alter * * Erase the privilege-enhancing security markings on an inode. * * If the inode has been found through an idmapped mount the user namespace of * the vfsmount must be passed through @mnt_userns. This function will then * take care to map the inode according to @mnt_userns before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply passs init_user_ns. * * Return: 0 if successful, -ve on error. */ int cap_inode_killpriv(struct user_namespace *mnt_userns, struct dentry *dentry) { int error; error = __vfs_removexattr(mnt_userns, dentry, XATTR_NAME_CAPS); if (error == -EOPNOTSUPP) error = 0; return error; } static bool rootid_owns_currentns(kuid_t kroot) { struct user_namespace *ns; if (!uid_valid(kroot)) return false; for (ns = current_user_ns(); ; ns = ns->parent) { if (from_kuid(ns, kroot) == 0) return true; if (ns == &init_user_ns) break; } return false; } static __u32 sansflags(__u32 m) { return m & ~VFS_CAP_FLAGS_EFFECTIVE; } static bool is_v2header(size_t size, const struct vfs_cap_data *cap) { if (size != XATTR_CAPS_SZ_2) return false; return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_2; } static bool is_v3header(size_t size, const struct vfs_cap_data *cap) { if (size != XATTR_CAPS_SZ_3) return false; return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_3; } /* * getsecurity: We are called for security.* before any attempt to read the * xattr from the inode itself. * * This gives us a chance to read the on-disk value and convert it. If we * return -EOPNOTSUPP, then vfs_getxattr() will call the i_op handler. * * Note we are not called by vfs_getxattr_alloc(), but that is only called * by the integrity subsystem, which really wants the unconverted values - * so that's good. */ int cap_inode_getsecurity(struct user_namespace *mnt_userns, struct inode *inode, const char *name, void **buffer, bool alloc) { int size, ret; kuid_t kroot; u32 nsmagic, magic; uid_t root, mappedroot; char *tmpbuf = NULL; struct vfs_cap_data *cap; struct vfs_ns_cap_data *nscap = NULL; struct dentry *dentry; struct user_namespace *fs_ns; if (strcmp(name, "capability") != 0) return -EOPNOTSUPP; dentry = d_find_any_alias(inode); if (!dentry) return -EINVAL; size = sizeof(struct vfs_ns_cap_data); ret = (int)vfs_getxattr_alloc(mnt_userns, dentry, XATTR_NAME_CAPS, &tmpbuf, size, GFP_NOFS); dput(dentry); if (ret < 0 || !tmpbuf) { size = ret; goto out_free; } fs_ns = inode->i_sb->s_user_ns; cap = (struct vfs_cap_data *) tmpbuf; if (is_v2header((size_t) ret, cap)) { root = 0; } else if (is_v3header((size_t) ret, cap)) { nscap = (struct vfs_ns_cap_data *) tmpbuf; root = le32_to_cpu(nscap->rootid); } else { size = -EINVAL; goto out_free; } kroot = make_kuid(fs_ns, root); /* If this is an idmapped mount shift the kuid. */ kroot = mapped_kuid_fs(mnt_userns, fs_ns, kroot); /* If the root kuid maps to a valid uid in current ns, then return * this as a nscap. */ mappedroot = from_kuid(current_user_ns(), kroot); if (mappedroot != (uid_t)-1 && mappedroot != (uid_t)0) { size = sizeof(struct vfs_ns_cap_data); if (alloc) { if (!nscap) { /* v2 -> v3 conversion */ nscap = kzalloc(size, GFP_ATOMIC); if (!nscap) { size = -ENOMEM; goto out_free; } nsmagic = VFS_CAP_REVISION_3; magic = le32_to_cpu(cap->magic_etc); if (magic & VFS_CAP_FLAGS_EFFECTIVE) nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); nscap->magic_etc = cpu_to_le32(nsmagic); } else { /* use allocated v3 buffer */ tmpbuf = NULL; } nscap->rootid = cpu_to_le32(mappedroot); *buffer = nscap; } goto out_free; } if (!rootid_owns_currentns(kroot)) { size = -EOVERFLOW; goto out_free; } /* This comes from a parent namespace. Return as a v2 capability */ size = sizeof(struct vfs_cap_data); if (alloc) { if (nscap) { /* v3 -> v2 conversion */ cap = kzalloc(size, GFP_ATOMIC); if (!cap) { size = -ENOMEM; goto out_free; } magic = VFS_CAP_REVISION_2; nsmagic = le32_to_cpu(nscap->magic_etc); if (nsmagic & VFS_CAP_FLAGS_EFFECTIVE) magic |= VFS_CAP_FLAGS_EFFECTIVE; memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32); cap->magic_etc = cpu_to_le32(magic); } else { /* use unconverted v2 */ tmpbuf = NULL; } *buffer = cap; } out_free: kfree(tmpbuf); return size; } /** * rootid_from_xattr - translate root uid of vfs caps * * @value: vfs caps value which may be modified by this function * @size: size of @ivalue * @task_ns: user namespace of the caller * @mnt_userns: user namespace of the mount the inode was found from * @fs_userns: user namespace of the filesystem * * If the inode has been found through an idmapped mount the user namespace of * the vfsmount must be passed through @mnt_userns. This function will then * take care to map the inode according to @mnt_userns before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply passs init_user_ns. */ static kuid_t rootid_from_xattr(const void *value, size_t size, struct user_namespace *task_ns, struct user_namespace *mnt_userns, struct user_namespace *fs_userns) { const struct vfs_ns_cap_data *nscap = value; kuid_t rootkid; uid_t rootid = 0; if (size == XATTR_CAPS_SZ_3) rootid = le32_to_cpu(nscap->rootid); rootkid = make_kuid(task_ns, rootid); return mapped_kuid_user(mnt_userns, fs_userns, rootkid); } static bool validheader(size_t size, const struct vfs_cap_data *cap) { return is_v2header(size, cap) || is_v3header(size, cap); } /** * cap_convert_nscap - check vfs caps * * @mnt_userns: user namespace of the mount the inode was found from * @dentry: used to retrieve inode to check permissions on * @ivalue: vfs caps value which may be modified by this function * @size: size of @ivalue * * User requested a write of security.capability. If needed, update the * xattr to change from v2 to v3, or to fixup the v3 rootid. * * If the inode has been found through an idmapped mount the user namespace of * the vfsmount must be passed through @mnt_userns. This function will then * take care to map the inode according to @mnt_userns before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply passs init_user_ns. * * Return: On success, return the new size; on error, return < 0. */ int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry, const void **ivalue, size_t size) { struct vfs_ns_cap_data *nscap; uid_t nsrootid; const struct vfs_cap_data *cap = *ivalue; __u32 magic, nsmagic; struct inode *inode = d_backing_inode(dentry); struct user_namespace *task_ns = current_user_ns(), *fs_ns = inode->i_sb->s_user_ns; kuid_t rootid; size_t newsize; if (!*ivalue) return -EINVAL; if (!validheader(size, cap)) return -EINVAL; if (!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_SETFCAP)) return -EPERM; if (size == XATTR_CAPS_SZ_2 && (mnt_userns == fs_ns)) if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP)) /* user is privileged, just write the v2 */ return size; rootid = rootid_from_xattr(*ivalue, size, task_ns, mnt_userns, fs_ns); if (!uid_valid(rootid)) return -EINVAL; nsrootid = from_kuid(fs_ns, rootid); if (nsrootid == -1) return -EINVAL; newsize = sizeof(struct vfs_ns_cap_data); nscap = kmalloc(newsize, GFP_ATOMIC); if (!nscap) return -ENOMEM; nscap->rootid = cpu_to_le32(nsrootid); nsmagic = VFS_CAP_REVISION_3; magic = le32_to_cpu(cap->magic_etc); if (magic & VFS_CAP_FLAGS_EFFECTIVE) nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; nscap->magic_etc = cpu_to_le32(nsmagic); memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); *ivalue = nscap; return newsize; } /* * Calculate the new process capability sets from the capability sets attached * to a file. */ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps, struct linux_binprm *bprm, bool *effective, bool *has_fcap) { struct cred *new = bprm->cred; unsigned i; int ret = 0; if (caps->magic_etc & VFS_CAP_FLAGS_EFFECTIVE) *effective = true; if (caps->magic_etc & VFS_CAP_REVISION_MASK) *has_fcap = true; CAP_FOR_EACH_U32(i) { __u32 permitted = caps->permitted.cap[i]; __u32 inheritable = caps->inheritable.cap[i]; /* * pP' = (X & fP) | (pI & fI) * The addition of pA' is handled later. */ new->cap_permitted.cap[i] = (new->cap_bset.cap[i] & permitted) | (new->cap_inheritable.cap[i] & inheritable); if (permitted & ~new->cap_permitted.cap[i]) /* insufficient to execute correctly */ ret = -EPERM; } /* * For legacy apps, with no internal support for recognizing they * do not have enough capabilities, we return an error if they are * missing some "forced" (aka file-permitted) capabilities. */ return *effective ? ret : 0; } /** * get_vfs_caps_from_disk - retrieve vfs caps from disk * * @mnt_userns: user namespace of the mount the inode was found from * @dentry: dentry from which @inode is retrieved * @cpu_caps: vfs capabilities * * Extract the on-exec-apply capability sets for an executable file. * * If the inode has been found through an idmapped mount the user namespace of * the vfsmount must be passed through @mnt_userns. This function will then * take care to map the inode according to @mnt_userns before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply passs init_user_ns. */ int get_vfs_caps_from_disk(struct user_namespace *mnt_userns, const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps) { struct inode *inode = d_backing_inode(dentry); __u32 magic_etc; unsigned tocopy, i; int size; struct vfs_ns_cap_data data, *nscaps = &data; struct vfs_cap_data *caps = (struct vfs_cap_data *) &data; kuid_t rootkuid; struct user_namespace *fs_ns; memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data)); if (!inode) return -ENODATA; fs_ns = inode->i_sb->s_user_ns; size = __vfs_getxattr((struct dentry *)dentry, inode, XATTR_NAME_CAPS, &data, XATTR_CAPS_SZ); if (size == -ENODATA || size == -EOPNOTSUPP) /* no data, that's ok */ return -ENODATA; if (size < 0) return size; if (size < sizeof(magic_etc)) return -EINVAL; cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps->magic_etc); rootkuid = make_kuid(fs_ns, 0); switch (magic_etc & VFS_CAP_REVISION_MASK) { case VFS_CAP_REVISION_1: if (size != XATTR_CAPS_SZ_1) return -EINVAL; tocopy = VFS_CAP_U32_1; break; case VFS_CAP_REVISION_2: if (size != XATTR_CAPS_SZ_2) return -EINVAL; tocopy = VFS_CAP_U32_2; break; case VFS_CAP_REVISION_3: if (size != XATTR_CAPS_SZ_3) return -EINVAL; tocopy = VFS_CAP_U32_3; rootkuid = make_kuid(fs_ns, le32_to_cpu(nscaps->rootid)); break; default: return -EINVAL; } /* Limit the caps to the mounter of the filesystem * or the more limited uid specified in the xattr. */ rootkuid = mapped_kuid_fs(mnt_userns, fs_ns, rootkuid); if (!rootid_owns_currentns(rootkuid)) return -ENODATA; CAP_FOR_EACH_U32(i) { if (i >= tocopy) break; cpu_caps->permitted.cap[i] = le32_to_cpu(caps->data[i].permitted); cpu_caps->inheritable.cap[i] = le32_to_cpu(caps->data[i].inheritable); } cpu_caps->permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; cpu_caps->inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; cpu_caps->rootid = rootkuid; return 0; } /* * Attempt to get the on-exec apply capability sets for an executable file from * its xattrs and, if present, apply them to the proposed credentials being * constructed by execve(). */ static int get_file_caps(struct linux_binprm *bprm, struct file *file, bool *effective, bool *has_fcap) { int rc = 0; struct cpu_vfs_cap_data vcaps; cap_clear(bprm->cred->cap_permitted); if (!file_caps_enabled) return 0; if (!mnt_may_suid(file->f_path.mnt)) return 0; /* * This check is redundant with mnt_may_suid() but is kept to make * explicit that capability bits are limited to s_user_ns and its * descendants. */ if (!current_in_userns(file->f_path.mnt->mnt_sb->s_user_ns)) return 0; rc = get_vfs_caps_from_disk(file_mnt_user_ns(file), file->f_path.dentry, &vcaps); if (rc < 0) { if (rc == -EINVAL) printk(KERN_NOTICE "Invalid argument reading file caps for %s\n", bprm->filename); else if (rc == -ENODATA) rc = 0; goto out; } rc = bprm_caps_from_vfs_caps(&vcaps, bprm, effective, has_fcap); out: if (rc) cap_clear(bprm->cred->cap_permitted); return rc; } static inline bool root_privileged(void) { return !issecure(SECURE_NOROOT); } static inline bool __is_real(kuid_t uid, struct cred *cred) { return uid_eq(cred->uid, uid); } static inline bool __is_eff(kuid_t uid, struct cred *cred) { return uid_eq(cred->euid, uid); } static inline bool __is_suid(kuid_t uid, struct cred *cred) { return !__is_real(uid, cred) && __is_eff(uid, cred); } /* * handle_privileged_root - Handle case of privileged root * @bprm: The execution parameters, including the proposed creds * @has_fcap: Are any file capabilities set? * @effective: Do we have effective root privilege? * @root_uid: This namespace' root UID WRT initial USER namespace * * Handle the case where root is privileged and hasn't been neutered by * SECURE_NOROOT. If file capabilities are set, they won't be combined with * set UID root and nothing is changed. If we are root, cap_permitted is * updated. If we have become set UID root, the effective bit is set. */ static void handle_privileged_root(struct linux_binprm *bprm, bool has_fcap, bool *effective, kuid_t root_uid) { const struct cred *old = current_cred(); struct cred *new = bprm->cred; if (!root_privileged()) return; /* * If the legacy file capability is set, then don't set privs * for a setuid root binary run by a non-root user. Do set it * for a root user just to cause least surprise to an admin. */ if (has_fcap && __is_suid(root_uid, new)) { warn_setuid_and_fcaps_mixed(bprm->filename); return; } /* * To support inheritance of root-permissions and suid-root * executables under compatibility mode, we override the * capability sets for the file. */ if (__is_eff(root_uid, new) || __is_real(root_uid, new)) { /* pP' = (cap_bset & ~0) | (pI & ~0) */ new->cap_permitted = cap_combine(old->cap_bset, old->cap_inheritable); } /* * If only the real uid is 0, we do not set the effective bit. */ if (__is_eff(root_uid, new)) *effective = true; } #define __cap_gained(field, target, source) \ !cap_issubset(target->cap_##field, source->cap_##field) #define __cap_grew(target, source, cred) \ !cap_issubset(cred->cap_##target, cred->cap_##source) #define __cap_full(field, cred) \ cap_issubset(CAP_FULL_SET, cred->cap_##field) static inline bool __is_setuid(struct cred *new, const struct cred *old) { return !uid_eq(new->euid, old->uid); } static inline bool __is_setgid(struct cred *new, const struct cred *old) { return !gid_eq(new->egid, old->gid); } /* * 1) Audit candidate if current->cap_effective is set * * We do not bother to audit if 3 things are true: * 1) cap_effective has all caps * 2) we became root *OR* are were already root * 3) root is supposed to have all caps (SECURE_NOROOT) * Since this is just a normal root execing a process. * * Number 1 above might fail if you don't have a full bset, but I think * that is interesting information to audit. * * A number of other conditions require logging: * 2) something prevented setuid root getting all caps * 3) non-setuid root gets fcaps * 4) non-setuid root gets ambient */ static inline bool nonroot_raised_pE(struct cred *new, const struct cred *old, kuid_t root, bool has_fcap) { bool ret = false; if ((__cap_grew(effective, ambient, new) && !(__cap_full(effective, new) && (__is_eff(root, new) || __is_real(root, new)) && root_privileged())) || (root_privileged() && __is_suid(root, new) && !__cap_full(effective, new)) || (!__is_setuid(new, old) && ((has_fcap && __cap_gained(permitted, new, old)) || __cap_gained(ambient, new, old)))) ret = true; return ret; } /** * cap_bprm_creds_from_file - Set up the proposed credentials for execve(). * @bprm: The execution parameters, including the proposed creds * @file: The file to pull the credentials from * * Set up the proposed credentials for a new execution context being * constructed by execve(). The proposed creds in @bprm->cred is altered, * which won't take effect immediately. * * Return: 0 if successful, -ve on error. */ int cap_bprm_creds_from_file(struct linux_binprm *bprm, struct file *file) { /* Process setpcap binaries and capabilities for uid 0 */ const struct cred *old = current_cred(); struct cred *new = bprm->cred; bool effective = false, has_fcap = false, is_setid; int ret; kuid_t root_uid; if (WARN_ON(!cap_ambient_invariant_ok(old))) return -EPERM; ret = get_file_caps(bprm, file, &effective, &has_fcap); if (ret < 0) return ret; root_uid = make_kuid(new->user_ns, 0); handle_privileged_root(bprm, has_fcap, &effective, root_uid); /* if we have fs caps, clear dangerous personality flags */ if (__cap_gained(permitted, new, old)) bprm->per_clear |= PER_CLEAR_ON_SETID; /* Don't let someone trace a set[ug]id/setpcap binary with the revised * credentials unless they have the appropriate permit. * * In addition, if NO_NEW_PRIVS, then ensure we get no new privs. */ is_setid = __is_setuid(new, old) || __is_setgid(new, old); if ((is_setid || __cap_gained(permitted, new, old)) && ((bprm->unsafe & ~LSM_UNSAFE_PTRACE) || !ptracer_capable(current, new->user_ns))) { /* downgrade; they get no more than they had, and maybe less */ if (!ns_capable(new->user_ns, CAP_SETUID) || (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS)) { new->euid = new->uid; new->egid = new->gid; } new->cap_permitted = cap_intersect(new->cap_permitted, old->cap_permitted); } new->suid = new->fsuid = new->euid; new->sgid = new->fsgid = new->egid; /* File caps or setid cancels ambient. */ if (has_fcap || is_setid) cap_clear(new->cap_ambient); /* * Now that we've computed pA', update pP' to give: * pP' = (X & fP) | (pI & fI) | pA' */ new->cap_permitted = cap_combine(new->cap_permitted, new->cap_ambient); /* * Set pE' = (fE ? pP' : pA'). Because pA' is zero if fE is set, * this is the same as pE' = (fE ? pP' : 0) | pA'. */ if (effective) new->cap_effective = new->cap_permitted; else new->cap_effective = new->cap_ambient; if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EPERM; if (nonroot_raised_pE(new, old, root_uid, has_fcap)) { ret = audit_log_bprm_fcaps(bprm, new, old); if (ret < 0) return ret; } new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EPERM; /* Check for privilege-elevated exec. */ if (is_setid || (!__is_real(root_uid, new) && (effective || __cap_grew(permitted, ambient, new)))) bprm->secureexec = 1; return 0; } /** * cap_inode_setxattr - Determine whether an xattr may be altered * @dentry: The inode/dentry being altered * @name: The name of the xattr to be changed * @value: The value that the xattr will be changed to * @size: The size of value * @flags: The replacement flag * * Determine whether an xattr may be altered or set on an inode, returning 0 if * permission is granted, -ve if denied. * * This is used to make sure security xattrs don't get updated or set by those * who aren't privileged to do so. */ int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct user_namespace *user_ns = dentry->d_sb->s_user_ns; /* Ignore non-security xattrs */ if (strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) != 0) return 0; /* * For XATTR_NAME_CAPS the check will be done in * cap_convert_nscap(), called by setxattr() */ if (strcmp(name, XATTR_NAME_CAPS) == 0) return 0; if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /** * cap_inode_removexattr - Determine whether an xattr may be removed * * @mnt_userns: User namespace of the mount the inode was found from * @dentry: The inode/dentry being altered * @name: The name of the xattr to be changed * * Determine whether an xattr may be removed from an inode, returning 0 if * permission is granted, -ve if denied. * * If the inode has been found through an idmapped mount the user namespace of * the vfsmount must be passed through @mnt_userns. This function will then * take care to map the inode according to @mnt_userns before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply passs init_user_ns. * * This is used to make sure security xattrs don't get removed by those who * aren't privileged to remove them. */ int cap_inode_removexattr(struct user_namespace *mnt_userns, struct dentry *dentry, const char *name) { struct user_namespace *user_ns = dentry->d_sb->s_user_ns; /* Ignore non-security xattrs */ if (strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) != 0) return 0; if (strcmp(name, XATTR_NAME_CAPS) == 0) { /* security.capability gets namespaced */ struct inode *inode = d_backing_inode(dentry); if (!inode) return -EINVAL; if (!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_SETFCAP)) return -EPERM; return 0; } if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /* * cap_emulate_setxuid() fixes the effective / permitted capabilities of * a process after a call to setuid, setreuid, or setresuid. * * 1) When set*uiding _from_ one of {r,e,s}uid == 0 _to_ all of * {r,e,s}uid != 0, the permitted and effective capabilities are * cleared. * * 2) When set*uiding _from_ euid == 0 _to_ euid != 0, the effective * capabilities of the process are cleared. * * 3) When set*uiding _from_ euid != 0 _to_ euid == 0, the effective * capabilities are set to the permitted capabilities. * * fsuid is handled elsewhere. fsuid == 0 and {r,e,s}uid!= 0 should * never happen. * * -astor * * cevans - New behaviour, Oct '99 * A process may, via prctl(), elect to keep its capabilities when it * calls setuid() and switches away from uid==0. Both permitted and * effective sets will be retained. * Without this change, it was impossible for a daemon to drop only some * of its privilege. The call to setuid(!=0) would drop all privileges! * Keeping uid 0 is not an option because uid 0 owns too many vital * files.. * Thanks to Olaf Kirch and Peter Benie for spotting this. */ static inline void cap_emulate_setxuid(struct cred *new, const struct cred *old) { kuid_t root_uid = make_kuid(old->user_ns, 0); if ((uid_eq(old->uid, root_uid) || uid_eq(old->euid, root_uid) || uid_eq(old->suid, root_uid)) && (!uid_eq(new->uid, root_uid) && !uid_eq(new->euid, root_uid) && !uid_eq(new->suid, root_uid))) { if (!issecure(SECURE_KEEP_CAPS)) { cap_clear(new->cap_permitted); cap_clear(new->cap_effective); } /* * Pre-ambient programs expect setresuid to nonroot followed * by exec to drop capabilities. We should make sure that * this remains the case. */ cap_clear(new->cap_ambient); } if (uid_eq(old->euid, root_uid) && !uid_eq(new->euid, root_uid)) cap_clear(new->cap_effective); if (!uid_eq(old->euid, root_uid) && uid_eq(new->euid, root_uid)) new->cap_effective = new->cap_permitted; } /** * cap_task_fix_setuid - Fix up the results of setuid() call * @new: The proposed credentials * @old: The current task's current credentials * @flags: Indications of what has changed * * Fix up the results of setuid() call before the credential changes are * actually applied. * * Return: 0 to grant the changes, -ve to deny them. */ int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { switch (flags) { case LSM_SETID_RE: case LSM_SETID_ID: case LSM_SETID_RES: /* juggle the capabilities to follow [RES]UID changes unless * otherwise suppressed */ if (!issecure(SECURE_NO_SETUID_FIXUP)) cap_emulate_setxuid(new, old); break; case LSM_SETID_FS: /* juggle the capabilties to follow FSUID changes, unless * otherwise suppressed * * FIXME - is fsuser used for all CAP_FS_MASK capabilities? * if not, we might be a bit too harsh here. */ if (!issecure(SECURE_NO_SETUID_FIXUP)) { kuid_t root_uid = make_kuid(old->user_ns, 0); if (uid_eq(old->fsuid, root_uid) && !uid_eq(new->fsuid, root_uid)) new->cap_effective = cap_drop_fs_set(new->cap_effective); if (!uid_eq(old->fsuid, root_uid) && uid_eq(new->fsuid, root_uid)) new->cap_effective = cap_raise_fs_set(new->cap_effective, new->cap_permitted); } break; default: return -EINVAL; } return 0; } /* * Rationale: code calling task_setscheduler, task_setioprio, and * task_setnice, assumes that * . if capable(cap_sys_nice), then those actions should be allowed * . if not capable(cap_sys_nice), but acting on your own processes, * then those actions should be allowed * This is insufficient now since you can call code without suid, but * yet with increased caps. * So we check for increased caps on the target process. */ static int cap_safe_nice(struct task_struct *p) { int is_subset, ret = 0; rcu_read_lock(); is_subset = cap_issubset(__task_cred(p)->cap_permitted, current_cred()->cap_permitted); if (!is_subset && !ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) ret = -EPERM; rcu_read_unlock(); return ret; } /** * cap_task_setscheduler - Detemine if scheduler policy change is permitted * @p: The task to affect * * Detemine if the requested scheduler policy change is permitted for the * specified task. * * Return: 0 if permission is granted, -ve if denied. */ int cap_task_setscheduler(struct task_struct *p) { return cap_safe_nice(p); } /** * cap_task_setioprio - Detemine if I/O priority change is permitted * @p: The task to affect * @ioprio: The I/O priority to set * * Detemine if the requested I/O priority change is permitted for the specified * task. * * Return: 0 if permission is granted, -ve if denied. */ int cap_task_setioprio(struct task_struct *p, int ioprio) { return cap_safe_nice(p); } /** * cap_task_setnice - Detemine if task priority change is permitted * @p: The task to affect * @nice: The nice value to set * * Detemine if the requested task priority change is permitted for the * specified task. * * Return: 0 if permission is granted, -ve if denied. */ int cap_task_setnice(struct task_struct *p, int nice) { return cap_safe_nice(p); } /* * Implement PR_CAPBSET_DROP. Attempt to remove the specified capability from * the current task's bounding set. Returns 0 on success, -ve on error. */ static int cap_prctl_drop(unsigned long cap) { struct cred *new; if (!ns_capable(current_user_ns(), CAP_SETPCAP)) return -EPERM; if (!cap_valid(cap)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; cap_lower(new->cap_bset, cap); return commit_creds(new); } /** * cap_task_prctl - Implement process control functions for this security module * @option: The process control function requested * @arg2: The argument data for this function * @arg3: The argument data for this function * @arg4: The argument data for this function * @arg5: The argument data for this function * * Allow process control functions (sys_prctl()) to alter capabilities; may * also deny access to other functions not otherwise implemented here. * * Return: 0 or +ve on success, -ENOSYS if this function is not implemented * here, other -ve on error. If -ENOSYS is returned, sys_prctl() and other LSM * modules will consider performing the function. */ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { const struct cred *old = current_cred(); struct cred *new; switch (option) { case PR_CAPBSET_READ: if (!cap_valid(arg2)) return -EINVAL; return !!cap_raised(old->cap_bset, arg2); case PR_CAPBSET_DROP: return cap_prctl_drop(arg2); /* * The next four prctl's remain to assist with transitioning a * system from legacy UID=0 based privilege (when filesystem * capabilities are not in use) to a system using filesystem * capabilities only - as the POSIX.1e draft intended. * * Note: * * PR_SET_SECUREBITS = * issecure_mask(SECURE_KEEP_CAPS_LOCKED) * | issecure_mask(SECURE_NOROOT) * | issecure_mask(SECURE_NOROOT_LOCKED) * | issecure_mask(SECURE_NO_SETUID_FIXUP) * | issecure_mask(SECURE_NO_SETUID_FIXUP_LOCKED) * * will ensure that the current process and all of its * children will be locked into a pure * capability-based-privilege environment. */ case PR_SET_SECUREBITS: if ((((old->securebits & SECURE_ALL_LOCKS) >> 1) & (old->securebits ^ arg2)) /*[1]*/ || ((old->securebits & SECURE_ALL_LOCKS & ~arg2)) /*[2]*/ || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS)) /*[3]*/ || (cap_capable(current_cred(), current_cred()->user_ns, CAP_SETPCAP, CAP_OPT_NONE) != 0) /*[4]*/ /* * [1] no changing of bits that are locked * [2] no unlocking of locks * [3] no setting of unsupported bits * [4] doing anything requires privilege (go read about * the "sendmail capabilities bug") */ ) /* cannot change a locked bit */ return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; new->securebits = arg2; return commit_creds(new); case PR_GET_SECUREBITS: return old->securebits; case PR_GET_KEEPCAPS: return !!issecure(SECURE_KEEP_CAPS); case PR_SET_KEEPCAPS: if (arg2 > 1) /* Note, we rely on arg2 being unsigned here */ return -EINVAL; if (issecure(SECURE_KEEP_CAPS_LOCKED)) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (arg2) new->securebits |= issecure_mask(SECURE_KEEP_CAPS); else new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); return commit_creds(new); case PR_CAP_AMBIENT: if (arg2 == PR_CAP_AMBIENT_CLEAR_ALL) { if (arg3 | arg4 | arg5) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; cap_clear(new->cap_ambient); return commit_creds(new); } if (((!cap_valid(arg3)) | arg4 | arg5)) return -EINVAL; if (arg2 == PR_CAP_AMBIENT_IS_SET) { return !!cap_raised(current_cred()->cap_ambient, arg3); } else if (arg2 != PR_CAP_AMBIENT_RAISE && arg2 != PR_CAP_AMBIENT_LOWER) { return -EINVAL; } else { if (arg2 == PR_CAP_AMBIENT_RAISE && (!cap_raised(current_cred()->cap_permitted, arg3) || !cap_raised(current_cred()->cap_inheritable, arg3) || issecure(SECURE_NO_CAP_AMBIENT_RAISE))) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (arg2 == PR_CAP_AMBIENT_RAISE) cap_raise(new->cap_ambient, arg3); else cap_lower(new->cap_ambient, arg3); return commit_creds(new); } default: /* No functionality available - continue with default */ return -ENOSYS; } } /** * cap_vm_enough_memory - Determine whether a new virtual mapping is permitted * @mm: The VM space in which the new mapping is to be made * @pages: The size of the mapping * * Determine whether the allocation of a new virtual mapping by the current * task is permitted. * * Return: 1 if permission is granted, 0 if not. */ int cap_vm_enough_memory(struct mm_struct *mm, long pages) { int cap_sys_admin = 0; if (cap_capable(current_cred(), &init_user_ns, CAP_SYS_ADMIN, CAP_OPT_NOAUDIT) == 0) cap_sys_admin = 1; return cap_sys_admin; } /** * cap_mmap_addr - check if able to map given addr * @addr: address attempting to be mapped * * If the process is attempting to map memory below dac_mmap_min_addr they need * CAP_SYS_RAWIO. The other parameters to this function are unused by the * capability security module. * * Return: 0 if this mapping should be allowed or -EPERM if not. */ int cap_mmap_addr(unsigned long addr) { int ret = 0; if (addr < dac_mmap_min_addr) { ret = cap_capable(current_cred(), &init_user_ns, CAP_SYS_RAWIO, CAP_OPT_NONE); /* set PF_SUPERPRIV if it turns out we allow the low mmap */ if (ret == 0) current->flags |= PF_SUPERPRIV; } return ret; } int cap_mmap_file(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) { return 0; } #ifdef CONFIG_SECURITY static struct security_hook_list capability_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(capable, cap_capable), LSM_HOOK_INIT(settime, cap_settime), LSM_HOOK_INIT(ptrace_access_check, cap_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, cap_ptrace_traceme), LSM_HOOK_INIT(capget, cap_capget), LSM_HOOK_INIT(capset, cap_capset), LSM_HOOK_INIT(bprm_creds_from_file, cap_bprm_creds_from_file), LSM_HOOK_INIT(inode_need_killpriv, cap_inode_need_killpriv), LSM_HOOK_INIT(inode_killpriv, cap_inode_killpriv), LSM_HOOK_INIT(inode_getsecurity, cap_inode_getsecurity), LSM_HOOK_INIT(mmap_addr, cap_mmap_addr), LSM_HOOK_INIT(mmap_file, cap_mmap_file), LSM_HOOK_INIT(task_fix_setuid, cap_task_fix_setuid), LSM_HOOK_INIT(task_prctl, cap_task_prctl), LSM_HOOK_INIT(task_setscheduler, cap_task_setscheduler), LSM_HOOK_INIT(task_setioprio, cap_task_setioprio), LSM_HOOK_INIT(task_setnice, cap_task_setnice), LSM_HOOK_INIT(vm_enough_memory, cap_vm_enough_memory), }; static int __init capability_init(void) { security_add_hooks(capability_hooks, ARRAY_SIZE(capability_hooks), "capability"); return 0; } DEFINE_LSM(capability) = { .name = "capability", .order = LSM_ORDER_FIRST, .init = capability_init, }; #endif /* CONFIG_SECURITY */ |
| 2025 2023 32 32 6 4 4 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <linux/rculist.h> #include <linux/list.h> #include <linux/hash.h> #include <linux/types.h> #include <linux/spinlock.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <linux/bpf_local_storage.h> #include <net/bpf_sk_storage.h> #include <net/sock.h> #include <uapi/linux/sock_diag.h> #include <uapi/linux/btf.h> #include <linux/rcupdate_trace.h> DEFINE_BPF_STORAGE_CACHE(sk_cache); static struct bpf_local_storage_data * bpf_sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit) { struct bpf_local_storage *sk_storage; struct bpf_local_storage_map *smap; sk_storage = rcu_dereference_check(sk->sk_bpf_storage, bpf_rcu_lock_held()); if (!sk_storage) return NULL; smap = (struct bpf_local_storage_map *)map; return bpf_local_storage_lookup(sk_storage, smap, cacheit_lockit); } static int bpf_sk_storage_del(struct sock *sk, struct bpf_map *map) { struct bpf_local_storage_data *sdata; sdata = bpf_sk_storage_lookup(sk, map, false); if (!sdata) return -ENOENT; bpf_selem_unlink(SELEM(sdata), true); return 0; } /* Called by __sk_destruct() & bpf_sk_storage_clone() */ void bpf_sk_storage_free(struct sock *sk) { struct bpf_local_storage *sk_storage; bool free_sk_storage = false; rcu_read_lock(); sk_storage = rcu_dereference(sk->sk_bpf_storage); if (!sk_storage) { rcu_read_unlock(); return; } raw_spin_lock_bh(&sk_storage->lock); free_sk_storage = bpf_local_storage_unlink_nolock(sk_storage); raw_spin_unlock_bh(&sk_storage->lock); rcu_read_unlock(); if (free_sk_storage) kfree_rcu(sk_storage, rcu); } static void bpf_sk_storage_map_free(struct bpf_map *map) { bpf_local_storage_map_free(map, &sk_cache, NULL); } static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) { return bpf_local_storage_map_alloc(attr, &sk_cache); } static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key) { return -ENOTSUPP; } static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key) { struct bpf_local_storage_data *sdata; struct socket *sock; int fd, err; fd = *(int *)key; sock = sockfd_lookup(fd, &err); if (sock) { sdata = bpf_sk_storage_lookup(sock->sk, map, true); sockfd_put(sock); return sdata ? sdata->data : NULL; } return ERR_PTR(err); } static int bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_local_storage_data *sdata; struct socket *sock; int fd, err; fd = *(int *)key; sock = sockfd_lookup(fd, &err); if (sock) { sdata = bpf_local_storage_update( sock->sk, (struct bpf_local_storage_map *)map, value, map_flags, GFP_ATOMIC); sockfd_put(sock); return PTR_ERR_OR_ZERO(sdata); } return err; } static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key) { struct socket *sock; int fd, err; fd = *(int *)key; sock = sockfd_lookup(fd, &err); if (sock) { err = bpf_sk_storage_del(sock->sk, map); sockfd_put(sock); return err; } return err; } static struct bpf_local_storage_elem * bpf_sk_storage_clone_elem(struct sock *newsk, struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem) { struct bpf_local_storage_elem *copy_selem; copy_selem = bpf_selem_alloc(smap, newsk, NULL, true, GFP_ATOMIC); if (!copy_selem) return NULL; if (map_value_has_spin_lock(&smap->map)) copy_map_value_locked(&smap->map, SDATA(copy_selem)->data, SDATA(selem)->data, true); else copy_map_value(&smap->map, SDATA(copy_selem)->data, SDATA(selem)->data); return copy_selem; } int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) { struct bpf_local_storage *new_sk_storage = NULL; struct bpf_local_storage *sk_storage; struct bpf_local_storage_elem *selem; int ret = 0; RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL); rcu_read_lock(); sk_storage = rcu_dereference(sk->sk_bpf_storage); if (!sk_storage || hlist_empty(&sk_storage->list)) goto out; hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) { struct bpf_local_storage_elem *copy_selem; struct bpf_local_storage_map *smap; struct bpf_map *map; smap = rcu_dereference(SDATA(selem)->smap); if (!(smap->map.map_flags & BPF_F_CLONE)) continue; /* Note that for lockless listeners adding new element * here can race with cleanup in bpf_local_storage_map_free. * Try to grab map refcnt to make sure that it's still * alive and prevent concurrent removal. */ map = bpf_map_inc_not_zero(&smap->map); if (IS_ERR(map)) continue; copy_selem = bpf_sk_storage_clone_elem(newsk, smap, selem); if (!copy_selem) { ret = -ENOMEM; bpf_map_put(map); goto out; } if (new_sk_storage) { bpf_selem_link_map(smap, copy_selem); bpf_selem_link_storage_nolock(new_sk_storage, copy_selem); } else { ret = bpf_local_storage_alloc(newsk, smap, copy_selem, GFP_ATOMIC); if (ret) { kfree(copy_selem); atomic_sub(smap->elem_size, &newsk->sk_omem_alloc); bpf_map_put(map); goto out; } new_sk_storage = rcu_dereference(copy_selem->local_storage); } bpf_map_put(map); } out: rcu_read_unlock(); /* In case of an error, don't free anything explicitly here, the * caller is responsible to call bpf_sk_storage_free. */ return ret; } /* *gfp_flags* is a hidden argument provided by the verifier */ BPF_CALL_5(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, void *, value, u64, flags, gfp_t, gfp_flags) { struct bpf_local_storage_data *sdata; WARN_ON_ONCE(!bpf_rcu_lock_held()); if (!sk || !sk_fullsock(sk) || flags > BPF_SK_STORAGE_GET_F_CREATE) return (unsigned long)NULL; sdata = bpf_sk_storage_lookup(sk, map, true); if (sdata) return (unsigned long)sdata->data; if (flags == BPF_SK_STORAGE_GET_F_CREATE && /* Cannot add new elem to a going away sk. * Otherwise, the new elem may become a leak * (and also other memory issues during map * destruction). */ refcount_inc_not_zero(&sk->sk_refcnt)) { sdata = bpf_local_storage_update( sk, (struct bpf_local_storage_map *)map, value, BPF_NOEXIST, gfp_flags); /* sk must be a fullsock (guaranteed by verifier), * so sock_gen_put() is unnecessary. */ sock_put(sk); return IS_ERR(sdata) ? (unsigned long)NULL : (unsigned long)sdata->data; } return (unsigned long)NULL; } BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk) { WARN_ON_ONCE(!bpf_rcu_lock_held()); if (!sk || !sk_fullsock(sk)) return -EINVAL; if (refcount_inc_not_zero(&sk->sk_refcnt)) { int err; err = bpf_sk_storage_del(sk, map); sock_put(sk); return err; } return -ENOENT; } static int bpf_sk_storage_charge(struct bpf_local_storage_map *smap, void *owner, u32 size) { int optmem_max = READ_ONCE(sysctl_optmem_max); struct sock *sk = (struct sock *)owner; /* same check as in sock_kmalloc() */ if (size <= optmem_max && atomic_read(&sk->sk_omem_alloc) + size < optmem_max) { atomic_add(size, &sk->sk_omem_alloc); return 0; } return -ENOMEM; } static void bpf_sk_storage_uncharge(struct bpf_local_storage_map *smap, void *owner, u32 size) { struct sock *sk = owner; atomic_sub(size, &sk->sk_omem_alloc); } static struct bpf_local_storage __rcu ** bpf_sk_storage_ptr(void *owner) { struct sock *sk = owner; return &sk->sk_bpf_storage; } BTF_ID_LIST_SINGLE(sk_storage_map_btf_ids, struct, bpf_local_storage_map) const struct bpf_map_ops sk_storage_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = bpf_local_storage_map_alloc_check, .map_alloc = bpf_sk_storage_map_alloc, .map_free = bpf_sk_storage_map_free, .map_get_next_key = notsupp_get_next_key, .map_lookup_elem = bpf_fd_sk_storage_lookup_elem, .map_update_elem = bpf_fd_sk_storage_update_elem, .map_delete_elem = bpf_fd_sk_storage_delete_elem, .map_check_btf = bpf_local_storage_map_check_btf, .map_btf_id = &sk_storage_map_btf_ids[0], .map_local_storage_charge = bpf_sk_storage_charge, .map_local_storage_uncharge = bpf_sk_storage_uncharge, .map_owner_storage_ptr = bpf_sk_storage_ptr, }; const struct bpf_func_proto bpf_sk_storage_get_proto = { .func = bpf_sk_storage_get, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, }; const struct bpf_func_proto bpf_sk_storage_get_cg_sock_proto = { .func = bpf_sk_storage_get, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_CTX, /* context is 'struct sock' */ .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, }; const struct bpf_func_proto bpf_sk_storage_delete_proto = { .func = bpf_sk_storage_delete, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, }; static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog) { const struct btf *btf_vmlinux; const struct btf_type *t; const char *tname; u32 btf_id; if (prog->aux->dst_prog) return false; /* Ensure the tracing program is not tracing * any bpf_sk_storage*() function and also * use the bpf_sk_storage_(get|delete) helper. */ switch (prog->expected_attach_type) { case BPF_TRACE_ITER: case BPF_TRACE_RAW_TP: /* bpf_sk_storage has no trace point */ return true; case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: btf_vmlinux = bpf_get_btf_vmlinux(); if (IS_ERR_OR_NULL(btf_vmlinux)) return false; btf_id = prog->aux->attach_btf_id; t = btf_type_by_id(btf_vmlinux, btf_id); tname = btf_name_by_offset(btf_vmlinux, t->name_off); return !!strncmp(tname, "bpf_sk_storage", strlen("bpf_sk_storage")); default: return false; } return false; } /* *gfp_flags* is a hidden argument provided by the verifier */ BPF_CALL_5(bpf_sk_storage_get_tracing, struct bpf_map *, map, struct sock *, sk, void *, value, u64, flags, gfp_t, gfp_flags) { WARN_ON_ONCE(!bpf_rcu_lock_held()); if (in_hardirq() || in_nmi()) return (unsigned long)NULL; return (unsigned long)____bpf_sk_storage_get(map, sk, value, flags, gfp_flags); } BPF_CALL_2(bpf_sk_storage_delete_tracing, struct bpf_map *, map, struct sock *, sk) { WARN_ON_ONCE(!bpf_rcu_lock_held()); if (in_hardirq() || in_nmi()) return -EPERM; return ____bpf_sk_storage_delete(map, sk); } const struct bpf_func_proto bpf_sk_storage_get_tracing_proto = { .func = bpf_sk_storage_get_tracing, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID, .arg2_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, .allowed = bpf_sk_storage_tracing_allowed, }; const struct bpf_func_proto bpf_sk_storage_delete_tracing_proto = { .func = bpf_sk_storage_delete_tracing, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID, .arg2_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], .allowed = bpf_sk_storage_tracing_allowed, }; struct bpf_sk_storage_diag { u32 nr_maps; struct bpf_map *maps[]; }; /* The reply will be like: * INET_DIAG_BPF_SK_STORAGES (nla_nest) * SK_DIAG_BPF_STORAGE (nla_nest) * SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32) * SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit) * SK_DIAG_BPF_STORAGE (nla_nest) * SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32) * SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit) * .... */ static int nla_value_size(u32 value_size) { /* SK_DIAG_BPF_STORAGE (nla_nest) * SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32) * SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit) */ return nla_total_size(0) + nla_total_size(sizeof(u32)) + nla_total_size_64bit(value_size); } void bpf_sk_storage_diag_free(struct bpf_sk_storage_diag *diag) { u32 i; if (!diag) return; for (i = 0; i < diag->nr_maps; i++) bpf_map_put(diag->maps[i]); kfree(diag); } EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_free); static bool diag_check_dup(const struct bpf_sk_storage_diag *diag, const struct bpf_map *map) { u32 i; for (i = 0; i < diag->nr_maps; i++) { if (diag->maps[i] == map) return true; } return false; } struct bpf_sk_storage_diag * bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) { struct bpf_sk_storage_diag *diag; struct nlattr *nla; u32 nr_maps = 0; int rem, err; /* bpf_local_storage_map is currently limited to CAP_SYS_ADMIN as * the map_alloc_check() side also does. */ if (!bpf_capable()) return ERR_PTR(-EPERM); nla_for_each_nested(nla, nla_stgs, rem) { if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD) { if (nla_len(nla) != sizeof(u32)) return ERR_PTR(-EINVAL); nr_maps++; } } diag = kzalloc(struct_size(diag, maps, nr_maps), GFP_KERNEL); if (!diag) return ERR_PTR(-ENOMEM); nla_for_each_nested(nla, nla_stgs, rem) { struct bpf_map *map; int map_fd; if (nla_type(nla) != SK_DIAG_BPF_STORAGE_REQ_MAP_FD) continue; map_fd = nla_get_u32(nla); map = bpf_map_get(map_fd); if (IS_ERR(map)) { err = PTR_ERR(map); goto err_free; } if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) { bpf_map_put(map); err = -EINVAL; goto err_free; } if (diag_check_dup(diag, map)) { bpf_map_put(map); err = -EEXIST; goto err_free; } diag->maps[diag->nr_maps++] = map; } return diag; err_free: bpf_sk_storage_diag_free(diag); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_alloc); static int diag_get(struct bpf_local_storage_data *sdata, struct sk_buff *skb) { struct nlattr *nla_stg, *nla_value; struct bpf_local_storage_map *smap; /* It cannot exceed max nlattr's payload */ BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < BPF_LOCAL_STORAGE_MAX_VALUE_SIZE); nla_stg = nla_nest_start(skb, SK_DIAG_BPF_STORAGE); if (!nla_stg) return -EMSGSIZE; smap = rcu_dereference(sdata->smap); if (nla_put_u32(skb, SK_DIAG_BPF_STORAGE_MAP_ID, smap->map.id)) goto errout; nla_value = nla_reserve_64bit(skb, SK_DIAG_BPF_STORAGE_MAP_VALUE, smap->map.value_size, SK_DIAG_BPF_STORAGE_PAD); if (!nla_value) goto errout; if (map_value_has_spin_lock(&smap->map)) copy_map_value_locked(&smap->map, nla_data(nla_value), sdata->data, true); else copy_map_value(&smap->map, nla_data(nla_value), sdata->data); nla_nest_end(skb, nla_stg); return 0; errout: nla_nest_cancel(skb, nla_stg); return -EMSGSIZE; } static int bpf_sk_storage_diag_put_all(struct sock *sk, struct sk_buff *skb, int stg_array_type, unsigned int *res_diag_size) { /* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */ unsigned int diag_size = nla_total_size(0); struct bpf_local_storage *sk_storage; struct bpf_local_storage_elem *selem; struct bpf_local_storage_map *smap; struct nlattr *nla_stgs; unsigned int saved_len; int err = 0; rcu_read_lock(); sk_storage = rcu_dereference(sk->sk_bpf_storage); if (!sk_storage || hlist_empty(&sk_storage->list)) { rcu_read_unlock(); return 0; } nla_stgs = nla_nest_start(skb, stg_array_type); if (!nla_stgs) /* Continue to learn diag_size */ err = -EMSGSIZE; saved_len = skb->len; hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) { smap = rcu_dereference(SDATA(selem)->smap); diag_size += nla_value_size(smap->map.value_size); if (nla_stgs && diag_get(SDATA(selem), skb)) /* Continue to learn diag_size */ err = -EMSGSIZE; } rcu_read_unlock(); if (nla_stgs) { if (saved_len == skb->len) nla_nest_cancel(skb, nla_stgs); else nla_nest_end(skb, nla_stgs); } if (diag_size == nla_total_size(0)) { *res_diag_size = 0; return 0; } *res_diag_size = diag_size; return err; } int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag, struct sock *sk, struct sk_buff *skb, int stg_array_type, unsigned int *res_diag_size) { /* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */ unsigned int diag_size = nla_total_size(0); struct bpf_local_storage *sk_storage; struct bpf_local_storage_data *sdata; struct nlattr *nla_stgs; unsigned int saved_len; int err = 0; u32 i; *res_diag_size = 0; /* No map has been specified. Dump all. */ if (!diag->nr_maps) return bpf_sk_storage_diag_put_all(sk, skb, stg_array_type, res_diag_size); rcu_read_lock(); sk_storage = rcu_dereference(sk->sk_bpf_storage); if (!sk_storage || hlist_empty(&sk_storage->list)) { rcu_read_unlock(); return 0; } nla_stgs = nla_nest_start(skb, stg_array_type); if (!nla_stgs) /* Continue to learn diag_size */ err = -EMSGSIZE; saved_len = skb->len; for (i = 0; i < diag->nr_maps; i++) { sdata = bpf_local_storage_lookup(sk_storage, (struct bpf_local_storage_map *)diag->maps[i], false); if (!sdata) continue; diag_size += nla_value_size(diag->maps[i]->value_size); if (nla_stgs && diag_get(sdata, skb)) /* Continue to learn diag_size */ err = -EMSGSIZE; } rcu_read_unlock(); if (nla_stgs) { if (saved_len == skb->len) nla_nest_cancel(skb, nla_stgs); else nla_nest_end(skb, nla_stgs); } if (diag_size == nla_total_size(0)) { *res_diag_size = 0; return 0; } *res_diag_size = diag_size; return err; } EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_put); struct bpf_iter_seq_sk_storage_map_info { struct bpf_map *map; unsigned int bucket_id; unsigned skip_elems; }; static struct bpf_local_storage_elem * bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, struct bpf_local_storage_elem *prev_selem) __acquires(RCU) __releases(RCU) { struct bpf_local_storage *sk_storage; struct bpf_local_storage_elem *selem; u32 skip_elems = info->skip_elems; struct bpf_local_storage_map *smap; u32 bucket_id = info->bucket_id; u32 i, count, n_buckets; struct bpf_local_storage_map_bucket *b; smap = (struct bpf_local_storage_map *)info->map; n_buckets = 1U << smap->bucket_log; if (bucket_id >= n_buckets) return NULL; /* try to find next selem in the same bucket */ selem = prev_selem; count = 0; while (selem) { selem = hlist_entry_safe(rcu_dereference(hlist_next_rcu(&selem->map_node)), struct bpf_local_storage_elem, map_node); if (!selem) { /* not found, unlock and go to the next bucket */ b = &smap->buckets[bucket_id++]; rcu_read_unlock(); skip_elems = 0; break; } sk_storage = rcu_dereference(selem->local_storage); if (sk_storage) { info->skip_elems = skip_elems + count; return selem; } count++; } for (i = bucket_id; i < (1U << smap->bucket_log); i++) { b = &smap->buckets[i]; rcu_read_lock(); count = 0; hlist_for_each_entry_rcu(selem, &b->list, map_node) { sk_storage = rcu_dereference(selem->local_storage); if (sk_storage && count >= skip_elems) { info->bucket_id = i; info->skip_elems = count; return selem; } count++; } rcu_read_unlock(); skip_elems = 0; } info->bucket_id = i; info->skip_elems = 0; return NULL; } static void *bpf_sk_storage_map_seq_start(struct seq_file *seq, loff_t *pos) { struct bpf_local_storage_elem *selem; selem = bpf_sk_storage_map_seq_find_next(seq->private, NULL); if (!selem) return NULL; if (*pos == 0) ++*pos; return selem; } static void *bpf_sk_storage_map_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct bpf_iter_seq_sk_storage_map_info *info = seq->private; ++*pos; ++info->skip_elems; return bpf_sk_storage_map_seq_find_next(seq->private, v); } struct bpf_iter__bpf_sk_storage_map { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct bpf_map *, map); __bpf_md_ptr(struct sock *, sk); __bpf_md_ptr(void *, value); }; DEFINE_BPF_ITER_FUNC(bpf_sk_storage_map, struct bpf_iter_meta *meta, struct bpf_map *map, struct sock *sk, void *value) static int __bpf_sk_storage_map_seq_show(struct seq_file *seq, struct bpf_local_storage_elem *selem) { struct bpf_iter_seq_sk_storage_map_info *info = seq->private; struct bpf_iter__bpf_sk_storage_map ctx = {}; struct bpf_local_storage *sk_storage; struct bpf_iter_meta meta; struct bpf_prog *prog; int ret = 0; meta.seq = seq; prog = bpf_iter_get_info(&meta, selem == NULL); if (prog) { ctx.meta = &meta; ctx.map = info->map; if (selem) { sk_storage = rcu_dereference(selem->local_storage); ctx.sk = sk_storage->owner; ctx.value = SDATA(selem)->data; } ret = bpf_iter_run_prog(prog, &ctx); } return ret; } static int bpf_sk_storage_map_seq_show(struct seq_file *seq, void *v) { return __bpf_sk_storage_map_seq_show(seq, v); } static void bpf_sk_storage_map_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { if (!v) (void)__bpf_sk_storage_map_seq_show(seq, v); else rcu_read_unlock(); } static int bpf_iter_init_sk_storage_map(void *priv_data, struct bpf_iter_aux_info *aux) { struct bpf_iter_seq_sk_storage_map_info *seq_info = priv_data; bpf_map_inc_with_uref(aux->map); seq_info->map = aux->map; return 0; } static void bpf_iter_fini_sk_storage_map(void *priv_data) { struct bpf_iter_seq_sk_storage_map_info *seq_info = priv_data; bpf_map_put_with_uref(seq_info->map); } static int bpf_iter_attach_map(struct bpf_prog *prog, union bpf_iter_link_info *linfo, struct bpf_iter_aux_info *aux) { struct bpf_map *map; int err = -EINVAL; if (!linfo->map.map_fd) return -EBADF; map = bpf_map_get_with_uref(linfo->map.map_fd); if (IS_ERR(map)) return PTR_ERR(map); if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) goto put_map; if (prog->aux->max_rdwr_access > map->value_size) { err = -EACCES; goto put_map; } aux->map = map; return 0; put_map: bpf_map_put_with_uref(map); return err; } static void bpf_iter_detach_map(struct bpf_iter_aux_info *aux) { bpf_map_put_with_uref(aux->map); } static const struct seq_operations bpf_sk_storage_map_seq_ops = { .start = bpf_sk_storage_map_seq_start, .next = bpf_sk_storage_map_seq_next, .stop = bpf_sk_storage_map_seq_stop, .show = bpf_sk_storage_map_seq_show, }; static const struct bpf_iter_seq_info iter_seq_info = { .seq_ops = &bpf_sk_storage_map_seq_ops, .init_seq_private = bpf_iter_init_sk_storage_map, .fini_seq_private = bpf_iter_fini_sk_storage_map, .seq_priv_size = sizeof(struct bpf_iter_seq_sk_storage_map_info), }; static struct bpf_iter_reg bpf_sk_storage_map_reg_info = { .target = "bpf_sk_storage_map", .attach_target = bpf_iter_attach_map, .detach_target = bpf_iter_detach_map, .show_fdinfo = bpf_iter_map_show_fdinfo, .fill_link_info = bpf_iter_map_fill_link_info, .ctx_arg_info_size = 2, .ctx_arg_info = { { offsetof(struct bpf_iter__bpf_sk_storage_map, sk), PTR_TO_BTF_ID_OR_NULL }, { offsetof(struct bpf_iter__bpf_sk_storage_map, value), PTR_TO_BUF | PTR_MAYBE_NULL }, }, .seq_info = &iter_seq_info, }; static int __init bpf_sk_storage_map_iter_init(void) { bpf_sk_storage_map_reg_info.ctx_arg_info[0].btf_id = btf_sock_ids[BTF_SOCK_TYPE_SOCK]; return bpf_iter_reg_target(&bpf_sk_storage_map_reg_info); } late_initcall(bpf_sk_storage_map_iter_init); |
| 102 102 102 102 102 102 23 23 23 23 23 23 23 916 914 917 914 912 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/truncate.c - code for taking down pages from address_spaces * * Copyright (C) 2002, Linus Torvalds * * 10Sep2002 Andrew Morton * Initial version. */ #include <linux/kernel.h> #include <linux/backing-dev.h> #include <linux/dax.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/export.h> #include <linux/pagemap.h> #include <linux/highmem.h> #include <linux/pagevec.h> #include <linux/task_io_accounting_ops.h> #include <linux/shmem_fs.h> #include <linux/cleancache.h> #include <linux/rmap.h> #include "internal.h" /* * Regular page slots are stabilized by the page lock even without the tree * itself locked. These unlocked entries need verification under the tree * lock. */ static inline void __clear_shadow_entry(struct address_space *mapping, pgoff_t index, void *entry) { XA_STATE(xas, &mapping->i_pages, index); xas_set_update(&xas, workingset_update_node); if (xas_load(&xas) != entry) return; xas_store(&xas, NULL); } static void clear_shadow_entry(struct address_space *mapping, pgoff_t index, void *entry) { spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); __clear_shadow_entry(mapping, index, entry); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); } /* * Unconditionally remove exceptional entries. Usually called from truncate * path. Note that the folio_batch may be altered by this function by removing * exceptional entries similar to what folio_batch_remove_exceptionals() does. */ static void truncate_folio_batch_exceptionals(struct address_space *mapping, struct folio_batch *fbatch, pgoff_t *indices) { int i, j; bool dax; /* Handled by shmem itself */ if (shmem_mapping(mapping)) return; for (j = 0; j < folio_batch_count(fbatch); j++) if (xa_is_value(fbatch->folios[j])) break; if (j == folio_batch_count(fbatch)) return; dax = dax_mapping(mapping); if (!dax) { spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); } for (i = j; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; pgoff_t index = indices[i]; if (!xa_is_value(folio)) { fbatch->folios[j++] = folio; continue; } if (unlikely(dax)) { dax_delete_mapping_entry(mapping, index); continue; } __clear_shadow_entry(mapping, index, folio); } if (!dax) { xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); } fbatch->nr = j; } /* * Invalidate exceptional entry if easily possible. This handles exceptional * entries for invalidate_inode_pages(). */ static int invalidate_exceptional_entry(struct address_space *mapping, pgoff_t index, void *entry) { /* Handled by shmem itself, or for DAX we do nothing. */ if (shmem_mapping(mapping) || dax_mapping(mapping)) return 1; clear_shadow_entry(mapping, index, entry); return 1; } /* * Invalidate exceptional entry if clean. This handles exceptional entries for * invalidate_inode_pages2() so for DAX it evicts only clean entries. */ static int invalidate_exceptional_entry2(struct address_space *mapping, pgoff_t index, void *entry) { /* Handled by shmem itself */ if (shmem_mapping(mapping)) return 1; if (dax_mapping(mapping)) return dax_invalidate_mapping_entry_sync(mapping, index); clear_shadow_entry(mapping, index, entry); return 1; } /** * folio_invalidate - Invalidate part or all of a folio. * @folio: The folio which is affected. * @offset: start of the range to invalidate * @length: length of the range to invalidate * * folio_invalidate() is called when all or part of the folio has become * invalidated by a truncate operation. * * folio_invalidate() does not have to release all buffers, but it must * ensure that no dirty buffer is left outside @offset and that no I/O * is underway against any of the blocks which are outside the truncation * point. Because the caller is about to free (and possibly reuse) those * blocks on-disk. */ void folio_invalidate(struct folio *folio, size_t offset, size_t length) { const struct address_space_operations *aops = folio->mapping->a_ops; if (aops->invalidate_folio) aops->invalidate_folio(folio, offset, length); } EXPORT_SYMBOL_GPL(folio_invalidate); /* * If truncate cannot remove the fs-private metadata from the page, the page * becomes orphaned. It will be left on the LRU and may even be mapped into * user pagetables if we're racing with filemap_fault(). * * We need to bail out if page->mapping is no longer equal to the original * mapping. This happens a) when the VM reclaimed the page while we waited on * its lock, b) when a concurrent invalidate_mapping_pages got there first and * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space. */ static void truncate_cleanup_folio(struct folio *folio) { if (folio_mapped(folio)) unmap_mapping_folio(folio); if (folio_needs_release(folio)) folio_invalidate(folio, 0, folio_size(folio)); /* * Some filesystems seem to re-dirty the page even after * the VM has canceled the dirty bit (eg ext3 journaling). * Hence dirty accounting check is placed after invalidation. */ folio_cancel_dirty(folio); folio_clear_mappedtodisk(folio); } int truncate_inode_folio(struct address_space *mapping, struct folio *folio) { if (folio->mapping != mapping) return -EIO; truncate_cleanup_folio(folio); filemap_remove_folio(folio); return 0; } /* * Handle partial folios. The folio may be entirely within the * range if a split has raced with us. If not, we zero the part of the * folio that's within the [start, end] range, and then split the folio if * it's large. split_page_range() will discard pages which now lie beyond * i_size, and we rely on the caller to discard pages which lie within a * newly created hole. * * Returns false if splitting failed so the caller can avoid * discarding the entire folio which is stubbornly unsplit. */ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) { loff_t pos = folio_pos(folio); unsigned int offset, length; if (pos < start) offset = start - pos; else offset = 0; length = folio_size(folio); if (pos + length <= (u64)end) length = length - offset; else length = end + 1 - pos - offset; folio_wait_writeback(folio); if (length == folio_size(folio)) { truncate_inode_folio(folio->mapping, folio); return true; } /* * We may be zeroing pages we're about to discard, but it avoids * doing a complex calculation here, and then doing the zeroing * anyway if the page split fails. */ folio_zero_range(folio, offset, length); cleancache_invalidate_page(folio->mapping, &folio->page); if (folio_needs_release(folio)) folio_invalidate(folio, offset, length); if (!folio_test_large(folio)) return true; if (split_folio(folio) == 0) return true; if (folio_test_dirty(folio)) return false; truncate_inode_folio(folio->mapping, folio); return true; } /* * Used to get rid of pages on hardware memory corruption. */ int generic_error_remove_page(struct address_space *mapping, struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); if (!mapping) return -EINVAL; /* * Only punch for normal data pages for now. * Handling other types like directories would need more auditing. */ if (!S_ISREG(mapping->host->i_mode)) return -EIO; return truncate_inode_folio(mapping, page_folio(page)); } EXPORT_SYMBOL(generic_error_remove_page); static long mapping_evict_folio(struct address_space *mapping, struct folio *folio) { if (folio_test_dirty(folio) || folio_test_writeback(folio)) return 0; /* The refcount will be elevated if any page in the folio is mapped */ if (folio_ref_count(folio) > folio_nr_pages(folio) + folio_has_private(folio) + 1) return 0; if (!filemap_release_folio(folio, 0)) return 0; return remove_mapping(mapping, folio); } /** * invalidate_inode_page() - Remove an unused page from the pagecache. * @page: The page to remove. * * Safely invalidate one page from its pagecache mapping. * It only drops clean, unused pages. * * Context: Page must be locked. * Return: The number of pages successfully removed. */ long invalidate_inode_page(struct page *page) { struct folio *folio = page_folio(page); struct address_space *mapping = folio_mapping(folio); /* The page may have been truncated before it was locked */ if (!mapping) return 0; return mapping_evict_folio(mapping, folio); } /** * truncate_inode_pages_range - truncate range of pages specified by start & end byte offsets * @mapping: mapping to truncate * @lstart: offset from which to truncate * @lend: offset to which to truncate (inclusive) * * Truncate the page cache, removing the pages that are between * specified offsets (and zeroing out partial pages * if lstart or lend + 1 is not page aligned). * * Truncate takes two passes - the first pass is nonblocking. It will not * block on page locks and it will not block on writeback. The second pass * will wait. This is to prevent as much IO as possible in the affected region. * The first pass will remove most pages, so the search cost of the second pass * is low. * * We pass down the cache-hot hint to the page freeing code. Even if the * mapping is large, it is probably the case that the final pages are the most * recently touched, and freeing happens in ascending file offset order. * * Note that since ->invalidate_folio() accepts range to invalidate * truncate_inode_pages_range is able to handle cases where lend + 1 is not * page aligned properly. */ void truncate_inode_pages_range(struct address_space *mapping, loff_t lstart, loff_t lend) { pgoff_t start; /* inclusive */ pgoff_t end; /* exclusive */ struct folio_batch fbatch; pgoff_t indices[PAGEVEC_SIZE]; pgoff_t index; int i; struct folio *folio; bool same_folio; if (mapping_empty(mapping)) goto out; /* * 'start' and 'end' always covers the range of pages to be fully * truncated. Partial pages are covered with 'partial_start' at the * start of the range and 'partial_end' at the end of the range. * Note that 'end' is exclusive while 'lend' is inclusive. */ start = (lstart + PAGE_SIZE - 1) >> PAGE_SHIFT; if (lend == -1) /* * lend == -1 indicates end-of-file so we have to set 'end' * to the highest possible pgoff_t and since the type is * unsigned we're using -1. */ end = -1; else end = (lend + 1) >> PAGE_SHIFT; folio_batch_init(&fbatch); index = start; while (index < end && find_lock_entries(mapping, index, end - 1, &fbatch, indices)) { index = indices[folio_batch_count(&fbatch) - 1] + 1; truncate_folio_batch_exceptionals(mapping, &fbatch, indices); for (i = 0; i < folio_batch_count(&fbatch); i++) truncate_cleanup_folio(fbatch.folios[i]); delete_from_page_cache_batch(mapping, &fbatch); for (i = 0; i < folio_batch_count(&fbatch); i++) folio_unlock(fbatch.folios[i]); folio_batch_release(&fbatch); cond_resched(); } same_folio = (lstart >> PAGE_SHIFT) == (lend >> PAGE_SHIFT); folio = __filemap_get_folio(mapping, lstart >> PAGE_SHIFT, FGP_LOCK, 0); if (folio) { same_folio = lend < folio_pos(folio) + folio_size(folio); if (!truncate_inode_partial_folio(folio, lstart, lend)) { start = folio->index + folio_nr_pages(folio); if (same_folio) end = folio->index; } folio_unlock(folio); folio_put(folio); folio = NULL; } if (!same_folio) folio = __filemap_get_folio(mapping, lend >> PAGE_SHIFT, FGP_LOCK, 0); if (folio) { if (!truncate_inode_partial_folio(folio, lstart, lend)) end = folio->index; folio_unlock(folio); folio_put(folio); } index = start; while (index < end) { cond_resched(); if (!find_get_entries(mapping, index, end - 1, &fbatch, indices)) { /* If all gone from start onwards, we're done */ if (index == start) break; /* Otherwise restart to make sure all gone */ index = start; continue; } for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; /* We rely upon deletion not changing page->index */ index = indices[i]; if (xa_is_value(folio)) continue; folio_lock(folio); VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); folio_wait_writeback(folio); truncate_inode_folio(mapping, folio); folio_unlock(folio); index = folio_index(folio) + folio_nr_pages(folio) - 1; } truncate_folio_batch_exceptionals(mapping, &fbatch, indices); folio_batch_release(&fbatch); index++; } out: cleancache_invalidate_inode(mapping); } EXPORT_SYMBOL(truncate_inode_pages_range); /** * truncate_inode_pages - truncate *all* the pages from an offset * @mapping: mapping to truncate * @lstart: offset from which to truncate * * Called under (and serialised by) inode->i_rwsem and * mapping->invalidate_lock. * * Note: When this function returns, there can be a page in the process of * deletion (inside __filemap_remove_folio()) in the specified range. Thus * mapping->nrpages can be non-zero when this function returns even after * truncation of the whole mapping. */ void truncate_inode_pages(struct address_space *mapping, loff_t lstart) { truncate_inode_pages_range(mapping, lstart, (loff_t)-1); } EXPORT_SYMBOL(truncate_inode_pages); /** * truncate_inode_pages_final - truncate *all* pages before inode dies * @mapping: mapping to truncate * * Called under (and serialized by) inode->i_rwsem. * * Filesystems have to use this in the .evict_inode path to inform the * VM that this is the final truncate and the inode is going away. */ void truncate_inode_pages_final(struct address_space *mapping) { /* * Page reclaim can not participate in regular inode lifetime * management (can't call iput()) and thus can race with the * inode teardown. Tell it when the address space is exiting, * so that it does not install eviction information after the * final truncate has begun. */ mapping_set_exiting(mapping); if (!mapping_empty(mapping)) { /* * As truncation uses a lockless tree lookup, cycle * the tree lock to make sure any ongoing tree * modification that does not see AS_EXITING is * completed before starting the final truncate. */ xa_lock_irq(&mapping->i_pages); xa_unlock_irq(&mapping->i_pages); } /* * Cleancache needs notification even if there are no pages or shadow * entries. */ truncate_inode_pages(mapping, 0); } EXPORT_SYMBOL(truncate_inode_pages_final); /** * invalidate_mapping_pagevec - Invalidate all the unlocked pages of one inode * @mapping: the address_space which holds the pages to invalidate * @start: the offset 'from' which to invalidate * @end: the offset 'to' which to invalidate (inclusive) * @nr_pagevec: invalidate failed page number for caller * * This helper is similar to invalidate_mapping_pages(), except that it accounts * for pages that are likely on a pagevec and counts them in @nr_pagevec, which * will be used by the caller. */ unsigned long invalidate_mapping_pagevec(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_pagevec) { pgoff_t indices[PAGEVEC_SIZE]; struct folio_batch fbatch; pgoff_t index = start; unsigned long ret; unsigned long count = 0; int i; folio_batch_init(&fbatch); while (find_lock_entries(mapping, index, end, &fbatch, indices)) { for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; /* We rely upon deletion not changing folio->index */ index = indices[i]; if (xa_is_value(folio)) { count += invalidate_exceptional_entry(mapping, index, folio); continue; } index += folio_nr_pages(folio) - 1; ret = mapping_evict_folio(mapping, folio); folio_unlock(folio); /* * Invalidation is a hint that the folio is no longer * of interest and try to speed up its reclaim. */ if (!ret) { deactivate_file_folio(folio); /* It is likely on the pagevec of a remote CPU */ if (nr_pagevec) (*nr_pagevec)++; } count += ret; } folio_batch_remove_exceptionals(&fbatch); folio_batch_release(&fbatch); cond_resched(); index++; } return count; } /** * invalidate_mapping_pages - Invalidate all clean, unlocked cache of one inode * @mapping: the address_space which holds the cache to invalidate * @start: the offset 'from' which to invalidate * @end: the offset 'to' which to invalidate (inclusive) * * This function removes pages that are clean, unmapped and unlocked, * as well as shadow entries. It will not block on IO activity. * * If you want to remove all the pages of one inode, regardless of * their use and writeback state, use truncate_inode_pages(). * * Return: the number of the cache entries that were invalidated */ unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end) { return invalidate_mapping_pagevec(mapping, start, end, NULL); } EXPORT_SYMBOL(invalidate_mapping_pages); /* * This is like invalidate_inode_page(), except it ignores the page's * refcount. We do this because invalidate_inode_pages2() needs stronger * invalidation guarantees, and cannot afford to leave pages behind because * shrink_page_list() has a temp ref on them, or because they're transiently * sitting in the lru_cache_add() pagevecs. */ static int invalidate_complete_folio2(struct address_space *mapping, struct folio *folio) { if (folio->mapping != mapping) return 0; if (!filemap_release_folio(folio, GFP_KERNEL)) return 0; spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); if (folio_test_dirty(folio)) goto failed; BUG_ON(folio_has_private(folio)); __filemap_remove_folio(folio, NULL); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); filemap_free_folio(mapping, folio); return 1; failed: xa_unlock_irq(&mapping->i_pages); spin_unlock(&mapping->host->i_lock); return 0; } static int folio_launder(struct address_space *mapping, struct folio *folio) { if (!folio_test_dirty(folio)) return 0; if (folio->mapping != mapping || mapping->a_ops->launder_folio == NULL) return 0; return mapping->a_ops->launder_folio(folio); } /** * invalidate_inode_pages2_range - remove range of pages from an address_space * @mapping: the address_space * @start: the page offset 'from' which to invalidate * @end: the page offset 'to' which to invalidate (inclusive) * * Any pages which are found to be mapped into pagetables are unmapped prior to * invalidation. * * Return: -EBUSY if any pages could not be invalidated. */ int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end) { pgoff_t indices[PAGEVEC_SIZE]; struct folio_batch fbatch; pgoff_t index; int i; int ret = 0; int ret2 = 0; int did_range_unmap = 0; if (mapping_empty(mapping)) goto out; folio_batch_init(&fbatch); index = start; while (find_get_entries(mapping, index, end, &fbatch, indices)) { for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; /* We rely upon deletion not changing folio->index */ index = indices[i]; if (xa_is_value(folio)) { if (!invalidate_exceptional_entry2(mapping, index, folio)) ret = -EBUSY; continue; } if (!did_range_unmap && folio_mapped(folio)) { /* * If folio is mapped, before taking its lock, * zap the rest of the file in one hit. */ unmap_mapping_pages(mapping, index, (1 + end - index), false); did_range_unmap = 1; } folio_lock(folio); VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); if (folio->mapping != mapping) { folio_unlock(folio); continue; } folio_wait_writeback(folio); if (folio_mapped(folio)) unmap_mapping_folio(folio); BUG_ON(folio_mapped(folio)); ret2 = folio_launder(mapping, folio); if (ret2 == 0) { if (!invalidate_complete_folio2(mapping, folio)) ret2 = -EBUSY; } if (ret2 < 0) ret = ret2; folio_unlock(folio); } folio_batch_remove_exceptionals(&fbatch); folio_batch_release(&fbatch); cond_resched(); index++; } /* * For DAX we invalidate page tables after invalidating page cache. We * could invalidate page tables while invalidating each entry however * that would be expensive. And doing range unmapping before doesn't * work as we have no cheap way to find whether page cache entry didn't * get remapped later. */ if (dax_mapping(mapping)) { unmap_mapping_pages(mapping, start, end - start + 1, false); } out: cleancache_invalidate_inode(mapping); return ret; } EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range); /** * invalidate_inode_pages2 - remove all pages from an address_space * @mapping: the address_space * * Any pages which are found to be mapped into pagetables are unmapped prior to * invalidation. * * Return: -EBUSY if any pages could not be invalidated. */ int invalidate_inode_pages2(struct address_space *mapping) { return invalidate_inode_pages2_range(mapping, 0, -1); } EXPORT_SYMBOL_GPL(invalidate_inode_pages2); /** * truncate_pagecache - unmap and remove pagecache that has been truncated * @inode: inode * @newsize: new file size * * inode's new i_size must already be written before truncate_pagecache * is called. * * This function should typically be called before the filesystem * releases resources associated with the freed range (eg. deallocates * blocks). This way, pagecache will always stay logically coherent * with on-disk format, and the filesystem would not have to deal with * situations such as writepage being called for a page that has already * had its underlying blocks deallocated. */ void truncate_pagecache(struct inode *inode, loff_t newsize) { struct address_space *mapping = inode->i_mapping; loff_t holebegin = round_up(newsize, PAGE_SIZE); /* * unmap_mapping_range is called twice, first simply for * efficiency so that truncate_inode_pages does fewer * single-page unmaps. However after this first call, and * before truncate_inode_pages finishes, it is possible for * private pages to be COWed, which remain after * truncate_inode_pages finishes, hence the second * unmap_mapping_range call must be made for correctness. */ unmap_mapping_range(mapping, holebegin, 0, 1); truncate_inode_pages(mapping, newsize); unmap_mapping_range(mapping, holebegin, 0, 1); } EXPORT_SYMBOL(truncate_pagecache); /** * truncate_setsize - update inode and pagecache for a new file size * @inode: inode * @newsize: new file size * * truncate_setsize updates i_size and performs pagecache truncation (if * necessary) to @newsize. It will be typically be called from the filesystem's * setattr function when ATTR_SIZE is passed in. * * Must be called with a lock serializing truncates and writes (generally * i_rwsem but e.g. xfs uses a different lock) and before all filesystem * specific block truncation has been performed. */ void truncate_setsize(struct inode *inode, loff_t newsize) { loff_t oldsize = inode->i_size; i_size_write(inode, newsize); if (newsize > oldsize) pagecache_isize_extended(inode, oldsize, newsize); truncate_pagecache(inode, newsize); } EXPORT_SYMBOL(truncate_setsize); /** * pagecache_isize_extended - update pagecache after extension of i_size * @inode: inode for which i_size was extended * @from: original inode size * @to: new inode size * * Handle extension of inode size either caused by extending truncate or by * write starting after current i_size. We mark the page straddling current * i_size RO so that page_mkwrite() is called on the nearest write access to * the page. This way filesystem can be sure that page_mkwrite() is called on * the page before user writes to the page via mmap after the i_size has been * changed. * * The function must be called after i_size is updated so that page fault * coming after we unlock the page will already see the new i_size. * The function must be called while we still hold i_rwsem - this not only * makes sure i_size is stable but also that userspace cannot observe new * i_size value before we are prepared to store mmap writes at new inode size. */ void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to) { int bsize = i_blocksize(inode); loff_t rounded_from; struct page *page; pgoff_t index; WARN_ON(to > inode->i_size); if (from >= to || bsize == PAGE_SIZE) return; /* Page straddling @from will not have any hole block created? */ rounded_from = round_up(from, bsize); if (to <= rounded_from || !(rounded_from & (PAGE_SIZE - 1))) return; index = from >> PAGE_SHIFT; page = find_lock_page(inode->i_mapping, index); /* Page not cached? Nothing to do */ if (!page) return; /* * See clear_page_dirty_for_io() for details why set_page_dirty() * is needed. */ if (page_mkclean(page)) set_page_dirty(page); unlock_page(page); put_page(page); } EXPORT_SYMBOL(pagecache_isize_extended); /** * truncate_pagecache_range - unmap and remove pagecache that is hole-punched * @inode: inode * @lstart: offset of beginning of hole * @lend: offset of last byte of hole * * This function should typically be called before the filesystem * releases resources associated with the freed range (eg. deallocates * blocks). This way, pagecache will always stay logically coherent * with on-disk format, and the filesystem would not have to deal with * situations such as writepage being called for a page that has already * had its underlying blocks deallocated. */ void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend) { struct address_space *mapping = inode->i_mapping; loff_t unmap_start = round_up(lstart, PAGE_SIZE); loff_t unmap_end = round_down(1 + lend, PAGE_SIZE) - 1; /* * This rounding is currently just for example: unmap_mapping_range * expands its hole outwards, whereas we want it to contract the hole * inwards. However, existing callers of truncate_pagecache_range are * doing their own page rounding first. Note that unmap_mapping_range * allows holelen 0 for all, and we allow lend -1 for end of file. */ /* * Unlike in truncate_pagecache, unmap_mapping_range is called only * once (before truncating pagecache), and without "even_cows" flag: * hole-punching should not remove private COWed pages from the hole. */ if ((u64)unmap_end > (u64)unmap_start) unmap_mapping_range(mapping, unmap_start, 1 + unmap_end - unmap_start, 0); truncate_inode_pages_range(mapping, lstart, lend); } EXPORT_SYMBOL(truncate_pagecache_range); |
| 30 28 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/crypto/hooks.c * * Encryption hooks for higher-level filesystem operations. */ #include "fscrypt_private.h" /** * fscrypt_file_open() - prepare to open a possibly-encrypted regular file * @inode: the inode being opened * @filp: the struct file being set up * * Currently, an encrypted regular file can only be opened if its encryption key * is available; access to the raw encrypted contents is not supported. * Therefore, we first set up the inode's encryption key (if not already done) * and return an error if it's unavailable. * * We also verify that if the parent directory (from the path via which the file * is being opened) is encrypted, then the inode being opened uses the same * encryption policy. This is needed as part of the enforcement that all files * in an encrypted directory tree use the same encryption policy, as a * protection against certain types of offline attacks. Note that this check is * needed even when opening an *unencrypted* file, since it's forbidden to have * an unencrypted file in an encrypted directory. * * Return: 0 on success, -ENOKEY if the key is missing, or another -errno code */ int fscrypt_file_open(struct inode *inode, struct file *filp) { int err; struct dentry *dir; err = fscrypt_require_key(inode); if (err) return err; dir = dget_parent(file_dentry(filp)); if (IS_ENCRYPTED(d_inode(dir)) && !fscrypt_has_permitted_context(d_inode(dir), inode)) { fscrypt_warn(inode, "Inconsistent encryption context (parent directory: %lu)", d_inode(dir)->i_ino); err = -EPERM; } dput(dir); return err; } EXPORT_SYMBOL_GPL(fscrypt_file_open); int __fscrypt_prepare_link(struct inode *inode, struct inode *dir, struct dentry *dentry) { if (fscrypt_is_nokey_name(dentry)) return -ENOKEY; /* * We don't need to separately check that the directory inode's key is * available, as it's implied by the dentry not being a no-key name. */ if (!fscrypt_has_permitted_context(dir, inode)) return -EXDEV; return 0; } EXPORT_SYMBOL_GPL(__fscrypt_prepare_link); int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { if (fscrypt_is_nokey_name(old_dentry) || fscrypt_is_nokey_name(new_dentry)) return -ENOKEY; /* * We don't need to separately check that the directory inodes' keys are * available, as it's implied by the dentries not being no-key names. */ if (old_dir != new_dir) { if (IS_ENCRYPTED(new_dir) && !fscrypt_has_permitted_context(new_dir, d_inode(old_dentry))) return -EXDEV; if ((flags & RENAME_EXCHANGE) && IS_ENCRYPTED(old_dir) && !fscrypt_has_permitted_context(old_dir, d_inode(new_dentry))) return -EXDEV; } return 0; } EXPORT_SYMBOL_GPL(__fscrypt_prepare_rename); int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry, struct fscrypt_name *fname) { int err = fscrypt_setup_filename(dir, &dentry->d_name, 1, fname); if (err && err != -ENOENT) return err; if (fname->is_nokey_name) { spin_lock(&dentry->d_lock); dentry->d_flags |= DCACHE_NOKEY_NAME; spin_unlock(&dentry->d_lock); } return err; } EXPORT_SYMBOL_GPL(__fscrypt_prepare_lookup); /** * fscrypt_prepare_lookup_partial() - prepare lookup without filename setup * @dir: the encrypted directory being searched * @dentry: the dentry being looked up in @dir * * This function should be used by the ->lookup and ->atomic_open methods of * filesystems that handle filename encryption and no-key name encoding * themselves and thus can't use fscrypt_prepare_lookup(). Like * fscrypt_prepare_lookup(), this will try to set up the directory's encryption * key and will set DCACHE_NOKEY_NAME on the dentry if the key is unavailable. * However, this function doesn't set up a struct fscrypt_name for the filename. * * Return: 0 on success; -errno on error. Note that the encryption key being * unavailable is not considered an error. It is also not an error if * the encryption policy is unsupported by this kernel; that is treated * like the key being unavailable, so that files can still be deleted. */ int fscrypt_prepare_lookup_partial(struct inode *dir, struct dentry *dentry) { int err = fscrypt_get_encryption_info(dir, true); if (!err && !fscrypt_has_encryption_key(dir)) { spin_lock(&dentry->d_lock); dentry->d_flags |= DCACHE_NOKEY_NAME; spin_unlock(&dentry->d_lock); } return err; } EXPORT_SYMBOL_GPL(fscrypt_prepare_lookup_partial); int __fscrypt_prepare_readdir(struct inode *dir) { return fscrypt_get_encryption_info(dir, true); } EXPORT_SYMBOL_GPL(__fscrypt_prepare_readdir); int __fscrypt_prepare_setattr(struct dentry *dentry, struct iattr *attr) { if (attr->ia_valid & ATTR_SIZE) return fscrypt_require_key(d_inode(dentry)); return 0; } EXPORT_SYMBOL_GPL(__fscrypt_prepare_setattr); /** * fscrypt_prepare_setflags() - prepare to change flags with FS_IOC_SETFLAGS * @inode: the inode on which flags are being changed * @oldflags: the old flags * @flags: the new flags * * The caller should be holding i_rwsem for write. * * Return: 0 on success; -errno if the flags change isn't allowed or if * another error occurs. */ int fscrypt_prepare_setflags(struct inode *inode, unsigned int oldflags, unsigned int flags) { struct fscrypt_info *ci; struct fscrypt_master_key *mk; int err; /* * When the CASEFOLD flag is set on an encrypted directory, we must * derive the secret key needed for the dirhash. This is only possible * if the directory uses a v2 encryption policy. */ if (IS_ENCRYPTED(inode) && (flags & ~oldflags & FS_CASEFOLD_FL)) { err = fscrypt_require_key(inode); if (err) return err; ci = inode->i_crypt_info; if (ci->ci_policy.version != FSCRYPT_POLICY_V2) return -EINVAL; mk = ci->ci_master_key; down_read(&mk->mk_sem); if (is_master_key_secret_present(&mk->mk_secret)) err = fscrypt_derive_dirhash_key(ci, mk); else err = -ENOKEY; up_read(&mk->mk_sem); return err; } return 0; } /** * fscrypt_prepare_symlink() - prepare to create a possibly-encrypted symlink * @dir: directory in which the symlink is being created * @target: plaintext symlink target * @len: length of @target excluding null terminator * @max_len: space the filesystem has available to store the symlink target * @disk_link: (out) the on-disk symlink target being prepared * * This function computes the size the symlink target will require on-disk, * stores it in @disk_link->len, and validates it against @max_len. An * encrypted symlink may be longer than the original. * * Additionally, @disk_link->name is set to @target if the symlink will be * unencrypted, but left NULL if the symlink will be encrypted. For encrypted * symlinks, the filesystem must call fscrypt_encrypt_symlink() to create the * on-disk target later. (The reason for the two-step process is that some * filesystems need to know the size of the symlink target before creating the * inode, e.g. to determine whether it will be a "fast" or "slow" symlink.) * * Return: 0 on success, -ENAMETOOLONG if the symlink target is too long, * -ENOKEY if the encryption key is missing, or another -errno code if a problem * occurred while setting up the encryption key. */ int fscrypt_prepare_symlink(struct inode *dir, const char *target, unsigned int len, unsigned int max_len, struct fscrypt_str *disk_link) { const union fscrypt_policy *policy; /* * To calculate the size of the encrypted symlink target we need to know * the amount of NUL padding, which is determined by the flags set in * the encryption policy which will be inherited from the directory. */ policy = fscrypt_policy_to_inherit(dir); if (policy == NULL) { /* Not encrypted */ disk_link->name = (unsigned char *)target; disk_link->len = len + 1; if (disk_link->len > max_len) return -ENAMETOOLONG; return 0; } if (IS_ERR(policy)) return PTR_ERR(policy); /* * Calculate the size of the encrypted symlink and verify it won't * exceed max_len. Note that for historical reasons, encrypted symlink * targets are prefixed with the ciphertext length, despite this * actually being redundant with i_size. This decreases by 2 bytes the * longest symlink target we can accept. * * We could recover 1 byte by not counting a null terminator, but * counting it (even though it is meaningless for ciphertext) is simpler * for now since filesystems will assume it is there and subtract it. */ if (!__fscrypt_fname_encrypted_size(policy, len, max_len - sizeof(struct fscrypt_symlink_data), &disk_link->len)) return -ENAMETOOLONG; disk_link->len += sizeof(struct fscrypt_symlink_data); disk_link->name = NULL; return 0; } EXPORT_SYMBOL_GPL(fscrypt_prepare_symlink); int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, unsigned int len, struct fscrypt_str *disk_link) { int err; struct qstr iname = QSTR_INIT(target, len); struct fscrypt_symlink_data *sd; unsigned int ciphertext_len; /* * fscrypt_prepare_new_inode() should have already set up the new * symlink inode's encryption key. We don't wait until now to do it, * since we may be in a filesystem transaction now. */ if (WARN_ON_ONCE(!fscrypt_has_encryption_key(inode))) return -ENOKEY; if (disk_link->name) { /* filesystem-provided buffer */ sd = (struct fscrypt_symlink_data *)disk_link->name; } else { sd = kmalloc(disk_link->len, GFP_NOFS); if (!sd) return -ENOMEM; } ciphertext_len = disk_link->len - sizeof(*sd); sd->len = cpu_to_le16(ciphertext_len); err = fscrypt_fname_encrypt(inode, &iname, sd->encrypted_path, ciphertext_len); if (err) goto err_free_sd; /* * Null-terminating the ciphertext doesn't make sense, but we still * count the null terminator in the length, so we might as well * initialize it just in case the filesystem writes it out. */ sd->encrypted_path[ciphertext_len] = '\0'; /* Cache the plaintext symlink target for later use by get_link() */ err = -ENOMEM; inode->i_link = kmemdup(target, len + 1, GFP_NOFS); if (!inode->i_link) goto err_free_sd; if (!disk_link->name) disk_link->name = (unsigned char *)sd; return 0; err_free_sd: if (!disk_link->name) kfree(sd); return err; } EXPORT_SYMBOL_GPL(__fscrypt_encrypt_symlink); /** * fscrypt_get_symlink() - get the target of an encrypted symlink * @inode: the symlink inode * @caddr: the on-disk contents of the symlink * @max_size: size of @caddr buffer * @done: if successful, will be set up to free the returned target if needed * * If the symlink's encryption key is available, we decrypt its target. * Otherwise, we encode its target for presentation. * * This may sleep, so the filesystem must have dropped out of RCU mode already. * * Return: the presentable symlink target or an ERR_PTR() */ const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, unsigned int max_size, struct delayed_call *done) { const struct fscrypt_symlink_data *sd; struct fscrypt_str cstr, pstr; bool has_key; int err; /* This is for encrypted symlinks only */ if (WARN_ON_ONCE(!IS_ENCRYPTED(inode))) return ERR_PTR(-EINVAL); /* If the decrypted target is already cached, just return it. */ pstr.name = READ_ONCE(inode->i_link); if (pstr.name) return pstr.name; /* * Try to set up the symlink's encryption key, but we can continue * regardless of whether the key is available or not. */ err = fscrypt_get_encryption_info(inode, false); if (err) return ERR_PTR(err); has_key = fscrypt_has_encryption_key(inode); /* * For historical reasons, encrypted symlink targets are prefixed with * the ciphertext length, even though this is redundant with i_size. */ if (max_size < sizeof(*sd)) return ERR_PTR(-EUCLEAN); sd = caddr; cstr.name = (unsigned char *)sd->encrypted_path; cstr.len = le16_to_cpu(sd->len); if (cstr.len == 0) return ERR_PTR(-EUCLEAN); if (cstr.len + sizeof(*sd) - 1 > max_size) return ERR_PTR(-EUCLEAN); err = fscrypt_fname_alloc_buffer(cstr.len, &pstr); if (err) return ERR_PTR(err); err = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr); if (err) goto err_kfree; err = -EUCLEAN; if (pstr.name[0] == '\0') goto err_kfree; pstr.name[pstr.len] = '\0'; /* * Cache decrypted symlink targets in i_link for later use. Don't cache * symlink targets encoded without the key, since those become outdated * once the key is added. This pairs with the READ_ONCE() above and in * the VFS path lookup code. */ if (!has_key || cmpxchg_release(&inode->i_link, NULL, pstr.name) != NULL) set_delayed_call(done, kfree_link, pstr.name); return pstr.name; err_kfree: kfree(pstr.name); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(fscrypt_get_symlink); /** * fscrypt_symlink_getattr() - set the correct st_size for encrypted symlinks * @path: the path for the encrypted symlink being queried * @stat: the struct being filled with the symlink's attributes * * Override st_size of encrypted symlinks to be the length of the decrypted * symlink target (or the no-key encoded symlink target, if the key is * unavailable) rather than the length of the encrypted symlink target. This is * necessary for st_size to match the symlink target that userspace actually * sees. POSIX requires this, and some userspace programs depend on it. * * This requires reading the symlink target from disk if needed, setting up the * inode's encryption key if possible, and then decrypting or encoding the * symlink target. This makes lstat() more heavyweight than is normally the * case. However, decrypted symlink targets will be cached in ->i_link, so * usually the symlink won't have to be read and decrypted again later if/when * it is actually followed, readlink() is called, or lstat() is called again. * * Return: 0 on success, -errno on failure */ int fscrypt_symlink_getattr(const struct path *path, struct kstat *stat) { struct dentry *dentry = path->dentry; struct inode *inode = d_inode(dentry); const char *link; DEFINE_DELAYED_CALL(done); /* * To get the symlink target that userspace will see (whether it's the * decrypted target or the no-key encoded target), we can just get it in * the same way the VFS does during path resolution and readlink(). */ link = READ_ONCE(inode->i_link); if (!link) { link = inode->i_op->get_link(dentry, inode, &done); if (IS_ERR(link)) return PTR_ERR(link); } stat->size = strlen(link); do_delayed_call(&done); return 0; } EXPORT_SYMBOL_GPL(fscrypt_symlink_getattr); |
| 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 728 728 182 729 7 728 730 728 161 161 183 609 609 271 25 295 5 41 16 8 242 51 186 203 33 237 45 213 198 13 56 3 3 6 1 33 25 7 2 4 531 296 237 640 640 640 640 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 | // SPDX-License-Identifier: GPL-2.0-only /* * xfrm_policy.c * * Changes: * Mitsuru KANDA @USAGI * Kazunori MIYAZAWA @USAGI * Kunihiro Ishiguro <kunihiro@ipinfusion.com> * IPv6 support * Kazunori MIYAZAWA @USAGI * YOSHIFUJI Hideaki * Split up af-specific portion * Derek Atkins <derek@ihtfp.com> Add the post_input processor * */ #include <linux/err.h> #include <linux/slab.h> #include <linux/kmod.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/workqueue.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/netfilter.h> #include <linux/module.h> #include <linux/cache.h> #include <linux/cpu.h> #include <linux/audit.h> #include <linux/rhashtable.h> #include <linux/if_tunnel.h> #include <net/dst.h> #include <net/flow.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/ip.h> #include <net/gre.h> #if IS_ENABLED(CONFIG_IPV6_MIP6) #include <net/mip6.h> #endif #ifdef CONFIG_XFRM_STATISTICS #include <net/snmp.h> #endif #ifdef CONFIG_XFRM_ESPINTCP #include <net/espintcp.h> #endif #include "xfrm_hash.h" #define XFRM_QUEUE_TMO_MIN ((unsigned)(HZ/10)) #define XFRM_QUEUE_TMO_MAX ((unsigned)(60*HZ)) #define XFRM_MAX_QUEUE_LEN 100 struct xfrm_flo { struct dst_entry *dst_orig; u8 flags; }; /* prefixes smaller than this are stored in lists, not trees. */ #define INEXACT_PREFIXLEN_IPV4 16 #define INEXACT_PREFIXLEN_IPV6 48 struct xfrm_pol_inexact_node { struct rb_node node; union { xfrm_address_t addr; struct rcu_head rcu; }; u8 prefixlen; struct rb_root root; /* the policies matching this node, can be empty list */ struct hlist_head hhead; }; /* xfrm inexact policy search tree: * xfrm_pol_inexact_bin = hash(dir,type,family,if_id); * | * +---- root_d: sorted by daddr:prefix * | | * | xfrm_pol_inexact_node * | | * | +- root: sorted by saddr/prefix * | | | * | | xfrm_pol_inexact_node * | | | * | | + root: unused * | | | * | | + hhead: saddr:daddr policies * | | * | +- coarse policies and all any:daddr policies * | * +---- root_s: sorted by saddr:prefix * | | * | xfrm_pol_inexact_node * | | * | + root: unused * | | * | + hhead: saddr:any policies * | * +---- coarse policies and all any:any policies * * Lookups return four candidate lists: * 1. any:any list from top-level xfrm_pol_inexact_bin * 2. any:daddr list from daddr tree * 3. saddr:daddr list from 2nd level daddr tree * 4. saddr:any list from saddr tree * * This result set then needs to be searched for the policy with * the lowest priority. If two results have same prio, youngest one wins. */ struct xfrm_pol_inexact_key { possible_net_t net; u32 if_id; u16 family; u8 dir, type; }; struct xfrm_pol_inexact_bin { struct xfrm_pol_inexact_key k; struct rhash_head head; /* list containing '*:*' policies */ struct hlist_head hhead; seqcount_spinlock_t count; /* tree sorted by daddr/prefix */ struct rb_root root_d; /* tree sorted by saddr/prefix */ struct rb_root root_s; /* slow path below */ struct list_head inexact_bins; struct rcu_head rcu; }; enum xfrm_pol_inexact_candidate_type { XFRM_POL_CAND_BOTH, XFRM_POL_CAND_SADDR, XFRM_POL_CAND_DADDR, XFRM_POL_CAND_ANY, XFRM_POL_CAND_MAX, }; struct xfrm_pol_inexact_candidates { struct hlist_head *res[XFRM_POL_CAND_MAX]; }; static DEFINE_SPINLOCK(xfrm_if_cb_lock); static struct xfrm_if_cb const __rcu *xfrm_if_cb __read_mostly; static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock); static struct xfrm_policy_afinfo const __rcu *xfrm_policy_afinfo[AF_INET6 + 1] __read_mostly; static struct kmem_cache *xfrm_dst_cache __ro_after_init; static struct rhashtable xfrm_policy_inexact_table; static const struct rhashtable_params xfrm_pol_inexact_params; static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr); static int stale_bundle(struct dst_entry *dst); static int xfrm_bundle_ok(struct xfrm_dst *xdst); static void xfrm_policy_queue_process(struct timer_list *t); static void __xfrm_policy_link(struct xfrm_policy *pol, int dir); static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, int dir); static struct xfrm_pol_inexact_bin * xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family, u8 dir, u32 if_id); static struct xfrm_pol_inexact_bin * xfrm_policy_inexact_lookup_rcu(struct net *net, u8 type, u16 family, u8 dir, u32 if_id); static struct xfrm_policy * xfrm_policy_insert_list(struct hlist_head *chain, struct xfrm_policy *policy, bool excl); static void xfrm_policy_insert_inexact_list(struct hlist_head *chain, struct xfrm_policy *policy); static bool xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand, struct xfrm_pol_inexact_bin *b, const xfrm_address_t *saddr, const xfrm_address_t *daddr); static inline bool xfrm_pol_hold_rcu(struct xfrm_policy *policy) { return refcount_inc_not_zero(&policy->refcnt); } static inline bool __xfrm4_selector_match(const struct xfrm_selector *sel, const struct flowi *fl) { const struct flowi4 *fl4 = &fl->u.ip4; return addr4_match(fl4->daddr, sel->daddr.a4, sel->prefixlen_d) && addr4_match(fl4->saddr, sel->saddr.a4, sel->prefixlen_s) && !((xfrm_flowi_dport(fl, &fl4->uli) ^ sel->dport) & sel->dport_mask) && !((xfrm_flowi_sport(fl, &fl4->uli) ^ sel->sport) & sel->sport_mask) && (fl4->flowi4_proto == sel->proto || !sel->proto) && (fl4->flowi4_oif == sel->ifindex || !sel->ifindex); } static inline bool __xfrm6_selector_match(const struct xfrm_selector *sel, const struct flowi *fl) { const struct flowi6 *fl6 = &fl->u.ip6; return addr_match(&fl6->daddr, &sel->daddr, sel->prefixlen_d) && addr_match(&fl6->saddr, &sel->saddr, sel->prefixlen_s) && !((xfrm_flowi_dport(fl, &fl6->uli) ^ sel->dport) & sel->dport_mask) && !((xfrm_flowi_sport(fl, &fl6->uli) ^ sel->sport) & sel->sport_mask) && (fl6->flowi6_proto == sel->proto || !sel->proto) && (fl6->flowi6_oif == sel->ifindex || !sel->ifindex); } bool xfrm_selector_match(const struct xfrm_selector *sel, const struct flowi *fl, unsigned short family) { switch (family) { case AF_INET: return __xfrm4_selector_match(sel, fl); case AF_INET6: return __xfrm6_selector_match(sel, fl); } return false; } static const struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family) { const struct xfrm_policy_afinfo *afinfo; if (unlikely(family >= ARRAY_SIZE(xfrm_policy_afinfo))) return NULL; rcu_read_lock(); afinfo = rcu_dereference(xfrm_policy_afinfo[family]); if (unlikely(!afinfo)) rcu_read_unlock(); return afinfo; } /* Called with rcu_read_lock(). */ static const struct xfrm_if_cb *xfrm_if_get_cb(void) { return rcu_dereference(xfrm_if_cb); } struct dst_entry *__xfrm_dst_lookup(int family, const struct xfrm_dst_lookup_params *params) { const struct xfrm_policy_afinfo *afinfo; struct dst_entry *dst; afinfo = xfrm_policy_get_afinfo(family); if (unlikely(afinfo == NULL)) return ERR_PTR(-EAFNOSUPPORT); dst = afinfo->dst_lookup(params); rcu_read_unlock(); return dst; } EXPORT_SYMBOL(__xfrm_dst_lookup); static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x, int tos, int oif, xfrm_address_t *prev_saddr, xfrm_address_t *prev_daddr, int family, u32 mark) { struct xfrm_dst_lookup_params params; struct net *net = xs_net(x); xfrm_address_t *saddr = &x->props.saddr; xfrm_address_t *daddr = &x->id.daddr; struct dst_entry *dst; if (x->type->flags & XFRM_TYPE_LOCAL_COADDR) { saddr = x->coaddr; daddr = prev_daddr; } if (x->type->flags & XFRM_TYPE_REMOTE_COADDR) { saddr = prev_saddr; daddr = x->coaddr; } params.net = net; params.saddr = saddr; params.daddr = daddr; params.tos = tos; params.oif = oif; params.mark = mark; params.ipproto = x->id.proto; if (x->encap) { switch (x->encap->encap_type) { case UDP_ENCAP_ESPINUDP: params.ipproto = IPPROTO_UDP; params.uli.ports.sport = x->encap->encap_sport; params.uli.ports.dport = x->encap->encap_dport; break; case TCP_ENCAP_ESPINTCP: params.ipproto = IPPROTO_TCP; params.uli.ports.sport = x->encap->encap_sport; params.uli.ports.dport = x->encap->encap_dport; break; } } dst = __xfrm_dst_lookup(family, ¶ms); if (!IS_ERR(dst)) { if (prev_saddr != saddr) memcpy(prev_saddr, saddr, sizeof(*prev_saddr)); if (prev_daddr != daddr) memcpy(prev_daddr, daddr, sizeof(*prev_daddr)); } return dst; } static inline unsigned long make_jiffies(long secs) { if (secs >= (MAX_SCHEDULE_TIMEOUT-1)/HZ) return MAX_SCHEDULE_TIMEOUT-1; else return secs*HZ; } static void xfrm_policy_timer(struct timer_list *t) { struct xfrm_policy *xp = from_timer(xp, t, timer); time64_t now = ktime_get_real_seconds(); time64_t next = TIME64_MAX; int warn = 0; int dir; read_lock(&xp->lock); if (unlikely(xp->walk.dead)) goto out; dir = xfrm_policy_id2dir(xp->index); if (xp->lft.hard_add_expires_seconds) { time64_t tmo = xp->lft.hard_add_expires_seconds + xp->curlft.add_time - now; if (tmo <= 0) goto expired; if (tmo < next) next = tmo; } if (xp->lft.hard_use_expires_seconds) { time64_t tmo = xp->lft.hard_use_expires_seconds + (READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now; if (tmo <= 0) goto expired; if (tmo < next) next = tmo; } if (xp->lft.soft_add_expires_seconds) { time64_t tmo = xp->lft.soft_add_expires_seconds + xp->curlft.add_time - now; if (tmo <= 0) { warn = 1; tmo = XFRM_KM_TIMEOUT; } if (tmo < next) next = tmo; } if (xp->lft.soft_use_expires_seconds) { time64_t tmo = xp->lft.soft_use_expires_seconds + (READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now; if (tmo <= 0) { warn = 1; tmo = XFRM_KM_TIMEOUT; } if (tmo < next) next = tmo; } if (warn) km_policy_expired(xp, dir, 0, 0); if (next != TIME64_MAX && !mod_timer(&xp->timer, jiffies + make_jiffies(next))) xfrm_pol_hold(xp); out: read_unlock(&xp->lock); xfrm_pol_put(xp); return; expired: read_unlock(&xp->lock); if (!xfrm_policy_delete(xp, dir)) km_policy_expired(xp, dir, 1, 0); xfrm_pol_put(xp); } /* Allocate xfrm_policy. Not used here, it is supposed to be used by pfkeyv2 * SPD calls. */ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp) { struct xfrm_policy *policy; policy = kzalloc(sizeof(struct xfrm_policy), gfp); if (policy) { write_pnet(&policy->xp_net, net); INIT_LIST_HEAD(&policy->walk.all); INIT_HLIST_NODE(&policy->bydst_inexact_list); INIT_HLIST_NODE(&policy->bydst); INIT_HLIST_NODE(&policy->byidx); rwlock_init(&policy->lock); refcount_set(&policy->refcnt, 1); skb_queue_head_init(&policy->polq.hold_queue); timer_setup(&policy->timer, xfrm_policy_timer, 0); timer_setup(&policy->polq.hold_timer, xfrm_policy_queue_process, 0); } return policy; } EXPORT_SYMBOL(xfrm_policy_alloc); static void xfrm_policy_destroy_rcu(struct rcu_head *head) { struct xfrm_policy *policy = container_of(head, struct xfrm_policy, rcu); security_xfrm_policy_free(policy->security); kfree(policy); } /* Destroy xfrm_policy: descendant resources must be released to this moment. */ void xfrm_policy_destroy(struct xfrm_policy *policy) { BUG_ON(!policy->walk.dead); if (del_timer(&policy->timer) || del_timer(&policy->polq.hold_timer)) BUG(); call_rcu(&policy->rcu, xfrm_policy_destroy_rcu); } EXPORT_SYMBOL(xfrm_policy_destroy); /* Rule must be locked. Release descendant resources, announce * entry dead. The rule must be unlinked from lists to the moment. */ static void xfrm_policy_kill(struct xfrm_policy *policy) { write_lock_bh(&policy->lock); policy->walk.dead = 1; write_unlock_bh(&policy->lock); atomic_inc(&policy->genid); if (del_timer(&policy->polq.hold_timer)) xfrm_pol_put(policy); skb_queue_purge(&policy->polq.hold_queue); if (del_timer(&policy->timer)) xfrm_pol_put(policy); xfrm_pol_put(policy); } static unsigned int xfrm_policy_hashmax __read_mostly = 1 * 1024 * 1024; static inline unsigned int idx_hash(struct net *net, u32 index) { return __idx_hash(index, net->xfrm.policy_idx_hmask); } /* calculate policy hash thresholds */ static void __get_hash_thresh(struct net *net, unsigned short family, int dir, u8 *dbits, u8 *sbits) { switch (family) { case AF_INET: *dbits = net->xfrm.policy_bydst[dir].dbits4; *sbits = net->xfrm.policy_bydst[dir].sbits4; break; case AF_INET6: *dbits = net->xfrm.policy_bydst[dir].dbits6; *sbits = net->xfrm.policy_bydst[dir].sbits6; break; default: *dbits = 0; *sbits = 0; } } static struct hlist_head *policy_hash_bysel(struct net *net, const struct xfrm_selector *sel, unsigned short family, int dir) { unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; unsigned int hash; u8 dbits; u8 sbits; __get_hash_thresh(net, family, dir, &dbits, &sbits); hash = __sel_hash(sel, family, hmask, dbits, sbits); if (hash == hmask + 1) return NULL; return rcu_dereference_check(net->xfrm.policy_bydst[dir].table, lockdep_is_held(&net->xfrm.xfrm_policy_lock)) + hash; } static struct hlist_head *policy_hash_direct(struct net *net, const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family, int dir) { unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; unsigned int hash; u8 dbits; u8 sbits; __get_hash_thresh(net, family, dir, &dbits, &sbits); hash = __addr_hash(daddr, saddr, family, hmask, dbits, sbits); return rcu_dereference_check(net->xfrm.policy_bydst[dir].table, lockdep_is_held(&net->xfrm.xfrm_policy_lock)) + hash; } static void xfrm_dst_hash_transfer(struct net *net, struct hlist_head *list, struct hlist_head *ndsttable, unsigned int nhashmask, int dir) { struct hlist_node *tmp, *entry0 = NULL; struct xfrm_policy *pol; unsigned int h0 = 0; u8 dbits; u8 sbits; redo: hlist_for_each_entry_safe(pol, tmp, list, bydst) { unsigned int h; __get_hash_thresh(net, pol->family, dir, &dbits, &sbits); h = __addr_hash(&pol->selector.daddr, &pol->selector.saddr, pol->family, nhashmask, dbits, sbits); if (!entry0) { hlist_del_rcu(&pol->bydst); hlist_add_head_rcu(&pol->bydst, ndsttable + h); h0 = h; } else { if (h != h0) continue; hlist_del_rcu(&pol->bydst); hlist_add_behind_rcu(&pol->bydst, entry0); } entry0 = &pol->bydst; } if (!hlist_empty(list)) { entry0 = NULL; goto redo; } } static void xfrm_idx_hash_transfer(struct hlist_head *list, struct hlist_head *nidxtable, unsigned int nhashmask) { struct hlist_node *tmp; struct xfrm_policy *pol; hlist_for_each_entry_safe(pol, tmp, list, byidx) { unsigned int h; h = __idx_hash(pol->index, nhashmask); hlist_add_head(&pol->byidx, nidxtable+h); } } static unsigned long xfrm_new_hash_mask(unsigned int old_hmask) { return ((old_hmask + 1) << 1) - 1; } static void xfrm_bydst_resize(struct net *net, int dir) { unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; unsigned int nhashmask = xfrm_new_hash_mask(hmask); unsigned int nsize = (nhashmask + 1) * sizeof(struct hlist_head); struct hlist_head *ndst = xfrm_hash_alloc(nsize); struct hlist_head *odst; int i; if (!ndst) return; spin_lock_bh(&net->xfrm.xfrm_policy_lock); write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table, lockdep_is_held(&net->xfrm.xfrm_policy_lock)); for (i = hmask; i >= 0; i--) xfrm_dst_hash_transfer(net, odst + i, ndst, nhashmask, dir); rcu_assign_pointer(net->xfrm.policy_bydst[dir].table, ndst); net->xfrm.policy_bydst[dir].hmask = nhashmask; write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); synchronize_rcu(); xfrm_hash_free(odst, (hmask + 1) * sizeof(struct hlist_head)); } static void xfrm_byidx_resize(struct net *net, int total) { unsigned int hmask = net->xfrm.policy_idx_hmask; unsigned int nhashmask = xfrm_new_hash_mask(hmask); unsigned int nsize = (nhashmask + 1) * sizeof(struct hlist_head); struct hlist_head *oidx = net->xfrm.policy_byidx; struct hlist_head *nidx = xfrm_hash_alloc(nsize); int i; if (!nidx) return; spin_lock_bh(&net->xfrm.xfrm_policy_lock); for (i = hmask; i >= 0; i--) xfrm_idx_hash_transfer(oidx + i, nidx, nhashmask); net->xfrm.policy_byidx = nidx; net->xfrm.policy_idx_hmask = nhashmask; spin_unlock_bh(&net->xfrm.xfrm_policy_lock); xfrm_hash_free(oidx, (hmask + 1) * sizeof(struct hlist_head)); } static inline int xfrm_bydst_should_resize(struct net *net, int dir, int *total) { unsigned int cnt = net->xfrm.policy_count[dir]; unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; if (total) *total += cnt; if ((hmask + 1) < xfrm_policy_hashmax && cnt > hmask) return 1; return 0; } static inline int xfrm_byidx_should_resize(struct net *net, int total) { unsigned int hmask = net->xfrm.policy_idx_hmask; if ((hmask + 1) < xfrm_policy_hashmax && total > hmask) return 1; return 0; } void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si) { si->incnt = net->xfrm.policy_count[XFRM_POLICY_IN]; si->outcnt = net->xfrm.policy_count[XFRM_POLICY_OUT]; si->fwdcnt = net->xfrm.policy_count[XFRM_POLICY_FWD]; si->inscnt = net->xfrm.policy_count[XFRM_POLICY_IN+XFRM_POLICY_MAX]; si->outscnt = net->xfrm.policy_count[XFRM_POLICY_OUT+XFRM_POLICY_MAX]; si->fwdscnt = net->xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX]; si->spdhcnt = net->xfrm.policy_idx_hmask; si->spdhmcnt = xfrm_policy_hashmax; } EXPORT_SYMBOL(xfrm_spd_getinfo); static DEFINE_MUTEX(hash_resize_mutex); static void xfrm_hash_resize(struct work_struct *work) { struct net *net = container_of(work, struct net, xfrm.policy_hash_work); int dir, total; mutex_lock(&hash_resize_mutex); total = 0; for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { if (xfrm_bydst_should_resize(net, dir, &total)) xfrm_bydst_resize(net, dir); } if (xfrm_byidx_should_resize(net, total)) xfrm_byidx_resize(net, total); mutex_unlock(&hash_resize_mutex); } /* Make sure *pol can be inserted into fastbin. * Useful to check that later insert requests will be successful * (provided xfrm_policy_lock is held throughout). */ static struct xfrm_pol_inexact_bin * xfrm_policy_inexact_alloc_bin(const struct xfrm_policy *pol, u8 dir) { struct xfrm_pol_inexact_bin *bin, *prev; struct xfrm_pol_inexact_key k = { .family = pol->family, .type = pol->type, .dir = dir, .if_id = pol->if_id, }; struct net *net = xp_net(pol); lockdep_assert_held(&net->xfrm.xfrm_policy_lock); write_pnet(&k.net, net); bin = rhashtable_lookup_fast(&xfrm_policy_inexact_table, &k, xfrm_pol_inexact_params); if (bin) return bin; bin = kzalloc(sizeof(*bin), GFP_ATOMIC); if (!bin) return NULL; bin->k = k; INIT_HLIST_HEAD(&bin->hhead); bin->root_d = RB_ROOT; bin->root_s = RB_ROOT; seqcount_spinlock_init(&bin->count, &net->xfrm.xfrm_policy_lock); prev = rhashtable_lookup_get_insert_key(&xfrm_policy_inexact_table, &bin->k, &bin->head, xfrm_pol_inexact_params); if (!prev) { list_add(&bin->inexact_bins, &net->xfrm.inexact_bins); return bin; } kfree(bin); return IS_ERR(prev) ? NULL : prev; } static bool xfrm_pol_inexact_addr_use_any_list(const xfrm_address_t *addr, int family, u8 prefixlen) { if (xfrm_addr_any(addr, family)) return true; if (family == AF_INET6 && prefixlen < INEXACT_PREFIXLEN_IPV6) return true; if (family == AF_INET && prefixlen < INEXACT_PREFIXLEN_IPV4) return true; return false; } static bool xfrm_policy_inexact_insert_use_any_list(const struct xfrm_policy *policy) { const xfrm_address_t *addr; bool saddr_any, daddr_any; u8 prefixlen; addr = &policy->selector.saddr; prefixlen = policy->selector.prefixlen_s; saddr_any = xfrm_pol_inexact_addr_use_any_list(addr, policy->family, prefixlen); addr = &policy->selector.daddr; prefixlen = policy->selector.prefixlen_d; daddr_any = xfrm_pol_inexact_addr_use_any_list(addr, policy->family, prefixlen); return saddr_any && daddr_any; } static void xfrm_pol_inexact_node_init(struct xfrm_pol_inexact_node *node, const xfrm_address_t *addr, u8 prefixlen) { node->addr = *addr; node->prefixlen = prefixlen; } static struct xfrm_pol_inexact_node * xfrm_pol_inexact_node_alloc(const xfrm_address_t *addr, u8 prefixlen) { struct xfrm_pol_inexact_node *node; node = kzalloc(sizeof(*node), GFP_ATOMIC); if (node) xfrm_pol_inexact_node_init(node, addr, prefixlen); return node; } static int xfrm_policy_addr_delta(const xfrm_address_t *a, const xfrm_address_t *b, u8 prefixlen, u16 family) { u32 ma, mb, mask; unsigned int pdw, pbi; int delta = 0; switch (family) { case AF_INET: if (prefixlen == 0) return 0; mask = ~0U << (32 - prefixlen); ma = ntohl(a->a4) & mask; mb = ntohl(b->a4) & mask; if (ma < mb) delta = -1; else if (ma > mb) delta = 1; break; case AF_INET6: pdw = prefixlen >> 5; pbi = prefixlen & 0x1f; if (pdw) { delta = memcmp(a->a6, b->a6, pdw << 2); if (delta) return delta; } if (pbi) { mask = ~0U << (32 - pbi); ma = ntohl(a->a6[pdw]) & mask; mb = ntohl(b->a6[pdw]) & mask; if (ma < mb) delta = -1; else if (ma > mb) delta = 1; } break; default: break; } return delta; } static void xfrm_policy_inexact_list_reinsert(struct net *net, struct xfrm_pol_inexact_node *n, u16 family) { unsigned int matched_s, matched_d; struct xfrm_policy *policy, *p; matched_s = 0; matched_d = 0; list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) { struct hlist_node *newpos = NULL; bool matches_s, matches_d; if (policy->walk.dead || !policy->bydst_reinsert) continue; WARN_ON_ONCE(policy->family != family); policy->bydst_reinsert = false; hlist_for_each_entry(p, &n->hhead, bydst) { if (policy->priority > p->priority) newpos = &p->bydst; else if (policy->priority == p->priority && policy->pos > p->pos) newpos = &p->bydst; else break; } if (newpos) hlist_add_behind_rcu(&policy->bydst, newpos); else hlist_add_head_rcu(&policy->bydst, &n->hhead); /* paranoia checks follow. * Check that the reinserted policy matches at least * saddr or daddr for current node prefix. * * Matching both is fine, matching saddr in one policy * (but not daddr) and then matching only daddr in another * is a bug. */ matches_s = xfrm_policy_addr_delta(&policy->selector.saddr, &n->addr, n->prefixlen, family) == 0; matches_d = xfrm_policy_addr_delta(&policy->selector.daddr, &n->addr, n->prefixlen, family) == 0; if (matches_s && matches_d) continue; WARN_ON_ONCE(!matches_s && !matches_d); if (matches_s) matched_s++; if (matches_d) matched_d++; WARN_ON_ONCE(matched_s && matched_d); } } static void xfrm_policy_inexact_node_reinsert(struct net *net, struct xfrm_pol_inexact_node *n, struct rb_root *new, u16 family) { struct xfrm_pol_inexact_node *node; struct rb_node **p, *parent; /* we should not have another subtree here */ WARN_ON_ONCE(!RB_EMPTY_ROOT(&n->root)); restart: parent = NULL; p = &new->rb_node; while (*p) { u8 prefixlen; int delta; parent = *p; node = rb_entry(*p, struct xfrm_pol_inexact_node, node); prefixlen = min(node->prefixlen, n->prefixlen); delta = xfrm_policy_addr_delta(&n->addr, &node->addr, prefixlen, family); if (delta < 0) { p = &parent->rb_left; } else if (delta > 0) { p = &parent->rb_right; } else { bool same_prefixlen = node->prefixlen == n->prefixlen; struct xfrm_policy *tmp; hlist_for_each_entry(tmp, &n->hhead, bydst) { tmp->bydst_reinsert = true; hlist_del_rcu(&tmp->bydst); } node->prefixlen = prefixlen; xfrm_policy_inexact_list_reinsert(net, node, family); if (same_prefixlen) { kfree_rcu(n, rcu); return; } rb_erase(*p, new); kfree_rcu(n, rcu); n = node; goto restart; } } rb_link_node_rcu(&n->node, parent, p); rb_insert_color(&n->node, new); } /* merge nodes v and n */ static void xfrm_policy_inexact_node_merge(struct net *net, struct xfrm_pol_inexact_node *v, struct xfrm_pol_inexact_node *n, u16 family) { struct xfrm_pol_inexact_node *node; struct xfrm_policy *tmp; struct rb_node *rnode; /* To-be-merged node v has a subtree. * * Dismantle it and insert its nodes to n->root. */ while ((rnode = rb_first(&v->root)) != NULL) { node = rb_entry(rnode, struct xfrm_pol_inexact_node, node); rb_erase(&node->node, &v->root); xfrm_policy_inexact_node_reinsert(net, node, &n->root, family); } hlist_for_each_entry(tmp, &v->hhead, bydst) { tmp->bydst_reinsert = true; hlist_del_rcu(&tmp->bydst); } xfrm_policy_inexact_list_reinsert(net, n, family); } static struct xfrm_pol_inexact_node * xfrm_policy_inexact_insert_node(struct net *net, struct rb_root *root, xfrm_address_t *addr, u16 family, u8 prefixlen, u8 dir) { struct xfrm_pol_inexact_node *cached = NULL; struct rb_node **p, *parent = NULL; struct xfrm_pol_inexact_node *node; p = &root->rb_node; while (*p) { int delta; parent = *p; node = rb_entry(*p, struct xfrm_pol_inexact_node, node); delta = xfrm_policy_addr_delta(addr, &node->addr, node->prefixlen, family); if (delta == 0 && prefixlen >= node->prefixlen) { WARN_ON_ONCE(cached); /* ipsec policies got lost */ return node; } if (delta < 0) p = &parent->rb_left; else p = &parent->rb_right; if (prefixlen < node->prefixlen) { delta = xfrm_policy_addr_delta(addr, &node->addr, prefixlen, family); if (delta) continue; /* This node is a subnet of the new prefix. It needs * to be removed and re-inserted with the smaller * prefix and all nodes that are now also covered * by the reduced prefixlen. */ rb_erase(&node->node, root); if (!cached) { xfrm_pol_inexact_node_init(node, addr, prefixlen); cached = node; } else { /* This node also falls within the new * prefixlen. Merge the to-be-reinserted * node and this one. */ xfrm_policy_inexact_node_merge(net, node, cached, family); kfree_rcu(node, rcu); } /* restart */ p = &root->rb_node; parent = NULL; } } node = cached; if (!node) { node = xfrm_pol_inexact_node_alloc(addr, prefixlen); if (!node) return NULL; } rb_link_node_rcu(&node->node, parent, p); rb_insert_color(&node->node, root); return node; } static void xfrm_policy_inexact_gc_tree(struct rb_root *r, bool rm) { struct xfrm_pol_inexact_node *node; struct rb_node *rn = rb_first(r); while (rn) { node = rb_entry(rn, struct xfrm_pol_inexact_node, node); xfrm_policy_inexact_gc_tree(&node->root, rm); rn = rb_next(rn); if (!hlist_empty(&node->hhead) || !RB_EMPTY_ROOT(&node->root)) { WARN_ON_ONCE(rm); continue; } rb_erase(&node->node, r); kfree_rcu(node, rcu); } } static void __xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b, bool net_exit) { write_seqcount_begin(&b->count); xfrm_policy_inexact_gc_tree(&b->root_d, net_exit); xfrm_policy_inexact_gc_tree(&b->root_s, net_exit); write_seqcount_end(&b->count); if (!RB_EMPTY_ROOT(&b->root_d) || !RB_EMPTY_ROOT(&b->root_s) || !hlist_empty(&b->hhead)) { WARN_ON_ONCE(net_exit); return; } if (rhashtable_remove_fast(&xfrm_policy_inexact_table, &b->head, xfrm_pol_inexact_params) == 0) { list_del(&b->inexact_bins); kfree_rcu(b, rcu); } } static void xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b) { struct net *net = read_pnet(&b->k.net); spin_lock_bh(&net->xfrm.xfrm_policy_lock); __xfrm_policy_inexact_prune_bin(b, false); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); } static void __xfrm_policy_inexact_flush(struct net *net) { struct xfrm_pol_inexact_bin *bin, *t; lockdep_assert_held(&net->xfrm.xfrm_policy_lock); list_for_each_entry_safe(bin, t, &net->xfrm.inexact_bins, inexact_bins) __xfrm_policy_inexact_prune_bin(bin, false); } static struct hlist_head * xfrm_policy_inexact_alloc_chain(struct xfrm_pol_inexact_bin *bin, struct xfrm_policy *policy, u8 dir) { struct xfrm_pol_inexact_node *n; struct net *net; net = xp_net(policy); lockdep_assert_held(&net->xfrm.xfrm_policy_lock); if (xfrm_policy_inexact_insert_use_any_list(policy)) return &bin->hhead; if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.daddr, policy->family, policy->selector.prefixlen_d)) { write_seqcount_begin(&bin->count); n = xfrm_policy_inexact_insert_node(net, &bin->root_s, &policy->selector.saddr, policy->family, policy->selector.prefixlen_s, dir); write_seqcount_end(&bin->count); if (!n) return NULL; return &n->hhead; } /* daddr is fixed */ write_seqcount_begin(&bin->count); n = xfrm_policy_inexact_insert_node(net, &bin->root_d, &policy->selector.daddr, policy->family, policy->selector.prefixlen_d, dir); write_seqcount_end(&bin->count); if (!n) return NULL; /* saddr is wildcard */ if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.saddr, policy->family, policy->selector.prefixlen_s)) return &n->hhead; write_seqcount_begin(&bin->count); n = xfrm_policy_inexact_insert_node(net, &n->root, &policy->selector.saddr, policy->family, policy->selector.prefixlen_s, dir); write_seqcount_end(&bin->count); if (!n) return NULL; return &n->hhead; } static struct xfrm_policy * xfrm_policy_inexact_insert(struct xfrm_policy *policy, u8 dir, int excl) { struct xfrm_pol_inexact_bin *bin; struct xfrm_policy *delpol; struct hlist_head *chain; struct net *net; bin = xfrm_policy_inexact_alloc_bin(policy, dir); if (!bin) return ERR_PTR(-ENOMEM); net = xp_net(policy); lockdep_assert_held(&net->xfrm.xfrm_policy_lock); chain = xfrm_policy_inexact_alloc_chain(bin, policy, dir); if (!chain) { __xfrm_policy_inexact_prune_bin(bin, false); return ERR_PTR(-ENOMEM); } delpol = xfrm_policy_insert_list(chain, policy, excl); if (delpol && excl) { __xfrm_policy_inexact_prune_bin(bin, false); return ERR_PTR(-EEXIST); } chain = &net->xfrm.policy_inexact[dir]; xfrm_policy_insert_inexact_list(chain, policy); if (delpol) __xfrm_policy_inexact_prune_bin(bin, false); return delpol; } static void xfrm_hash_rebuild(struct work_struct *work) { struct net *net = container_of(work, struct net, xfrm.policy_hthresh.work); unsigned int hmask; struct xfrm_policy *pol; struct xfrm_policy *policy; struct hlist_head *chain; struct hlist_head *odst; struct hlist_node *newpos; int i; int dir; unsigned seq; u8 lbits4, rbits4, lbits6, rbits6; mutex_lock(&hash_resize_mutex); /* read selector prefixlen thresholds */ do { seq = read_seqbegin(&net->xfrm.policy_hthresh.lock); lbits4 = net->xfrm.policy_hthresh.lbits4; rbits4 = net->xfrm.policy_hthresh.rbits4; lbits6 = net->xfrm.policy_hthresh.lbits6; rbits6 = net->xfrm.policy_hthresh.rbits6; } while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq)); spin_lock_bh(&net->xfrm.xfrm_policy_lock); write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); /* make sure that we can insert the indirect policies again before * we start with destructive action. */ list_for_each_entry(policy, &net->xfrm.policy_all, walk.all) { struct xfrm_pol_inexact_bin *bin; u8 dbits, sbits; if (policy->walk.dead) continue; dir = xfrm_policy_id2dir(policy->index); if (dir >= XFRM_POLICY_MAX) continue; if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) { if (policy->family == AF_INET) { dbits = rbits4; sbits = lbits4; } else { dbits = rbits6; sbits = lbits6; } } else { if (policy->family == AF_INET) { dbits = lbits4; sbits = rbits4; } else { dbits = lbits6; sbits = rbits6; } } if (policy->selector.prefixlen_d < dbits || policy->selector.prefixlen_s < sbits) continue; bin = xfrm_policy_inexact_alloc_bin(policy, dir); if (!bin) goto out_unlock; if (!xfrm_policy_inexact_alloc_chain(bin, policy, dir)) goto out_unlock; } /* reset the bydst and inexact table in all directions */ for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { struct hlist_node *n; hlist_for_each_entry_safe(policy, n, &net->xfrm.policy_inexact[dir], bydst_inexact_list) { hlist_del_rcu(&policy->bydst); hlist_del_init(&policy->bydst_inexact_list); } hmask = net->xfrm.policy_bydst[dir].hmask; odst = net->xfrm.policy_bydst[dir].table; for (i = hmask; i >= 0; i--) { hlist_for_each_entry_safe(policy, n, odst + i, bydst) hlist_del_rcu(&policy->bydst); } if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) { /* dir out => dst = remote, src = local */ net->xfrm.policy_bydst[dir].dbits4 = rbits4; net->xfrm.policy_bydst[dir].sbits4 = lbits4; net->xfrm.policy_bydst[dir].dbits6 = rbits6; net->xfrm.policy_bydst[dir].sbits6 = lbits6; } else { /* dir in/fwd => dst = local, src = remote */ net->xfrm.policy_bydst[dir].dbits4 = lbits4; net->xfrm.policy_bydst[dir].sbits4 = rbits4; net->xfrm.policy_bydst[dir].dbits6 = lbits6; net->xfrm.policy_bydst[dir].sbits6 = rbits6; } } /* re-insert all policies by order of creation */ list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) { if (policy->walk.dead) continue; dir = xfrm_policy_id2dir(policy->index); if (dir >= XFRM_POLICY_MAX) { /* skip socket policies */ continue; } newpos = NULL; chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); if (!chain) { void *p = xfrm_policy_inexact_insert(policy, dir, 0); WARN_ONCE(IS_ERR(p), "reinsert: %ld\n", PTR_ERR(p)); continue; } hlist_for_each_entry(pol, chain, bydst) { if (policy->priority >= pol->priority) newpos = &pol->bydst; else break; } if (newpos) hlist_add_behind_rcu(&policy->bydst, newpos); else hlist_add_head_rcu(&policy->bydst, chain); } out_unlock: __xfrm_policy_inexact_flush(net); write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); mutex_unlock(&hash_resize_mutex); } void xfrm_policy_hash_rebuild(struct net *net) { schedule_work(&net->xfrm.policy_hthresh.work); } EXPORT_SYMBOL(xfrm_policy_hash_rebuild); /* Generate new index... KAME seems to generate them ordered by cost * of an absolute inpredictability of ordering of rules. This will not pass. */ static u32 xfrm_gen_index(struct net *net, int dir, u32 index) { static u32 idx_generator; for (;;) { struct hlist_head *list; struct xfrm_policy *p; u32 idx; int found; if (!index) { idx = (idx_generator | dir); idx_generator += 8; } else { idx = index; index = 0; } if (idx == 0) idx = 8; list = net->xfrm.policy_byidx + idx_hash(net, idx); found = 0; hlist_for_each_entry(p, list, byidx) { if (p->index == idx) { found = 1; break; } } if (!found) return idx; } } static inline int selector_cmp(struct xfrm_selector *s1, struct xfrm_selector *s2) { u32 *p1 = (u32 *) s1; u32 *p2 = (u32 *) s2; int len = sizeof(struct xfrm_selector) / sizeof(u32); int i; for (i = 0; i < len; i++) { if (p1[i] != p2[i]) return 1; } return 0; } static void xfrm_policy_requeue(struct xfrm_policy *old, struct xfrm_policy *new) { struct xfrm_policy_queue *pq = &old->polq; struct sk_buff_head list; if (skb_queue_empty(&pq->hold_queue)) return; __skb_queue_head_init(&list); spin_lock_bh(&pq->hold_queue.lock); skb_queue_splice_init(&pq->hold_queue, &list); if (del_timer(&pq->hold_timer)) xfrm_pol_put(old); spin_unlock_bh(&pq->hold_queue.lock); pq = &new->polq; spin_lock_bh(&pq->hold_queue.lock); skb_queue_splice(&list, &pq->hold_queue); pq->timeout = XFRM_QUEUE_TMO_MIN; if (!mod_timer(&pq->hold_timer, jiffies)) xfrm_pol_hold(new); spin_unlock_bh(&pq->hold_queue.lock); } static inline bool xfrm_policy_mark_match(const struct xfrm_mark *mark, struct xfrm_policy *pol) { return mark->v == pol->mark.v && mark->m == pol->mark.m; } static u32 xfrm_pol_bin_key(const void *data, u32 len, u32 seed) { const struct xfrm_pol_inexact_key *k = data; u32 a = k->type << 24 | k->dir << 16 | k->family; return jhash_3words(a, k->if_id, net_hash_mix(read_pnet(&k->net)), seed); } static u32 xfrm_pol_bin_obj(const void *data, u32 len, u32 seed) { const struct xfrm_pol_inexact_bin *b = data; return xfrm_pol_bin_key(&b->k, 0, seed); } static int xfrm_pol_bin_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct xfrm_pol_inexact_key *key = arg->key; const struct xfrm_pol_inexact_bin *b = ptr; int ret; if (!net_eq(read_pnet(&b->k.net), read_pnet(&key->net))) return -1; ret = b->k.dir ^ key->dir; if (ret) return ret; ret = b->k.type ^ key->type; if (ret) return ret; ret = b->k.family ^ key->family; if (ret) return ret; return b->k.if_id ^ key->if_id; } static const struct rhashtable_params xfrm_pol_inexact_params = { .head_offset = offsetof(struct xfrm_pol_inexact_bin, head), .hashfn = xfrm_pol_bin_key, .obj_hashfn = xfrm_pol_bin_obj, .obj_cmpfn = xfrm_pol_bin_cmp, .automatic_shrinking = true, }; static void xfrm_policy_insert_inexact_list(struct hlist_head *chain, struct xfrm_policy *policy) { struct xfrm_policy *pol, *delpol = NULL; struct hlist_node *newpos = NULL; int i = 0; hlist_for_each_entry(pol, chain, bydst_inexact_list) { if (pol->type == policy->type && pol->if_id == policy->if_id && !selector_cmp(&pol->selector, &policy->selector) && xfrm_policy_mark_match(&policy->mark, pol) && xfrm_sec_ctx_match(pol->security, policy->security) && !WARN_ON(delpol)) { delpol = pol; if (policy->priority > pol->priority) continue; } else if (policy->priority >= pol->priority) { newpos = &pol->bydst_inexact_list; continue; } if (delpol) break; } if (newpos) hlist_add_behind_rcu(&policy->bydst_inexact_list, newpos); else hlist_add_head_rcu(&policy->bydst_inexact_list, chain); hlist_for_each_entry(pol, chain, bydst_inexact_list) { pol->pos = i; i++; } } static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain, struct xfrm_policy *policy, bool excl) { struct xfrm_policy *pol, *newpos = NULL, *delpol = NULL; hlist_for_each_entry(pol, chain, bydst) { if (pol->type == policy->type && pol->if_id == policy->if_id && !selector_cmp(&pol->selector, &policy->selector) && xfrm_policy_mark_match(&policy->mark, pol) && xfrm_sec_ctx_match(pol->security, policy->security) && !WARN_ON(delpol)) { if (excl) return ERR_PTR(-EEXIST); delpol = pol; if (policy->priority > pol->priority) continue; } else if (policy->priority >= pol->priority) { newpos = pol; continue; } if (delpol) break; } if (newpos) hlist_add_behind_rcu(&policy->bydst, &newpos->bydst); else hlist_add_head_rcu(&policy->bydst, chain); return delpol; } int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) { struct net *net = xp_net(policy); struct xfrm_policy *delpol; struct hlist_head *chain; spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); if (chain) delpol = xfrm_policy_insert_list(chain, policy, excl); else delpol = xfrm_policy_inexact_insert(policy, dir, excl); if (IS_ERR(delpol)) { spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return PTR_ERR(delpol); } __xfrm_policy_link(policy, dir); /* After previous checking, family can either be AF_INET or AF_INET6 */ if (policy->family == AF_INET) rt_genid_bump_ipv4(net); else rt_genid_bump_ipv6(net); if (delpol) { xfrm_policy_requeue(delpol, policy); __xfrm_policy_unlink(delpol, dir); } policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir, policy->index); hlist_add_head(&policy->byidx, net->xfrm.policy_byidx+idx_hash(net, policy->index)); policy->curlft.add_time = ktime_get_real_seconds(); policy->curlft.use_time = 0; if (!mod_timer(&policy->timer, jiffies + HZ)) xfrm_pol_hold(policy); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (delpol) xfrm_policy_kill(delpol); else if (xfrm_bydst_should_resize(net, dir, NULL)) schedule_work(&net->xfrm.policy_hash_work); return 0; } EXPORT_SYMBOL(xfrm_policy_insert); static struct xfrm_policy * __xfrm_policy_bysel_ctx(struct hlist_head *chain, const struct xfrm_mark *mark, u32 if_id, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx) { struct xfrm_policy *pol; if (!chain) return NULL; hlist_for_each_entry(pol, chain, bydst) { if (pol->type == type && pol->if_id == if_id && xfrm_policy_mark_match(mark, pol) && !selector_cmp(sel, &pol->selector) && xfrm_sec_ctx_match(ctx, pol->security)) return pol; } return NULL; } struct xfrm_policy * xfrm_policy_bysel_ctx(struct net *net, const struct xfrm_mark *mark, u32 if_id, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx, int delete, int *err) { struct xfrm_pol_inexact_bin *bin = NULL; struct xfrm_policy *pol, *ret = NULL; struct hlist_head *chain; *err = 0; spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_bysel(net, sel, sel->family, dir); if (!chain) { struct xfrm_pol_inexact_candidates cand; int i; bin = xfrm_policy_inexact_lookup(net, type, sel->family, dir, if_id); if (!bin) { spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return NULL; } if (!xfrm_policy_find_inexact_candidates(&cand, bin, &sel->saddr, &sel->daddr)) { spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return NULL; } pol = NULL; for (i = 0; i < ARRAY_SIZE(cand.res); i++) { struct xfrm_policy *tmp; tmp = __xfrm_policy_bysel_ctx(cand.res[i], mark, if_id, type, dir, sel, ctx); if (!tmp) continue; if (!pol || tmp->pos < pol->pos) pol = tmp; } } else { pol = __xfrm_policy_bysel_ctx(chain, mark, if_id, type, dir, sel, ctx); } if (pol) { xfrm_pol_hold(pol); if (delete) { *err = security_xfrm_policy_delete(pol->security); if (*err) { spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return pol; } __xfrm_policy_unlink(pol, dir); } ret = pol; } spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (ret && delete) xfrm_policy_kill(ret); if (bin && delete) xfrm_policy_inexact_prune_bin(bin); return ret; } EXPORT_SYMBOL(xfrm_policy_bysel_ctx); struct xfrm_policy * xfrm_policy_byid(struct net *net, const struct xfrm_mark *mark, u32 if_id, u8 type, int dir, u32 id, int delete, int *err) { struct xfrm_policy *pol, *ret; struct hlist_head *chain; *err = -ENOENT; if (xfrm_policy_id2dir(id) != dir) return NULL; *err = 0; spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = net->xfrm.policy_byidx + idx_hash(net, id); ret = NULL; hlist_for_each_entry(pol, chain, byidx) { if (pol->type == type && pol->index == id && pol->if_id == if_id && xfrm_policy_mark_match(mark, pol)) { xfrm_pol_hold(pol); if (delete) { *err = security_xfrm_policy_delete( pol->security); if (*err) { spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return pol; } __xfrm_policy_unlink(pol, dir); } ret = pol; break; } } spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (ret && delete) xfrm_policy_kill(ret); return ret; } EXPORT_SYMBOL(xfrm_policy_byid); #ifdef CONFIG_SECURITY_NETWORK_XFRM static inline int xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid) { struct xfrm_policy *pol; int err = 0; list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) { if (pol->walk.dead || xfrm_policy_id2dir(pol->index) >= XFRM_POLICY_MAX || pol->type != type) continue; err = security_xfrm_policy_delete(pol->security); if (err) { xfrm_audit_policy_delete(pol, 0, task_valid); return err; } } return err; } #else static inline int xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid) { return 0; } #endif int xfrm_policy_flush(struct net *net, u8 type, bool task_valid) { int dir, err = 0, cnt = 0; struct xfrm_policy *pol; spin_lock_bh(&net->xfrm.xfrm_policy_lock); err = xfrm_policy_flush_secctx_check(net, type, task_valid); if (err) goto out; again: list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) { if (pol->walk.dead) continue; dir = xfrm_policy_id2dir(pol->index); if (dir >= XFRM_POLICY_MAX || pol->type != type) continue; __xfrm_policy_unlink(pol, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); cnt++; xfrm_audit_policy_delete(pol, 1, task_valid); xfrm_policy_kill(pol); spin_lock_bh(&net->xfrm.xfrm_policy_lock); goto again; } if (cnt) __xfrm_policy_inexact_flush(net); else err = -ESRCH; out: spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return err; } EXPORT_SYMBOL(xfrm_policy_flush); int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, int (*func)(struct xfrm_policy *, int, int, void*), void *data) { struct xfrm_policy *pol; struct xfrm_policy_walk_entry *x; int error = 0; if (walk->type >= XFRM_POLICY_TYPE_MAX && walk->type != XFRM_POLICY_TYPE_ANY) return -EINVAL; if (list_empty(&walk->walk.all) && walk->seq != 0) return 0; spin_lock_bh(&net->xfrm.xfrm_policy_lock); if (list_empty(&walk->walk.all)) x = list_first_entry(&net->xfrm.policy_all, struct xfrm_policy_walk_entry, all); else x = list_first_entry(&walk->walk.all, struct xfrm_policy_walk_entry, all); list_for_each_entry_from(x, &net->xfrm.policy_all, all) { if (x->dead) continue; pol = container_of(x, struct xfrm_policy, walk); if (walk->type != XFRM_POLICY_TYPE_ANY && walk->type != pol->type) continue; error = func(pol, xfrm_policy_id2dir(pol->index), walk->seq, data); if (error) { list_move_tail(&walk->walk.all, &x->all); goto out; } walk->seq++; } if (walk->seq == 0) { error = -ENOENT; goto out; } list_del_init(&walk->walk.all); out: spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return error; } EXPORT_SYMBOL(xfrm_policy_walk); void xfrm_policy_walk_init(struct xfrm_policy_walk *walk, u8 type) { INIT_LIST_HEAD(&walk->walk.all); walk->walk.dead = 1; walk->type = type; walk->seq = 0; } EXPORT_SYMBOL(xfrm_policy_walk_init); void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net) { if (list_empty(&walk->walk.all)) return; spin_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME where is net? */ list_del(&walk->walk.all); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); } EXPORT_SYMBOL(xfrm_policy_walk_done); /* * Find policy to apply to this flow. * * Returns 0 if policy found, else an -errno. */ static int xfrm_policy_match(const struct xfrm_policy *pol, const struct flowi *fl, u8 type, u16 family, u32 if_id) { const struct xfrm_selector *sel = &pol->selector; int ret = -ESRCH; bool match; if (pol->family != family || pol->if_id != if_id || (fl->flowi_mark & pol->mark.m) != pol->mark.v || pol->type != type) return ret; match = xfrm_selector_match(sel, fl, family); if (match) ret = security_xfrm_policy_lookup(pol->security, fl->flowi_secid); return ret; } static struct xfrm_pol_inexact_node * xfrm_policy_lookup_inexact_addr(const struct rb_root *r, seqcount_spinlock_t *count, const xfrm_address_t *addr, u16 family) { const struct rb_node *parent; int seq; again: seq = read_seqcount_begin(count); parent = rcu_dereference_raw(r->rb_node); while (parent) { struct xfrm_pol_inexact_node *node; int delta; node = rb_entry(parent, struct xfrm_pol_inexact_node, node); delta = xfrm_policy_addr_delta(addr, &node->addr, node->prefixlen, family); if (delta < 0) { parent = rcu_dereference_raw(parent->rb_left); continue; } else if (delta > 0) { parent = rcu_dereference_raw(parent->rb_right); continue; } return node; } if (read_seqcount_retry(count, seq)) goto again; return NULL; } static bool xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand, struct xfrm_pol_inexact_bin *b, const xfrm_address_t *saddr, const xfrm_address_t *daddr) { struct xfrm_pol_inexact_node *n; u16 family; if (!b) return false; family = b->k.family; memset(cand, 0, sizeof(*cand)); cand->res[XFRM_POL_CAND_ANY] = &b->hhead; n = xfrm_policy_lookup_inexact_addr(&b->root_d, &b->count, daddr, family); if (n) { cand->res[XFRM_POL_CAND_DADDR] = &n->hhead; n = xfrm_policy_lookup_inexact_addr(&n->root, &b->count, saddr, family); if (n) cand->res[XFRM_POL_CAND_BOTH] = &n->hhead; } n = xfrm_policy_lookup_inexact_addr(&b->root_s, &b->count, saddr, family); if (n) cand->res[XFRM_POL_CAND_SADDR] = &n->hhead; return true; } static struct xfrm_pol_inexact_bin * xfrm_policy_inexact_lookup_rcu(struct net *net, u8 type, u16 family, u8 dir, u32 if_id) { struct xfrm_pol_inexact_key k = { .family = family, .type = type, .dir = dir, .if_id = if_id, }; write_pnet(&k.net, net); return rhashtable_lookup(&xfrm_policy_inexact_table, &k, xfrm_pol_inexact_params); } static struct xfrm_pol_inexact_bin * xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family, u8 dir, u32 if_id) { struct xfrm_pol_inexact_bin *bin; lockdep_assert_held(&net->xfrm.xfrm_policy_lock); rcu_read_lock(); bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id); rcu_read_unlock(); return bin; } static struct xfrm_policy * __xfrm_policy_eval_candidates(struct hlist_head *chain, struct xfrm_policy *prefer, const struct flowi *fl, u8 type, u16 family, u32 if_id) { u32 priority = prefer ? prefer->priority : ~0u; struct xfrm_policy *pol; if (!chain) return NULL; hlist_for_each_entry_rcu(pol, chain, bydst) { int err; if (pol->priority > priority) break; err = xfrm_policy_match(pol, fl, type, family, if_id); if (err) { if (err != -ESRCH) return ERR_PTR(err); continue; } if (prefer) { /* matches. Is it older than *prefer? */ if (pol->priority == priority && prefer->pos < pol->pos) return prefer; } return pol; } return NULL; } static struct xfrm_policy * xfrm_policy_eval_candidates(struct xfrm_pol_inexact_candidates *cand, struct xfrm_policy *prefer, const struct flowi *fl, u8 type, u16 family, u32 if_id) { struct xfrm_policy *tmp; int i; for (i = 0; i < ARRAY_SIZE(cand->res); i++) { tmp = __xfrm_policy_eval_candidates(cand->res[i], prefer, fl, type, family, if_id); if (!tmp) continue; if (IS_ERR(tmp)) return tmp; prefer = tmp; } return prefer; } static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, const struct flowi *fl, u16 family, u8 dir, u32 if_id) { struct xfrm_pol_inexact_candidates cand; const xfrm_address_t *daddr, *saddr; struct xfrm_pol_inexact_bin *bin; struct xfrm_policy *pol, *ret; struct hlist_head *chain; unsigned int sequence; int err; daddr = xfrm_flowi_daddr(fl, family); saddr = xfrm_flowi_saddr(fl, family); if (unlikely(!daddr || !saddr)) return NULL; rcu_read_lock(); retry: do { sequence = read_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); chain = policy_hash_direct(net, daddr, saddr, family, dir); } while (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence)); ret = NULL; hlist_for_each_entry_rcu(pol, chain, bydst) { err = xfrm_policy_match(pol, fl, type, family, if_id); if (err) { if (err == -ESRCH) continue; else { ret = ERR_PTR(err); goto fail; } } else { ret = pol; break; } } bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id); if (!bin || !xfrm_policy_find_inexact_candidates(&cand, bin, saddr, daddr)) goto skip_inexact; pol = xfrm_policy_eval_candidates(&cand, ret, fl, type, family, if_id); if (pol) { ret = pol; if (IS_ERR(pol)) goto fail; } skip_inexact: if (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence)) goto retry; if (ret && !xfrm_pol_hold_rcu(ret)) goto retry; fail: rcu_read_unlock(); return ret; } static struct xfrm_policy *xfrm_policy_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, u32 if_id) { #ifdef CONFIG_XFRM_SUB_POLICY struct xfrm_policy *pol; pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family, dir, if_id); if (pol != NULL) return pol; #endif return xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, dir, if_id); } static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, const struct flowi *fl, u16 family, u32 if_id) { struct xfrm_policy *pol; rcu_read_lock(); again: pol = rcu_dereference(sk->sk_policy[dir]); if (pol != NULL) { bool match; int err = 0; if (pol->family != family) { pol = NULL; goto out; } match = xfrm_selector_match(&pol->selector, fl, family); if (match) { if ((READ_ONCE(sk->sk_mark) & pol->mark.m) != pol->mark.v || pol->if_id != if_id) { pol = NULL; goto out; } err = security_xfrm_policy_lookup(pol->security, fl->flowi_secid); if (!err) { if (!xfrm_pol_hold_rcu(pol)) goto again; } else if (err == -ESRCH) { pol = NULL; } else { pol = ERR_PTR(err); } } else pol = NULL; } out: rcu_read_unlock(); return pol; } static void __xfrm_policy_link(struct xfrm_policy *pol, int dir) { struct net *net = xp_net(pol); list_add(&pol->walk.all, &net->xfrm.policy_all); net->xfrm.policy_count[dir]++; xfrm_pol_hold(pol); } static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, int dir) { struct net *net = xp_net(pol); if (list_empty(&pol->walk.all)) return NULL; /* Socket policies are not hashed. */ if (!hlist_unhashed(&pol->bydst)) { hlist_del_rcu(&pol->bydst); hlist_del_init(&pol->bydst_inexact_list); hlist_del(&pol->byidx); } list_del_init(&pol->walk.all); net->xfrm.policy_count[dir]--; return pol; } static void xfrm_sk_policy_link(struct xfrm_policy *pol, int dir) { __xfrm_policy_link(pol, XFRM_POLICY_MAX + dir); } static void xfrm_sk_policy_unlink(struct xfrm_policy *pol, int dir) { __xfrm_policy_unlink(pol, XFRM_POLICY_MAX + dir); } int xfrm_policy_delete(struct xfrm_policy *pol, int dir) { struct net *net = xp_net(pol); spin_lock_bh(&net->xfrm.xfrm_policy_lock); pol = __xfrm_policy_unlink(pol, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (pol) { xfrm_policy_kill(pol); return 0; } return -ENOENT; } EXPORT_SYMBOL(xfrm_policy_delete); int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) { struct net *net = sock_net(sk); struct xfrm_policy *old_pol; #ifdef CONFIG_XFRM_SUB_POLICY if (pol && pol->type != XFRM_POLICY_TYPE_MAIN) return -EINVAL; #endif spin_lock_bh(&net->xfrm.xfrm_policy_lock); old_pol = rcu_dereference_protected(sk->sk_policy[dir], lockdep_is_held(&net->xfrm.xfrm_policy_lock)); if (pol) { pol->curlft.add_time = ktime_get_real_seconds(); pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir, 0); xfrm_sk_policy_link(pol, dir); } rcu_assign_pointer(sk->sk_policy[dir], pol); if (old_pol) { if (pol) xfrm_policy_requeue(old_pol, pol); /* Unlinking succeeds always. This is the only function * allowed to delete or replace socket policy. */ xfrm_sk_policy_unlink(old_pol, dir); } spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (old_pol) { xfrm_policy_kill(old_pol); } return 0; } static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir) { struct xfrm_policy *newp = xfrm_policy_alloc(xp_net(old), GFP_ATOMIC); struct net *net = xp_net(old); if (newp) { newp->selector = old->selector; if (security_xfrm_policy_clone(old->security, &newp->security)) { kfree(newp); return NULL; /* ENOMEM */ } newp->lft = old->lft; newp->curlft = old->curlft; newp->mark = old->mark; newp->if_id = old->if_id; newp->action = old->action; newp->flags = old->flags; newp->xfrm_nr = old->xfrm_nr; newp->index = old->index; newp->type = old->type; newp->family = old->family; memcpy(newp->xfrm_vec, old->xfrm_vec, newp->xfrm_nr*sizeof(struct xfrm_tmpl)); spin_lock_bh(&net->xfrm.xfrm_policy_lock); xfrm_sk_policy_link(newp, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); xfrm_pol_put(newp); } return newp; } int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { const struct xfrm_policy *p; struct xfrm_policy *np; int i, ret = 0; rcu_read_lock(); for (i = 0; i < 2; i++) { p = rcu_dereference(osk->sk_policy[i]); if (p) { np = clone_policy(p, i); if (unlikely(!np)) { ret = -ENOMEM; break; } rcu_assign_pointer(sk->sk_policy[i], np); } } rcu_read_unlock(); return ret; } static int xfrm_get_saddr(unsigned short family, xfrm_address_t *saddr, const struct xfrm_dst_lookup_params *params) { int err; const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); if (unlikely(afinfo == NULL)) return -EINVAL; err = afinfo->get_saddr(saddr, params); rcu_read_unlock(); return err; } /* Resolve list of templates for the flow, given policy. */ static int xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, struct xfrm_state **xfrm, unsigned short family) { struct net *net = xp_net(policy); int nx; int i, error; xfrm_address_t *daddr = xfrm_flowi_daddr(fl, family); xfrm_address_t *saddr = xfrm_flowi_saddr(fl, family); xfrm_address_t tmp; for (nx = 0, i = 0; i < policy->xfrm_nr; i++) { struct xfrm_state *x; xfrm_address_t *remote = daddr; xfrm_address_t *local = saddr; struct xfrm_tmpl *tmpl = &policy->xfrm_vec[i]; if (tmpl->mode == XFRM_MODE_TUNNEL || tmpl->mode == XFRM_MODE_BEET) { remote = &tmpl->id.daddr; local = &tmpl->saddr; if (xfrm_addr_any(local, tmpl->encap_family)) { struct xfrm_dst_lookup_params params; memset(¶ms, 0, sizeof(params)); params.net = net; params.oif = fl->flowi_oif; params.daddr = remote; error = xfrm_get_saddr(tmpl->encap_family, &tmp, ¶ms); if (error) goto fail; local = &tmp; } } x = xfrm_state_find(remote, local, fl, tmpl, policy, &error, family, policy->if_id); if (x && x->km.state == XFRM_STATE_VALID) { xfrm[nx++] = x; daddr = remote; saddr = local; continue; } if (x) { error = (x->km.state == XFRM_STATE_ERROR ? -EINVAL : -EAGAIN); xfrm_state_put(x); } else if (error == -ESRCH) { error = -EAGAIN; } if (!tmpl->optional) goto fail; } return nx; fail: for (nx--; nx >= 0; nx--) xfrm_state_put(xfrm[nx]); return error; } static int xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, const struct flowi *fl, struct xfrm_state **xfrm, unsigned short family) { struct xfrm_state *tp[XFRM_MAX_DEPTH]; struct xfrm_state **tpp = (npols > 1) ? tp : xfrm; int cnx = 0; int error; int ret; int i; for (i = 0; i < npols; i++) { if (cnx + pols[i]->xfrm_nr >= XFRM_MAX_DEPTH) { error = -ENOBUFS; goto fail; } ret = xfrm_tmpl_resolve_one(pols[i], fl, &tpp[cnx], family); if (ret < 0) { error = ret; goto fail; } else cnx += ret; } /* found states are sorted for outbound processing */ if (npols > 1) xfrm_state_sort(xfrm, tpp, cnx, family); return cnx; fail: for (cnx--; cnx >= 0; cnx--) xfrm_state_put(tpp[cnx]); return error; } static int xfrm_get_tos(const struct flowi *fl, int family) { if (family == AF_INET) return IPTOS_RT_MASK & fl->u.ip4.flowi4_tos; return 0; } static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family) { const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); struct dst_ops *dst_ops; struct xfrm_dst *xdst; if (!afinfo) return ERR_PTR(-EINVAL); switch (family) { case AF_INET: dst_ops = &net->xfrm.xfrm4_dst_ops; break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: dst_ops = &net->xfrm.xfrm6_dst_ops; break; #endif default: BUG(); } xdst = dst_alloc(dst_ops, NULL, 1, DST_OBSOLETE_NONE, 0); if (likely(xdst)) { memset_after(xdst, 0, u.dst); } else xdst = ERR_PTR(-ENOBUFS); rcu_read_unlock(); return xdst; } static void xfrm_init_path(struct xfrm_dst *path, struct dst_entry *dst, int nfheader_len) { if (dst->ops->family == AF_INET6) { struct rt6_info *rt = (struct rt6_info *)dst; path->path_cookie = rt6_get_cookie(rt); path->u.rt6.rt6i_nfheader_len = nfheader_len; } } static inline int xfrm_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, const struct flowi *fl) { const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(xdst->u.dst.ops->family); int err; if (!afinfo) return -EINVAL; err = afinfo->fill_dst(xdst, dev, fl); rcu_read_unlock(); return err; } /* Allocate chain of dst_entry's, attach known xfrm's, calculate * all the metrics... Shortly, bundle a bundle. */ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, struct xfrm_dst **bundle, int nx, const struct flowi *fl, struct dst_entry *dst) { const struct xfrm_state_afinfo *afinfo; const struct xfrm_mode *inner_mode; struct net *net = xp_net(policy); unsigned long now = jiffies; struct net_device *dev; struct xfrm_dst *xdst_prev = NULL; struct xfrm_dst *xdst0 = NULL; int i = 0; int err; int header_len = 0; int nfheader_len = 0; int trailer_len = 0; int tos; int family = policy->selector.family; xfrm_address_t saddr, daddr; xfrm_flowi_addr_get(fl, &saddr, &daddr, family); tos = xfrm_get_tos(fl, family); dst_hold(dst); for (; i < nx; i++) { struct xfrm_dst *xdst = xfrm_alloc_dst(net, family); struct dst_entry *dst1 = &xdst->u.dst; err = PTR_ERR(xdst); if (IS_ERR(xdst)) { dst_release(dst); goto put_states; } bundle[i] = xdst; if (!xdst_prev) xdst0 = xdst; else /* Ref count is taken during xfrm_alloc_dst() * No need to do dst_clone() on dst1 */ xfrm_dst_set_child(xdst_prev, &xdst->u.dst); if (xfrm[i]->sel.family == AF_UNSPEC) { inner_mode = xfrm_ip2inner_mode(xfrm[i], xfrm_af2proto(family)); if (!inner_mode) { err = -EAFNOSUPPORT; dst_release(dst); goto put_states; } } else inner_mode = &xfrm[i]->inner_mode; xdst->route = dst; dst_copy_metrics(dst1, dst); if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { __u32 mark = 0; int oif; if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m) mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]); family = xfrm[i]->props.family; oif = fl->flowi_oif ? : fl->flowi_l3mdev; dst = xfrm_dst_lookup(xfrm[i], tos, oif, &saddr, &daddr, family, mark); err = PTR_ERR(dst); if (IS_ERR(dst)) goto put_states; } else dst_hold(dst); dst1->xfrm = xfrm[i]; xdst->xfrm_genid = xfrm[i]->genid; dst1->obsolete = DST_OBSOLETE_FORCE_CHK; dst1->lastuse = now; dst1->input = dst_discard; rcu_read_lock(); afinfo = xfrm_state_afinfo_get_rcu(inner_mode->family); if (likely(afinfo)) dst1->output = afinfo->output; else dst1->output = dst_discard_out; rcu_read_unlock(); xdst_prev = xdst; header_len += xfrm[i]->props.header_len; if (xfrm[i]->type->flags & XFRM_TYPE_NON_FRAGMENT) nfheader_len += xfrm[i]->props.header_len; trailer_len += xfrm[i]->props.trailer_len; } xfrm_dst_set_child(xdst_prev, dst); xdst0->path = dst; err = -ENODEV; dev = dst->dev; if (!dev) goto free_dst; xfrm_init_path(xdst0, dst, nfheader_len); xfrm_init_pmtu(bundle, nx); for (xdst_prev = xdst0; xdst_prev != (struct xfrm_dst *)dst; xdst_prev = (struct xfrm_dst *) xfrm_dst_child(&xdst_prev->u.dst)) { err = xfrm_fill_dst(xdst_prev, dev, fl); if (err) goto free_dst; xdst_prev->u.dst.header_len = header_len; xdst_prev->u.dst.trailer_len = trailer_len; header_len -= xdst_prev->u.dst.xfrm->props.header_len; trailer_len -= xdst_prev->u.dst.xfrm->props.trailer_len; } return &xdst0->u.dst; put_states: for (; i < nx; i++) xfrm_state_put(xfrm[i]); free_dst: if (xdst0) dst_release_immediate(&xdst0->u.dst); return ERR_PTR(err); } static int xfrm_expand_policies(const struct flowi *fl, u16 family, struct xfrm_policy **pols, int *num_pols, int *num_xfrms) { int i; if (*num_pols == 0 || !pols[0]) { *num_pols = 0; *num_xfrms = 0; return 0; } if (IS_ERR(pols[0])) { *num_pols = 0; return PTR_ERR(pols[0]); } *num_xfrms = pols[0]->xfrm_nr; #ifdef CONFIG_XFRM_SUB_POLICY if (pols[0]->action == XFRM_POLICY_ALLOW && pols[0]->type != XFRM_POLICY_TYPE_MAIN) { pols[1] = xfrm_policy_lookup_bytype(xp_net(pols[0]), XFRM_POLICY_TYPE_MAIN, fl, family, XFRM_POLICY_OUT, pols[0]->if_id); if (pols[1]) { if (IS_ERR(pols[1])) { xfrm_pols_put(pols, *num_pols); *num_pols = 0; return PTR_ERR(pols[1]); } (*num_pols)++; (*num_xfrms) += pols[1]->xfrm_nr; } } #endif for (i = 0; i < *num_pols; i++) { if (pols[i]->action != XFRM_POLICY_ALLOW) { *num_xfrms = -1; break; } } return 0; } static struct xfrm_dst * xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, const struct flowi *fl, u16 family, struct dst_entry *dst_orig) { struct net *net = xp_net(pols[0]); struct xfrm_state *xfrm[XFRM_MAX_DEPTH]; struct xfrm_dst *bundle[XFRM_MAX_DEPTH]; struct xfrm_dst *xdst; struct dst_entry *dst; int err; /* Try to instantiate a bundle */ err = xfrm_tmpl_resolve(pols, num_pols, fl, xfrm, family); if (err <= 0) { if (err == 0) return NULL; if (err != -EAGAIN) XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR); return ERR_PTR(err); } dst = xfrm_bundle_create(pols[0], xfrm, bundle, err, fl, dst_orig); if (IS_ERR(dst)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLEGENERROR); return ERR_CAST(dst); } xdst = (struct xfrm_dst *)dst; xdst->num_xfrms = err; xdst->num_pols = num_pols; memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols); xdst->policy_genid = atomic_read(&pols[0]->genid); return xdst; } static void xfrm_policy_queue_process(struct timer_list *t) { struct sk_buff *skb; struct sock *sk; struct dst_entry *dst; struct xfrm_policy *pol = from_timer(pol, t, polq.hold_timer); struct net *net = xp_net(pol); struct xfrm_policy_queue *pq = &pol->polq; struct flowi fl; struct sk_buff_head list; __u32 skb_mark; spin_lock(&pq->hold_queue.lock); skb = skb_peek(&pq->hold_queue); if (!skb) { spin_unlock(&pq->hold_queue.lock); goto out; } dst = skb_dst(skb); sk = skb->sk; /* Fixup the mark to support VTI. */ skb_mark = skb->mark; skb->mark = pol->mark.v; xfrm_decode_session(skb, &fl, dst->ops->family); skb->mark = skb_mark; spin_unlock(&pq->hold_queue.lock); dst_hold(xfrm_dst_path(dst)); dst = xfrm_lookup(net, xfrm_dst_path(dst), &fl, sk, XFRM_LOOKUP_QUEUE); if (IS_ERR(dst)) goto purge_queue; if (dst->flags & DST_XFRM_QUEUE) { dst_release(dst); if (pq->timeout >= XFRM_QUEUE_TMO_MAX) goto purge_queue; pq->timeout = pq->timeout << 1; if (!mod_timer(&pq->hold_timer, jiffies + pq->timeout)) xfrm_pol_hold(pol); goto out; } dst_release(dst); __skb_queue_head_init(&list); spin_lock(&pq->hold_queue.lock); pq->timeout = 0; skb_queue_splice_init(&pq->hold_queue, &list); spin_unlock(&pq->hold_queue.lock); while (!skb_queue_empty(&list)) { skb = __skb_dequeue(&list); /* Fixup the mark to support VTI. */ skb_mark = skb->mark; skb->mark = pol->mark.v; xfrm_decode_session(skb, &fl, skb_dst(skb)->ops->family); skb->mark = skb_mark; dst_hold(xfrm_dst_path(skb_dst(skb))); dst = xfrm_lookup(net, xfrm_dst_path(skb_dst(skb)), &fl, skb->sk, 0); if (IS_ERR(dst)) { kfree_skb(skb); continue; } nf_reset_ct(skb); skb_dst_drop(skb); skb_dst_set(skb, dst); dst_output(net, skb->sk, skb); } out: xfrm_pol_put(pol); return; purge_queue: pq->timeout = 0; skb_queue_purge(&pq->hold_queue); xfrm_pol_put(pol); } static int xdst_queue_output(struct net *net, struct sock *sk, struct sk_buff *skb) { unsigned long sched_next; struct dst_entry *dst = skb_dst(skb); struct xfrm_dst *xdst = (struct xfrm_dst *) dst; struct xfrm_policy *pol = xdst->pols[0]; struct xfrm_policy_queue *pq = &pol->polq; if (unlikely(skb_fclone_busy(sk, skb))) { kfree_skb(skb); return 0; } if (pq->hold_queue.qlen > XFRM_MAX_QUEUE_LEN) { kfree_skb(skb); return -EAGAIN; } skb_dst_force(skb); spin_lock_bh(&pq->hold_queue.lock); if (!pq->timeout) pq->timeout = XFRM_QUEUE_TMO_MIN; sched_next = jiffies + pq->timeout; if (del_timer(&pq->hold_timer)) { if (time_before(pq->hold_timer.expires, sched_next)) sched_next = pq->hold_timer.expires; xfrm_pol_put(pol); } __skb_queue_tail(&pq->hold_queue, skb); if (!mod_timer(&pq->hold_timer, sched_next)) xfrm_pol_hold(pol); spin_unlock_bh(&pq->hold_queue.lock); return 0; } static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net, struct xfrm_flo *xflo, const struct flowi *fl, int num_xfrms, u16 family) { int err; struct net_device *dev; struct dst_entry *dst; struct dst_entry *dst1; struct xfrm_dst *xdst; xdst = xfrm_alloc_dst(net, family); if (IS_ERR(xdst)) return xdst; if (!(xflo->flags & XFRM_LOOKUP_QUEUE) || net->xfrm.sysctl_larval_drop || num_xfrms <= 0) return xdst; dst = xflo->dst_orig; dst1 = &xdst->u.dst; dst_hold(dst); xdst->route = dst; dst_copy_metrics(dst1, dst); dst1->obsolete = DST_OBSOLETE_FORCE_CHK; dst1->flags |= DST_XFRM_QUEUE; dst1->lastuse = jiffies; dst1->input = dst_discard; dst1->output = xdst_queue_output; dst_hold(dst); xfrm_dst_set_child(xdst, dst); xdst->path = dst; xfrm_init_path((struct xfrm_dst *)dst1, dst, 0); err = -ENODEV; dev = dst->dev; if (!dev) goto free_dst; err = xfrm_fill_dst(xdst, dev, fl); if (err) goto free_dst; out: return xdst; free_dst: dst_release(dst1); xdst = ERR_PTR(err); goto out; } static struct xfrm_dst *xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, struct xfrm_flo *xflo, u32 if_id) { struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; int num_pols = 0, num_xfrms = 0, err; struct xfrm_dst *xdst; /* Resolve policies to use if we couldn't get them from * previous cache entry */ num_pols = 1; pols[0] = xfrm_policy_lookup(net, fl, family, dir, if_id); err = xfrm_expand_policies(fl, family, pols, &num_pols, &num_xfrms); if (err < 0) goto inc_error; if (num_pols == 0) return NULL; if (num_xfrms <= 0) goto make_dummy_bundle; xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family, xflo->dst_orig); if (IS_ERR(xdst)) { err = PTR_ERR(xdst); if (err == -EREMOTE) { xfrm_pols_put(pols, num_pols); return NULL; } if (err != -EAGAIN) goto error; goto make_dummy_bundle; } else if (xdst == NULL) { num_xfrms = 0; goto make_dummy_bundle; } return xdst; make_dummy_bundle: /* We found policies, but there's no bundles to instantiate: * either because the policy blocks, has no transformations or * we could not build template (no xfrm_states).*/ xdst = xfrm_create_dummy_bundle(net, xflo, fl, num_xfrms, family); if (IS_ERR(xdst)) { xfrm_pols_put(pols, num_pols); return ERR_CAST(xdst); } xdst->num_pols = num_pols; xdst->num_xfrms = num_xfrms; memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols); return xdst; inc_error: XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR); error: xfrm_pols_put(pols, num_pols); return ERR_PTR(err); } static struct dst_entry *make_blackhole(struct net *net, u16 family, struct dst_entry *dst_orig) { const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); struct dst_entry *ret; if (!afinfo) { dst_release(dst_orig); return ERR_PTR(-EINVAL); } else { ret = afinfo->blackhole_route(net, dst_orig); } rcu_read_unlock(); return ret; } /* Finds/creates a bundle for given flow and if_id * * At the moment we eat a raw IP route. Mostly to speed up lookups * on interfaces with disabled IPsec. * * xfrm_lookup uses an if_id of 0 by default, and is provided for * compatibility */ struct dst_entry *xfrm_lookup_with_ifid(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags, u32 if_id) { struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; struct xfrm_dst *xdst; struct dst_entry *dst, *route; u16 family = dst_orig->ops->family; u8 dir = XFRM_POLICY_OUT; int i, err, num_pols, num_xfrms = 0, drop_pols = 0; dst = NULL; xdst = NULL; route = NULL; sk = sk_const_to_full_sk(sk); if (sk && sk->sk_policy[XFRM_POLICY_OUT]) { num_pols = 1; pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family, if_id); err = xfrm_expand_policies(fl, family, pols, &num_pols, &num_xfrms); if (err < 0) goto dropdst; if (num_pols) { if (num_xfrms <= 0) { drop_pols = num_pols; goto no_transform; } xdst = xfrm_resolve_and_create_bundle( pols, num_pols, fl, family, dst_orig); if (IS_ERR(xdst)) { xfrm_pols_put(pols, num_pols); err = PTR_ERR(xdst); if (err == -EREMOTE) goto nopol; goto dropdst; } else if (xdst == NULL) { num_xfrms = 0; drop_pols = num_pols; goto no_transform; } route = xdst->route; } } if (xdst == NULL) { struct xfrm_flo xflo; xflo.dst_orig = dst_orig; xflo.flags = flags; /* To accelerate a bit... */ if (!if_id && ((dst_orig->flags & DST_NOXFRM) || !net->xfrm.policy_count[XFRM_POLICY_OUT])) goto nopol; xdst = xfrm_bundle_lookup(net, fl, family, dir, &xflo, if_id); if (xdst == NULL) goto nopol; if (IS_ERR(xdst)) { err = PTR_ERR(xdst); goto dropdst; } num_pols = xdst->num_pols; num_xfrms = xdst->num_xfrms; memcpy(pols, xdst->pols, sizeof(struct xfrm_policy *) * num_pols); route = xdst->route; } dst = &xdst->u.dst; if (route == NULL && num_xfrms > 0) { /* The only case when xfrm_bundle_lookup() returns a * bundle with null route, is when the template could * not be resolved. It means policies are there, but * bundle could not be created, since we don't yet * have the xfrm_state's. We need to wait for KM to * negotiate new SA's or bail out with error.*/ if (net->xfrm.sysctl_larval_drop) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); err = -EREMOTE; goto error; } err = -EAGAIN; XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); goto error; } no_transform: if (num_pols == 0) goto nopol; if ((flags & XFRM_LOOKUP_ICMP) && !(pols[0]->flags & XFRM_POLICY_ICMP)) { err = -ENOENT; goto error; } for (i = 0; i < num_pols; i++) WRITE_ONCE(pols[i]->curlft.use_time, ktime_get_real_seconds()); if (num_xfrms < 0) { /* Prohibit the flow */ XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLBLOCK); err = -EPERM; goto error; } else if (num_xfrms > 0) { /* Flow transformed */ dst_release(dst_orig); } else { /* Flow passes untransformed */ dst_release(dst); dst = dst_orig; } ok: xfrm_pols_put(pols, drop_pols); if (dst && dst->xfrm && dst->xfrm->props.mode == XFRM_MODE_TUNNEL) dst->flags |= DST_XFRM_TUNNEL; return dst; nopol: if ((!dst_orig->dev || !(dst_orig->dev->flags & IFF_LOOPBACK)) && net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK) { err = -EPERM; goto error; } if (!(flags & XFRM_LOOKUP_ICMP)) { dst = dst_orig; goto ok; } err = -ENOENT; error: dst_release(dst); dropdst: if (!(flags & XFRM_LOOKUP_KEEP_DST_REF)) dst_release(dst_orig); xfrm_pols_put(pols, drop_pols); return ERR_PTR(err); } EXPORT_SYMBOL(xfrm_lookup_with_ifid); /* Main function: finds/creates a bundle for given flow. * * At the moment we eat a raw IP route. Mostly to speed up lookups * on interfaces with disabled IPsec. */ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags) { return xfrm_lookup_with_ifid(net, dst_orig, fl, sk, flags, 0); } EXPORT_SYMBOL(xfrm_lookup); /* Callers of xfrm_lookup_route() must ensure a call to dst_output(). * Otherwise we may send out blackholed packets. */ struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags) { struct dst_entry *dst = xfrm_lookup(net, dst_orig, fl, sk, flags | XFRM_LOOKUP_QUEUE | XFRM_LOOKUP_KEEP_DST_REF); if (PTR_ERR(dst) == -EREMOTE) return make_blackhole(net, dst_orig->ops->family, dst_orig); if (IS_ERR(dst)) dst_release(dst_orig); return dst; } EXPORT_SYMBOL(xfrm_lookup_route); static inline int xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl) { struct sec_path *sp = skb_sec_path(skb); struct xfrm_state *x; if (!sp || idx < 0 || idx >= sp->len) return 0; x = sp->xvec[idx]; if (!x->type->reject) return 0; return x->type->reject(x, skb, fl); } /* When skb is transformed back to its "native" form, we have to * check policy restrictions. At the moment we make this in maximally * stupid way. Shame on me. :-) Of course, connected sockets must * have policy cached at them. */ static inline int xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, unsigned short family, u32 if_id) { if (xfrm_state_kern(x)) return tmpl->optional && !xfrm_state_addr_cmp(tmpl, x, tmpl->encap_family); return x->id.proto == tmpl->id.proto && (x->id.spi == tmpl->id.spi || !tmpl->id.spi) && (x->props.reqid == tmpl->reqid || !tmpl->reqid) && x->props.mode == tmpl->mode && (tmpl->allalgs || (tmpl->aalgos & (1<<x->props.aalgo)) || !(xfrm_id_proto_match(tmpl->id.proto, IPSEC_PROTO_ANY))) && !(x->props.mode != XFRM_MODE_TRANSPORT && xfrm_state_addr_cmp(tmpl, x, family)) && (if_id == 0 || if_id == x->if_id); } /* * 0 or more than 0 is returned when validation is succeeded (either bypass * because of optional transport mode, or next index of the matched secpath * state with the template. * -1 is returned when no matching template is found. * Otherwise "-2 - errored_index" is returned. */ static inline int xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int start, unsigned short family, u32 if_id) { int idx = start; if (tmpl->optional) { if (tmpl->mode == XFRM_MODE_TRANSPORT) return start; } else start = -1; for (; idx < sp->len; idx++) { if (xfrm_state_ok(tmpl, sp->xvec[idx], family, if_id)) return ++idx; if (sp->xvec[idx]->props.mode != XFRM_MODE_TRANSPORT) { if (idx < sp->verified_cnt) { /* Secpath entry previously verified, consider optional and * continue searching */ continue; } if (start == -1) start = -2-idx; break; } } return start; } static void decode_session4(struct sk_buff *skb, struct flowi *fl, bool reverse) { const struct iphdr *iph = ip_hdr(skb); int ihl = iph->ihl; u8 *xprth = skb_network_header(skb) + ihl * 4; struct flowi4 *fl4 = &fl->u.ip4; int oif = 0; if (skb_dst(skb) && skb_dst(skb)->dev) oif = skb_dst(skb)->dev->ifindex; memset(fl4, 0, sizeof(struct flowi4)); fl4->flowi4_mark = skb->mark; fl4->flowi4_oif = reverse ? skb->skb_iif : oif; fl4->flowi4_proto = iph->protocol; fl4->daddr = reverse ? iph->saddr : iph->daddr; fl4->saddr = reverse ? iph->daddr : iph->saddr; fl4->flowi4_tos = iph->tos & ~INET_ECN_MASK; if (!ip_is_fragment(iph)) { switch (iph->protocol) { case IPPROTO_UDP: case IPPROTO_UDPLITE: case IPPROTO_TCP: case IPPROTO_SCTP: case IPPROTO_DCCP: if (xprth + 4 < skb->data || pskb_may_pull(skb, xprth + 4 - skb->data)) { __be16 *ports; xprth = skb_network_header(skb) + ihl * 4; ports = (__be16 *)xprth; fl4->fl4_sport = ports[!!reverse]; fl4->fl4_dport = ports[!reverse]; } break; case IPPROTO_ICMP: if (xprth + 2 < skb->data || pskb_may_pull(skb, xprth + 2 - skb->data)) { u8 *icmp; xprth = skb_network_header(skb) + ihl * 4; icmp = xprth; fl4->fl4_icmp_type = icmp[0]; fl4->fl4_icmp_code = icmp[1]; } break; case IPPROTO_GRE: if (xprth + 12 < skb->data || pskb_may_pull(skb, xprth + 12 - skb->data)) { __be16 *greflags; __be32 *gre_hdr; xprth = skb_network_header(skb) + ihl * 4; greflags = (__be16 *)xprth; gre_hdr = (__be32 *)xprth; if (greflags[0] & GRE_KEY) { if (greflags[0] & GRE_CSUM) gre_hdr++; fl4->fl4_gre_key = gre_hdr[1]; } } break; default: break; } } } #if IS_ENABLED(CONFIG_IPV6) static void decode_session6(struct sk_buff *skb, struct flowi *fl, bool reverse) { struct flowi6 *fl6 = &fl->u.ip6; int onlyproto = 0; const struct ipv6hdr *hdr = ipv6_hdr(skb); u32 offset = sizeof(*hdr); struct ipv6_opt_hdr *exthdr; const unsigned char *nh = skb_network_header(skb); u16 nhoff = IP6CB(skb)->nhoff; int oif = 0; u8 nexthdr; if (!nhoff) nhoff = offsetof(struct ipv6hdr, nexthdr); nexthdr = nh[nhoff]; if (skb_dst(skb) && skb_dst(skb)->dev) oif = skb_dst(skb)->dev->ifindex; memset(fl6, 0, sizeof(struct flowi6)); fl6->flowi6_mark = skb->mark; fl6->flowi6_oif = reverse ? skb->skb_iif : oif; fl6->daddr = reverse ? hdr->saddr : hdr->daddr; fl6->saddr = reverse ? hdr->daddr : hdr->saddr; while (nh + offset + sizeof(*exthdr) < skb->data || pskb_may_pull(skb, nh + offset + sizeof(*exthdr) - skb->data)) { nh = skb_network_header(skb); exthdr = (struct ipv6_opt_hdr *)(nh + offset); switch (nexthdr) { case NEXTHDR_FRAGMENT: onlyproto = 1; fallthrough; case NEXTHDR_ROUTING: case NEXTHDR_HOP: case NEXTHDR_DEST: offset += ipv6_optlen(exthdr); nexthdr = exthdr->nexthdr; break; case IPPROTO_UDP: case IPPROTO_UDPLITE: case IPPROTO_TCP: case IPPROTO_SCTP: case IPPROTO_DCCP: if (!onlyproto && (nh + offset + 4 < skb->data || pskb_may_pull(skb, nh + offset + 4 - skb->data))) { __be16 *ports; nh = skb_network_header(skb); ports = (__be16 *)(nh + offset); fl6->fl6_sport = ports[!!reverse]; fl6->fl6_dport = ports[!reverse]; } fl6->flowi6_proto = nexthdr; return; case IPPROTO_ICMPV6: if (!onlyproto && (nh + offset + 2 < skb->data || pskb_may_pull(skb, nh + offset + 2 - skb->data))) { u8 *icmp; nh = skb_network_header(skb); icmp = (u8 *)(nh + offset); fl6->fl6_icmp_type = icmp[0]; fl6->fl6_icmp_code = icmp[1]; } fl6->flowi6_proto = nexthdr; return; case IPPROTO_GRE: if (!onlyproto && (nh + offset + 12 < skb->data || pskb_may_pull(skb, nh + offset + 12 - skb->data))) { struct gre_base_hdr *gre_hdr; __be32 *gre_key; nh = skb_network_header(skb); gre_hdr = (struct gre_base_hdr *)(nh + offset); gre_key = (__be32 *)(gre_hdr + 1); if (gre_hdr->flags & GRE_KEY) { if (gre_hdr->flags & GRE_CSUM) gre_key++; fl6->fl6_gre_key = *gre_key; } } fl6->flowi6_proto = nexthdr; return; #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPPROTO_MH: offset += ipv6_optlen(exthdr); if (!onlyproto && (nh + offset + 3 < skb->data || pskb_may_pull(skb, nh + offset + 3 - skb->data))) { struct ip6_mh *mh; nh = skb_network_header(skb); mh = (struct ip6_mh *)(nh + offset); fl6->fl6_mh_type = mh->ip6mh_type; } fl6->flowi6_proto = nexthdr; return; #endif default: fl6->flowi6_proto = nexthdr; return; } } } #endif int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl, unsigned int family, int reverse) { switch (family) { case AF_INET: decode_session4(skb, fl, reverse); break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: decode_session6(skb, fl, reverse); break; #endif default: return -EAFNOSUPPORT; } return security_xfrm_decode_session(skb, &fl->flowi_secid); } EXPORT_SYMBOL(__xfrm_decode_session); static inline int secpath_has_nontransport(const struct sec_path *sp, int k, int *idxp) { for (; k < sp->len; k++) { if (sp->xvec[k]->props.mode != XFRM_MODE_TRANSPORT) { *idxp = k; return 1; } } return 0; } int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, unsigned short family) { struct net *net = dev_net(skb->dev); struct xfrm_policy *pol; struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; int npols = 0; int xfrm_nr; int pi; int reverse; struct flowi fl; int xerr_idx = -1; const struct xfrm_if_cb *ifcb; struct sec_path *sp; u32 if_id = 0; rcu_read_lock(); ifcb = xfrm_if_get_cb(); if (ifcb) { struct xfrm_if_decode_session_result r; if (ifcb->decode_session(skb, family, &r)) { if_id = r.if_id; net = r.net; } } rcu_read_unlock(); reverse = dir & ~XFRM_POLICY_MASK; dir &= XFRM_POLICY_MASK; if (__xfrm_decode_session(skb, &fl, family, reverse) < 0) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); return 0; } nf_nat_decode_session(skb, &fl, family); /* First, check used SA against their selectors. */ sp = skb_sec_path(skb); if (sp) { int i; for (i = sp->len - 1; i >= 0; i--) { struct xfrm_state *x = sp->xvec[i]; if (!xfrm_selector_match(&x->sel, &fl, family)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH); return 0; } } } pol = NULL; sk = sk_to_full_sk(sk); if (sk && sk->sk_policy[dir]) { pol = xfrm_sk_policy_lookup(sk, dir, &fl, family, if_id); if (IS_ERR(pol)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); return 0; } } if (!pol) pol = xfrm_policy_lookup(net, &fl, family, dir, if_id); if (IS_ERR(pol)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); return 0; } if (!pol) { if (net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS); return 0; } if (sp && secpath_has_nontransport(sp, 0, &xerr_idx)) { xfrm_secpath_reject(xerr_idx, skb, &fl); XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS); return 0; } return 1; } /* This lockless write can happen from different cpus. */ WRITE_ONCE(pol->curlft.use_time, ktime_get_real_seconds()); pols[0] = pol; npols++; #ifdef CONFIG_XFRM_SUB_POLICY if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) { pols[1] = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, &fl, family, XFRM_POLICY_IN, if_id); if (pols[1]) { if (IS_ERR(pols[1])) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); xfrm_pol_put(pols[0]); return 0; } /* This write can happen from different cpus. */ WRITE_ONCE(pols[1]->curlft.use_time, ktime_get_real_seconds()); npols++; } } #endif if (pol->action == XFRM_POLICY_ALLOW) { static struct sec_path dummy; struct xfrm_tmpl *tp[XFRM_MAX_DEPTH]; struct xfrm_tmpl *stp[XFRM_MAX_DEPTH]; struct xfrm_tmpl **tpp = tp; int ti = 0; int i, k; sp = skb_sec_path(skb); if (!sp) sp = &dummy; for (pi = 0; pi < npols; pi++) { if (pols[pi] != pol && pols[pi]->action != XFRM_POLICY_ALLOW) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLBLOCK); goto reject; } if (ti + pols[pi]->xfrm_nr >= XFRM_MAX_DEPTH) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); goto reject_error; } for (i = 0; i < pols[pi]->xfrm_nr; i++) tpp[ti++] = &pols[pi]->xfrm_vec[i]; } xfrm_nr = ti; if (npols > 1) { xfrm_tmpl_sort(stp, tpp, xfrm_nr, family); tpp = stp; } /* For each tunnel xfrm, find the first matching tmpl. * For each tmpl before that, find corresponding xfrm. * Order is _important_. Later we will implement * some barriers, but at the moment barriers * are implied between each two transformations. * Upon success, marks secpath entries as having been * verified to allow them to be skipped in future policy * checks (e.g. nested tunnels). */ for (i = xfrm_nr-1, k = 0; i >= 0; i--) { k = xfrm_policy_ok(tpp[i], sp, k, family, if_id); if (k < 0) { if (k < -1) /* "-2 - errored_index" returned */ xerr_idx = -(2+k); XFRM_INC_STATS(net, LINUX_MIB_XFRMINTMPLMISMATCH); goto reject; } } if (secpath_has_nontransport(sp, k, &xerr_idx)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINTMPLMISMATCH); goto reject; } xfrm_pols_put(pols, npols); sp->verified_cnt = k; return 1; } XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLBLOCK); reject: xfrm_secpath_reject(xerr_idx, skb, &fl); reject_error: xfrm_pols_put(pols, npols); return 0; } EXPORT_SYMBOL(__xfrm_policy_check); int __xfrm_route_forward(struct sk_buff *skb, unsigned short family) { struct net *net = dev_net(skb->dev); struct flowi fl; struct dst_entry *dst; int res = 1; if (xfrm_decode_session(skb, &fl, family) < 0) { XFRM_INC_STATS(net, LINUX_MIB_XFRMFWDHDRERROR); return 0; } skb_dst_force(skb); if (!skb_dst(skb)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMFWDHDRERROR); return 0; } dst = xfrm_lookup(net, skb_dst(skb), &fl, NULL, XFRM_LOOKUP_QUEUE); if (IS_ERR(dst)) { res = 0; dst = NULL; } skb_dst_set(skb, dst); return res; } EXPORT_SYMBOL(__xfrm_route_forward); /* Optimize later using cookies and generation ids. */ static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie) { /* Code (such as __xfrm4_bundle_create()) sets dst->obsolete * to DST_OBSOLETE_FORCE_CHK to force all XFRM destinations to * get validated by dst_ops->check on every use. We do this * because when a normal route referenced by an XFRM dst is * obsoleted we do not go looking around for all parent * referencing XFRM dsts so that we can invalidate them. It * is just too much work. Instead we make the checks here on * every use. For example: * * XFRM dst A --> IPv4 dst X * * X is the "xdst->route" of A (X is also the "dst->path" of A * in this example). If X is marked obsolete, "A" will not * notice. That's what we are validating here via the * stale_bundle() check. * * When a dst is removed from the fib tree, DST_OBSOLETE_DEAD will * be marked on it. * This will force stale_bundle() to fail on any xdst bundle with * this dst linked in it. */ if (dst->obsolete < 0 && !stale_bundle(dst)) return dst; return NULL; } static int stale_bundle(struct dst_entry *dst) { return !xfrm_bundle_ok((struct xfrm_dst *)dst); } void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev) { while ((dst = xfrm_dst_child(dst)) && dst->xfrm && dst->dev == dev) { dst->dev = blackhole_netdev; dev_hold(dst->dev); dev_put(dev); } } EXPORT_SYMBOL(xfrm_dst_ifdown); static void xfrm_link_failure(struct sk_buff *skb) { /* Impossible. Such dst must be popped before reaches point of failure. */ } static void xfrm_negative_advice(struct sock *sk, struct dst_entry *dst) { if (dst->obsolete) sk_dst_reset(sk); } static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr) { while (nr--) { struct xfrm_dst *xdst = bundle[nr]; u32 pmtu, route_mtu_cached; struct dst_entry *dst; dst = &xdst->u.dst; pmtu = dst_mtu(xfrm_dst_child(dst)); xdst->child_mtu_cached = pmtu; pmtu = xfrm_state_mtu(dst->xfrm, pmtu); route_mtu_cached = dst_mtu(xdst->route); xdst->route_mtu_cached = route_mtu_cached; if (pmtu > route_mtu_cached) pmtu = route_mtu_cached; dst_metric_set(dst, RTAX_MTU, pmtu); } } /* Check that the bundle accepts the flow and its components are * still valid. */ static int xfrm_bundle_ok(struct xfrm_dst *first) { struct xfrm_dst *bundle[XFRM_MAX_DEPTH]; struct dst_entry *dst = &first->u.dst; struct xfrm_dst *xdst; int start_from, nr; u32 mtu; if (!dst_check(xfrm_dst_path(dst), ((struct xfrm_dst *)dst)->path_cookie) || (dst->dev && !netif_running(dst->dev))) return 0; if (dst->flags & DST_XFRM_QUEUE) return 1; start_from = nr = 0; do { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; if (dst->xfrm->km.state != XFRM_STATE_VALID) return 0; if (xdst->xfrm_genid != dst->xfrm->genid) return 0; if (xdst->num_pols > 0 && xdst->policy_genid != atomic_read(&xdst->pols[0]->genid)) return 0; bundle[nr++] = xdst; mtu = dst_mtu(xfrm_dst_child(dst)); if (xdst->child_mtu_cached != mtu) { start_from = nr; xdst->child_mtu_cached = mtu; } if (!dst_check(xdst->route, xdst->route_cookie)) return 0; mtu = dst_mtu(xdst->route); if (xdst->route_mtu_cached != mtu) { start_from = nr; xdst->route_mtu_cached = mtu; } dst = xfrm_dst_child(dst); } while (dst->xfrm); if (likely(!start_from)) return 1; xdst = bundle[start_from - 1]; mtu = xdst->child_mtu_cached; while (start_from--) { dst = &xdst->u.dst; mtu = xfrm_state_mtu(dst->xfrm, mtu); if (mtu > xdst->route_mtu_cached) mtu = xdst->route_mtu_cached; dst_metric_set(dst, RTAX_MTU, mtu); if (!start_from) break; xdst = bundle[start_from - 1]; xdst->child_mtu_cached = mtu; } return 1; } static unsigned int xfrm_default_advmss(const struct dst_entry *dst) { return dst_metric_advmss(xfrm_dst_path(dst)); } static unsigned int xfrm_mtu(const struct dst_entry *dst) { unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); return mtu ? : dst_mtu(xfrm_dst_path(dst)); } static const void *xfrm_get_dst_nexthop(const struct dst_entry *dst, const void *daddr) { while (dst->xfrm) { const struct xfrm_state *xfrm = dst->xfrm; dst = xfrm_dst_child(dst); if (xfrm->props.mode == XFRM_MODE_TRANSPORT) continue; if (xfrm->type->flags & XFRM_TYPE_REMOTE_COADDR) daddr = xfrm->coaddr; else if (!(xfrm->type->flags & XFRM_TYPE_LOCAL_COADDR)) daddr = &xfrm->id.daddr; } return daddr; } static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr) { const struct dst_entry *path = xfrm_dst_path(dst); if (!skb) daddr = xfrm_get_dst_nexthop(dst, daddr); return path->ops->neigh_lookup(path, skb, daddr); } static void xfrm_confirm_neigh(const struct dst_entry *dst, const void *daddr) { const struct dst_entry *path = xfrm_dst_path(dst); daddr = xfrm_get_dst_nexthop(dst, daddr); path->ops->confirm_neigh(path, daddr); } int xfrm_policy_register_afinfo(const struct xfrm_policy_afinfo *afinfo, int family) { int err = 0; if (WARN_ON(family >= ARRAY_SIZE(xfrm_policy_afinfo))) return -EAFNOSUPPORT; spin_lock(&xfrm_policy_afinfo_lock); if (unlikely(xfrm_policy_afinfo[family] != NULL)) err = -EEXIST; else { struct dst_ops *dst_ops = afinfo->dst_ops; if (likely(dst_ops->kmem_cachep == NULL)) dst_ops->kmem_cachep = xfrm_dst_cache; if (likely(dst_ops->check == NULL)) dst_ops->check = xfrm_dst_check; if (likely(dst_ops->default_advmss == NULL)) dst_ops->default_advmss = xfrm_default_advmss; if (likely(dst_ops->mtu == NULL)) dst_ops->mtu = xfrm_mtu; if (likely(dst_ops->negative_advice == NULL)) dst_ops->negative_advice = (void *)xfrm_negative_advice; if (likely(dst_ops->link_failure == NULL)) dst_ops->link_failure = xfrm_link_failure; if (likely(dst_ops->neigh_lookup == NULL)) dst_ops->neigh_lookup = xfrm_neigh_lookup; if (likely(!dst_ops->confirm_neigh)) dst_ops->confirm_neigh = xfrm_confirm_neigh; rcu_assign_pointer(xfrm_policy_afinfo[family], afinfo); } spin_unlock(&xfrm_policy_afinfo_lock); return err; } EXPORT_SYMBOL(xfrm_policy_register_afinfo); void xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo *afinfo) { struct dst_ops *dst_ops = afinfo->dst_ops; int i; for (i = 0; i < ARRAY_SIZE(xfrm_policy_afinfo); i++) { if (xfrm_policy_afinfo[i] != afinfo) continue; RCU_INIT_POINTER(xfrm_policy_afinfo[i], NULL); break; } synchronize_rcu(); dst_ops->kmem_cachep = NULL; dst_ops->check = NULL; dst_ops->negative_advice = NULL; dst_ops->link_failure = NULL; } EXPORT_SYMBOL(xfrm_policy_unregister_afinfo); void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb) { spin_lock(&xfrm_if_cb_lock); rcu_assign_pointer(xfrm_if_cb, ifcb); spin_unlock(&xfrm_if_cb_lock); } EXPORT_SYMBOL(xfrm_if_register_cb); void xfrm_if_unregister_cb(void) { RCU_INIT_POINTER(xfrm_if_cb, NULL); synchronize_rcu(); } EXPORT_SYMBOL(xfrm_if_unregister_cb); #ifdef CONFIG_XFRM_STATISTICS static int __net_init xfrm_statistics_init(struct net *net) { int rv; net->mib.xfrm_statistics = alloc_percpu(struct linux_xfrm_mib); if (!net->mib.xfrm_statistics) return -ENOMEM; rv = xfrm_proc_init(net); if (rv < 0) free_percpu(net->mib.xfrm_statistics); return rv; } static void xfrm_statistics_fini(struct net *net) { xfrm_proc_fini(net); free_percpu(net->mib.xfrm_statistics); } #else static int __net_init xfrm_statistics_init(struct net *net) { return 0; } static void xfrm_statistics_fini(struct net *net) { } #endif static int __net_init xfrm_policy_init(struct net *net) { unsigned int hmask, sz; int dir, err; if (net_eq(net, &init_net)) { xfrm_dst_cache = kmem_cache_create("xfrm_dst_cache", sizeof(struct xfrm_dst), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); err = rhashtable_init(&xfrm_policy_inexact_table, &xfrm_pol_inexact_params); BUG_ON(err); } hmask = 8 - 1; sz = (hmask+1) * sizeof(struct hlist_head); net->xfrm.policy_byidx = xfrm_hash_alloc(sz); if (!net->xfrm.policy_byidx) goto out_byidx; net->xfrm.policy_idx_hmask = hmask; for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { struct xfrm_policy_hash *htab; net->xfrm.policy_count[dir] = 0; net->xfrm.policy_count[XFRM_POLICY_MAX + dir] = 0; INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]); htab = &net->xfrm.policy_bydst[dir]; htab->table = xfrm_hash_alloc(sz); if (!htab->table) goto out_bydst; htab->hmask = hmask; htab->dbits4 = 32; htab->sbits4 = 32; htab->dbits6 = 128; htab->sbits6 = 128; } net->xfrm.policy_hthresh.lbits4 = 32; net->xfrm.policy_hthresh.rbits4 = 32; net->xfrm.policy_hthresh.lbits6 = 128; net->xfrm.policy_hthresh.rbits6 = 128; seqlock_init(&net->xfrm.policy_hthresh.lock); INIT_LIST_HEAD(&net->xfrm.policy_all); INIT_LIST_HEAD(&net->xfrm.inexact_bins); INIT_WORK(&net->xfrm.policy_hash_work, xfrm_hash_resize); INIT_WORK(&net->xfrm.policy_hthresh.work, xfrm_hash_rebuild); return 0; out_bydst: for (dir--; dir >= 0; dir--) { struct xfrm_policy_hash *htab; htab = &net->xfrm.policy_bydst[dir]; xfrm_hash_free(htab->table, sz); } xfrm_hash_free(net->xfrm.policy_byidx, sz); out_byidx: return -ENOMEM; } static void xfrm_policy_fini(struct net *net) { struct xfrm_pol_inexact_bin *b, *t; unsigned int sz; int dir; flush_work(&net->xfrm.policy_hash_work); #ifdef CONFIG_XFRM_SUB_POLICY xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, false); #endif xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, false); WARN_ON(!list_empty(&net->xfrm.policy_all)); for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { struct xfrm_policy_hash *htab; WARN_ON(!hlist_empty(&net->xfrm.policy_inexact[dir])); htab = &net->xfrm.policy_bydst[dir]; sz = (htab->hmask + 1) * sizeof(struct hlist_head); WARN_ON(!hlist_empty(htab->table)); xfrm_hash_free(htab->table, sz); } sz = (net->xfrm.policy_idx_hmask + 1) * sizeof(struct hlist_head); WARN_ON(!hlist_empty(net->xfrm.policy_byidx)); xfrm_hash_free(net->xfrm.policy_byidx, sz); spin_lock_bh(&net->xfrm.xfrm_policy_lock); list_for_each_entry_safe(b, t, &net->xfrm.inexact_bins, inexact_bins) __xfrm_policy_inexact_prune_bin(b, true); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); } static int __net_init xfrm_net_init(struct net *net) { int rv; /* Initialize the per-net locks here */ spin_lock_init(&net->xfrm.xfrm_state_lock); spin_lock_init(&net->xfrm.xfrm_policy_lock); seqcount_spinlock_init(&net->xfrm.xfrm_policy_hash_generation, &net->xfrm.xfrm_policy_lock); mutex_init(&net->xfrm.xfrm_cfg_mutex); net->xfrm.policy_default[XFRM_POLICY_IN] = XFRM_USERPOLICY_ACCEPT; net->xfrm.policy_default[XFRM_POLICY_FWD] = XFRM_USERPOLICY_ACCEPT; net->xfrm.policy_default[XFRM_POLICY_OUT] = XFRM_USERPOLICY_ACCEPT; rv = xfrm_statistics_init(net); if (rv < 0) goto out_statistics; rv = xfrm_state_init(net); if (rv < 0) goto out_state; rv = xfrm_policy_init(net); if (rv < 0) goto out_policy; rv = xfrm_sysctl_init(net); if (rv < 0) goto out_sysctl; return 0; out_sysctl: xfrm_policy_fini(net); out_policy: xfrm_state_fini(net); out_state: xfrm_statistics_fini(net); out_statistics: return rv; } static void __net_exit xfrm_net_exit(struct net *net) { xfrm_sysctl_fini(net); xfrm_policy_fini(net); xfrm_state_fini(net); xfrm_statistics_fini(net); } static struct pernet_operations __net_initdata xfrm_net_ops = { .init = xfrm_net_init, .exit = xfrm_net_exit, }; void __init xfrm_init(void) { register_pernet_subsys(&xfrm_net_ops); xfrm_dev_init(); xfrm_input_init(); #ifdef CONFIG_XFRM_ESPINTCP espintcp_init(); #endif } #ifdef CONFIG_AUDITSYSCALL static void xfrm_audit_common_policyinfo(struct xfrm_policy *xp, struct audit_buffer *audit_buf) { struct xfrm_sec_ctx *ctx = xp->security; struct xfrm_selector *sel = &xp->selector; if (ctx) audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s", ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str); switch (sel->family) { case AF_INET: audit_log_format(audit_buf, " src=%pI4", &sel->saddr.a4); if (sel->prefixlen_s != 32) audit_log_format(audit_buf, " src_prefixlen=%d", sel->prefixlen_s); audit_log_format(audit_buf, " dst=%pI4", &sel->daddr.a4); if (sel->prefixlen_d != 32) audit_log_format(audit_buf, " dst_prefixlen=%d", sel->prefixlen_d); break; case AF_INET6: audit_log_format(audit_buf, " src=%pI6", sel->saddr.a6); if (sel->prefixlen_s != 128) audit_log_format(audit_buf, " src_prefixlen=%d", sel->prefixlen_s); audit_log_format(audit_buf, " dst=%pI6", sel->daddr.a6); if (sel->prefixlen_d != 128) audit_log_format(audit_buf, " dst_prefixlen=%d", sel->prefixlen_d); break; } } void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, bool task_valid) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SPD-add"); if (audit_buf == NULL) return; xfrm_audit_helper_usrinfo(task_valid, audit_buf); audit_log_format(audit_buf, " res=%u", result); xfrm_audit_common_policyinfo(xp, audit_buf); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_policy_add); void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result, bool task_valid) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SPD-delete"); if (audit_buf == NULL) return; xfrm_audit_helper_usrinfo(task_valid, audit_buf); audit_log_format(audit_buf, " res=%u", result); xfrm_audit_common_policyinfo(xp, audit_buf); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_policy_delete); #endif #ifdef CONFIG_XFRM_MIGRATE static bool xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp, const struct xfrm_selector *sel_tgt) { if (sel_cmp->proto == IPSEC_ULPROTO_ANY) { if (sel_tgt->family == sel_cmp->family && xfrm_addr_equal(&sel_tgt->daddr, &sel_cmp->daddr, sel_cmp->family) && xfrm_addr_equal(&sel_tgt->saddr, &sel_cmp->saddr, sel_cmp->family) && sel_tgt->prefixlen_d == sel_cmp->prefixlen_d && sel_tgt->prefixlen_s == sel_cmp->prefixlen_s) { return true; } } else { if (memcmp(sel_tgt, sel_cmp, sizeof(*sel_tgt)) == 0) { return true; } } return false; } static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *sel, u8 dir, u8 type, struct net *net, u32 if_id) { struct xfrm_policy *pol, *ret = NULL; struct hlist_head *chain; u32 priority = ~0U; spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_direct(net, &sel->daddr, &sel->saddr, sel->family, dir); hlist_for_each_entry(pol, chain, bydst) { if ((if_id == 0 || pol->if_id == if_id) && xfrm_migrate_selector_match(sel, &pol->selector) && pol->type == type) { ret = pol; priority = ret->priority; break; } } chain = &net->xfrm.policy_inexact[dir]; hlist_for_each_entry(pol, chain, bydst_inexact_list) { if ((pol->priority >= priority) && ret) break; if ((if_id == 0 || pol->if_id == if_id) && xfrm_migrate_selector_match(sel, &pol->selector) && pol->type == type) { ret = pol; break; } } xfrm_pol_hold(ret); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return ret; } static int migrate_tmpl_match(const struct xfrm_migrate *m, const struct xfrm_tmpl *t) { int match = 0; if (t->mode == m->mode && t->id.proto == m->proto && (m->reqid == 0 || t->reqid == m->reqid)) { switch (t->mode) { case XFRM_MODE_TUNNEL: case XFRM_MODE_BEET: if (xfrm_addr_equal(&t->id.daddr, &m->old_daddr, m->old_family) && xfrm_addr_equal(&t->saddr, &m->old_saddr, m->old_family)) { match = 1; } break; case XFRM_MODE_TRANSPORT: /* in case of transport mode, template does not store any IP addresses, hence we just compare mode and protocol */ match = 1; break; default: break; } } return match; } /* update endpoint address(es) of template(s) */ static int xfrm_policy_migrate(struct xfrm_policy *pol, struct xfrm_migrate *m, int num_migrate) { struct xfrm_migrate *mp; int i, j, n = 0; write_lock_bh(&pol->lock); if (unlikely(pol->walk.dead)) { /* target policy has been deleted */ write_unlock_bh(&pol->lock); return -ENOENT; } for (i = 0; i < pol->xfrm_nr; i++) { for (j = 0, mp = m; j < num_migrate; j++, mp++) { if (!migrate_tmpl_match(mp, &pol->xfrm_vec[i])) continue; n++; if (pol->xfrm_vec[i].mode != XFRM_MODE_TUNNEL && pol->xfrm_vec[i].mode != XFRM_MODE_BEET) continue; /* update endpoints */ memcpy(&pol->xfrm_vec[i].id.daddr, &mp->new_daddr, sizeof(pol->xfrm_vec[i].id.daddr)); memcpy(&pol->xfrm_vec[i].saddr, &mp->new_saddr, sizeof(pol->xfrm_vec[i].saddr)); pol->xfrm_vec[i].encap_family = mp->new_family; /* flush bundles */ atomic_inc(&pol->genid); } } write_unlock_bh(&pol->lock); if (!n) return -ENODATA; return 0; } static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate) { int i, j; if (num_migrate < 1 || num_migrate > XFRM_MAX_DEPTH) return -EINVAL; for (i = 0; i < num_migrate; i++) { if (xfrm_addr_any(&m[i].new_daddr, m[i].new_family) || xfrm_addr_any(&m[i].new_saddr, m[i].new_family)) return -EINVAL; /* check if there is any duplicated entry */ for (j = i + 1; j < num_migrate; j++) { if (!memcmp(&m[i].old_daddr, &m[j].old_daddr, sizeof(m[i].old_daddr)) && !memcmp(&m[i].old_saddr, &m[j].old_saddr, sizeof(m[i].old_saddr)) && m[i].proto == m[j].proto && m[i].mode == m[j].mode && m[i].reqid == m[j].reqid && m[i].old_family == m[j].old_family) return -EINVAL; } } return 0; } int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_migrate, struct xfrm_kmaddress *k, struct net *net, struct xfrm_encap_tmpl *encap, u32 if_id) { int i, err, nx_cur = 0, nx_new = 0; struct xfrm_policy *pol = NULL; struct xfrm_state *x, *xc; struct xfrm_state *x_cur[XFRM_MAX_DEPTH]; struct xfrm_state *x_new[XFRM_MAX_DEPTH]; struct xfrm_migrate *mp; /* Stage 0 - sanity checks */ if ((err = xfrm_migrate_check(m, num_migrate)) < 0) goto out; if (dir >= XFRM_POLICY_MAX) { err = -EINVAL; goto out; } /* Stage 1 - find policy */ if ((pol = xfrm_migrate_policy_find(sel, dir, type, net, if_id)) == NULL) { err = -ENOENT; goto out; } /* Stage 2 - find and update state(s) */ for (i = 0, mp = m; i < num_migrate; i++, mp++) { if ((x = xfrm_migrate_state_find(mp, net, if_id))) { x_cur[nx_cur] = x; nx_cur++; xc = xfrm_state_migrate(x, mp, encap); if (xc) { x_new[nx_new] = xc; nx_new++; } else { err = -ENODATA; goto restore_state; } } } /* Stage 3 - update policy */ if ((err = xfrm_policy_migrate(pol, m, num_migrate)) < 0) goto restore_state; /* Stage 4 - delete old state(s) */ if (nx_cur) { xfrm_states_put(x_cur, nx_cur); xfrm_states_delete(x_cur, nx_cur); } /* Stage 5 - announce */ km_migrate(sel, dir, type, m, num_migrate, k, encap); xfrm_pol_put(pol); return 0; out: return err; restore_state: if (pol) xfrm_pol_put(pol); if (nx_cur) xfrm_states_put(x_cur, nx_cur); if (nx_new) xfrm_states_delete(x_new, nx_new); return err; } EXPORT_SYMBOL(xfrm_migrate); #endif |
| 9191 9193 7 7 7 902 902 50 50 388 388 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 | // SPDX-License-Identifier: GPL-2.0 /* * Fast batching percpu counters. */ #include <linux/percpu_counter.h> #include <linux/mutex.h> #include <linux/init.h> #include <linux/cpu.h> #include <linux/module.h> #include <linux/debugobjects.h> #ifdef CONFIG_HOTPLUG_CPU static LIST_HEAD(percpu_counters); static DEFINE_SPINLOCK(percpu_counters_lock); #endif #ifdef CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER static const struct debug_obj_descr percpu_counter_debug_descr; static bool percpu_counter_fixup_free(void *addr, enum debug_obj_state state) { struct percpu_counter *fbc = addr; switch (state) { case ODEBUG_STATE_ACTIVE: percpu_counter_destroy(fbc); debug_object_free(fbc, &percpu_counter_debug_descr); return true; default: return false; } } static const struct debug_obj_descr percpu_counter_debug_descr = { .name = "percpu_counter", .fixup_free = percpu_counter_fixup_free, }; static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) { debug_object_init(fbc, &percpu_counter_debug_descr); debug_object_activate(fbc, &percpu_counter_debug_descr); } static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) { debug_object_deactivate(fbc, &percpu_counter_debug_descr); debug_object_free(fbc, &percpu_counter_debug_descr); } #else /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) { } static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) { } #endif /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ void percpu_counter_set(struct percpu_counter *fbc, s64 amount) { int cpu; unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); for_each_possible_cpu(cpu) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); *pcount = 0; } fbc->count = amount; raw_spin_unlock_irqrestore(&fbc->lock, flags); } EXPORT_SYMBOL(percpu_counter_set); /* * This function is both preempt and irq safe. The former is due to explicit * preemption disable. The latter is guaranteed by the fact that the slow path * is explicitly protected by an irq-safe spinlock whereas the fast patch uses * this_cpu_add which is irq-safe by definition. Hence there is no need muck * with irq state before calling this one */ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; preempt_disable(); count = __this_cpu_read(*fbc->counters) + amount; if (abs(count) >= batch) { unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); fbc->count += count; __this_cpu_sub(*fbc->counters, count - amount); raw_spin_unlock_irqrestore(&fbc->lock, flags); } else { this_cpu_add(*fbc->counters, amount); } preempt_enable(); } EXPORT_SYMBOL(percpu_counter_add_batch); /* * For percpu_counter with a big batch, the devication of its count could * be big, and there is requirement to reduce the deviation, like when the * counter's batch could be runtime decreased to get a better accuracy, * which can be achieved by running this sync function on each CPU. */ void percpu_counter_sync(struct percpu_counter *fbc) { unsigned long flags; s64 count; raw_spin_lock_irqsave(&fbc->lock, flags); count = __this_cpu_read(*fbc->counters); fbc->count += count; __this_cpu_sub(*fbc->counters, count); raw_spin_unlock_irqrestore(&fbc->lock, flags); } EXPORT_SYMBOL(percpu_counter_sync); /* * Add up all the per-cpu counts, return the result. This is a more accurate * but much slower version of percpu_counter_read_positive() */ s64 __percpu_counter_sum(struct percpu_counter *fbc) { s64 ret; int cpu; unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); ret = fbc->count; for_each_online_cpu(cpu) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); ret += *pcount; } raw_spin_unlock_irqrestore(&fbc->lock, flags); return ret; } EXPORT_SYMBOL(__percpu_counter_sum); int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp, struct lock_class_key *key) { unsigned long flags __maybe_unused; raw_spin_lock_init(&fbc->lock); lockdep_set_class(&fbc->lock, key); fbc->count = amount; fbc->counters = alloc_percpu_gfp(s32, gfp); if (!fbc->counters) return -ENOMEM; debug_percpu_counter_activate(fbc); #ifdef CONFIG_HOTPLUG_CPU INIT_LIST_HEAD(&fbc->list); spin_lock_irqsave(&percpu_counters_lock, flags); list_add(&fbc->list, &percpu_counters); spin_unlock_irqrestore(&percpu_counters_lock, flags); #endif return 0; } EXPORT_SYMBOL(__percpu_counter_init); void percpu_counter_destroy(struct percpu_counter *fbc) { unsigned long flags __maybe_unused; if (!fbc->counters) return; debug_percpu_counter_deactivate(fbc); #ifdef CONFIG_HOTPLUG_CPU spin_lock_irqsave(&percpu_counters_lock, flags); list_del(&fbc->list); spin_unlock_irqrestore(&percpu_counters_lock, flags); #endif free_percpu(fbc->counters); fbc->counters = NULL; } EXPORT_SYMBOL(percpu_counter_destroy); int percpu_counter_batch __read_mostly = 32; EXPORT_SYMBOL(percpu_counter_batch); static int compute_batch_value(unsigned int cpu) { int nr = num_online_cpus(); percpu_counter_batch = max(32, nr*2); return 0; } static int percpu_counter_cpu_dead(unsigned int cpu) { #ifdef CONFIG_HOTPLUG_CPU struct percpu_counter *fbc; compute_batch_value(cpu); spin_lock_irq(&percpu_counters_lock); list_for_each_entry(fbc, &percpu_counters, list) { s32 *pcount; raw_spin_lock(&fbc->lock); pcount = per_cpu_ptr(fbc->counters, cpu); fbc->count += *pcount; *pcount = 0; raw_spin_unlock(&fbc->lock); } spin_unlock_irq(&percpu_counters_lock); #endif return 0; } /* * Compare counter against given value. * Return 1 if greater, 0 if equal and -1 if less */ int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) { s64 count; count = percpu_counter_read(fbc); /* Check to see if rough count will be sufficient for comparison */ if (abs(count - rhs) > (batch * num_online_cpus())) { if (count > rhs) return 1; else return -1; } /* Need to use precise count */ count = percpu_counter_sum(fbc); if (count > rhs) return 1; else if (count < rhs) return -1; else return 0; } EXPORT_SYMBOL(__percpu_counter_compare); static int __init percpu_counter_startup(void) { int ret; ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "lib/percpu_cnt:online", compute_batch_value, NULL); WARN_ON(ret < 0); ret = cpuhp_setup_state_nocalls(CPUHP_PERCPU_CNT_DEAD, "lib/percpu_cnt:dead", NULL, percpu_counter_cpu_dead); WARN_ON(ret < 0); return 0; } module_init(percpu_counter_startup); |
| 2 102 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 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 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM filemap #if !defined(_TRACE_FILEMAP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FILEMAP_H #include <linux/types.h> #include <linux/tracepoint.h> #include <linux/mm.h> #include <linux/memcontrol.h> #include <linux/device.h> #include <linux/kdev_t.h> #include <linux/errseq.h> DECLARE_EVENT_CLASS(mm_filemap_op_page_cache, TP_PROTO(struct folio *folio), TP_ARGS(folio), TP_STRUCT__entry( __field(unsigned long, pfn) __field(unsigned long, i_ino) __field(unsigned long, index) __field(dev_t, s_dev) __field(unsigned char, order) ), TP_fast_assign( __entry->pfn = folio_pfn(folio); __entry->i_ino = folio->mapping->host->i_ino; __entry->index = folio->index; if (folio->mapping->host->i_sb) __entry->s_dev = folio->mapping->host->i_sb->s_dev; else __entry->s_dev = folio->mapping->host->i_rdev; __entry->order = folio_order(folio); ), TP_printk("dev %d:%d ino %lx pfn=0x%lx ofs=%lu order=%u", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->pfn, __entry->index << PAGE_SHIFT, __entry->order) ); DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_delete_from_page_cache, TP_PROTO(struct folio *folio), TP_ARGS(folio) ); DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_add_to_page_cache, TP_PROTO(struct folio *folio), TP_ARGS(folio) ); TRACE_EVENT(filemap_set_wb_err, TP_PROTO(struct address_space *mapping, errseq_t eseq), TP_ARGS(mapping, eseq), TP_STRUCT__entry( __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(errseq_t, errseq) ), TP_fast_assign( __entry->i_ino = mapping->host->i_ino; __entry->errseq = eseq; if (mapping->host->i_sb) __entry->s_dev = mapping->host->i_sb->s_dev; else __entry->s_dev = mapping->host->i_rdev; ), TP_printk("dev=%d:%d ino=0x%lx errseq=0x%x", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->errseq) ); TRACE_EVENT(file_check_and_advance_wb_err, TP_PROTO(struct file *file, errseq_t old), TP_ARGS(file, old), TP_STRUCT__entry( __field(struct file *, file) __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(errseq_t, old) __field(errseq_t, new) ), TP_fast_assign( __entry->file = file; __entry->i_ino = file->f_mapping->host->i_ino; if (file->f_mapping->host->i_sb) __entry->s_dev = file->f_mapping->host->i_sb->s_dev; else __entry->s_dev = file->f_mapping->host->i_rdev; __entry->old = old; __entry->new = file->f_wb_err; ), TP_printk("file=%p dev=%d:%d ino=0x%lx old=0x%x new=0x%x", __entry->file, MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->old, __entry->new) ); #endif /* _TRACE_FILEMAP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 61 61 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the TCP module. * * Version: @(#)tcp.h 1.0.5 05/23/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _TCP_H #define _TCP_H #define FASTRETRANS_DEBUG 1 #include <linux/list.h> #include <linux/tcp.h> #include <linux/bug.h> #include <linux/slab.h> #include <linux/cache.h> #include <linux/percpu.h> #include <linux/skbuff.h> #include <linux/kref.h> #include <linux/ktime.h> #include <linux/indirect_call_wrapper.h> #include <net/inet_connection_sock.h> #include <net/inet_timewait_sock.h> #include <net/inet_hashtables.h> #include <net/checksum.h> #include <net/request_sock.h> #include <net/sock_reuseport.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ip.h> #include <net/tcp_states.h> #include <net/inet_ecn.h> #include <net/dst.h> #include <net/mptcp.h> #include <linux/seq_file.h> #include <linux/memcontrol.h> #include <linux/bpf-cgroup.h> #include <linux/siphash.h> extern struct inet_hashinfo tcp_hashinfo; DECLARE_PER_CPU(unsigned int, tcp_orphan_count); int tcp_orphan_count_sum(void); void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_HEADER L1_CACHE_ALIGN(128 + MAX_HEADER) #define MAX_TCP_OPTION_SPACE 40 #define TCP_MIN_SND_MSS 48 #define TCP_MIN_GSO_SIZE (TCP_MIN_SND_MSS - MAX_TCP_OPTION_SPACE) /* * Never offer a window over 32767 without using window scaling. Some * poor stacks do signed 16bit maths! */ #define MAX_TCP_WINDOW 32767U /* Minimal accepted MSS. It is (60+60+8) - (20+20). */ #define TCP_MIN_MSS 88U /* The initial MTU to use for probing */ #define TCP_BASE_MSS 1024 /* probing interval, default to 10 minutes as per RFC4821 */ #define TCP_PROBE_INTERVAL 600 /* Specify interval when tcp mtu probing will stop */ #define TCP_PROBE_THRESHOLD 8 /* After receiving this amount of duplicate ACKs fast retransmit starts. */ #define TCP_FASTRETRANS_THRESH 3 /* Maximal number of ACKs sent quickly to accelerate slow-start. */ #define TCP_MAX_QUICKACKS 16U /* Maximal number of window scale according to RFC1323 */ #define TCP_MAX_WSCALE 14U /* urg_data states */ #define TCP_URG_VALID 0x0100 #define TCP_URG_NOTYET 0x0200 #define TCP_URG_READ 0x0400 #define TCP_RETR1 3 /* * This is how many retries it does before it * tries to figure out if the gateway is * down. Minimal RFC value is 3; it corresponds * to ~3sec-8min depending on RTO. */ #define TCP_RETR2 15 /* * This should take at least * 90 minutes to time out. * RFC1122 says that the limit is 100 sec. * 15 is ~13-30min depending on RTO. */ #define TCP_SYN_RETRIES 6 /* This is how many retries are done * when active opening a connection. * RFC1122 says the minimum retry MUST * be at least 180secs. Nevertheless * this value is corresponding to * 63secs of retransmission with the * current initial RTO. */ #define TCP_SYNACK_RETRIES 5 /* This is how may retries are done * when passive opening a connection. * This is corresponding to 31secs of * retransmission with the current * initial RTO. */ #define TCP_TIMEWAIT_LEN (60*HZ) /* how long to wait to destroy TIME-WAIT * state, about 60 seconds */ #define TCP_FIN_TIMEOUT TCP_TIMEWAIT_LEN /* BSD style FIN_WAIT2 deadlock breaker. * It used to be 3min, new value is 60sec, * to combine FIN-WAIT-2 timeout with * TIME-WAIT timer. */ #define TCP_FIN_TIMEOUT_MAX (120 * HZ) /* max TCP_LINGER2 value (two minutes) */ #define TCP_DELACK_MAX ((unsigned)(HZ/5)) /* maximal time to delay before sending an ACK */ #if HZ >= 100 #define TCP_DELACK_MIN ((unsigned)(HZ/25)) /* minimal time to delay before sending an ACK */ #define TCP_ATO_MIN ((unsigned)(HZ/25)) #else #define TCP_DELACK_MIN 4U #define TCP_ATO_MIN 4U #endif #define TCP_RTO_MAX ((unsigned)(120*HZ)) #define TCP_RTO_MIN ((unsigned)(HZ/5)) #define TCP_TIMEOUT_MIN (2U) /* Min timeout for TCP timers in jiffies */ #define TCP_TIMEOUT_MIN_US (2*USEC_PER_MSEC) /* Min TCP timeout in microsecs */ #define TCP_TIMEOUT_INIT ((unsigned)(1*HZ)) /* RFC6298 2.1 initial RTO value */ #define TCP_TIMEOUT_FALLBACK ((unsigned)(3*HZ)) /* RFC 1122 initial RTO value, now * used as a fallback RTO for the * initial data transmission if no * valid RTT sample has been acquired, * most likely due to retrans in 3WHS. */ #define TCP_RESOURCE_PROBE_INTERVAL ((unsigned)(HZ/2U)) /* Maximal interval between probes * for local resources. */ #define TCP_KEEPALIVE_TIME (120*60*HZ) /* two hours */ #define TCP_KEEPALIVE_PROBES 9 /* Max of 9 keepalive probes */ #define TCP_KEEPALIVE_INTVL (75*HZ) #define MAX_TCP_KEEPIDLE 32767 #define MAX_TCP_KEEPINTVL 32767 #define MAX_TCP_KEEPCNT 127 #define MAX_TCP_SYNCNT 127 #define TCP_SYNQ_INTERVAL (HZ/5) /* Period of SYNACK timer */ #define TCP_PAWS_24DAYS (60 * 60 * 24 * 24) #define TCP_PAWS_MSL 60 /* Per-host timestamps are invalidated * after this time. It should be equal * (or greater than) TCP_TIMEWAIT_LEN * to provide reliability equal to one * provided by timewait state. */ #define TCP_PAWS_WINDOW 1 /* Replay window for per-host * timestamps. It must be less than * minimal timewait lifetime. */ /* * TCP option */ #define TCPOPT_NOP 1 /* Padding */ #define TCPOPT_EOL 0 /* End of options */ #define TCPOPT_MSS 2 /* Segment size negotiating */ #define TCPOPT_WINDOW 3 /* Window scaling */ #define TCPOPT_SACK_PERM 4 /* SACK Permitted */ #define TCPOPT_SACK 5 /* SACK Block */ #define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */ #define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */ #define TCPOPT_MPTCP 30 /* Multipath TCP (RFC6824) */ #define TCPOPT_FASTOPEN 34 /* Fast open (RFC7413) */ #define TCPOPT_EXP 254 /* Experimental */ /* Magic number to be after the option value for sharing TCP * experimental options. See draft-ietf-tcpm-experimental-options-00.txt */ #define TCPOPT_FASTOPEN_MAGIC 0xF989 #define TCPOPT_SMC_MAGIC 0xE2D4C3D9 /* * TCP option lengths */ #define TCPOLEN_MSS 4 #define TCPOLEN_WINDOW 3 #define TCPOLEN_SACK_PERM 2 #define TCPOLEN_TIMESTAMP 10 #define TCPOLEN_MD5SIG 18 #define TCPOLEN_FASTOPEN_BASE 2 #define TCPOLEN_EXP_FASTOPEN_BASE 4 #define TCPOLEN_EXP_SMC_BASE 6 /* But this is what stacks really send out. */ #define TCPOLEN_TSTAMP_ALIGNED 12 #define TCPOLEN_WSCALE_ALIGNED 4 #define TCPOLEN_SACKPERM_ALIGNED 4 #define TCPOLEN_SACK_BASE 2 #define TCPOLEN_SACK_BASE_ALIGNED 4 #define TCPOLEN_SACK_PERBLOCK 8 #define TCPOLEN_MD5SIG_ALIGNED 20 #define TCPOLEN_MSS_ALIGNED 4 #define TCPOLEN_EXP_SMC_BASE_ALIGNED 8 /* Flags in tp->nonagle */ #define TCP_NAGLE_OFF 1 /* Nagle's algo is disabled */ #define TCP_NAGLE_CORK 2 /* Socket is corked */ #define TCP_NAGLE_PUSH 4 /* Cork is overridden for already queued data */ /* TCP thin-stream limits */ #define TCP_THIN_LINEAR_RETRIES 6 /* After 6 linear retries, do exp. backoff */ /* TCP initial congestion window as per rfc6928 */ #define TCP_INIT_CWND 10 /* Bit Flags for sysctl_tcp_fastopen */ #define TFO_CLIENT_ENABLE 1 #define TFO_SERVER_ENABLE 2 #define TFO_CLIENT_NO_COOKIE 4 /* Data in SYN w/o cookie option */ /* Accept SYN data w/o any cookie option */ #define TFO_SERVER_COOKIE_NOT_REQD 0x200 /* Force enable TFO on all listeners, i.e., not requiring the * TCP_FASTOPEN socket option. */ #define TFO_SERVER_WO_SOCKOPT1 0x400 /* sysctl variables for tcp */ extern int sysctl_tcp_max_orphans; extern long sysctl_tcp_mem[3]; #define TCP_RACK_LOSS_DETECTION 0x1 /* Use RACK to detect losses */ #define TCP_RACK_STATIC_REO_WND 0x2 /* Use static RACK reo wnd */ #define TCP_RACK_NO_DUPTHRESH 0x4 /* Do not use DUPACK threshold in RACK */ extern atomic_long_t tcp_memory_allocated; DECLARE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc); extern struct percpu_counter tcp_sockets_allocated; extern unsigned long tcp_memory_pressure; /* optimized version of sk_under_memory_pressure() for TCP sockets */ static inline bool tcp_under_memory_pressure(const struct sock *sk) { if (mem_cgroup_sockets_enabled && sk->sk_memcg && mem_cgroup_under_socket_pressure(sk->sk_memcg)) return true; return READ_ONCE(tcp_memory_pressure); } /* * The next routines deal with comparing 32 bit unsigned ints * and worry about wraparound (automatic with unsigned arithmetic). */ static inline bool before(__u32 seq1, __u32 seq2) { return (__s32)(seq1-seq2) < 0; } #define after(seq2, seq1) before(seq1, seq2) /* is s2<=s1<=s3 ? */ static inline bool between(__u32 seq1, __u32 seq2, __u32 seq3) { return seq3 - seq2 >= seq1 - seq2; } static inline bool tcp_out_of_memory(struct sock *sk) { if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF && sk_memory_allocated(sk) > sk_prot_mem_limits(sk, 2)) return true; return false; } static inline void tcp_wmem_free_skb(struct sock *sk, struct sk_buff *skb) { sk_wmem_queued_add(sk, -skb->truesize); if (!skb_zcopy_pure(skb)) sk_mem_uncharge(sk, skb->truesize); else sk_mem_uncharge(sk, SKB_TRUESIZE(skb_end_offset(skb))); __kfree_skb(skb); } void sk_forced_mem_schedule(struct sock *sk, int size); bool tcp_check_oom(struct sock *sk, int shift); extern struct proto tcp_prot; #define TCP_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.tcp_statistics, field) #define __TCP_INC_STATS(net, field) __SNMP_INC_STATS((net)->mib.tcp_statistics, field) #define TCP_DEC_STATS(net, field) SNMP_DEC_STATS((net)->mib.tcp_statistics, field) #define TCP_ADD_STATS(net, field, val) SNMP_ADD_STATS((net)->mib.tcp_statistics, field, val) void tcp_tasklet_init(void); int tcp_v4_err(struct sk_buff *skb, u32); void tcp_shutdown(struct sock *sk, int how); int tcp_v4_early_demux(struct sk_buff *skb); int tcp_v4_rcv(struct sk_buff *skb); void tcp_remove_empty_skb(struct sock *sk); int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw); int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, size_t size, struct ubuf_info *uarg); int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags); ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, size_t size, int flags); int tcp_send_mss(struct sock *sk, int *size_goal, int flags); void tcp_push(struct sock *sk, int flags, int mss_now, int nonagle, int size_goal); void tcp_release_cb(struct sock *sk); void tcp_wfree(struct sk_buff *skb); void tcp_write_timer_handler(struct sock *sk); void tcp_delack_timer_handler(struct sock *sk); int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg); int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb); void tcp_rcv_established(struct sock *sk, struct sk_buff *skb); void tcp_rcv_space_adjust(struct sock *sk); int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp); void tcp_twsk_destructor(struct sock *sk); void tcp_twsk_purge(struct list_head *net_exit_list); ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, bool force_schedule); static inline void tcp_dec_quickack_mode(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ack.quick) { /* How many ACKs S/ACKing new data have we sent? */ const unsigned int pkts = inet_csk_ack_scheduled(sk) ? 1 : 0; if (pkts >= icsk->icsk_ack.quick) { icsk->icsk_ack.quick = 0; /* Leaving quickack mode we deflate ATO. */ icsk->icsk_ack.ato = TCP_ATO_MIN; } else icsk->icsk_ack.quick -= pkts; } } #define TCP_ECN_OK 1 #define TCP_ECN_QUEUE_CWR 2 #define TCP_ECN_DEMAND_CWR 4 #define TCP_ECN_SEEN 8 enum tcp_tw_status { TCP_TW_SUCCESS = 0, TCP_TW_RST = 1, TCP_TW_ACK = 2, TCP_TW_SYN = 3 }; enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, const struct tcphdr *th); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req, bool fastopen, bool *lost_race); int tcp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); void tcp_enter_loss(struct sock *sk); void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int newly_lost, int flag); void tcp_clear_retrans(struct tcp_sock *tp); void tcp_update_metrics(struct sock *sk); void tcp_init_metrics(struct sock *sk); void tcp_metrics_init(void); bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst); void __tcp_close(struct sock *sk, long timeout); void tcp_close(struct sock *sk, long timeout); void tcp_init_sock(struct sock *sk); void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb); __poll_t tcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int do_tcp_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen); int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); bool tcp_bpf_bypass_getsockopt(int level, int optname); int do_tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); void tcp_set_keepalive(struct sock *sk, int val); void tcp_syn_ack_timeout(const struct request_sock *req); int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len); int tcp_set_rcvlowat(struct sock *sk, int val); int tcp_set_window_clamp(struct sock *sk, int val); void tcp_update_recv_tstamps(struct sk_buff *skb, struct scm_timestamping_internal *tss); void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, struct scm_timestamping_internal *tss); void tcp_data_ready(struct sock *sk); #ifdef CONFIG_MMU int tcp_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma); #endif void tcp_parse_options(const struct net *net, const struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab, struct tcp_fastopen_cookie *foc); const u8 *tcp_parse_md5sig_option(const struct tcphdr *th); /* * BPF SKB-less helpers */ u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph, struct tcphdr *th, u32 *cookie); u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph, struct tcphdr *th, u32 *cookie); u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss); u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct tcphdr *th); /* * TCP v4 functions exported for the inet6 API */ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb); void tcp_v4_mtu_reduced(struct sock *sk); void tcp_req_err(struct sock *sk, u32 seq, bool abort); void tcp_ld_RTO_revert(struct sock *sk, u32 seq); int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb); struct sock *tcp_create_openreq_child(const struct sock *sk, struct request_sock *req, struct sk_buff *skb); void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst); struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, struct request_sock *req_unhash, bool *own_req); int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); int tcp_connect(struct sock *sk); enum tcp_synack_type { TCP_SYNACK_NORMAL, TCP_SYNACK_FASTOPEN, TCP_SYNACK_COOKIE, }; struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb); int tcp_disconnect(struct sock *sk, int flags); void tcp_finish_connect(struct sock *sk, struct sk_buff *skb); int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size); void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb); /* From syncookies.c */ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, u32 tsoff); int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, u32 cookie); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb); #ifdef CONFIG_SYN_COOKIES /* Syncookies use a monotonic timer which increments every 60 seconds. * This counter is used both as a hash input and partially encoded into * the cookie value. A cookie is only validated further if the delta * between the current counter value and the encoded one is less than this, * i.e. a sent cookie is valid only at most for 2*60 seconds (or less if * the counter advances immediately after a cookie is generated). */ #define MAX_SYNCOOKIE_AGE 2 #define TCP_SYNCOOKIE_PERIOD (60 * HZ) #define TCP_SYNCOOKIE_VALID (MAX_SYNCOOKIE_AGE * TCP_SYNCOOKIE_PERIOD) /* syncookies: remember time of last synqueue overflow * But do not dirty this field too often (once per second is enough) * It is racy as we do not hold a lock, but race is very minor. */ static inline void tcp_synq_overflow(const struct sock *sk) { unsigned int last_overflow; unsigned int now = jiffies; if (sk->sk_reuseport) { struct sock_reuseport *reuse; reuse = rcu_dereference(sk->sk_reuseport_cb); if (likely(reuse)) { last_overflow = READ_ONCE(reuse->synq_overflow_ts); if (!time_between32(now, last_overflow, last_overflow + HZ)) WRITE_ONCE(reuse->synq_overflow_ts, now); return; } } last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp); if (!time_between32(now, last_overflow, last_overflow + HZ)) WRITE_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp, now); } /* syncookies: no recent synqueue overflow on this listening socket? */ static inline bool tcp_synq_no_recent_overflow(const struct sock *sk) { unsigned int last_overflow; unsigned int now = jiffies; if (sk->sk_reuseport) { struct sock_reuseport *reuse; reuse = rcu_dereference(sk->sk_reuseport_cb); if (likely(reuse)) { last_overflow = READ_ONCE(reuse->synq_overflow_ts); return !time_between32(now, last_overflow - HZ, last_overflow + TCP_SYNCOOKIE_VALID); } } last_overflow = READ_ONCE(tcp_sk(sk)->rx_opt.ts_recent_stamp); /* If last_overflow <= jiffies <= last_overflow + TCP_SYNCOOKIE_VALID, * then we're under synflood. However, we have to use * 'last_overflow - HZ' as lower bound. That's because a concurrent * tcp_synq_overflow() could update .ts_recent_stamp after we read * jiffies but before we store .ts_recent_stamp into last_overflow, * which could lead to rejecting a valid syncookie. */ return !time_between32(now, last_overflow - HZ, last_overflow + TCP_SYNCOOKIE_VALID); } static inline u32 tcp_cookie_time(void) { u64 val = get_jiffies_64(); do_div(val, TCP_SYNCOOKIE_PERIOD); return val; } u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, u16 *mssp); __u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss); u64 cookie_init_timestamp(struct request_sock *req, u64 now); bool cookie_timestamp_decode(const struct net *net, struct tcp_options_received *opt); bool cookie_ecn_ok(const struct tcp_options_received *opt, const struct net *net, const struct dst_entry *dst); /* From net/ipv6/syncookies.c */ int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th, u32 cookie); struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb); u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, const struct tcphdr *th, u16 *mssp); __u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss); #endif /* tcp_output.c */ void tcp_skb_entail(struct sock *sk, struct sk_buff *skb); void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb); void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, int nonagle); int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs); int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs); void tcp_retransmit_timer(struct sock *sk); void tcp_xmit_retransmit_queue(struct sock *); void tcp_simple_retransmit(struct sock *); void tcp_enter_recovery(struct sock *sk, bool ece_ack); int tcp_trim_head(struct sock *, struct sk_buff *, u32); enum tcp_queue { TCP_FRAG_IN_WRITE_QUEUE, TCP_FRAG_IN_RTX_QUEUE, }; int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, struct sk_buff *skb, u32 len, unsigned int mss_now, gfp_t gfp); void tcp_send_probe0(struct sock *); void tcp_send_partial(struct sock *); int tcp_write_wakeup(struct sock *, int mib); void tcp_send_fin(struct sock *sk); void tcp_send_active_reset(struct sock *sk, gfp_t priority); int tcp_send_synack(struct sock *); void tcp_push_one(struct sock *, unsigned int mss_now); void __tcp_send_ack(struct sock *sk, u32 rcv_nxt); void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); void tcp_send_loss_probe(struct sock *sk); bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto); void tcp_skb_collapse_tstamp(struct sk_buff *skb, const struct sk_buff *next_skb); /* tcp_input.c */ void tcp_rearm_rto(struct sock *sk); void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); void tcp_done_with_error(struct sock *sk, int err); void tcp_reset(struct sock *sk, struct sk_buff *skb); void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb); void tcp_fin(struct sock *sk); void tcp_check_space(struct sock *sk); void tcp_sack_compress_send_ack(struct sock *sk); /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); static inline void tcp_clear_xmit_timers(struct sock *sk) { if (hrtimer_try_to_cancel(&tcp_sk(sk)->pacing_timer) == 1) __sock_put(sk); if (hrtimer_try_to_cancel(&tcp_sk(sk)->compressed_ack_timer) == 1) __sock_put(sk); inet_csk_clear_xmit_timers(sk); } unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu); unsigned int tcp_current_mss(struct sock *sk); u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when); /* Bound MSS / TSO packet size with the half of the window */ static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize) { int cutoff; /* When peer uses tiny windows, there is no use in packetizing * to sub-MSS pieces for the sake of SWS or making sure there * are enough packets in the pipe for fast recovery. * * On the other hand, for extremely large MSS devices, handling * smaller than MSS windows in this way does make sense. */ if (tp->max_window > TCP_MSS_DEFAULT) cutoff = (tp->max_window >> 1); else cutoff = tp->max_window; if (cutoff && pktsize > cutoff) return max_t(int, cutoff, 68U - tp->tcp_header_len); else return pktsize; } /* tcp.c */ void tcp_get_info(struct sock *, struct tcp_info *); /* Read 'sendfile()'-style from a TCP socket */ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor); struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off); void tcp_read_done(struct sock *sk, size_t len); void tcp_initialize_rcv_mss(struct sock *sk); int tcp_mtu_to_mss(struct sock *sk, int pmtu); int tcp_mss_to_mtu(struct sock *sk, int mss); void tcp_mtup_init(struct sock *sk); static inline void tcp_bound_rto(const struct sock *sk) { if (inet_csk(sk)->icsk_rto > TCP_RTO_MAX) inet_csk(sk)->icsk_rto = TCP_RTO_MAX; } static inline u32 __tcp_set_rto(const struct tcp_sock *tp) { return usecs_to_jiffies((tp->srtt_us >> 3) + tp->rttvar_us); } static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd) { /* mptcp hooks are only on the slow path */ if (sk_is_mptcp((struct sock *)tp)) return; tp->pred_flags = htonl((tp->tcp_header_len << 26) | ntohl(TCP_FLAG_ACK) | snd_wnd); } static inline void tcp_fast_path_on(struct tcp_sock *tp) { __tcp_fast_path_on(tp, tp->snd_wnd >> tp->rx_opt.snd_wscale); } static inline void tcp_fast_path_check(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); if (RB_EMPTY_ROOT(&tp->out_of_order_queue) && tp->rcv_wnd && atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf && !tp->urg_data) tcp_fast_path_on(tp); } /* Compute the actual rto_min value */ static inline u32 tcp_rto_min(struct sock *sk) { const struct dst_entry *dst = __sk_dst_get(sk); u32 rto_min = inet_csk(sk)->icsk_rto_min; if (dst && dst_metric_locked(dst, RTAX_RTO_MIN)) rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN); return rto_min; } static inline u32 tcp_rto_min_us(struct sock *sk) { return jiffies_to_usecs(tcp_rto_min(sk)); } static inline bool tcp_ca_dst_locked(const struct dst_entry *dst) { return dst_metric_locked(dst, RTAX_CC_ALGO); } /* Minimum RTT in usec. ~0 means not available. */ static inline u32 tcp_min_rtt(const struct tcp_sock *tp) { return minmax_get(&tp->rtt_min); } /* Compute the actual receive window we are currently advertising. * Rcv_nxt can be after the window if our peer push more data * than the offered window. */ static inline u32 tcp_receive_window(const struct tcp_sock *tp) { s32 win = tp->rcv_wup + tp->rcv_wnd - tp->rcv_nxt; if (win < 0) win = 0; return (u32) win; } /* Choose a new window, without checks for shrinking, and without * scaling applied to the result. The caller does these things * if necessary. This is a "raw" window selection. */ u32 __tcp_select_window(struct sock *sk); void tcp_send_window_probe(struct sock *sk); /* TCP uses 32bit jiffies to save some space. * Note that this is different from tcp_time_stamp, which * historically has been the same until linux-4.13. */ #define tcp_jiffies32 ((u32)jiffies) /* * Deliver a 32bit value for TCP timestamp option (RFC 7323) * It is no longer tied to jiffies, but to 1 ms clock. * Note: double check if you want to use tcp_jiffies32 instead of this. */ #define TCP_TS_HZ 1000 static inline u64 tcp_clock_ns(void) { return ktime_get_ns(); } static inline u64 tcp_clock_us(void) { return div_u64(tcp_clock_ns(), NSEC_PER_USEC); } /* This should only be used in contexts where tp->tcp_mstamp is up to date */ static inline u32 tcp_time_stamp(const struct tcp_sock *tp) { return div_u64(tp->tcp_mstamp, USEC_PER_SEC / TCP_TS_HZ); } /* Convert a nsec timestamp into TCP TSval timestamp (ms based currently) */ static inline u64 tcp_ns_to_ts(u64 ns) { return div_u64(ns, NSEC_PER_SEC / TCP_TS_HZ); } /* Could use tcp_clock_us() / 1000, but this version uses a single divide */ static inline u32 tcp_time_stamp_raw(void) { return tcp_ns_to_ts(tcp_clock_ns()); } void tcp_mstamp_refresh(struct tcp_sock *tp); static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0) { return max_t(s64, t1 - t0, 0); } static inline u32 tcp_skb_timestamp(const struct sk_buff *skb) { return tcp_ns_to_ts(skb->skb_mstamp_ns); } /* provide the departure time in us unit */ static inline u64 tcp_skb_timestamp_us(const struct sk_buff *skb) { return div_u64(skb->skb_mstamp_ns, NSEC_PER_USEC); } #define tcp_flag_byte(th) (((u_int8_t *)th)[13]) #define TCPHDR_FIN 0x01 #define TCPHDR_SYN 0x02 #define TCPHDR_RST 0x04 #define TCPHDR_PSH 0x08 #define TCPHDR_ACK 0x10 #define TCPHDR_URG 0x20 #define TCPHDR_ECE 0x40 #define TCPHDR_CWR 0x80 #define TCPHDR_SYN_ECN (TCPHDR_SYN | TCPHDR_ECE | TCPHDR_CWR) /* This is what the send packet queuing engine uses to pass * TCP per-packet control information to the transmission code. * We also store the host-order sequence numbers in here too. * This is 44 bytes if IPV6 is enabled. * If this grows please adjust skbuff.h:skbuff->cb[xxx] size appropriately. */ struct tcp_skb_cb { __u32 seq; /* Starting sequence number */ __u32 end_seq; /* SEQ + FIN + SYN + datalen */ union { /* Note : tcp_tw_isn is used in input path only * (isn chosen by tcp_timewait_state_process()) * * tcp_gso_segs/size are used in write queue only, * cf tcp_skb_pcount()/tcp_skb_mss() */ __u32 tcp_tw_isn; struct { u16 tcp_gso_segs; u16 tcp_gso_size; }; }; __u8 tcp_flags; /* TCP header flags. (tcp[13]) */ __u8 sacked; /* State flags for SACK. */ #define TCPCB_SACKED_ACKED 0x01 /* SKB ACK'd by a SACK block */ #define TCPCB_SACKED_RETRANS 0x02 /* SKB retransmitted */ #define TCPCB_LOST 0x04 /* SKB is lost */ #define TCPCB_TAGBITS 0x07 /* All tag bits */ #define TCPCB_REPAIRED 0x10 /* SKB repaired (no skb_mstamp_ns) */ #define TCPCB_EVER_RETRANS 0x80 /* Ever retransmitted frame */ #define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS| \ TCPCB_REPAIRED) __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */ __u8 txstamp_ack:1, /* Record TX timestamp for ack? */ eor:1, /* Is skb MSG_EOR marked? */ has_rxtstamp:1, /* SKB has a RX timestamp */ unused:5; __u32 ack_seq; /* Sequence number ACK'd */ union { struct { #define TCPCB_DELIVERED_CE_MASK ((1U<<20) - 1) /* There is space for up to 24 bytes */ __u32 is_app_limited:1, /* cwnd not fully used? */ delivered_ce:20, unused:11; /* pkts S/ACKed so far upon tx of skb, incl retrans: */ __u32 delivered; /* start of send pipeline phase */ u64 first_tx_mstamp; /* when we reached the "delivered" count */ u64 delivered_mstamp; } tx; /* only used for outgoing skbs */ union { struct inet_skb_parm h4; #if IS_ENABLED(CONFIG_IPV6) struct inet6_skb_parm h6; #endif } header; /* For incoming skbs */ }; }; #define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0])) extern const struct inet_connection_sock_af_ops ipv4_specific; #if IS_ENABLED(CONFIG_IPV6) /* This is the variant of inet6_iif() that must be used by TCP, * as TCP moves IP6CB into a different location in skb->cb[] */ static inline int tcp_v6_iif(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->header.h6.iif; } static inline int tcp_v6_iif_l3_slave(const struct sk_buff *skb) { bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags); return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif; } /* TCP_SKB_CB reference means this can not be used from early demux */ static inline int tcp_v6_sdif(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (skb && ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags)) return TCP_SKB_CB(skb)->header.h6.iif; #endif return 0; } extern const struct inet_connection_sock_af_ops ipv6_specific; INDIRECT_CALLABLE_DECLARE(void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb)); INDIRECT_CALLABLE_DECLARE(int tcp_v6_rcv(struct sk_buff *skb)); void tcp_v6_early_demux(struct sk_buff *skb); #endif /* TCP_SKB_CB reference means this can not be used from early demux */ static inline int tcp_v4_sdif(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (skb && ipv4_l3mdev_skb(TCP_SKB_CB(skb)->header.h4.flags)) return TCP_SKB_CB(skb)->header.h4.iif; #endif return 0; } /* Due to TSO, an SKB can be composed of multiple actual * packets. To keep these tracked properly, we use this. */ static inline int tcp_skb_pcount(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->tcp_gso_segs; } static inline void tcp_skb_pcount_set(struct sk_buff *skb, int segs) { TCP_SKB_CB(skb)->tcp_gso_segs = segs; } static inline void tcp_skb_pcount_add(struct sk_buff *skb, int segs) { TCP_SKB_CB(skb)->tcp_gso_segs += segs; } /* This is valid iff skb is in write queue and tcp_skb_pcount() > 1. */ static inline int tcp_skb_mss(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->tcp_gso_size; } static inline bool tcp_skb_can_collapse_to(const struct sk_buff *skb) { return likely(!TCP_SKB_CB(skb)->eor); } static inline bool tcp_skb_can_collapse(const struct sk_buff *to, const struct sk_buff *from) { return likely(tcp_skb_can_collapse_to(to) && mptcp_skb_can_collapse(to, from) && skb_pure_zcopy_same(to, from)); } /* Events passed to congestion control interface */ enum tcp_ca_event { CA_EVENT_TX_START, /* first transmit when no packets in flight */ CA_EVENT_CWND_RESTART, /* congestion window restart */ CA_EVENT_COMPLETE_CWR, /* end of congestion recovery */ CA_EVENT_LOSS, /* loss timeout */ CA_EVENT_ECN_NO_CE, /* ECT set, but not CE marked */ CA_EVENT_ECN_IS_CE, /* received CE marked IP packet */ }; /* Information about inbound ACK, passed to cong_ops->in_ack_event() */ enum tcp_ca_ack_event_flags { CA_ACK_SLOWPATH = (1 << 0), /* In slow path processing */ CA_ACK_WIN_UPDATE = (1 << 1), /* ACK updated window */ CA_ACK_ECE = (1 << 2), /* ECE bit is set on ack */ }; /* * Interface for adding new TCP congestion control handlers */ #define TCP_CA_NAME_MAX 16 #define TCP_CA_MAX 128 #define TCP_CA_BUF_MAX (TCP_CA_NAME_MAX*TCP_CA_MAX) #define TCP_CA_UNSPEC 0 /* Algorithm can be set on socket without CAP_NET_ADMIN privileges */ #define TCP_CONG_NON_RESTRICTED 0x1 /* Requires ECN/ECT set on all packets */ #define TCP_CONG_NEEDS_ECN 0x2 #define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN) union tcp_cc_info; struct ack_sample { u32 pkts_acked; s32 rtt_us; u32 in_flight; }; /* A rate sample measures the number of (original/retransmitted) data * packets delivered "delivered" over an interval of time "interval_us". * The tcp_rate.c code fills in the rate sample, and congestion * control modules that define a cong_control function to run at the end * of ACK processing can optionally chose to consult this sample when * setting cwnd and pacing rate. * A sample is invalid if "delivered" or "interval_us" is negative. */ struct rate_sample { u64 prior_mstamp; /* starting timestamp for interval */ u32 prior_delivered; /* tp->delivered at "prior_mstamp" */ u32 prior_delivered_ce;/* tp->delivered_ce at "prior_mstamp" */ s32 delivered; /* number of packets delivered over interval */ s32 delivered_ce; /* number of packets delivered w/ CE marks*/ long interval_us; /* time for tp->delivered to incr "delivered" */ u32 snd_interval_us; /* snd interval for delivered packets */ u32 rcv_interval_us; /* rcv interval for delivered packets */ long rtt_us; /* RTT of last (S)ACKed packet (or -1) */ int losses; /* number of packets marked lost upon ACK */ u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */ u32 prior_in_flight; /* in flight before this ACK */ u32 last_end_seq; /* end_seq of most recently ACKed packet */ bool is_app_limited; /* is sample from packet with bubble in pipe? */ bool is_retrans; /* is sample from retransmission? */ bool is_ack_delayed; /* is this (likely) a delayed ACK? */ }; struct tcp_congestion_ops { /* fast path fields are put first to fill one cache line */ /* return slow start threshold (required) */ u32 (*ssthresh)(struct sock *sk); /* do new cwnd calculation (required) */ void (*cong_avoid)(struct sock *sk, u32 ack, u32 acked); /* call before changing ca_state (optional) */ void (*set_state)(struct sock *sk, u8 new_state); /* call when cwnd event occurs (optional) */ void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev); /* call when ack arrives (optional) */ void (*in_ack_event)(struct sock *sk, u32 flags); /* hook for packet ack accounting (optional) */ void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample); /* override sysctl_tcp_min_tso_segs */ u32 (*min_tso_segs)(struct sock *sk); /* call when packets are delivered to update cwnd and pacing rate, * after all the ca_state processing. (optional) */ void (*cong_control)(struct sock *sk, const struct rate_sample *rs); /* new value of cwnd after loss (required) */ u32 (*undo_cwnd)(struct sock *sk); /* returns the multiplier used in tcp_sndbuf_expand (optional) */ u32 (*sndbuf_expand)(struct sock *sk); /* control/slow paths put last */ /* get info for inet_diag (optional) */ size_t (*get_info)(struct sock *sk, u32 ext, int *attr, union tcp_cc_info *info); char name[TCP_CA_NAME_MAX]; struct module *owner; struct list_head list; u32 key; u32 flags; /* initialize private data (optional) */ void (*init)(struct sock *sk); /* cleanup private data (optional) */ void (*release)(struct sock *sk); } ____cacheline_aligned_in_smp; int tcp_register_congestion_control(struct tcp_congestion_ops *type); void tcp_unregister_congestion_control(struct tcp_congestion_ops *type); void tcp_assign_congestion_control(struct sock *sk); void tcp_init_congestion_control(struct sock *sk); void tcp_cleanup_congestion_control(struct sock *sk); int tcp_set_default_congestion_control(struct net *net, const char *name); void tcp_get_default_congestion_control(struct net *net, char *name); void tcp_get_available_congestion_control(char *buf, size_t len); void tcp_get_allowed_congestion_control(char *buf, size_t len); int tcp_set_allowed_congestion_control(char *allowed); int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool cap_net_admin); u32 tcp_slow_start(struct tcp_sock *tp, u32 acked); void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked); u32 tcp_reno_ssthresh(struct sock *sk); u32 tcp_reno_undo_cwnd(struct sock *sk); void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked); extern struct tcp_congestion_ops tcp_reno; struct tcp_congestion_ops *tcp_ca_find(const char *name); struct tcp_congestion_ops *tcp_ca_find_key(u32 key); u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca); #ifdef CONFIG_INET char *tcp_ca_get_name_by_key(u32 key, char *buffer); #else static inline char *tcp_ca_get_name_by_key(u32 key, char *buffer) { return NULL; } #endif static inline bool tcp_ca_needs_ecn(const struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN; } static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) { const struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ca_ops->cwnd_event) icsk->icsk_ca_ops->cwnd_event(sk, event); } /* From tcp_cong.c */ void tcp_set_ca_state(struct sock *sk, const u8 ca_state); /* From tcp_rate.c */ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb); void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, struct rate_sample *rs); void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, bool is_sack_reneg, struct rate_sample *rs); void tcp_rate_check_app_limited(struct sock *sk); static inline bool tcp_skb_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) { return t1 > t2 || (t1 == t2 && after(seq1, seq2)); } /* These functions determine how the current flow behaves in respect of SACK * handling. SACK is negotiated with the peer, and therefore it can vary * between different flows. * * tcp_is_sack - SACK enabled * tcp_is_reno - No SACK */ static inline int tcp_is_sack(const struct tcp_sock *tp) { return likely(tp->rx_opt.sack_ok); } static inline bool tcp_is_reno(const struct tcp_sock *tp) { return !tcp_is_sack(tp); } static inline unsigned int tcp_left_out(const struct tcp_sock *tp) { return tp->sacked_out + tp->lost_out; } /* This determines how many packets are "in the network" to the best * of our knowledge. In many cases it is conservative, but where * detailed information is available from the receiver (via SACK * blocks etc.) we can make more aggressive calculations. * * Use this for decisions involving congestion control, use just * tp->packets_out to determine if the send queue is empty or not. * * Read this equation as: * * "Packets sent once on transmission queue" MINUS * "Packets left network, but not honestly ACKed yet" PLUS * "Packets fast retransmitted" */ static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp) { return tp->packets_out - tcp_left_out(tp) + tp->retrans_out; } #define TCP_INFINITE_SSTHRESH 0x7fffffff static inline u32 tcp_snd_cwnd(const struct tcp_sock *tp) { return tp->snd_cwnd; } static inline void tcp_snd_cwnd_set(struct tcp_sock *tp, u32 val) { WARN_ON_ONCE((int)val <= 0); tp->snd_cwnd = val; } static inline bool tcp_in_slow_start(const struct tcp_sock *tp) { return tcp_snd_cwnd(tp) < tp->snd_ssthresh; } static inline bool tcp_in_initial_slowstart(const struct tcp_sock *tp) { return tp->snd_ssthresh >= TCP_INFINITE_SSTHRESH; } static inline bool tcp_in_cwnd_reduction(const struct sock *sk) { return (TCPF_CA_CWR | TCPF_CA_Recovery) & (1 << inet_csk(sk)->icsk_ca_state); } /* If cwnd > ssthresh, we may raise ssthresh to be half-way to cwnd. * The exception is cwnd reduction phase, when cwnd is decreasing towards * ssthresh. */ static inline __u32 tcp_current_ssthresh(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); if (tcp_in_cwnd_reduction(sk)) return tp->snd_ssthresh; else return max(tp->snd_ssthresh, ((tcp_snd_cwnd(tp) >> 1) + (tcp_snd_cwnd(tp) >> 2))); } /* Use define here intentionally to get WARN_ON location shown at the caller */ #define tcp_verify_left_out(tp) WARN_ON(tcp_left_out(tp) > tp->packets_out) void tcp_enter_cwr(struct sock *sk); __u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst); /* The maximum number of MSS of available cwnd for which TSO defers * sending if not using sysctl_tcp_tso_win_divisor. */ static inline __u32 tcp_max_tso_deferred_mss(const struct tcp_sock *tp) { return 3; } /* Returns end sequence number of the receiver's advertised window */ static inline u32 tcp_wnd_end(const struct tcp_sock *tp) { return tp->snd_una + tp->snd_wnd; } /* We follow the spirit of RFC2861 to validate cwnd but implement a more * flexible approach. The RFC suggests cwnd should not be raised unless * it was fully used previously. And that's exactly what we do in * congestion avoidance mode. But in slow start we allow cwnd to grow * as long as the application has used half the cwnd. * Example : * cwnd is 10 (IW10), but application sends 9 frames. * We allow cwnd to reach 18 when all frames are ACKed. * This check is safe because it's as aggressive as slow start which already * risks 100% overshoot. The advantage is that we discourage application to * either send more filler packets or data to artificially blow up the cwnd * usage, and allow application-limited process to probe bw more aggressively. */ static inline bool tcp_is_cwnd_limited(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); if (tp->is_cwnd_limited) return true; /* If in slow start, ensure cwnd grows to twice what was ACKed. */ if (tcp_in_slow_start(tp)) return tcp_snd_cwnd(tp) < 2 * tp->max_packets_out; return false; } /* BBR congestion control needs pacing. * Same remark for SO_MAX_PACING_RATE. * sch_fq packet scheduler is efficiently handling pacing, * but is not always installed/used. * Return true if TCP stack should pace packets itself. */ static inline bool tcp_needs_internal_pacing(const struct sock *sk) { return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED; } /* Estimates in how many jiffies next packet for this flow can be sent. * Scheduling a retransmit timer too early would be silly. */ static inline unsigned long tcp_pacing_delay(const struct sock *sk) { s64 delay = tcp_sk(sk)->tcp_wstamp_ns - tcp_sk(sk)->tcp_clock_cache; return delay > 0 ? nsecs_to_jiffies(delay) : 0; } static inline void tcp_reset_xmit_timer(struct sock *sk, const int what, unsigned long when, const unsigned long max_when) { inet_csk_reset_xmit_timer(sk, what, when + tcp_pacing_delay(sk), max_when); } /* Something is really bad, we could not queue an additional packet, * because qdisc is full or receiver sent a 0 window, or we are paced. * We do not want to add fuel to the fire, or abort too early, * so make sure the timer we arm now is at least 200ms in the future, * regardless of current icsk_rto value (as it could be ~2ms) */ static inline unsigned long tcp_probe0_base(const struct sock *sk) { return max_t(unsigned long, inet_csk(sk)->icsk_rto, TCP_RTO_MIN); } /* Variant of inet_csk_rto_backoff() used for zero window probes */ static inline unsigned long tcp_probe0_when(const struct sock *sk, unsigned long max_when) { u8 backoff = min_t(u8, ilog2(TCP_RTO_MAX / TCP_RTO_MIN) + 1, inet_csk(sk)->icsk_backoff); u64 when = (u64)tcp_probe0_base(sk) << backoff; return (unsigned long)min_t(u64, when, max_when); } static inline void tcp_check_probe_timer(struct sock *sk) { if (!tcp_sk(sk)->packets_out && !inet_csk(sk)->icsk_pending) tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, tcp_probe0_base(sk), TCP_RTO_MAX); } static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq) { tp->snd_wl1 = seq; } static inline void tcp_update_wl(struct tcp_sock *tp, u32 seq) { tp->snd_wl1 = seq; } /* * Calculate(/check) TCP checksum */ static inline __sum16 tcp_v4_check(int len, __be32 saddr, __be32 daddr, __wsum base) { return csum_tcpudp_magic(saddr, daddr, len, IPPROTO_TCP, base); } static inline bool tcp_checksum_complete(struct sk_buff *skb) { return !skb_csum_unnecessary(skb) && __skb_checksum_complete(skb); } bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason); int tcp_filter(struct sock *sk, struct sk_buff *skb); void tcp_set_state(struct sock *sk, int state); void tcp_done(struct sock *sk); int tcp_abort(struct sock *sk, int err); static inline void tcp_sack_reset(struct tcp_options_received *rx_opt) { rx_opt->dsack = 0; rx_opt->num_sacks = 0; } void tcp_cwnd_restart(struct sock *sk, s32 delta); static inline void tcp_slow_start_after_idle_check(struct sock *sk) { const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; struct tcp_sock *tp = tcp_sk(sk); s32 delta; if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) || tp->packets_out || ca_ops->cong_control) return; delta = tcp_jiffies32 - tp->lsndtime; if (delta > inet_csk(sk)->icsk_rto) tcp_cwnd_restart(sk, delta); } /* Determine a window scaling and initial window to offer. */ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, __u32 *rcv_wnd, __u32 *window_clamp, int wscale_ok, __u8 *rcv_wscale, __u32 init_rcv_wnd); static inline int tcp_win_from_space(const struct sock *sk, int space) { int tcp_adv_win_scale = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale); return tcp_adv_win_scale <= 0 ? (space>>(-tcp_adv_win_scale)) : space - (space>>tcp_adv_win_scale); } /* Note: caller must be prepared to deal with negative returns */ static inline int tcp_space(const struct sock *sk) { return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - READ_ONCE(sk->sk_backlog.len) - atomic_read(&sk->sk_rmem_alloc)); } static inline int tcp_full_space(const struct sock *sk) { return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } static inline void __tcp_adjust_rcv_ssthresh(struct sock *sk, u32 new_ssthresh) { int unused_mem = sk_unused_reserved_mem(sk); struct tcp_sock *tp = tcp_sk(sk); tp->rcv_ssthresh = min(tp->rcv_ssthresh, new_ssthresh); if (unused_mem) tp->rcv_ssthresh = max_t(u32, tp->rcv_ssthresh, tcp_win_from_space(sk, unused_mem)); } static inline void tcp_adjust_rcv_ssthresh(struct sock *sk) { __tcp_adjust_rcv_ssthresh(sk, 4U * tcp_sk(sk)->advmss); } void tcp_cleanup_rbuf(struct sock *sk, int copied); void __tcp_cleanup_rbuf(struct sock *sk, int copied); /* We provision sk_rcvbuf around 200% of sk_rcvlowat. * If 87.5 % (7/8) of the space has been consumed, we want to override * SO_RCVLOWAT constraint, since we are receiving skbs with too small * len/truesize ratio. */ static inline bool tcp_rmem_pressure(const struct sock *sk) { int rcvbuf, threshold; if (tcp_under_memory_pressure(sk)) return true; rcvbuf = READ_ONCE(sk->sk_rcvbuf); threshold = rcvbuf - (rcvbuf >> 3); return atomic_read(&sk->sk_rmem_alloc) > threshold; } static inline bool tcp_epollin_ready(const struct sock *sk, int target) { const struct tcp_sock *tp = tcp_sk(sk); int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq); if (avail <= 0) return false; return (avail >= target) || tcp_rmem_pressure(sk) || (tcp_receive_window(tp) <= inet_csk(sk)->icsk_ack.rcv_mss); } extern void tcp_openreq_init_rwin(struct request_sock *req, const struct sock *sk_listener, const struct dst_entry *dst); void tcp_enter_memory_pressure(struct sock *sk); void tcp_leave_memory_pressure(struct sock *sk); static inline int keepalive_intvl_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); int val; /* Paired with WRITE_ONCE() in tcp_sock_set_keepintvl() * and do_tcp_setsockopt(). */ val = READ_ONCE(tp->keepalive_intvl); return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_intvl); } static inline int keepalive_time_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); int val; /* Paired with WRITE_ONCE() in tcp_sock_set_keepidle_locked() */ val = READ_ONCE(tp->keepalive_time); return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time); } static inline int keepalive_probes(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); int val; /* Paired with WRITE_ONCE() in tcp_sock_set_keepcnt() * and do_tcp_setsockopt(). */ val = READ_ONCE(tp->keepalive_probes); return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes); } static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) { const struct inet_connection_sock *icsk = &tp->inet_conn; return min_t(u32, tcp_jiffies32 - icsk->icsk_ack.lrcvtime, tcp_jiffies32 - tp->rcv_tstamp); } static inline int tcp_fin_time(const struct sock *sk) { int fin_timeout = tcp_sk(sk)->linger2 ? : READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fin_timeout); const int rto = inet_csk(sk)->icsk_rto; if (fin_timeout < (rto << 2) - (rto >> 1)) fin_timeout = (rto << 2) - (rto >> 1); return fin_timeout; } static inline bool tcp_paws_check(const struct tcp_options_received *rx_opt, int paws_win) { if ((s32)(rx_opt->ts_recent - rx_opt->rcv_tsval) <= paws_win) return true; if (unlikely(!time_before32(ktime_get_seconds(), rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS))) return true; /* * Some OSes send SYN and SYNACK messages with tsval=0 tsecr=0, * then following tcp messages have valid values. Ignore 0 value, * or else 'negative' tsval might forbid us to accept their packets. */ if (!rx_opt->ts_recent) return true; return false; } static inline bool tcp_paws_reject(const struct tcp_options_received *rx_opt, int rst) { if (tcp_paws_check(rx_opt, 0)) return false; /* RST segments are not recommended to carry timestamp, and, if they do, it is recommended to ignore PAWS because "their cleanup function should take precedence over timestamps." Certainly, it is mistake. It is necessary to understand the reasons of this constraint to relax it: if peer reboots, clock may go out-of-sync and half-open connections will not be reset. Actually, the problem would be not existing if all the implementations followed draft about maintaining clock via reboots. Linux-2.2 DOES NOT! However, we can relax time bounds for RST segments to MSL. */ if (rst && !time_before32(ktime_get_seconds(), rx_opt->ts_recent_stamp + TCP_PAWS_MSL)) return false; return true; } bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, int mib_idx, u32 *last_oow_ack_time); static inline void tcp_mib_init(struct net *net) { /* See RFC 2012 */ TCP_ADD_STATS(net, TCP_MIB_RTOALGORITHM, 1); TCP_ADD_STATS(net, TCP_MIB_RTOMIN, TCP_RTO_MIN*1000/HZ); TCP_ADD_STATS(net, TCP_MIB_RTOMAX, TCP_RTO_MAX*1000/HZ); TCP_ADD_STATS(net, TCP_MIB_MAXCONN, -1); } /* from STCP */ static inline void tcp_clear_retrans_hints_partial(struct tcp_sock *tp) { tp->lost_skb_hint = NULL; } static inline void tcp_clear_all_retrans_hints(struct tcp_sock *tp) { tcp_clear_retrans_hints_partial(tp); tp->retransmit_skb_hint = NULL; } union tcp_md5_addr { struct in_addr a4; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr a6; #endif }; /* - key database */ struct tcp_md5sig_key { struct hlist_node node; u8 keylen; u8 family; /* AF_INET or AF_INET6 */ u8 prefixlen; u8 flags; union tcp_md5_addr addr; int l3index; /* set if key added with L3 scope */ u8 key[TCP_MD5SIG_MAXKEYLEN]; struct rcu_head rcu; }; /* - sock block */ struct tcp_md5sig_info { struct hlist_head head; struct rcu_head rcu; }; /* - pseudo header */ struct tcp4_pseudohdr { __be32 saddr; __be32 daddr; __u8 pad; __u8 protocol; __be16 len; }; struct tcp6_pseudohdr { struct in6_addr saddr; struct in6_addr daddr; __be32 len; __be32 protocol; /* including padding */ }; union tcp_md5sum_block { struct tcp4_pseudohdr ip4; #if IS_ENABLED(CONFIG_IPV6) struct tcp6_pseudohdr ip6; #endif }; /* - pool: digest algorithm, hash description and scratch buffer */ struct tcp_md5sig_pool { struct ahash_request *md5_req; void *scratch; }; /* - functions */ int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, const struct sock *sk, const struct sk_buff *skb); int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags, const u8 *newkey, u8 newkeylen, gfp_t gfp); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags); struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk); #ifdef CONFIG_TCP_MD5SIG #include <linux/jump_label.h> extern struct static_key_false tcp_md5_needed; struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family); static inline struct tcp_md5sig_key * tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family) { if (!static_branch_unlikely(&tcp_md5_needed)) return NULL; return __tcp_md5_do_lookup(sk, l3index, addr, family); } enum skb_drop_reason tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, const void *saddr, const void *daddr, int family, int dif, int sdif); #define tcp_twsk_md5_key(twsk) ((twsk)->tw_md5_key) #else static inline struct tcp_md5sig_key * tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family) { return NULL; } static inline enum skb_drop_reason tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, const void *saddr, const void *daddr, int family, int dif, int sdif) { return SKB_NOT_DROPPED_YET; } #define tcp_twsk_md5_key(twsk) NULL #endif bool tcp_alloc_md5sig_pool(void); struct tcp_md5sig_pool *tcp_get_md5sig_pool(void); static inline void tcp_put_md5sig_pool(void) { local_bh_enable(); } int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *, const struct sk_buff *, unsigned int header_len); int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key); /* From tcp_fastopen.c */ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie); void tcp_fastopen_cache_set(struct sock *sk, u16 mss, struct tcp_fastopen_cookie *cookie, bool syn_lost, u16 try_exp); struct tcp_fastopen_request { /* Fast Open cookie. Size 0 means a cookie request */ struct tcp_fastopen_cookie cookie; struct msghdr *data; /* data in MSG_FASTOPEN */ size_t size; int copied; /* queued in tcp_connect() */ struct ubuf_info *uarg; }; void tcp_free_fastopen_req(struct tcp_sock *tp); void tcp_fastopen_destroy_cipher(struct sock *sk); void tcp_fastopen_ctx_destroy(struct net *net); int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk, void *primary_key, void *backup_key); int tcp_fastopen_get_cipher(struct net *net, struct inet_connection_sock *icsk, u64 *key); void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb); struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct tcp_fastopen_cookie *foc, const struct dst_entry *dst); void tcp_fastopen_init_key_once(struct net *net); bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie); bool tcp_fastopen_defer_connect(struct sock *sk, int *err); #define TCP_FASTOPEN_KEY_LENGTH sizeof(siphash_key_t) #define TCP_FASTOPEN_KEY_MAX 2 #define TCP_FASTOPEN_KEY_BUF_LENGTH \ (TCP_FASTOPEN_KEY_LENGTH * TCP_FASTOPEN_KEY_MAX) /* Fastopen key context */ struct tcp_fastopen_context { siphash_key_t key[TCP_FASTOPEN_KEY_MAX]; int num; struct rcu_head rcu; }; void tcp_fastopen_active_disable(struct sock *sk); bool tcp_fastopen_active_should_disable(struct sock *sk); void tcp_fastopen_active_disable_ofo_check(struct sock *sk); void tcp_fastopen_active_detect_blackhole(struct sock *sk, bool expired); /* Caller needs to wrap with rcu_read_(un)lock() */ static inline struct tcp_fastopen_context *tcp_fastopen_get_ctx(const struct sock *sk) { struct tcp_fastopen_context *ctx; ctx = rcu_dereference(inet_csk(sk)->icsk_accept_queue.fastopenq.ctx); if (!ctx) ctx = rcu_dereference(sock_net(sk)->ipv4.tcp_fastopen_ctx); return ctx; } static inline bool tcp_fastopen_cookie_match(const struct tcp_fastopen_cookie *foc, const struct tcp_fastopen_cookie *orig) { if (orig->len == TCP_FASTOPEN_COOKIE_SIZE && orig->len == foc->len && !memcmp(orig->val, foc->val, foc->len)) return true; return false; } static inline int tcp_fastopen_context_len(const struct tcp_fastopen_context *ctx) { return ctx->num; } /* Latencies incurred by various limits for a sender. They are * chronograph-like stats that are mutually exclusive. */ enum tcp_chrono { TCP_CHRONO_UNSPEC, TCP_CHRONO_BUSY, /* Actively sending data (non-empty write queue) */ TCP_CHRONO_RWND_LIMITED, /* Stalled by insufficient receive window */ TCP_CHRONO_SNDBUF_LIMITED, /* Stalled by insufficient send buffer */ __TCP_CHRONO_MAX, }; void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type); void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type); /* This helper is needed, because skb->tcp_tsorted_anchor uses * the same memory storage than skb->destructor/_skb_refdst */ static inline void tcp_skb_tsorted_anchor_cleanup(struct sk_buff *skb) { skb->destructor = NULL; skb->_skb_refdst = 0UL; } #define tcp_skb_tsorted_save(skb) { \ unsigned long _save = skb->_skb_refdst; \ skb->_skb_refdst = 0UL; #define tcp_skb_tsorted_restore(skb) \ skb->_skb_refdst = _save; \ } void tcp_write_queue_purge(struct sock *sk); static inline struct sk_buff *tcp_rtx_queue_head(const struct sock *sk) { return skb_rb_first(&sk->tcp_rtx_queue); } static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk) { return skb_rb_last(&sk->tcp_rtx_queue); } static inline struct sk_buff *tcp_write_queue_tail(const struct sock *sk) { return skb_peek_tail(&sk->sk_write_queue); } #define tcp_for_write_queue_from_safe(skb, tmp, sk) \ skb_queue_walk_from_safe(&(sk)->sk_write_queue, skb, tmp) static inline struct sk_buff *tcp_send_head(const struct sock *sk) { return skb_peek(&sk->sk_write_queue); } static inline bool tcp_skb_is_last(const struct sock *sk, const struct sk_buff *skb) { return skb_queue_is_last(&sk->sk_write_queue, skb); } /** * tcp_write_queue_empty - test if any payload (or FIN) is available in write queue * @sk: socket * * Since the write queue can have a temporary empty skb in it, * we must not use "return skb_queue_empty(&sk->sk_write_queue)" */ static inline bool tcp_write_queue_empty(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); return tp->write_seq == tp->snd_nxt; } static inline bool tcp_rtx_queue_empty(const struct sock *sk) { return RB_EMPTY_ROOT(&sk->tcp_rtx_queue); } static inline bool tcp_rtx_and_write_queues_empty(const struct sock *sk) { return tcp_rtx_queue_empty(sk) && tcp_write_queue_empty(sk); } static inline void tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb) { __skb_queue_tail(&sk->sk_write_queue, skb); /* Queue it, remembering where we must start sending. */ if (sk->sk_write_queue.next == skb) tcp_chrono_start(sk, TCP_CHRONO_BUSY); } /* Insert new before skb on the write queue of sk. */ static inline void tcp_insert_write_queue_before(struct sk_buff *new, struct sk_buff *skb, struct sock *sk) { __skb_queue_before(&sk->sk_write_queue, skb, new); } static inline void tcp_unlink_write_queue(struct sk_buff *skb, struct sock *sk) { tcp_skb_tsorted_anchor_cleanup(skb); __skb_unlink(skb, &sk->sk_write_queue); } void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb); static inline void tcp_rtx_queue_unlink(struct sk_buff *skb, struct sock *sk) { tcp_skb_tsorted_anchor_cleanup(skb); rb_erase(&skb->rbnode, &sk->tcp_rtx_queue); } static inline void tcp_rtx_queue_unlink_and_free(struct sk_buff *skb, struct sock *sk) { list_del(&skb->tcp_tsorted_anchor); tcp_rtx_queue_unlink(skb, sk); tcp_wmem_free_skb(sk, skb); } static inline void tcp_push_pending_frames(struct sock *sk) { if (tcp_send_head(sk)) { struct tcp_sock *tp = tcp_sk(sk); __tcp_push_pending_frames(sk, tcp_current_mss(sk), tp->nonagle); } } /* Start sequence of the skb just after the highest skb with SACKed * bit, valid only if sacked_out > 0 or when the caller has ensured * validity by itself. */ static inline u32 tcp_highest_sack_seq(struct tcp_sock *tp) { if (!tp->sacked_out) return tp->snd_una; if (tp->highest_sack == NULL) return tp->snd_nxt; return TCP_SKB_CB(tp->highest_sack)->seq; } static inline void tcp_advance_highest_sack(struct sock *sk, struct sk_buff *skb) { tcp_sk(sk)->highest_sack = skb_rb_next(skb); } static inline struct sk_buff *tcp_highest_sack(struct sock *sk) { return tcp_sk(sk)->highest_sack; } static inline void tcp_highest_sack_reset(struct sock *sk) { tcp_sk(sk)->highest_sack = tcp_rtx_queue_head(sk); } /* Called when old skb is about to be deleted and replaced by new skb */ static inline void tcp_highest_sack_replace(struct sock *sk, struct sk_buff *old, struct sk_buff *new) { if (old == tcp_highest_sack(sk)) tcp_sk(sk)->highest_sack = new; } /* This helper checks if socket has IP_TRANSPARENT set */ static inline bool inet_sk_transparent(const struct sock *sk) { switch (sk->sk_state) { case TCP_TIME_WAIT: return inet_twsk(sk)->tw_transparent; case TCP_NEW_SYN_RECV: return inet_rsk(inet_reqsk(sk))->no_srccheck; } return inet_sk(sk)->transparent; } /* Determines whether this is a thin stream (which may suffer from * increased latency). Used to trigger latency-reducing mechanisms. */ static inline bool tcp_stream_is_thin(struct tcp_sock *tp) { return tp->packets_out < 4 && !tcp_in_initial_slowstart(tp); } /* /proc */ enum tcp_seq_states { TCP_SEQ_STATE_LISTENING, TCP_SEQ_STATE_ESTABLISHED, }; void *tcp_seq_start(struct seq_file *seq, loff_t *pos); void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos); void tcp_seq_stop(struct seq_file *seq, void *v); struct tcp_seq_afinfo { sa_family_t family; }; struct tcp_iter_state { struct seq_net_private p; enum tcp_seq_states state; struct sock *syn_wait_sk; int bucket, offset, sbucket, num; loff_t last_pos; }; extern struct request_sock_ops tcp_request_sock_ops; extern struct request_sock_ops tcp6_request_sock_ops; void tcp_v4_destroy_sock(struct sock *sk); struct sk_buff *tcp_gso_segment(struct sk_buff *skb, netdev_features_t features); struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb); INDIRECT_CALLABLE_DECLARE(int tcp4_gro_complete(struct sk_buff *skb, int thoff)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)); INDIRECT_CALLABLE_DECLARE(int tcp6_gro_complete(struct sk_buff *skb, int thoff)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb)); int tcp_gro_complete(struct sk_buff *skb); void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); u32 val; val = READ_ONCE(tp->notsent_lowat); return val ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat); } bool tcp_stream_memory_free(const struct sock *sk, int wake); #ifdef CONFIG_PROC_FS int tcp4_proc_init(void); void tcp4_proc_exit(void); #endif int tcp_rtx_synack(const struct sock *sk, struct request_sock *req); int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb); /* TCP af-specific functions */ struct tcp_sock_af_ops { #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *(*md5_lookup) (const struct sock *sk, const struct sock *addr_sk); int (*calc_md5_hash)(char *location, const struct tcp_md5sig_key *md5, const struct sock *sk, const struct sk_buff *skb); int (*md5_parse)(struct sock *sk, int optname, sockptr_t optval, int optlen); #endif }; struct tcp_request_sock_ops { u16 mss_clamp; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *(*req_md5_lookup)(const struct sock *sk, const struct sock *addr_sk); int (*calc_md5_hash) (char *location, const struct tcp_md5sig_key *md5, const struct sock *sk, const struct sk_buff *skb); #endif #ifdef CONFIG_SYN_COOKIES __u32 (*cookie_init_seq)(const struct sk_buff *skb, __u16 *mss); #endif struct dst_entry *(*route_req)(const struct sock *sk, struct sk_buff *skb, struct flowi *fl, struct request_sock *req); u32 (*init_seq)(const struct sk_buff *skb); u32 (*init_ts_off)(const struct net *net, const struct sk_buff *skb); int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb); }; extern const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops; #if IS_ENABLED(CONFIG_IPV6) extern const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops; #endif #ifdef CONFIG_SYN_COOKIES static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, const struct sock *sk, struct sk_buff *skb, __u16 *mss) { tcp_synq_overflow(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT); return ops->cookie_init_seq(skb, mss); } #else static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, const struct sock *sk, struct sk_buff *skb, __u16 *mss) { return 0; } #endif int tcpv4_offload_init(void); void tcp_v4_init(void); void tcp_init(void); /* tcp_recovery.c */ void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb); void tcp_newreno_mark_lost(struct sock *sk, bool snd_una_advanced); extern s32 tcp_rack_skb_timeout(struct tcp_sock *tp, struct sk_buff *skb, u32 reo_wnd); extern bool tcp_rack_mark_lost(struct sock *sk); extern void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, u64 xmit_time); extern void tcp_rack_reo_timeout(struct sock *sk); extern void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs); /* At how many usecs into the future should the RTO fire? */ static inline s64 tcp_rto_delta_us(const struct sock *sk) { const struct sk_buff *skb = tcp_rtx_queue_head(sk); u32 rto = inet_csk(sk)->icsk_rto; if (likely(skb)) { u64 rto_time_stamp_us = tcp_skb_timestamp_us(skb) + jiffies_to_usecs(rto); return rto_time_stamp_us - tcp_sk(sk)->tcp_mstamp; } else { WARN_ONCE(1, "rtx queue emtpy: " "out:%u sacked:%u lost:%u retrans:%u " "tlp_high_seq:%u sk_state:%u ca_state:%u " "advmss:%u mss_cache:%u pmtu:%u\n", tcp_sk(sk)->packets_out, tcp_sk(sk)->sacked_out, tcp_sk(sk)->lost_out, tcp_sk(sk)->retrans_out, tcp_sk(sk)->tlp_high_seq, sk->sk_state, inet_csk(sk)->icsk_ca_state, tcp_sk(sk)->advmss, tcp_sk(sk)->mss_cache, inet_csk(sk)->icsk_pmtu_cookie); return jiffies_to_usecs(rto); } } /* * Save and compile IPv4 options, return a pointer to it */ static inline struct ip_options_rcu *tcp_v4_save_options(struct net *net, struct sk_buff *skb) { const struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt; struct ip_options_rcu *dopt = NULL; if (opt->optlen) { int opt_size = sizeof(*dopt) + opt->optlen; dopt = kmalloc(opt_size, GFP_ATOMIC); if (dopt && __ip_options_echo(net, &dopt->opt, skb, opt)) { kfree(dopt); dopt = NULL; } } return dopt; } /* locally generated TCP pure ACKs have skb->truesize == 2 * (check tcp_send_ack() in net/ipv4/tcp_output.c ) * This is much faster than dissecting the packet to find out. * (Think of GRE encapsulations, IPv4, IPv6, ...) */ static inline bool skb_is_tcp_pure_ack(const struct sk_buff *skb) { return skb->truesize == 2; } static inline void skb_set_tcp_pure_ack(struct sk_buff *skb) { skb->truesize = 2; } static inline int tcp_inq(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); int answ; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { answ = 0; } else if (sock_flag(sk, SOCK_URGINLINE) || !tp->urg_data || before(tp->urg_seq, tp->copied_seq) || !before(tp->urg_seq, tp->rcv_nxt)) { answ = tp->rcv_nxt - tp->copied_seq; /* Subtract 1, if FIN was received */ if (answ && sock_flag(sk, SOCK_DONE)) answ--; } else { answ = tp->urg_seq - tp->copied_seq; } return answ; } int tcp_peek_len(struct socket *sock); static inline void tcp_segs_in(struct tcp_sock *tp, const struct sk_buff *skb) { u16 segs_in; segs_in = max_t(u16, 1, skb_shinfo(skb)->gso_segs); /* We update these fields while other threads might * read them from tcp_get_info() */ WRITE_ONCE(tp->segs_in, tp->segs_in + segs_in); if (skb->len > tcp_hdrlen(skb)) WRITE_ONCE(tp->data_segs_in, tp->data_segs_in + segs_in); } /* * TCP listen path runs lockless. * We forced "struct sock" to be const qualified to make sure * we don't modify one of its field by mistake. * Here, we increment sk_drops which is an atomic_t, so we can safely * make sock writable again. */ static inline void tcp_listendrop(const struct sock *sk) { atomic_inc(&((struct sock *)sk)->sk_drops); __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS); } enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer); /* * Interface for adding Upper Level Protocols over TCP */ #define TCP_ULP_NAME_MAX 16 #define TCP_ULP_MAX 128 #define TCP_ULP_BUF_MAX (TCP_ULP_NAME_MAX*TCP_ULP_MAX) struct tcp_ulp_ops { struct list_head list; /* initialize ulp */ int (*init)(struct sock *sk); /* update ulp */ void (*update)(struct sock *sk, struct proto *p, void (*write_space)(struct sock *sk)); /* cleanup ulp */ void (*release)(struct sock *sk); /* diagnostic */ int (*get_info)(const struct sock *sk, struct sk_buff *skb); size_t (*get_info_size)(const struct sock *sk); /* clone ulp */ void (*clone)(const struct request_sock *req, struct sock *newsk, const gfp_t priority); char name[TCP_ULP_NAME_MAX]; struct module *owner; }; int tcp_register_ulp(struct tcp_ulp_ops *type); void tcp_unregister_ulp(struct tcp_ulp_ops *type); int tcp_set_ulp(struct sock *sk, const char *name); void tcp_get_available_ulp(char *buf, size_t len); void tcp_cleanup_ulp(struct sock *sk); void tcp_update_ulp(struct sock *sk, struct proto *p, void (*write_space)(struct sock *sk)); #define MODULE_ALIAS_TCP_ULP(name) \ __MODULE_INFO(alias, alias_userspace, name); \ __MODULE_INFO(alias, alias_tcp_ulp, "tcp-ulp-" name) #ifdef CONFIG_NET_SOCK_MSG struct sk_msg; struct sk_psock; #ifdef CONFIG_BPF_SYSCALL struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock); int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); void tcp_bpf_clone(const struct sock *sk, struct sock *newsk); #endif /* CONFIG_BPF_SYSCALL */ #ifdef CONFIG_INET void tcp_eat_skb(struct sock *sk, struct sk_buff *skb); #else static inline void tcp_eat_skb(struct sock *sk, struct sk_buff *skb) { } #endif int tcp_bpf_sendmsg_redir(struct sock *sk, bool ingress, struct sk_msg *msg, u32 bytes, int flags); #endif /* CONFIG_NET_SOCK_MSG */ #if !defined(CONFIG_BPF_SYSCALL) || !defined(CONFIG_NET_SOCK_MSG) static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) { } #endif #ifdef CONFIG_CGROUP_BPF static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, struct sk_buff *skb, unsigned int end_offset) { skops->skb = skb; skops->skb_data_end = skb->data + end_offset; } #else static inline void bpf_skops_init_skb(struct bpf_sock_ops_kern *skops, struct sk_buff *skb, unsigned int end_offset) { } #endif /* Call BPF_SOCK_OPS program that returns an int. If the return value * is < 0, then the BPF op failed (for example if the loaded BPF * program does not support the chosen operation or there is no BPF * program loaded). */ #ifdef CONFIG_BPF static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args) { struct bpf_sock_ops_kern sock_ops; int ret; memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); if (sk_fullsock(sk)) { sock_ops.is_fullsock = 1; sock_owned_by_me(sk); } sock_ops.sk = sk; sock_ops.op = op; if (nargs > 0) memcpy(sock_ops.args, args, nargs * sizeof(*args)); ret = BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops); if (ret == 0) ret = sock_ops.reply; else ret = -1; return ret; } static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2) { u32 args[2] = {arg1, arg2}; return tcp_call_bpf(sk, op, 2, args); } static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2, u32 arg3) { u32 args[3] = {arg1, arg2, arg3}; return tcp_call_bpf(sk, op, 3, args); } #else static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args) { return -EPERM; } static inline int tcp_call_bpf_2arg(struct sock *sk, int op, u32 arg1, u32 arg2) { return -EPERM; } static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2, u32 arg3) { return -EPERM; } #endif static inline u32 tcp_timeout_init(struct sock *sk) { int timeout; timeout = tcp_call_bpf(sk, BPF_SOCK_OPS_TIMEOUT_INIT, 0, NULL); if (timeout <= 0) timeout = TCP_TIMEOUT_INIT; return min_t(int, timeout, TCP_RTO_MAX); } static inline u32 tcp_rwnd_init_bpf(struct sock *sk) { int rwnd; rwnd = tcp_call_bpf(sk, BPF_SOCK_OPS_RWND_INIT, 0, NULL); if (rwnd < 0) rwnd = 0; return rwnd; } static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk) { return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN, 0, NULL) == 1); } static inline void tcp_bpf_rtt(struct sock *sk) { if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_RTT_CB_FLAG)) tcp_call_bpf(sk, BPF_SOCK_OPS_RTT_CB, 0, NULL); } #if IS_ENABLED(CONFIG_SMC) extern struct static_key_false tcp_have_smc; #endif #if IS_ENABLED(CONFIG_TLS_DEVICE) void clean_acked_data_enable(struct inet_connection_sock *icsk, void (*cad)(struct sock *sk, u32 ack_seq)); void clean_acked_data_disable(struct inet_connection_sock *icsk); void clean_acked_data_flush(void); #endif DECLARE_STATIC_KEY_FALSE(tcp_tx_delay_enabled); static inline void tcp_add_tx_delay(struct sk_buff *skb, const struct tcp_sock *tp) { if (static_branch_unlikely(&tcp_tx_delay_enabled)) skb->skb_mstamp_ns += (u64)tp->tcp_tx_delay * NSEC_PER_USEC; } /* Compute Earliest Departure Time for some control packets * like ACK or RST for TIME_WAIT or non ESTABLISHED sockets. */ static inline u64 tcp_transmit_time(const struct sock *sk) { if (static_branch_unlikely(&tcp_tx_delay_enabled)) { u32 delay = (sk->sk_state == TCP_TIME_WAIT) ? tcp_twsk(sk)->tw_tx_delay : tcp_sk(sk)->tcp_tx_delay; return tcp_clock_ns() + (u64)delay * NSEC_PER_USEC; } return 0; } #endif /* _TCP_H */ |
| 1625 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 | // SPDX-License-Identifier: GPL-2.0 /* * USB-ACPI glue code * * Copyright 2012 Red Hat <mjg@redhat.com> */ #include <linux/module.h> #include <linux/usb.h> #include <linux/device.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/acpi.h> #include <linux/pci.h> #include <linux/usb/hcd.h> #include "hub.h" /** * usb_acpi_power_manageable - check whether usb port has * acpi power resource. * @hdev: USB device belonging to the usb hub * @index: port index based zero * * Return true if the port has acpi power resource and false if no. */ bool usb_acpi_power_manageable(struct usb_device *hdev, int index) { acpi_handle port_handle; int port1 = index + 1; port_handle = usb_get_hub_port_acpi_handle(hdev, port1); if (port_handle) return acpi_bus_power_manageable(port_handle); else return false; } EXPORT_SYMBOL_GPL(usb_acpi_power_manageable); #define UUID_USB_CONTROLLER_DSM "ce2ee385-00e6-48cb-9f05-2edb927c4899" #define USB_DSM_DISABLE_U1_U2_FOR_PORT 5 /** * usb_acpi_port_lpm_incapable - check if lpm should be disabled for a port. * @hdev: USB device belonging to the usb hub * @index: zero based port index * * Some USB3 ports may not support USB3 link power management U1/U2 states * due to different retimer setup. ACPI provides _DSM method which returns 0x01 * if U1 and U2 states should be disabled. Evaluate _DSM with: * Arg0: UUID = ce2ee385-00e6-48cb-9f05-2edb927c4899 * Arg1: Revision ID = 0 * Arg2: Function Index = 5 * Arg3: (empty) * * Return 1 if USB3 port is LPM incapable, negative on error, otherwise 0 */ int usb_acpi_port_lpm_incapable(struct usb_device *hdev, int index) { union acpi_object *obj; acpi_handle port_handle; int port1 = index + 1; guid_t guid; int ret; ret = guid_parse(UUID_USB_CONTROLLER_DSM, &guid); if (ret) return ret; port_handle = usb_get_hub_port_acpi_handle(hdev, port1); if (!port_handle) { dev_dbg(&hdev->dev, "port-%d no acpi handle\n", port1); return -ENODEV; } if (!acpi_check_dsm(port_handle, &guid, 0, BIT(USB_DSM_DISABLE_U1_U2_FOR_PORT))) { dev_dbg(&hdev->dev, "port-%d no _DSM function %d\n", port1, USB_DSM_DISABLE_U1_U2_FOR_PORT); return -ENODEV; } obj = acpi_evaluate_dsm(port_handle, &guid, 0, USB_DSM_DISABLE_U1_U2_FOR_PORT, NULL); if (!obj) return -ENODEV; if (obj->type != ACPI_TYPE_INTEGER) { dev_dbg(&hdev->dev, "evaluate port-%d _DSM failed\n", port1); ACPI_FREE(obj); return -EINVAL; } if (obj->integer.value == 0x01) ret = 1; ACPI_FREE(obj); return ret; } EXPORT_SYMBOL_GPL(usb_acpi_port_lpm_incapable); /** * usb_acpi_set_power_state - control usb port's power via acpi power * resource * @hdev: USB device belonging to the usb hub * @index: port index based zero * @enable: power state expected to be set * * Notice to use usb_acpi_power_manageable() to check whether the usb port * has acpi power resource before invoking this function. * * Returns 0 on success, else negative errno. */ int usb_acpi_set_power_state(struct usb_device *hdev, int index, bool enable) { struct usb_hub *hub = usb_hub_to_struct_hub(hdev); struct usb_port *port_dev; acpi_handle port_handle; unsigned char state; int port1 = index + 1; int error = -EINVAL; if (!hub) return -ENODEV; port_dev = hub->ports[port1 - 1]; port_handle = (acpi_handle) usb_get_hub_port_acpi_handle(hdev, port1); if (!port_handle) return error; if (enable) state = ACPI_STATE_D0; else state = ACPI_STATE_D3_COLD; error = acpi_bus_set_power(port_handle, state); if (!error) dev_dbg(&port_dev->dev, "acpi: power was set to %d\n", enable); else dev_dbg(&port_dev->dev, "acpi: power failed to be set\n"); return error; } EXPORT_SYMBOL_GPL(usb_acpi_set_power_state); static enum usb_port_connect_type usb_acpi_get_connect_type(acpi_handle handle, struct acpi_pld_info *pld) { enum usb_port_connect_type connect_type = USB_PORT_CONNECT_TYPE_UNKNOWN; struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; union acpi_object *upc = NULL; acpi_status status; /* * According to 9.14 in ACPI Spec 6.2. _PLD indicates whether usb port * is user visible and _UPC indicates whether it is connectable. If * the port was visible and connectable, it could be freely connected * and disconnected with USB devices. If no visible and connectable, * a usb device is directly hard-wired to the port. If no visible and * no connectable, the port would be not used. */ status = acpi_evaluate_object(handle, "_UPC", NULL, &buffer); if (ACPI_FAILURE(status)) goto out; upc = buffer.pointer; if (!upc || (upc->type != ACPI_TYPE_PACKAGE) || upc->package.count != 4) goto out; if (upc->package.elements[0].integer.value) if (pld->user_visible) connect_type = USB_PORT_CONNECT_TYPE_HOT_PLUG; else connect_type = USB_PORT_CONNECT_TYPE_HARD_WIRED; else if (!pld->user_visible) connect_type = USB_PORT_NOT_USED; out: kfree(upc); return connect_type; } /* * Private to usb-acpi, all the core needs to know is that * port_dev->location is non-zero when it has been set by the firmware. */ #define USB_ACPI_LOCATION_VALID (1 << 31) static struct acpi_device * usb_acpi_get_companion_for_port(struct usb_port *port_dev) { struct usb_device *udev; struct acpi_device *adev; acpi_handle *parent_handle; int port1; /* Get the struct usb_device point of port's hub */ udev = to_usb_device(port_dev->dev.parent->parent); /* * The root hub ports' parent is the root hub. The non-root-hub * ports' parent is the parent hub port which the hub is * connected to. */ if (!udev->parent) { adev = ACPI_COMPANION(&udev->dev); port1 = usb_hcd_find_raw_port_number(bus_to_hcd(udev->bus), port_dev->portnum); } else { parent_handle = usb_get_hub_port_acpi_handle(udev->parent, udev->portnum); if (!parent_handle) return NULL; adev = acpi_fetch_acpi_dev(parent_handle); port1 = port_dev->portnum; } return acpi_find_child_by_adr(adev, port1); } static struct acpi_device * usb_acpi_find_companion_for_port(struct usb_port *port_dev) { struct acpi_device *adev; struct acpi_pld_info *pld; acpi_handle *handle; acpi_status status; adev = usb_acpi_get_companion_for_port(port_dev); if (!adev) return NULL; handle = adev->handle; status = acpi_get_physical_device_location(handle, &pld); if (ACPI_SUCCESS(status) && pld) { port_dev->location = USB_ACPI_LOCATION_VALID | pld->group_token << 8 | pld->group_position; port_dev->connect_type = usb_acpi_get_connect_type(handle, pld); ACPI_FREE(pld); } return adev; } static struct acpi_device * usb_acpi_find_companion_for_device(struct usb_device *udev) { struct acpi_device *adev; struct usb_port *port_dev; struct usb_hub *hub; if (!udev->parent) { /* * root hub is only child (_ADR=0) under its parent, the HC. * sysdev pointer is the HC as seen from firmware. */ adev = ACPI_COMPANION(udev->bus->sysdev); return acpi_find_child_device(adev, 0, false); } hub = usb_hub_to_struct_hub(udev->parent); if (!hub) return NULL; /* * This is an embedded USB device connected to a port and such * devices share port's ACPI companion. */ port_dev = hub->ports[udev->portnum - 1]; return usb_acpi_get_companion_for_port(port_dev); } static struct acpi_device *usb_acpi_find_companion(struct device *dev) { /* * The USB hierarchy like following: * * Device (EHC1) * Device (HUBN) * Device (PR01) * Device (PR11) * Device (PR12) * Device (FN12) * Device (FN13) * Device (PR13) * ... * where HUBN is root hub, and PRNN are USB ports and devices * connected to them, and FNNN are individualk functions for * connected composite USB devices. PRNN and FNNN may contain * _CRS and other methods describing sideband resources for * the connected device. * * On the kernel side both root hub and embedded USB devices are * represented as instances of usb_device structure, and ports * are represented as usb_port structures, so the whole process * is split into 2 parts: finding companions for devices and * finding companions for ports. * * Note that we do not handle individual functions of composite * devices yet, for that we would need to assign companions to * devices corresponding to USB interfaces. */ if (is_usb_device(dev)) return usb_acpi_find_companion_for_device(to_usb_device(dev)); else if (is_usb_port(dev)) return usb_acpi_find_companion_for_port(to_usb_port(dev)); return NULL; } static bool usb_acpi_bus_match(struct device *dev) { return is_usb_device(dev) || is_usb_port(dev); } static struct acpi_bus_type usb_acpi_bus = { .name = "USB", .match = usb_acpi_bus_match, .find_companion = usb_acpi_find_companion, }; int usb_acpi_register(void) { return register_acpi_bus_type(&usb_acpi_bus); } void usb_acpi_unregister(void) { unregister_acpi_bus_type(&usb_acpi_bus); } |
| 395 647 2304 3540 808 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PID_H #define _LINUX_PID_H #include <linux/rculist.h> #include <linux/wait.h> #include <linux/refcount.h> enum pid_type { PIDTYPE_PID, PIDTYPE_TGID, PIDTYPE_PGID, PIDTYPE_SID, PIDTYPE_MAX, }; /* * What is struct pid? * * A struct pid is the kernel's internal notion of a process identifier. * It refers to individual tasks, process groups, and sessions. While * there are processes attached to it the struct pid lives in a hash * table, so it and then the processes that it refers to can be found * quickly from the numeric pid value. The attached processes may be * quickly accessed by following pointers from struct pid. * * Storing pid_t values in the kernel and referring to them later has a * problem. The process originally with that pid may have exited and the * pid allocator wrapped, and another process could have come along * and been assigned that pid. * * Referring to user space processes by holding a reference to struct * task_struct has a problem. When the user space process exits * the now useless task_struct is still kept. A task_struct plus a * stack consumes around 10K of low kernel memory. More precisely * this is THREAD_SIZE + sizeof(struct task_struct). By comparison * a struct pid is about 64 bytes. * * Holding a reference to struct pid solves both of these problems. * It is small so holding a reference does not consume a lot of * resources, and since a new struct pid is allocated when the numeric pid * value is reused (when pids wrap around) we don't mistakenly refer to new * processes. */ /* * struct upid is used to get the id of the struct pid, as it is * seen in particular namespace. Later the struct pid is found with * find_pid_ns() using the int nr and struct pid_namespace *ns. */ struct upid { int nr; struct pid_namespace *ns; }; struct pid { refcount_t count; unsigned int level; spinlock_t lock; /* lists of tasks that use this pid */ struct hlist_head tasks[PIDTYPE_MAX]; struct hlist_head inodes; /* wait queue for pidfd notifications */ wait_queue_head_t wait_pidfd; struct rcu_head rcu; struct upid numbers[1]; }; extern struct pid init_struct_pid; extern const struct file_operations pidfd_fops; struct file; extern struct pid *pidfd_pid(const struct file *file); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags); struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags); int pidfd_create(struct pid *pid, unsigned int flags); static inline struct pid *get_pid(struct pid *pid) { if (pid) refcount_inc(&pid->count); return pid; } extern void put_pid(struct pid *pid); extern struct task_struct *pid_task(struct pid *pid, enum pid_type); static inline bool pid_has_task(struct pid *pid, enum pid_type type) { return !hlist_empty(&pid->tasks[type]); } extern struct task_struct *get_pid_task(struct pid *pid, enum pid_type); extern struct pid *get_task_pid(struct task_struct *task, enum pid_type type); /* * these helpers must be called with the tasklist_lock write-held. */ extern void attach_pid(struct task_struct *task, enum pid_type); extern void detach_pid(struct task_struct *task, enum pid_type); extern void change_pid(struct task_struct *task, enum pid_type, struct pid *pid); extern void exchange_tids(struct task_struct *task, struct task_struct *old); extern void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type); struct pid_namespace; extern struct pid_namespace init_pid_ns; extern int pid_max; extern int pid_max_min, pid_max_max; /* * look up a PID in the hash table. Must be called with the tasklist_lock * or rcu_read_lock() held. * * find_pid_ns() finds the pid in the namespace specified * find_vpid() finds the pid by its virtual id, i.e. in the current namespace * * see also find_task_by_vpid() set in include/linux/sched.h */ extern struct pid *find_pid_ns(int nr, struct pid_namespace *ns); extern struct pid *find_vpid(int nr); /* * Lookup a PID in the hash table, and return with it's count elevated. */ extern struct pid *find_get_pid(int nr); extern struct pid *find_ge_pid(int nr, struct pid_namespace *); extern struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, size_t set_tid_size); extern void free_pid(struct pid *pid); extern void disable_pid_allocation(struct pid_namespace *ns); /* * ns_of_pid() returns the pid namespace in which the specified pid was * allocated. * * NOTE: * ns_of_pid() is expected to be called for a process (task) that has * an attached 'struct pid' (see attach_pid(), detach_pid()) i.e @pid * is expected to be non-NULL. If @pid is NULL, caller should handle * the resulting NULL pid-ns. */ static inline struct pid_namespace *ns_of_pid(struct pid *pid) { struct pid_namespace *ns = NULL; if (pid) ns = pid->numbers[pid->level].ns; return ns; } /* * is_child_reaper returns true if the pid is the init process * of the current namespace. As this one could be checked before * pid_ns->child_reaper is assigned in copy_process, we check * with the pid number. */ static inline bool is_child_reaper(struct pid *pid) { return pid->numbers[pid->level].nr == 1; } /* * the helpers to get the pid's id seen from different namespaces * * pid_nr() : global id, i.e. the id seen from the init namespace; * pid_vnr() : virtual id, i.e. the id seen from the pid namespace of * current. * pid_nr_ns() : id seen from the ns specified. * * see also task_xid_nr() etc in include/linux/sched.h */ static inline pid_t pid_nr(struct pid *pid) { pid_t nr = 0; if (pid) nr = pid->numbers[0].nr; return nr; } pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns); pid_t pid_vnr(struct pid *pid); #define do_each_pid_task(pid, type, task) \ do { \ if ((pid) != NULL) \ hlist_for_each_entry_rcu((task), \ &(pid)->tasks[type], pid_links[type]) { /* * Both old and new leaders may be attached to * the same pid in the middle of de_thread(). */ #define while_each_pid_task(pid, type, task) \ if (type == PIDTYPE_PID) \ break; \ } \ } while (0) #define do_each_pid_thread(pid, type, task) \ do_each_pid_task(pid, type, task) { \ struct task_struct *tg___ = task; \ for_each_thread(tg___, task) { #define while_each_pid_thread(pid, type, task) \ } \ task = tg___; \ } while_each_pid_task(pid, type, task) #endif /* _LINUX_PID_H */ |
| 245 5245 732 274 5297 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PERCPU_RWSEM_H #define _LINUX_PERCPU_RWSEM_H #include <linux/atomic.h> #include <linux/percpu.h> #include <linux/rcuwait.h> #include <linux/wait.h> #include <linux/rcu_sync.h> #include <linux/lockdep.h> void _trace_android_vh_record_pcpu_rwsem_starttime( struct task_struct *tsk, unsigned long settime); struct percpu_rw_semaphore { struct rcu_sync rss; unsigned int __percpu *read_count; struct rcuwait writer; wait_queue_head_t waiters; atomic_t block; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif }; void _trace_android_vh_record_pcpu_rwsem_time_early( unsigned long settime, struct percpu_rw_semaphore *sem); #ifdef CONFIG_DEBUG_LOCK_ALLOC #define __PERCPU_RWSEM_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname }, #else #define __PERCPU_RWSEM_DEP_MAP_INIT(lockname) #endif #define __DEFINE_PERCPU_RWSEM(name, is_static) \ static DEFINE_PER_CPU(unsigned int, __percpu_rwsem_rc_##name); \ is_static struct percpu_rw_semaphore name = { \ .rss = __RCU_SYNC_INITIALIZER(name.rss), \ .read_count = &__percpu_rwsem_rc_##name, \ .writer = __RCUWAIT_INITIALIZER(name.writer), \ .waiters = __WAIT_QUEUE_HEAD_INITIALIZER(name.waiters), \ .block = ATOMIC_INIT(0), \ __PERCPU_RWSEM_DEP_MAP_INIT(name) \ } #define DEFINE_PERCPU_RWSEM(name) \ __DEFINE_PERCPU_RWSEM(name, /* not static */) #define DEFINE_STATIC_PERCPU_RWSEM(name) \ __DEFINE_PERCPU_RWSEM(name, static) extern bool __percpu_down_read(struct percpu_rw_semaphore *, bool); static inline void percpu_down_read(struct percpu_rw_semaphore *sem) { might_sleep(); rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_); preempt_disable(); _trace_android_vh_record_pcpu_rwsem_time_early(jiffies, sem); /* * We are in an RCU-sched read-side critical section, so the writer * cannot both change sem->state from readers_fast and start checking * counters while we are here. So if we see !sem->state, we know that * the writer won't be checking until we're past the preempt_enable() * and that once the synchronize_rcu() is done, the writer will see * anything we did within this RCU-sched read-size critical section. */ if (likely(rcu_sync_is_idle(&sem->rss))) this_cpu_inc(*sem->read_count); else __percpu_down_read(sem, false); /* Unconditional memory barrier */ /* * The preempt_enable() prevents the compiler from * bleeding the critical section out. */ preempt_enable(); _trace_android_vh_record_pcpu_rwsem_starttime(current, jiffies); } static inline bool percpu_down_read_trylock(struct percpu_rw_semaphore *sem) { bool ret = true; preempt_disable(); /* * Same as in percpu_down_read(). */ if (likely(rcu_sync_is_idle(&sem->rss))) this_cpu_inc(*sem->read_count); else ret = __percpu_down_read(sem, true); /* Unconditional memory barrier */ preempt_enable(); /* * The barrier() from preempt_enable() prevents the compiler from * bleeding the critical section out. */ if (ret) { _trace_android_vh_record_pcpu_rwsem_time_early(jiffies, sem); _trace_android_vh_record_pcpu_rwsem_starttime(current, jiffies); rwsem_acquire_read(&sem->dep_map, 0, 1, _RET_IP_); } return ret; } static inline void percpu_up_read(struct percpu_rw_semaphore *sem) { rwsem_release(&sem->dep_map, _RET_IP_); preempt_disable(); /* * Same as in percpu_down_read(). */ if (likely(rcu_sync_is_idle(&sem->rss))) { this_cpu_dec(*sem->read_count); } else { /* * slowpath; reader will only ever wake a single blocked * writer. */ smp_mb(); /* B matches C */ /* * In other words, if they see our decrement (presumably to * aggregate zero, as that is the only time it matters) they * will also see our critical section. */ this_cpu_dec(*sem->read_count); rcuwait_wake_up(&sem->writer); } _trace_android_vh_record_pcpu_rwsem_time_early(0, sem); _trace_android_vh_record_pcpu_rwsem_starttime(current, 0); preempt_enable(); } extern bool percpu_is_read_locked(struct percpu_rw_semaphore *); extern void percpu_down_write(struct percpu_rw_semaphore *); extern void percpu_up_write(struct percpu_rw_semaphore *); static inline bool percpu_is_write_locked(struct percpu_rw_semaphore *sem) { return atomic_read(&sem->block); } extern int __percpu_init_rwsem(struct percpu_rw_semaphore *, const char *, struct lock_class_key *); extern void percpu_free_rwsem(struct percpu_rw_semaphore *); #define percpu_init_rwsem(sem) \ ({ \ static struct lock_class_key rwsem_key; \ __percpu_init_rwsem(sem, #sem, &rwsem_key); \ }) #define percpu_rwsem_is_held(sem) lockdep_is_held(sem) #define percpu_rwsem_assert_held(sem) lockdep_assert_held(sem) static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem, bool read, unsigned long ip) { lock_release(&sem->dep_map, ip); } static inline void percpu_rwsem_acquire(struct percpu_rw_semaphore *sem, bool read, unsigned long ip) { lock_acquire(&sem->dep_map, 0, 1, read, 1, NULL, ip); } #endif |
| 34 34 33 34 34 2 34 1019 1019 1017 647 1 640 640 640 640 640 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Pseudo-driver for the loopback interface. * * Version: @(#)loopback.c 1.0.4b 08/16/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Donald Becker, <becker@scyld.com> * * Alan Cox : Fixed oddments for NET3.014 * Alan Cox : Rejig for NET3.029 snap #3 * Alan Cox : Fixed NET3.029 bugs and sped up * Larry McVoy : Tiny tweak to double performance * Alan Cox : Backed out LMV's tweak - the linux mm * can't take it... * Michael Griffith: Don't bother computing the checksums * on packets received on the loopback * interface. * Alexey Kuznetsov: Potential hang under some extreme * cases removed. */ #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/fs.h> #include <linux/types.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/errno.h> #include <linux/fcntl.h> #include <linux/in.h> #include <linux/uaccess.h> #include <linux/io.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/skbuff.h> #include <linux/ethtool.h> #include <net/sch_generic.h> #include <net/sock.h> #include <net/checksum.h> #include <linux/if_ether.h> /* For the statistics structure. */ #include <linux/if_arp.h> /* For ARPHRD_ETHER */ #include <linux/ip.h> #include <linux/tcp.h> #include <linux/percpu.h> #include <linux/net_tstamp.h> #include <net/net_namespace.h> #include <linux/u64_stats_sync.h> /* blackhole_netdev - a device used for dsts that are marked expired! * This is global device (instead of per-net-ns) since it's not needed * to be per-ns and gets initialized at boot time. */ struct net_device *blackhole_netdev; EXPORT_SYMBOL(blackhole_netdev); /* The higher levels take care of making this non-reentrant (it's * called with bh's disabled). */ static netdev_tx_t loopback_xmit(struct sk_buff *skb, struct net_device *dev) { int len; skb_tx_timestamp(skb); /* do not fool net_timestamp_check() with various clock bases */ skb_clear_tstamp(skb); skb_orphan(skb); /* Before queueing this packet to __netif_rx(), * make sure dst is refcounted. */ skb_dst_force(skb); skb->protocol = eth_type_trans(skb, dev); len = skb->len; if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) dev_lstats_add(dev, len); return NETDEV_TX_OK; } void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes) { int i; *packets = 0; *bytes = 0; for_each_possible_cpu(i) { const struct pcpu_lstats *lb_stats; u64 tbytes, tpackets; unsigned int start; lb_stats = per_cpu_ptr(dev->lstats, i); do { start = u64_stats_fetch_begin_irq(&lb_stats->syncp); tpackets = u64_stats_read(&lb_stats->packets); tbytes = u64_stats_read(&lb_stats->bytes); } while (u64_stats_fetch_retry_irq(&lb_stats->syncp, start)); *bytes += tbytes; *packets += tpackets; } } EXPORT_SYMBOL(dev_lstats_read); static void loopback_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { u64 packets, bytes; dev_lstats_read(dev, &packets, &bytes); stats->rx_packets = packets; stats->tx_packets = packets; stats->rx_bytes = bytes; stats->tx_bytes = bytes; } static u32 always_on(struct net_device *dev) { return 1; } static const struct ethtool_ops loopback_ethtool_ops = { .get_link = always_on, .get_ts_info = ethtool_op_get_ts_info, }; static int loopback_dev_init(struct net_device *dev) { dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); if (!dev->lstats) return -ENOMEM; return 0; } static void loopback_dev_free(struct net_device *dev) { dev_net(dev)->loopback_dev = NULL; free_percpu(dev->lstats); } static const struct net_device_ops loopback_ops = { .ndo_init = loopback_dev_init, .ndo_start_xmit = loopback_xmit, .ndo_get_stats64 = loopback_get_stats64, .ndo_set_mac_address = eth_mac_addr, }; static void gen_lo_setup(struct net_device *dev, unsigned int mtu, const struct ethtool_ops *eth_ops, const struct header_ops *hdr_ops, const struct net_device_ops *dev_ops, void (*dev_destructor)(struct net_device *dev)) { dev->mtu = mtu; dev->hard_header_len = ETH_HLEN; /* 14 */ dev->min_header_len = ETH_HLEN; /* 14 */ dev->addr_len = ETH_ALEN; /* 6 */ dev->type = ARPHRD_LOOPBACK; /* 0x0001*/ dev->flags = IFF_LOOPBACK; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE; netif_keep_dst(dev); dev->hw_features = NETIF_F_GSO_SOFTWARE; dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | NETIF_F_HW_CSUM | NETIF_F_RXCSUM | NETIF_F_SCTP_CRC | NETIF_F_HIGHDMA | NETIF_F_LLTX | NETIF_F_NETNS_LOCAL | NETIF_F_VLAN_CHALLENGED | NETIF_F_LOOPBACK; dev->ethtool_ops = eth_ops; dev->header_ops = hdr_ops; dev->netdev_ops = dev_ops; dev->needs_free_netdev = true; dev->priv_destructor = dev_destructor; netif_set_tso_max_size(dev, GSO_MAX_SIZE); } /* The loopback device is special. There is only one instance * per network namespace. */ static void loopback_setup(struct net_device *dev) { gen_lo_setup(dev, (64 * 1024), &loopback_ethtool_ops, ð_header_ops, &loopback_ops, loopback_dev_free); } /* Setup and register the loopback device. */ static __net_init int loopback_net_init(struct net *net) { struct net_device *dev; int err; err = -ENOMEM; dev = alloc_netdev(0, "lo", NET_NAME_PREDICTABLE, loopback_setup); if (!dev) goto out; dev_net_set(dev, net); err = register_netdev(dev); if (err) goto out_free_netdev; BUG_ON(dev->ifindex != LOOPBACK_IFINDEX); net->loopback_dev = dev; return 0; out_free_netdev: free_netdev(dev); out: if (net_eq(net, &init_net)) panic("loopback: Failed to register netdevice: %d\n", err); return err; } /* Registered in net/core/dev.c */ struct pernet_operations __net_initdata loopback_net_ops = { .init = loopback_net_init, }; /* blackhole netdevice */ static netdev_tx_t blackhole_netdev_xmit(struct sk_buff *skb, struct net_device *dev) { kfree_skb(skb); net_warn_ratelimited("%s(): Dropping skb.\n", __func__); return NETDEV_TX_OK; } static const struct net_device_ops blackhole_netdev_ops = { .ndo_start_xmit = blackhole_netdev_xmit, }; /* This is a dst-dummy device used specifically for invalidated * DSTs and unlike loopback, this is not per-ns. */ static void blackhole_netdev_setup(struct net_device *dev) { gen_lo_setup(dev, ETH_MIN_MTU, NULL, NULL, &blackhole_netdev_ops, NULL); } /* Setup and register the blackhole_netdev. */ static int __init blackhole_netdev_init(void) { blackhole_netdev = alloc_netdev(0, "blackhole_dev", NET_NAME_UNKNOWN, blackhole_netdev_setup); if (!blackhole_netdev) return -ENOMEM; rtnl_lock(); dev_init_scheduler(blackhole_netdev); dev_activate(blackhole_netdev); rtnl_unlock(); blackhole_netdev->flags |= IFF_UP | IFF_RUNNING; dev_net_set(blackhole_netdev, &init_net); return 0; } device_initcall(blackhole_netdev_init); |
| 104 1 41 99 99 30 99 41 17 24 24 105 74 31 98 41 41 7 34 105 105 105 105 98 105 7 7 34 34 34 63 63 27 2 63 34 34 34 34 98 96 96 1 1 1 108 86 105 34 98 34 110 6 1 105 105 41 41 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * uprobes-based tracing events * * Copyright (C) IBM Corporation, 2010-2012 * Author: Srikar Dronamraju <srikar@linux.vnet.ibm.com> */ #define pr_fmt(fmt) "trace_uprobe: " fmt #include <linux/bpf-cgroup.h> #include <linux/security.h> #include <linux/ctype.h> #include <linux/module.h> #include <linux/uaccess.h> #include <linux/uprobes.h> #include <linux/namei.h> #include <linux/string.h> #include <linux/rculist.h> #include <linux/filter.h> #include "trace_dynevent.h" #include "trace_probe.h" #include "trace_probe_tmpl.h" #define UPROBE_EVENT_SYSTEM "uprobes" struct uprobe_trace_entry_head { struct trace_entry ent; unsigned long vaddr[]; }; #define SIZEOF_TRACE_ENTRY(is_return) \ (sizeof(struct uprobe_trace_entry_head) + \ sizeof(unsigned long) * (is_return ? 2 : 1)) #define DATAOF_TRACE_ENTRY(entry, is_return) \ ((void*)(entry) + SIZEOF_TRACE_ENTRY(is_return)) static int trace_uprobe_create(const char *raw_command); static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev); static int trace_uprobe_release(struct dyn_event *ev); static bool trace_uprobe_is_busy(struct dyn_event *ev); static bool trace_uprobe_match(const char *system, const char *event, int argc, const char **argv, struct dyn_event *ev); static struct dyn_event_operations trace_uprobe_ops = { .create = trace_uprobe_create, .show = trace_uprobe_show, .is_busy = trace_uprobe_is_busy, .free = trace_uprobe_release, .match = trace_uprobe_match, }; /* * uprobe event core functions */ struct trace_uprobe { struct dyn_event devent; struct uprobe_consumer consumer; struct path path; struct inode *inode; char *filename; unsigned long offset; unsigned long ref_ctr_offset; unsigned long nhit; struct trace_probe tp; }; static bool is_trace_uprobe(struct dyn_event *ev) { return ev->ops == &trace_uprobe_ops; } static struct trace_uprobe *to_trace_uprobe(struct dyn_event *ev) { return container_of(ev, struct trace_uprobe, devent); } /** * for_each_trace_uprobe - iterate over the trace_uprobe list * @pos: the struct trace_uprobe * for each entry * @dpos: the struct dyn_event * to use as a loop cursor */ #define for_each_trace_uprobe(pos, dpos) \ for_each_dyn_event(dpos) \ if (is_trace_uprobe(dpos) && (pos = to_trace_uprobe(dpos))) static int register_uprobe_event(struct trace_uprobe *tu); static int unregister_uprobe_event(struct trace_uprobe *tu); struct uprobe_dispatch_data { struct trace_uprobe *tu; unsigned long bp_addr; }; static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs); static int uretprobe_dispatcher(struct uprobe_consumer *con, unsigned long func, struct pt_regs *regs); #ifdef CONFIG_STACK_GROWSUP static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n) { return addr - (n * sizeof(long)); } #else static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n) { return addr + (n * sizeof(long)); } #endif static unsigned long get_user_stack_nth(struct pt_regs *regs, unsigned int n) { unsigned long ret; unsigned long addr = user_stack_pointer(regs); addr = adjust_stack_addr(addr, n); if (copy_from_user(&ret, (void __force __user *) addr, sizeof(ret))) return 0; return ret; } /* * Uprobes-specific fetch functions */ static nokprobe_inline int probe_mem_read(void *dest, void *src, size_t size) { void __user *vaddr = (void __force __user *)src; return copy_from_user(dest, vaddr, size) ? -EFAULT : 0; } static nokprobe_inline int probe_mem_read_user(void *dest, void *src, size_t size) { return probe_mem_read(dest, src, size); } /* * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max * length and relative data location. */ static nokprobe_inline int fetch_store_string(unsigned long addr, void *dest, void *base) { long ret; u32 loc = *(u32 *)dest; int maxlen = get_loc_len(loc); u8 *dst = get_loc_data(dest, base); void __user *src = (void __force __user *) addr; if (unlikely(!maxlen)) return -ENOMEM; if (addr == FETCH_TOKEN_COMM) ret = strlcpy(dst, current->comm, maxlen); else ret = strncpy_from_user(dst, src, maxlen); if (ret >= 0) { if (ret == maxlen) dst[ret - 1] = '\0'; else /* * Include the terminating null byte. In this case it * was copied by strncpy_from_user but not accounted * for in ret. */ ret++; *(u32 *)dest = make_data_loc(ret, (void *)dst - base); } else *(u32 *)dest = make_data_loc(0, (void *)dst - base); return ret; } static nokprobe_inline int fetch_store_string_user(unsigned long addr, void *dest, void *base) { return fetch_store_string(addr, dest, base); } /* Return the length of string -- including null terminal byte */ static nokprobe_inline int fetch_store_strlen(unsigned long addr) { int len; void __user *vaddr = (void __force __user *) addr; if (addr == FETCH_TOKEN_COMM) len = strlen(current->comm) + 1; else len = strnlen_user(vaddr, MAX_STRING_SIZE); return (len > MAX_STRING_SIZE) ? 0 : len; } static nokprobe_inline int fetch_store_strlen_user(unsigned long addr) { return fetch_store_strlen(addr); } static unsigned long translate_user_vaddr(unsigned long file_offset) { unsigned long base_addr; struct uprobe_dispatch_data *udd; udd = (void *) current->utask->vaddr; base_addr = udd->bp_addr - udd->tu->offset; return base_addr + file_offset; } /* Note that we don't verify it, since the code does not come from user space */ static int process_fetch_insn(struct fetch_insn *code, void *rec, void *dest, void *base) { struct pt_regs *regs = rec; unsigned long val; /* 1st stage: get value from context */ switch (code->op) { case FETCH_OP_REG: val = regs_get_register(regs, code->param); break; case FETCH_OP_STACK: val = get_user_stack_nth(regs, code->param); break; case FETCH_OP_STACKP: val = user_stack_pointer(regs); break; case FETCH_OP_RETVAL: val = regs_return_value(regs); break; case FETCH_OP_IMM: val = code->immediate; break; case FETCH_OP_COMM: val = FETCH_TOKEN_COMM; break; case FETCH_OP_DATA: val = (unsigned long)code->data; break; case FETCH_OP_FOFFS: val = translate_user_vaddr(code->immediate); break; default: return -EILSEQ; } code++; return process_fetch_insn_bottom(code, val, dest, base); } NOKPROBE_SYMBOL(process_fetch_insn) static inline void init_trace_uprobe_filter(struct trace_uprobe_filter *filter) { rwlock_init(&filter->rwlock); filter->nr_systemwide = 0; INIT_LIST_HEAD(&filter->perf_events); } static inline bool uprobe_filter_is_empty(struct trace_uprobe_filter *filter) { return !filter->nr_systemwide && list_empty(&filter->perf_events); } static inline bool is_ret_probe(struct trace_uprobe *tu) { return tu->consumer.ret_handler != NULL; } static bool trace_uprobe_is_busy(struct dyn_event *ev) { struct trace_uprobe *tu = to_trace_uprobe(ev); return trace_probe_is_enabled(&tu->tp); } static bool trace_uprobe_match_command_head(struct trace_uprobe *tu, int argc, const char **argv) { char buf[MAX_ARGSTR_LEN + 1]; int len; if (!argc) return true; len = strlen(tu->filename); if (strncmp(tu->filename, argv[0], len) || argv[0][len] != ':') return false; if (tu->ref_ctr_offset == 0) snprintf(buf, sizeof(buf), "0x%0*lx", (int)(sizeof(void *) * 2), tu->offset); else snprintf(buf, sizeof(buf), "0x%0*lx(0x%lx)", (int)(sizeof(void *) * 2), tu->offset, tu->ref_ctr_offset); if (strcmp(buf, &argv[0][len + 1])) return false; argc--; argv++; return trace_probe_match_command_args(&tu->tp, argc, argv); } static bool trace_uprobe_match(const char *system, const char *event, int argc, const char **argv, struct dyn_event *ev) { struct trace_uprobe *tu = to_trace_uprobe(ev); return (event[0] == '\0' || strcmp(trace_probe_name(&tu->tp), event) == 0) && (!system || strcmp(trace_probe_group_name(&tu->tp), system) == 0) && trace_uprobe_match_command_head(tu, argc, argv); } static nokprobe_inline struct trace_uprobe * trace_uprobe_primary_from_call(struct trace_event_call *call) { struct trace_probe *tp; tp = trace_probe_primary_from_call(call); if (WARN_ON_ONCE(!tp)) return NULL; return container_of(tp, struct trace_uprobe, tp); } /* * Allocate new trace_uprobe and initialize it (including uprobes). */ static struct trace_uprobe * alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) { struct trace_uprobe *tu; int ret; tu = kzalloc(struct_size(tu, tp.args, nargs), GFP_KERNEL); if (!tu) return ERR_PTR(-ENOMEM); ret = trace_probe_init(&tu->tp, event, group, true); if (ret < 0) goto error; dyn_event_init(&tu->devent, &trace_uprobe_ops); tu->consumer.handler = uprobe_dispatcher; if (is_ret) tu->consumer.ret_handler = uretprobe_dispatcher; init_trace_uprobe_filter(tu->tp.event->filter); return tu; error: kfree(tu); return ERR_PTR(ret); } static void free_trace_uprobe(struct trace_uprobe *tu) { if (!tu) return; path_put(&tu->path); trace_probe_cleanup(&tu->tp); kfree(tu->filename); kfree(tu); } static struct trace_uprobe *find_probe_event(const char *event, const char *group) { struct dyn_event *pos; struct trace_uprobe *tu; for_each_trace_uprobe(tu, pos) if (strcmp(trace_probe_name(&tu->tp), event) == 0 && strcmp(trace_probe_group_name(&tu->tp), group) == 0) return tu; return NULL; } /* Unregister a trace_uprobe and probe_event */ static int unregister_trace_uprobe(struct trace_uprobe *tu) { int ret; if (trace_probe_has_sibling(&tu->tp)) goto unreg; /* If there's a reference to the dynamic event */ if (trace_event_dyn_busy(trace_probe_event_call(&tu->tp))) return -EBUSY; ret = unregister_uprobe_event(tu); if (ret) return ret; unreg: dyn_event_remove(&tu->devent); trace_probe_unlink(&tu->tp); free_trace_uprobe(tu); return 0; } static bool trace_uprobe_has_same_uprobe(struct trace_uprobe *orig, struct trace_uprobe *comp) { struct trace_probe_event *tpe = orig->tp.event; struct inode *comp_inode = d_real_inode(comp->path.dentry); int i; list_for_each_entry(orig, &tpe->probes, tp.list) { if (comp_inode != d_real_inode(orig->path.dentry) || comp->offset != orig->offset) continue; /* * trace_probe_compare_arg_type() ensured that nr_args and * each argument name and type are same. Let's compare comm. */ for (i = 0; i < orig->tp.nr_args; i++) { if (strcmp(orig->tp.args[i].comm, comp->tp.args[i].comm)) break; } if (i == orig->tp.nr_args) return true; } return false; } static int append_trace_uprobe(struct trace_uprobe *tu, struct trace_uprobe *to) { int ret; ret = trace_probe_compare_arg_type(&tu->tp, &to->tp); if (ret) { /* Note that argument starts index = 2 */ trace_probe_log_set_index(ret + 1); trace_probe_log_err(0, DIFF_ARG_TYPE); return -EEXIST; } if (trace_uprobe_has_same_uprobe(to, tu)) { trace_probe_log_set_index(0); trace_probe_log_err(0, SAME_PROBE); return -EEXIST; } /* Append to existing event */ ret = trace_probe_append(&tu->tp, &to->tp); if (!ret) dyn_event_add(&tu->devent, trace_probe_event_call(&tu->tp)); return ret; } /* * Uprobe with multiple reference counter is not allowed. i.e. * If inode and offset matches, reference counter offset *must* * match as well. Though, there is one exception: If user is * replacing old trace_uprobe with new one(same group/event), * then we allow same uprobe with new reference counter as far * as the new one does not conflict with any other existing * ones. */ static int validate_ref_ctr_offset(struct trace_uprobe *new) { struct dyn_event *pos; struct trace_uprobe *tmp; struct inode *new_inode = d_real_inode(new->path.dentry); for_each_trace_uprobe(tmp, pos) { if (new_inode == d_real_inode(tmp->path.dentry) && new->offset == tmp->offset && new->ref_ctr_offset != tmp->ref_ctr_offset) { pr_warn("Reference counter offset mismatch."); return -EINVAL; } } return 0; } /* Register a trace_uprobe and probe_event */ static int register_trace_uprobe(struct trace_uprobe *tu) { struct trace_uprobe *old_tu; int ret; mutex_lock(&event_mutex); ret = validate_ref_ctr_offset(tu); if (ret) goto end; /* register as an event */ old_tu = find_probe_event(trace_probe_name(&tu->tp), trace_probe_group_name(&tu->tp)); if (old_tu) { if (is_ret_probe(tu) != is_ret_probe(old_tu)) { trace_probe_log_set_index(0); trace_probe_log_err(0, DIFF_PROBE_TYPE); ret = -EEXIST; } else { ret = append_trace_uprobe(tu, old_tu); } goto end; } ret = register_uprobe_event(tu); if (ret) { if (ret == -EEXIST) { trace_probe_log_set_index(0); trace_probe_log_err(0, EVENT_EXIST); } else pr_warn("Failed to register probe event(%d)\n", ret); goto end; } dyn_event_add(&tu->devent, trace_probe_event_call(&tu->tp)); end: mutex_unlock(&event_mutex); return ret; } /* * Argument syntax: * - Add uprobe: p|r[:[GRP/][EVENT]] PATH:OFFSET[%return][(REF)] [FETCHARGS] */ static int __trace_uprobe_create(int argc, const char **argv) { struct trace_uprobe *tu; const char *event = NULL, *group = UPROBE_EVENT_SYSTEM; char *arg, *filename, *rctr, *rctr_end, *tmp; char buf[MAX_EVENT_NAME_LEN]; char gbuf[MAX_EVENT_NAME_LEN]; enum probe_print_type ptype; struct path path; unsigned long offset, ref_ctr_offset; bool is_return = false; int i, ret; ref_ctr_offset = 0; switch (argv[0][0]) { case 'r': is_return = true; break; case 'p': break; default: return -ECANCELED; } if (argc < 2) return -ECANCELED; if (argv[0][1] == ':') event = &argv[0][2]; if (!strchr(argv[1], '/')) return -ECANCELED; filename = kstrdup(argv[1], GFP_KERNEL); if (!filename) return -ENOMEM; /* Find the last occurrence, in case the path contains ':' too. */ arg = strrchr(filename, ':'); if (!arg || !isdigit(arg[1])) { kfree(filename); return -ECANCELED; } trace_probe_log_init("trace_uprobe", argc, argv); trace_probe_log_set_index(1); /* filename is the 2nd argument */ *arg++ = '\0'; ret = kern_path(filename, LOOKUP_FOLLOW, &path); if (ret) { trace_probe_log_err(0, FILE_NOT_FOUND); kfree(filename); trace_probe_log_clear(); return ret; } if (!d_is_reg(path.dentry)) { trace_probe_log_err(0, NO_REGULAR_FILE); ret = -EINVAL; goto fail_address_parse; } /* Parse reference counter offset if specified. */ rctr = strchr(arg, '('); if (rctr) { rctr_end = strchr(rctr, ')'); if (!rctr_end) { ret = -EINVAL; rctr_end = rctr + strlen(rctr); trace_probe_log_err(rctr_end - filename, REFCNT_OPEN_BRACE); goto fail_address_parse; } else if (rctr_end[1] != '\0') { ret = -EINVAL; trace_probe_log_err(rctr_end + 1 - filename, BAD_REFCNT_SUFFIX); goto fail_address_parse; } *rctr++ = '\0'; *rctr_end = '\0'; ret = kstrtoul(rctr, 0, &ref_ctr_offset); if (ret) { trace_probe_log_err(rctr - filename, BAD_REFCNT); goto fail_address_parse; } } /* Check if there is %return suffix */ tmp = strchr(arg, '%'); if (tmp) { if (!strcmp(tmp, "%return")) { *tmp = '\0'; is_return = true; } else { trace_probe_log_err(tmp - filename, BAD_ADDR_SUFFIX); ret = -EINVAL; goto fail_address_parse; } } /* Parse uprobe offset. */ ret = kstrtoul(arg, 0, &offset); if (ret) { trace_probe_log_err(arg - filename, BAD_UPROBE_OFFS); goto fail_address_parse; } /* setup a probe */ trace_probe_log_set_index(0); if (event) { ret = traceprobe_parse_event_name(&event, &group, gbuf, event - argv[0]); if (ret) goto fail_address_parse; } if (!event) { char *tail; char *ptr; tail = kstrdup(kbasename(filename), GFP_KERNEL); if (!tail) { ret = -ENOMEM; goto fail_address_parse; } ptr = strpbrk(tail, ".-_"); if (ptr) *ptr = '\0'; snprintf(buf, MAX_EVENT_NAME_LEN, "%c_%s_0x%lx", 'p', tail, offset); event = buf; kfree(tail); } argc -= 2; argv += 2; tu = alloc_trace_uprobe(group, event, argc, is_return); if (IS_ERR(tu)) { ret = PTR_ERR(tu); /* This must return -ENOMEM otherwise there is a bug */ WARN_ON_ONCE(ret != -ENOMEM); goto fail_address_parse; } tu->offset = offset; tu->ref_ctr_offset = ref_ctr_offset; tu->path = path; tu->filename = filename; /* parse arguments */ for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) { trace_probe_log_set_index(i + 2); ret = traceprobe_parse_probe_arg(&tu->tp, i, argv[i], is_return ? TPARG_FL_RETURN : 0); if (ret) goto error; } ptype = is_ret_probe(tu) ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL; ret = traceprobe_set_print_fmt(&tu->tp, ptype); if (ret < 0) goto error; ret = register_trace_uprobe(tu); if (!ret) goto out; error: free_trace_uprobe(tu); out: trace_probe_log_clear(); return ret; fail_address_parse: trace_probe_log_clear(); path_put(&path); kfree(filename); return ret; } int trace_uprobe_create(const char *raw_command) { return trace_probe_create(raw_command, __trace_uprobe_create); } static int create_or_delete_trace_uprobe(const char *raw_command) { int ret; if (raw_command[0] == '-') return dyn_event_release(raw_command, &trace_uprobe_ops); ret = trace_uprobe_create(raw_command); return ret == -ECANCELED ? -EINVAL : ret; } static int trace_uprobe_release(struct dyn_event *ev) { struct trace_uprobe *tu = to_trace_uprobe(ev); return unregister_trace_uprobe(tu); } /* Probes listing interfaces */ static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev) { struct trace_uprobe *tu = to_trace_uprobe(ev); char c = is_ret_probe(tu) ? 'r' : 'p'; int i; seq_printf(m, "%c:%s/%s %s:0x%0*lx", c, trace_probe_group_name(&tu->tp), trace_probe_name(&tu->tp), tu->filename, (int)(sizeof(void *) * 2), tu->offset); if (tu->ref_ctr_offset) seq_printf(m, "(0x%lx)", tu->ref_ctr_offset); for (i = 0; i < tu->tp.nr_args; i++) seq_printf(m, " %s=%s", tu->tp.args[i].name, tu->tp.args[i].comm); seq_putc(m, '\n'); return 0; } static int probes_seq_show(struct seq_file *m, void *v) { struct dyn_event *ev = v; if (!is_trace_uprobe(ev)) return 0; return trace_uprobe_show(m, ev); } static const struct seq_operations probes_seq_op = { .start = dyn_event_seq_start, .next = dyn_event_seq_next, .stop = dyn_event_seq_stop, .show = probes_seq_show }; static int probes_open(struct inode *inode, struct file *file) { int ret; ret = security_locked_down(LOCKDOWN_TRACEFS); if (ret) return ret; if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { ret = dyn_events_release_all(&trace_uprobe_ops); if (ret) return ret; } return seq_open(file, &probes_seq_op); } static ssize_t probes_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { return trace_parse_run_command(file, buffer, count, ppos, create_or_delete_trace_uprobe); } static const struct file_operations uprobe_events_ops = { .owner = THIS_MODULE, .open = probes_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, .write = probes_write, }; /* Probes profiling interfaces */ static int probes_profile_seq_show(struct seq_file *m, void *v) { struct dyn_event *ev = v; struct trace_uprobe *tu; if (!is_trace_uprobe(ev)) return 0; tu = to_trace_uprobe(ev); seq_printf(m, " %s %-44s %15lu\n", tu->filename, trace_probe_name(&tu->tp), tu->nhit); return 0; } static const struct seq_operations profile_seq_op = { .start = dyn_event_seq_start, .next = dyn_event_seq_next, .stop = dyn_event_seq_stop, .show = probes_profile_seq_show }; static int profile_open(struct inode *inode, struct file *file) { int ret; ret = security_locked_down(LOCKDOWN_TRACEFS); if (ret) return ret; return seq_open(file, &profile_seq_op); } static const struct file_operations uprobe_profile_ops = { .owner = THIS_MODULE, .open = profile_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; struct uprobe_cpu_buffer { struct mutex mutex; void *buf; int dsize; }; static struct uprobe_cpu_buffer __percpu *uprobe_cpu_buffer; static int uprobe_buffer_refcnt; #define MAX_UCB_BUFFER_SIZE PAGE_SIZE static int uprobe_buffer_init(void) { int cpu, err_cpu; uprobe_cpu_buffer = alloc_percpu(struct uprobe_cpu_buffer); if (uprobe_cpu_buffer == NULL) return -ENOMEM; for_each_possible_cpu(cpu) { struct page *p = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, 0); if (p == NULL) { err_cpu = cpu; goto err; } per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf = page_address(p); mutex_init(&per_cpu_ptr(uprobe_cpu_buffer, cpu)->mutex); } return 0; err: for_each_possible_cpu(cpu) { if (cpu == err_cpu) break; free_page((unsigned long)per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf); } free_percpu(uprobe_cpu_buffer); return -ENOMEM; } static int uprobe_buffer_enable(void) { int ret = 0; BUG_ON(!mutex_is_locked(&event_mutex)); if (uprobe_buffer_refcnt++ == 0) { ret = uprobe_buffer_init(); if (ret < 0) uprobe_buffer_refcnt--; } return ret; } static void uprobe_buffer_disable(void) { int cpu; BUG_ON(!mutex_is_locked(&event_mutex)); if (--uprobe_buffer_refcnt == 0) { for_each_possible_cpu(cpu) free_page((unsigned long)per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf); free_percpu(uprobe_cpu_buffer); uprobe_cpu_buffer = NULL; } } static struct uprobe_cpu_buffer *uprobe_buffer_get(void) { struct uprobe_cpu_buffer *ucb; int cpu; cpu = raw_smp_processor_id(); ucb = per_cpu_ptr(uprobe_cpu_buffer, cpu); /* * Use per-cpu buffers for fastest access, but we might migrate * so the mutex makes sure we have sole access to it. */ mutex_lock(&ucb->mutex); return ucb; } static void uprobe_buffer_put(struct uprobe_cpu_buffer *ucb) { mutex_unlock(&ucb->mutex); } static struct uprobe_cpu_buffer *prepare_uprobe_buffer(struct trace_uprobe *tu, struct pt_regs *regs) { struct uprobe_cpu_buffer *ucb; int dsize, esize; esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); dsize = __get_data_size(&tu->tp, regs); ucb = uprobe_buffer_get(); ucb->dsize = tu->tp.size + dsize; if (WARN_ON_ONCE(ucb->dsize > MAX_UCB_BUFFER_SIZE)) { ucb->dsize = MAX_UCB_BUFFER_SIZE; dsize = MAX_UCB_BUFFER_SIZE - tu->tp.size; } store_trace_args(ucb->buf, &tu->tp, regs, esize, dsize); return ucb; } static void __uprobe_trace_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, struct uprobe_cpu_buffer *ucb, struct trace_event_file *trace_file) { struct uprobe_trace_entry_head *entry; struct trace_event_buffer fbuffer; void *data; int size, esize; struct trace_event_call *call = trace_probe_event_call(&tu->tp); WARN_ON(call != trace_file->event_call); if (trace_trigger_soft_disabled(trace_file)) return; esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); size = esize + ucb->dsize; entry = trace_event_buffer_reserve(&fbuffer, trace_file, size); if (!entry) return; if (is_ret_probe(tu)) { entry->vaddr[0] = func; entry->vaddr[1] = instruction_pointer(regs); data = DATAOF_TRACE_ENTRY(entry, true); } else { entry->vaddr[0] = instruction_pointer(regs); data = DATAOF_TRACE_ENTRY(entry, false); } memcpy(data, ucb->buf, ucb->dsize); trace_event_buffer_commit(&fbuffer); } /* uprobe handler */ static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs, struct uprobe_cpu_buffer *ucb) { struct event_file_link *link; if (is_ret_probe(tu)) return 0; rcu_read_lock(); trace_probe_for_each_link_rcu(link, &tu->tp) __uprobe_trace_func(tu, 0, regs, ucb, link->file); rcu_read_unlock(); return 0; } static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, struct uprobe_cpu_buffer *ucb) { struct event_file_link *link; rcu_read_lock(); trace_probe_for_each_link_rcu(link, &tu->tp) __uprobe_trace_func(tu, func, regs, ucb, link->file); rcu_read_unlock(); } /* Event entry printers */ static enum print_line_t print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *event) { struct uprobe_trace_entry_head *entry; struct trace_seq *s = &iter->seq; struct trace_uprobe *tu; u8 *data; entry = (struct uprobe_trace_entry_head *)iter->ent; tu = trace_uprobe_primary_from_call( container_of(event, struct trace_event_call, event)); if (unlikely(!tu)) goto out; if (is_ret_probe(tu)) { trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", trace_probe_name(&tu->tp), entry->vaddr[1], entry->vaddr[0]); data = DATAOF_TRACE_ENTRY(entry, true); } else { trace_seq_printf(s, "%s: (0x%lx)", trace_probe_name(&tu->tp), entry->vaddr[0]); data = DATAOF_TRACE_ENTRY(entry, false); } if (print_probe_args(s, tu->tp.args, tu->tp.nr_args, data, entry) < 0) goto out; trace_seq_putc(s, '\n'); out: return trace_handle_return(s); } typedef bool (*filter_func_t)(struct uprobe_consumer *self, enum uprobe_filter_ctx ctx, struct mm_struct *mm); static int trace_uprobe_enable(struct trace_uprobe *tu, filter_func_t filter) { int ret; tu->consumer.filter = filter; tu->inode = d_real_inode(tu->path.dentry); if (tu->ref_ctr_offset) ret = uprobe_register_refctr(tu->inode, tu->offset, tu->ref_ctr_offset, &tu->consumer); else ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); if (ret) tu->inode = NULL; return ret; } static void __probe_event_disable(struct trace_probe *tp) { struct trace_uprobe *tu; tu = container_of(tp, struct trace_uprobe, tp); WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) { if (!tu->inode) continue; uprobe_unregister(tu->inode, tu->offset, &tu->consumer); tu->inode = NULL; } } static int probe_event_enable(struct trace_event_call *call, struct trace_event_file *file, filter_func_t filter) { struct trace_probe *tp; struct trace_uprobe *tu; bool enabled; int ret; tp = trace_probe_primary_from_call(call); if (WARN_ON_ONCE(!tp)) return -ENODEV; enabled = trace_probe_is_enabled(tp); /* This may also change "enabled" state */ if (file) { if (trace_probe_test_flag(tp, TP_FLAG_PROFILE)) return -EINTR; ret = trace_probe_add_file(tp, file); if (ret < 0) return ret; } else { if (trace_probe_test_flag(tp, TP_FLAG_TRACE)) return -EINTR; trace_probe_set_flag(tp, TP_FLAG_PROFILE); } tu = container_of(tp, struct trace_uprobe, tp); WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); if (enabled) return 0; ret = uprobe_buffer_enable(); if (ret) goto err_flags; list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) { ret = trace_uprobe_enable(tu, filter); if (ret) { __probe_event_disable(tp); goto err_buffer; } } return 0; err_buffer: uprobe_buffer_disable(); err_flags: if (file) trace_probe_remove_file(tp, file); else trace_probe_clear_flag(tp, TP_FLAG_PROFILE); return ret; } static void probe_event_disable(struct trace_event_call *call, struct trace_event_file *file) { struct trace_probe *tp; tp = trace_probe_primary_from_call(call); if (WARN_ON_ONCE(!tp)) return; if (!trace_probe_is_enabled(tp)) return; if (file) { if (trace_probe_remove_file(tp, file) < 0) return; if (trace_probe_is_enabled(tp)) return; } else trace_probe_clear_flag(tp, TP_FLAG_PROFILE); __probe_event_disable(tp); uprobe_buffer_disable(); } static int uprobe_event_define_fields(struct trace_event_call *event_call) { int ret, size; struct uprobe_trace_entry_head field; struct trace_uprobe *tu; tu = trace_uprobe_primary_from_call(event_call); if (unlikely(!tu)) return -ENODEV; if (is_ret_probe(tu)) { DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_FUNC, 0); DEFINE_FIELD(unsigned long, vaddr[1], FIELD_STRING_RETIP, 0); size = SIZEOF_TRACE_ENTRY(true); } else { DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_IP, 0); size = SIZEOF_TRACE_ENTRY(false); } return traceprobe_define_arg_fields(event_call, size, &tu->tp); } #ifdef CONFIG_PERF_EVENTS static bool __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm) { struct perf_event *event; if (filter->nr_systemwide) return true; list_for_each_entry(event, &filter->perf_events, hw.tp_list) { if (event->hw.target->mm == mm) return true; } return false; } static inline bool trace_uprobe_filter_event(struct trace_uprobe_filter *filter, struct perf_event *event) { return __uprobe_perf_filter(filter, event->hw.target->mm); } static bool trace_uprobe_filter_remove(struct trace_uprobe_filter *filter, struct perf_event *event) { bool done; write_lock(&filter->rwlock); if (event->hw.target) { list_del(&event->hw.tp_list); done = filter->nr_systemwide || (event->hw.target->flags & PF_EXITING) || trace_uprobe_filter_event(filter, event); } else { filter->nr_systemwide--; done = filter->nr_systemwide; } write_unlock(&filter->rwlock); return done; } /* This returns true if the filter always covers target mm */ static bool trace_uprobe_filter_add(struct trace_uprobe_filter *filter, struct perf_event *event) { bool done; write_lock(&filter->rwlock); if (event->hw.target) { /* * event->parent != NULL means copy_process(), we can avoid * uprobe_apply(). current->mm must be probed and we can rely * on dup_mmap() which preserves the already installed bp's. * * attr.enable_on_exec means that exec/mmap will install the * breakpoints we need. */ done = filter->nr_systemwide || event->parent || event->attr.enable_on_exec || trace_uprobe_filter_event(filter, event); list_add(&event->hw.tp_list, &filter->perf_events); } else { done = filter->nr_systemwide; filter->nr_systemwide++; } write_unlock(&filter->rwlock); return done; } static int uprobe_perf_close(struct trace_event_call *call, struct perf_event *event) { struct trace_probe *tp; struct trace_uprobe *tu; int ret = 0; tp = trace_probe_primary_from_call(call); if (WARN_ON_ONCE(!tp)) return -ENODEV; tu = container_of(tp, struct trace_uprobe, tp); if (trace_uprobe_filter_remove(tu->tp.event->filter, event)) return 0; list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) { ret = uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); if (ret) break; } return ret; } static int uprobe_perf_open(struct trace_event_call *call, struct perf_event *event) { struct trace_probe *tp; struct trace_uprobe *tu; int err = 0; tp = trace_probe_primary_from_call(call); if (WARN_ON_ONCE(!tp)) return -ENODEV; tu = container_of(tp, struct trace_uprobe, tp); if (trace_uprobe_filter_add(tu->tp.event->filter, event)) return 0; list_for_each_entry(tu, trace_probe_probe_list(tp), tp.list) { err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); if (err) { uprobe_perf_close(call, event); break; } } return err; } static bool uprobe_perf_filter(struct uprobe_consumer *uc, enum uprobe_filter_ctx ctx, struct mm_struct *mm) { struct trace_uprobe_filter *filter; struct trace_uprobe *tu; int ret; tu = container_of(uc, struct trace_uprobe, consumer); filter = tu->tp.event->filter; read_lock(&filter->rwlock); ret = __uprobe_perf_filter(filter, mm); read_unlock(&filter->rwlock); return ret; } static void __uprobe_perf_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, struct uprobe_cpu_buffer *ucb) { struct trace_event_call *call = trace_probe_event_call(&tu->tp); struct uprobe_trace_entry_head *entry; struct hlist_head *head; void *data; int size, esize; int rctx; #ifdef CONFIG_BPF_EVENTS if (bpf_prog_array_valid(call)) { u32 ret; ret = bpf_prog_run_array_sleepable(call->prog_array, regs, bpf_prog_run); if (!ret) return; } #endif /* CONFIG_BPF_EVENTS */ esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); size = esize + ucb->dsize; size = ALIGN(size + sizeof(u32), sizeof(u64)) - sizeof(u32); if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough")) return; preempt_disable(); head = this_cpu_ptr(call->perf_events); if (hlist_empty(head)) goto out; entry = perf_trace_buf_alloc(size, NULL, &rctx); if (!entry) goto out; if (is_ret_probe(tu)) { entry->vaddr[0] = func; entry->vaddr[1] = instruction_pointer(regs); data = DATAOF_TRACE_ENTRY(entry, true); } else { entry->vaddr[0] = instruction_pointer(regs); data = DATAOF_TRACE_ENTRY(entry, false); } memcpy(data, ucb->buf, ucb->dsize); if (size - esize > ucb->dsize) memset(data + ucb->dsize, 0, size - esize - ucb->dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); out: preempt_enable(); } /* uprobe profile handler */ static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs, struct uprobe_cpu_buffer *ucb) { if (!uprobe_perf_filter(&tu->consumer, 0, current->mm)) return UPROBE_HANDLER_REMOVE; if (!is_ret_probe(tu)) __uprobe_perf_func(tu, 0, regs, ucb); return 0; } static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, struct uprobe_cpu_buffer *ucb) { __uprobe_perf_func(tu, func, regs, ucb); } int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, const char **filename, u64 *probe_offset, u64 *probe_addr, bool perf_type_tracepoint) { const char *pevent = trace_event_name(event->tp_event); const char *group = event->tp_event->class->system; struct trace_uprobe *tu; if (perf_type_tracepoint) tu = find_probe_event(pevent, group); else tu = trace_uprobe_primary_from_call(event->tp_event); if (!tu) return -EINVAL; *fd_type = is_ret_probe(tu) ? BPF_FD_TYPE_URETPROBE : BPF_FD_TYPE_UPROBE; *filename = tu->filename; *probe_offset = tu->offset; *probe_addr = 0; return 0; } #endif /* CONFIG_PERF_EVENTS */ static int trace_uprobe_register(struct trace_event_call *event, enum trace_reg type, void *data) { struct trace_event_file *file = data; switch (type) { case TRACE_REG_REGISTER: return probe_event_enable(event, file, NULL); case TRACE_REG_UNREGISTER: probe_event_disable(event, file); return 0; #ifdef CONFIG_PERF_EVENTS case TRACE_REG_PERF_REGISTER: return probe_event_enable(event, NULL, uprobe_perf_filter); case TRACE_REG_PERF_UNREGISTER: probe_event_disable(event, NULL); return 0; case TRACE_REG_PERF_OPEN: return uprobe_perf_open(event, data); case TRACE_REG_PERF_CLOSE: return uprobe_perf_close(event, data); #endif default: return 0; } } static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) { struct trace_uprobe *tu; struct uprobe_dispatch_data udd; struct uprobe_cpu_buffer *ucb; int ret = 0; tu = container_of(con, struct trace_uprobe, consumer); tu->nhit++; udd.tu = tu; udd.bp_addr = instruction_pointer(regs); current->utask->vaddr = (unsigned long) &udd; if (WARN_ON_ONCE(!uprobe_cpu_buffer)) return 0; ucb = prepare_uprobe_buffer(tu, regs); if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE)) ret |= uprobe_trace_func(tu, regs, ucb); #ifdef CONFIG_PERF_EVENTS if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE)) ret |= uprobe_perf_func(tu, regs, ucb); #endif uprobe_buffer_put(ucb); return ret; } static int uretprobe_dispatcher(struct uprobe_consumer *con, unsigned long func, struct pt_regs *regs) { struct trace_uprobe *tu; struct uprobe_dispatch_data udd; struct uprobe_cpu_buffer *ucb; tu = container_of(con, struct trace_uprobe, consumer); udd.tu = tu; udd.bp_addr = func; current->utask->vaddr = (unsigned long) &udd; if (WARN_ON_ONCE(!uprobe_cpu_buffer)) return 0; ucb = prepare_uprobe_buffer(tu, regs); if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE)) uretprobe_trace_func(tu, func, regs, ucb); #ifdef CONFIG_PERF_EVENTS if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE)) uretprobe_perf_func(tu, func, regs, ucb); #endif uprobe_buffer_put(ucb); return 0; } static struct trace_event_functions uprobe_funcs = { .trace = print_uprobe_event }; static struct trace_event_fields uprobe_fields_array[] = { { .type = TRACE_FUNCTION_TYPE, .define_fields = uprobe_event_define_fields }, {} }; static inline void init_trace_event_call(struct trace_uprobe *tu) { struct trace_event_call *call = trace_probe_event_call(&tu->tp); call->event.funcs = &uprobe_funcs; call->class->fields_array = uprobe_fields_array; call->flags = TRACE_EVENT_FL_UPROBE | TRACE_EVENT_FL_CAP_ANY; call->class->reg = trace_uprobe_register; } static int register_uprobe_event(struct trace_uprobe *tu) { init_trace_event_call(tu); return trace_probe_register_event_call(&tu->tp); } static int unregister_uprobe_event(struct trace_uprobe *tu) { return trace_probe_unregister_event_call(&tu->tp); } #ifdef CONFIG_PERF_EVENTS struct trace_event_call * create_local_trace_uprobe(char *name, unsigned long offs, unsigned long ref_ctr_offset, bool is_return) { enum probe_print_type ptype; struct trace_uprobe *tu; struct path path; int ret; ret = kern_path(name, LOOKUP_FOLLOW, &path); if (ret) return ERR_PTR(ret); if (!d_is_reg(path.dentry)) { path_put(&path); return ERR_PTR(-EINVAL); } /* * local trace_kprobes are not added to dyn_event, so they are never * searched in find_trace_kprobe(). Therefore, there is no concern of * duplicated name "DUMMY_EVENT" here. */ tu = alloc_trace_uprobe(UPROBE_EVENT_SYSTEM, "DUMMY_EVENT", 0, is_return); if (IS_ERR(tu)) { pr_info("Failed to allocate trace_uprobe.(%d)\n", (int)PTR_ERR(tu)); path_put(&path); return ERR_CAST(tu); } tu->offset = offs; tu->path = path; tu->ref_ctr_offset = ref_ctr_offset; tu->filename = kstrdup(name, GFP_KERNEL); if (!tu->filename) { ret = -ENOMEM; goto error; } init_trace_event_call(tu); ptype = is_ret_probe(tu) ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL; if (traceprobe_set_print_fmt(&tu->tp, ptype) < 0) { ret = -ENOMEM; goto error; } return trace_probe_event_call(&tu->tp); error: free_trace_uprobe(tu); return ERR_PTR(ret); } void destroy_local_trace_uprobe(struct trace_event_call *event_call) { struct trace_uprobe *tu; tu = trace_uprobe_primary_from_call(event_call); free_trace_uprobe(tu); } #endif /* CONFIG_PERF_EVENTS */ /* Make a trace interface for controlling probe points */ static __init int init_uprobe_trace(void) { int ret; ret = dyn_event_register(&trace_uprobe_ops); if (ret) return ret; ret = tracing_init_dentry(); if (ret) return 0; trace_create_file("uprobe_events", TRACE_MODE_WRITE, NULL, NULL, &uprobe_events_ops); /* Profile interface */ trace_create_file("uprobe_profile", TRACE_MODE_READ, NULL, NULL, &uprobe_profile_ops); return 0; } fs_initcall(init_uprobe_trace); |
| 20 1 19 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * The IP to API glue. * * Authors: see ip.c * * Fixes: * Many : Split from ip.c , see ip.c for history. * Martin Mares : TOS setting fixed. * Alan Cox : Fixed a couple of oopses in Martin's * TOS tweaks. * Mike McLagan : Routing by source */ #include <linux/module.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/skbuff.h> #include <linux/ip.h> #include <linux/icmp.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/tcp_states.h> #include <linux/udp.h> #include <linux/igmp.h> #include <linux/netfilter.h> #include <linux/route.h> #include <linux/mroute.h> #include <net/inet_ecn.h> #include <net/route.h> #include <net/xfrm.h> #include <net/compat.h> #include <net/checksum.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/transp_v6.h> #endif #include <net/ip_fib.h> #include <linux/errqueue.h> #include <linux/uaccess.h> #include <linux/bpfilter.h> /* * SOL_IP control messages. */ static void ip_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb) { struct in_pktinfo info = *PKTINFO_SKB_CB(skb); info.ipi_addr.s_addr = ip_hdr(skb)->daddr; put_cmsg(msg, SOL_IP, IP_PKTINFO, sizeof(info), &info); } static void ip_cmsg_recv_ttl(struct msghdr *msg, struct sk_buff *skb) { int ttl = ip_hdr(skb)->ttl; put_cmsg(msg, SOL_IP, IP_TTL, sizeof(int), &ttl); } static void ip_cmsg_recv_tos(struct msghdr *msg, struct sk_buff *skb) { put_cmsg(msg, SOL_IP, IP_TOS, 1, &ip_hdr(skb)->tos); } static void ip_cmsg_recv_opts(struct msghdr *msg, struct sk_buff *skb) { if (IPCB(skb)->opt.optlen == 0) return; put_cmsg(msg, SOL_IP, IP_RECVOPTS, IPCB(skb)->opt.optlen, ip_hdr(skb) + 1); } static void ip_cmsg_recv_retopts(struct net *net, struct msghdr *msg, struct sk_buff *skb) { unsigned char optbuf[sizeof(struct ip_options) + 40]; struct ip_options *opt = (struct ip_options *)optbuf; if (IPCB(skb)->opt.optlen == 0) return; if (ip_options_echo(net, opt, skb)) { msg->msg_flags |= MSG_CTRUNC; return; } ip_options_undo(opt); put_cmsg(msg, SOL_IP, IP_RETOPTS, opt->optlen, opt->__data); } static void ip_cmsg_recv_fragsize(struct msghdr *msg, struct sk_buff *skb) { int val; if (IPCB(skb)->frag_max_size == 0) return; val = IPCB(skb)->frag_max_size; put_cmsg(msg, SOL_IP, IP_RECVFRAGSIZE, sizeof(val), &val); } static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb, int tlen, int offset) { __wsum csum = skb->csum; if (skb->ip_summed != CHECKSUM_COMPLETE) return; if (offset != 0) { int tend_off = skb_transport_offset(skb) + tlen; csum = csum_sub(csum, skb_checksum(skb, tend_off, offset, 0)); } put_cmsg(msg, SOL_IP, IP_CHECKSUM, sizeof(__wsum), &csum); } static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb) { char *secdata; u32 seclen, secid; int err; err = security_socket_getpeersec_dgram(NULL, skb, &secid); if (err) return; err = security_secid_to_secctx(secid, &secdata, &seclen); if (err) return; put_cmsg(msg, SOL_IP, SCM_SECURITY, seclen, secdata); security_release_secctx(secdata, seclen); } static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) { __be16 _ports[2], *ports; struct sockaddr_in sin; /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ ports = skb_header_pointer(skb, skb_transport_offset(skb), sizeof(_ports), &_ports); if (!ports) return; sin.sin_family = AF_INET; sin.sin_addr.s_addr = ip_hdr(skb)->daddr; sin.sin_port = ports[1]; memset(sin.sin_zero, 0, sizeof(sin.sin_zero)); put_cmsg(msg, SOL_IP, IP_ORIGDSTADDR, sizeof(sin), &sin); } void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, int tlen, int offset) { struct inet_sock *inet = inet_sk(sk); unsigned int flags = inet->cmsg_flags; /* Ordered by supposed usage frequency */ if (flags & IP_CMSG_PKTINFO) { ip_cmsg_recv_pktinfo(msg, skb); flags &= ~IP_CMSG_PKTINFO; if (!flags) return; } if (flags & IP_CMSG_TTL) { ip_cmsg_recv_ttl(msg, skb); flags &= ~IP_CMSG_TTL; if (!flags) return; } if (flags & IP_CMSG_TOS) { ip_cmsg_recv_tos(msg, skb); flags &= ~IP_CMSG_TOS; if (!flags) return; } if (flags & IP_CMSG_RECVOPTS) { ip_cmsg_recv_opts(msg, skb); flags &= ~IP_CMSG_RECVOPTS; if (!flags) return; } if (flags & IP_CMSG_RETOPTS) { ip_cmsg_recv_retopts(sock_net(sk), msg, skb); flags &= ~IP_CMSG_RETOPTS; if (!flags) return; } if (flags & IP_CMSG_PASSSEC) { ip_cmsg_recv_security(msg, skb); flags &= ~IP_CMSG_PASSSEC; if (!flags) return; } if (flags & IP_CMSG_ORIGDSTADDR) { ip_cmsg_recv_dstaddr(msg, skb); flags &= ~IP_CMSG_ORIGDSTADDR; if (!flags) return; } if (flags & IP_CMSG_CHECKSUM) ip_cmsg_recv_checksum(msg, skb, tlen, offset); if (flags & IP_CMSG_RECVFRAGSIZE) ip_cmsg_recv_fragsize(msg, skb); } EXPORT_SYMBOL(ip_cmsg_recv_offset); int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, bool allow_ipv6) { int err, val; struct cmsghdr *cmsg; struct net *net = sock_net(sk); for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; #if IS_ENABLED(CONFIG_IPV6) if (allow_ipv6 && cmsg->cmsg_level == SOL_IPV6 && cmsg->cmsg_type == IPV6_PKTINFO) { struct in6_pktinfo *src_info; if (cmsg->cmsg_len < CMSG_LEN(sizeof(*src_info))) return -EINVAL; src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg); if (!ipv6_addr_v4mapped(&src_info->ipi6_addr)) return -EINVAL; if (src_info->ipi6_ifindex) ipc->oif = src_info->ipi6_ifindex; ipc->addr = src_info->ipi6_addr.s6_addr32[3]; continue; } #endif if (cmsg->cmsg_level == SOL_SOCKET) { err = __sock_cmsg_send(sk, msg, cmsg, &ipc->sockc); if (err) return err; continue; } if (cmsg->cmsg_level != SOL_IP) continue; switch (cmsg->cmsg_type) { case IP_RETOPTS: err = cmsg->cmsg_len - sizeof(struct cmsghdr); /* Our caller is responsible for freeing ipc->opt */ err = ip_options_get(net, &ipc->opt, KERNEL_SOCKPTR(CMSG_DATA(cmsg)), err < 40 ? err : 40); if (err) return err; break; case IP_PKTINFO: { struct in_pktinfo *info; if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct in_pktinfo))) return -EINVAL; info = (struct in_pktinfo *)CMSG_DATA(cmsg); if (info->ipi_ifindex) ipc->oif = info->ipi_ifindex; ipc->addr = info->ipi_spec_dst.s_addr; break; } case IP_TTL: if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) return -EINVAL; val = *(int *)CMSG_DATA(cmsg); if (val < 1 || val > 255) return -EINVAL; ipc->ttl = val; break; case IP_TOS: if (cmsg->cmsg_len == CMSG_LEN(sizeof(int))) val = *(int *)CMSG_DATA(cmsg); else if (cmsg->cmsg_len == CMSG_LEN(sizeof(u8))) val = *(u8 *)CMSG_DATA(cmsg); else return -EINVAL; if (val < 0 || val > 255) return -EINVAL; ipc->tos = val; ipc->priority = rt_tos2priority(ipc->tos); break; case IP_PROTOCOL: if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) return -EINVAL; val = *(int *)CMSG_DATA(cmsg); if (val < 1 || val > 255) return -EINVAL; ipc->protocol = val; break; default: return -EINVAL; } } return 0; } static void ip_ra_destroy_rcu(struct rcu_head *head) { struct ip_ra_chain *ra = container_of(head, struct ip_ra_chain, rcu); sock_put(ra->saved_sk); kfree(ra); } int ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct sock *)) { struct ip_ra_chain *ra, *new_ra; struct ip_ra_chain __rcu **rap; struct net *net = sock_net(sk); if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num == IPPROTO_RAW) return -EINVAL; new_ra = on ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL; if (on && !new_ra) return -ENOMEM; mutex_lock(&net->ipv4.ra_mutex); for (rap = &net->ipv4.ra_chain; (ra = rcu_dereference_protected(*rap, lockdep_is_held(&net->ipv4.ra_mutex))) != NULL; rap = &ra->next) { if (ra->sk == sk) { if (on) { mutex_unlock(&net->ipv4.ra_mutex); kfree(new_ra); return -EADDRINUSE; } /* dont let ip_call_ra_chain() use sk again */ ra->sk = NULL; RCU_INIT_POINTER(*rap, ra->next); mutex_unlock(&net->ipv4.ra_mutex); if (ra->destructor) ra->destructor(sk); /* * Delay sock_put(sk) and kfree(ra) after one rcu grace * period. This guarantee ip_call_ra_chain() dont need * to mess with socket refcounts. */ ra->saved_sk = sk; call_rcu(&ra->rcu, ip_ra_destroy_rcu); return 0; } } if (!new_ra) { mutex_unlock(&net->ipv4.ra_mutex); return -ENOBUFS; } new_ra->sk = sk; new_ra->destructor = destructor; RCU_INIT_POINTER(new_ra->next, ra); rcu_assign_pointer(*rap, new_ra); sock_hold(sk); mutex_unlock(&net->ipv4.ra_mutex); return 0; } static void ipv4_icmp_error_rfc4884(const struct sk_buff *skb, struct sock_ee_data_rfc4884 *out) { switch (icmp_hdr(skb)->type) { case ICMP_DEST_UNREACH: case ICMP_TIME_EXCEEDED: case ICMP_PARAMETERPROB: ip_icmp_error_rfc4884(skb, out, sizeof(struct icmphdr), icmp_hdr(skb)->un.reserved[1] * 4); } } void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload) { struct sock_exterr_skb *serr; skb = skb_clone(skb, GFP_ATOMIC); if (!skb) return; serr = SKB_EXT_ERR(skb); serr->ee.ee_errno = err; serr->ee.ee_origin = SO_EE_ORIGIN_ICMP; serr->ee.ee_type = icmp_hdr(skb)->type; serr->ee.ee_code = icmp_hdr(skb)->code; serr->ee.ee_pad = 0; serr->ee.ee_info = info; serr->ee.ee_data = 0; serr->addr_offset = (u8 *)&(((struct iphdr *)(icmp_hdr(skb) + 1))->daddr) - skb_network_header(skb); serr->port = port; if (skb_pull(skb, payload - skb->data)) { if (inet_sk(sk)->recverr_rfc4884) ipv4_icmp_error_rfc4884(skb, &serr->ee.ee_rfc4884); skb_reset_transport_header(skb); if (sock_queue_err_skb(sk, skb) == 0) return; } kfree_skb(skb); } void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 info) { struct inet_sock *inet = inet_sk(sk); struct sock_exterr_skb *serr; struct iphdr *iph; struct sk_buff *skb; if (!inet->recverr) return; skb = alloc_skb(sizeof(struct iphdr), GFP_ATOMIC); if (!skb) return; skb_put(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); iph = ip_hdr(skb); iph->daddr = daddr; serr = SKB_EXT_ERR(skb); serr->ee.ee_errno = err; serr->ee.ee_origin = SO_EE_ORIGIN_LOCAL; serr->ee.ee_type = 0; serr->ee.ee_code = 0; serr->ee.ee_pad = 0; serr->ee.ee_info = info; serr->ee.ee_data = 0; serr->addr_offset = (u8 *)&iph->daddr - skb_network_header(skb); serr->port = port; __skb_pull(skb, skb_tail_pointer(skb) - skb->data); skb_reset_transport_header(skb); if (sock_queue_err_skb(sk, skb)) kfree_skb(skb); } /* For some errors we have valid addr_offset even with zero payload and * zero port. Also, addr_offset should be supported if port is set. */ static inline bool ipv4_datagram_support_addr(struct sock_exterr_skb *serr) { return serr->ee.ee_origin == SO_EE_ORIGIN_ICMP || serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL || serr->port; } /* IPv4 supports cmsg on all imcp errors and some timestamps * * Timestamp code paths do not initialize the fields expected by cmsg: * the PKTINFO fields in skb->cb[]. Fill those in here. */ static bool ipv4_datagram_support_cmsg(const struct sock *sk, struct sk_buff *skb, int ee_origin) { struct in_pktinfo *info; if (ee_origin == SO_EE_ORIGIN_ICMP) return true; if (ee_origin == SO_EE_ORIGIN_LOCAL) return false; /* Support IP_PKTINFO on tstamp packets if requested, to correlate * timestamp with egress dev. Not possible for packets without iif * or without payload (SOF_TIMESTAMPING_OPT_TSONLY). */ info = PKTINFO_SKB_CB(skb); if (!(READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_CMSG) || !info->ipi_ifindex) return false; info->ipi_spec_dst.s_addr = ip_hdr(skb)->saddr; return true; } /* * Handle MSG_ERRQUEUE */ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { struct sock_exterr_skb *serr; struct sk_buff *skb; DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); struct { struct sock_extended_err ee; struct sockaddr_in offender; } errhdr; int err; int copied; err = -EAGAIN; skb = sock_dequeue_err_skb(sk); if (!skb) goto out; copied = skb->len; if (copied > len) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (unlikely(err)) { kfree_skb(skb); return err; } sock_recv_timestamp(msg, sk, skb); serr = SKB_EXT_ERR(skb); if (sin && ipv4_datagram_support_addr(serr)) { sin->sin_family = AF_INET; sin->sin_addr.s_addr = *(__be32 *)(skb_network_header(skb) + serr->addr_offset); sin->sin_port = serr->port; memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); *addr_len = sizeof(*sin); } memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); sin = &errhdr.offender; memset(sin, 0, sizeof(*sin)); if (ipv4_datagram_support_cmsg(sk, skb, serr->ee.ee_origin)) { sin->sin_family = AF_INET; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; if (inet_sk(sk)->cmsg_flags) ip_cmsg_recv(msg, skb); } put_cmsg(msg, SOL_IP, IP_RECVERR, sizeof(errhdr), &errhdr); /* Now we could try to dump offended packet options */ msg->msg_flags |= MSG_ERRQUEUE; err = copied; consume_skb(skb); out: return err; } void __ip_sock_set_tos(struct sock *sk, int val) { if (sk->sk_type == SOCK_STREAM) { val &= ~INET_ECN_MASK; val |= inet_sk(sk)->tos & INET_ECN_MASK; } if (inet_sk(sk)->tos != val) { inet_sk(sk)->tos = val; WRITE_ONCE(sk->sk_priority, rt_tos2priority(val)); sk_dst_reset(sk); } } void ip_sock_set_tos(struct sock *sk, int val) { lock_sock(sk); __ip_sock_set_tos(sk, val); release_sock(sk); } EXPORT_SYMBOL(ip_sock_set_tos); void ip_sock_set_freebind(struct sock *sk) { lock_sock(sk); inet_sk(sk)->freebind = true; release_sock(sk); } EXPORT_SYMBOL(ip_sock_set_freebind); void ip_sock_set_recverr(struct sock *sk) { lock_sock(sk); inet_sk(sk)->recverr = true; release_sock(sk); } EXPORT_SYMBOL(ip_sock_set_recverr); int ip_sock_set_mtu_discover(struct sock *sk, int val) { if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT) return -EINVAL; lock_sock(sk); inet_sk(sk)->pmtudisc = val; release_sock(sk); return 0; } EXPORT_SYMBOL(ip_sock_set_mtu_discover); void ip_sock_set_pktinfo(struct sock *sk) { lock_sock(sk); inet_sk(sk)->cmsg_flags |= IP_CMSG_PKTINFO; release_sock(sk); } EXPORT_SYMBOL(ip_sock_set_pktinfo); /* * Socket option code for IP. This is the end of the line after any * TCP,UDP etc options on an IP socket. */ static bool setsockopt_needs_rtnl(int optname) { switch (optname) { case IP_ADD_MEMBERSHIP: case IP_ADD_SOURCE_MEMBERSHIP: case IP_BLOCK_SOURCE: case IP_DROP_MEMBERSHIP: case IP_DROP_SOURCE_MEMBERSHIP: case IP_MSFILTER: case IP_UNBLOCK_SOURCE: case MCAST_BLOCK_SOURCE: case MCAST_MSFILTER: case MCAST_JOIN_GROUP: case MCAST_JOIN_SOURCE_GROUP: case MCAST_LEAVE_GROUP: case MCAST_LEAVE_SOURCE_GROUP: case MCAST_UNBLOCK_SOURCE: return true; } return false; } static int set_mcast_msfilter(struct sock *sk, int ifindex, int numsrc, int fmode, struct sockaddr_storage *group, struct sockaddr_storage *list) { struct ip_msfilter *msf; struct sockaddr_in *psin; int err, i; msf = kmalloc(IP_MSFILTER_SIZE(numsrc), GFP_KERNEL); if (!msf) return -ENOBUFS; psin = (struct sockaddr_in *)group; if (psin->sin_family != AF_INET) goto Eaddrnotavail; msf->imsf_multiaddr = psin->sin_addr.s_addr; msf->imsf_interface = 0; msf->imsf_fmode = fmode; msf->imsf_numsrc = numsrc; for (i = 0; i < numsrc; ++i) { psin = (struct sockaddr_in *)&list[i]; if (psin->sin_family != AF_INET) goto Eaddrnotavail; msf->imsf_slist_flex[i] = psin->sin_addr.s_addr; } err = ip_mc_msfilter(sk, msf, ifindex); kfree(msf); return err; Eaddrnotavail: kfree(msf); return -EADDRNOTAVAIL; } static int copy_group_source_from_sockptr(struct group_source_req *greqs, sockptr_t optval, int optlen) { if (in_compat_syscall()) { struct compat_group_source_req gr32; if (optlen != sizeof(gr32)) return -EINVAL; if (copy_from_sockptr(&gr32, optval, sizeof(gr32))) return -EFAULT; greqs->gsr_interface = gr32.gsr_interface; greqs->gsr_group = gr32.gsr_group; greqs->gsr_source = gr32.gsr_source; } else { if (optlen != sizeof(*greqs)) return -EINVAL; if (copy_from_sockptr(greqs, optval, sizeof(*greqs))) return -EFAULT; } return 0; } static int do_mcast_group_source(struct sock *sk, int optname, sockptr_t optval, int optlen) { struct group_source_req greqs; struct ip_mreq_source mreqs; struct sockaddr_in *psin; int omode, add, err; err = copy_group_source_from_sockptr(&greqs, optval, optlen); if (err) return err; if (greqs.gsr_group.ss_family != AF_INET || greqs.gsr_source.ss_family != AF_INET) return -EADDRNOTAVAIL; psin = (struct sockaddr_in *)&greqs.gsr_group; mreqs.imr_multiaddr = psin->sin_addr.s_addr; psin = (struct sockaddr_in *)&greqs.gsr_source; mreqs.imr_sourceaddr = psin->sin_addr.s_addr; mreqs.imr_interface = 0; /* use index for mc_source */ if (optname == MCAST_BLOCK_SOURCE) { omode = MCAST_EXCLUDE; add = 1; } else if (optname == MCAST_UNBLOCK_SOURCE) { omode = MCAST_EXCLUDE; add = 0; } else if (optname == MCAST_JOIN_SOURCE_GROUP) { struct ip_mreqn mreq; psin = (struct sockaddr_in *)&greqs.gsr_group; mreq.imr_multiaddr = psin->sin_addr; mreq.imr_address.s_addr = 0; mreq.imr_ifindex = greqs.gsr_interface; err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE); if (err && err != -EADDRINUSE) return err; greqs.gsr_interface = mreq.imr_ifindex; omode = MCAST_INCLUDE; add = 1; } else /* MCAST_LEAVE_SOURCE_GROUP */ { omode = MCAST_INCLUDE; add = 0; } return ip_mc_source(add, omode, sk, &mreqs, greqs.gsr_interface); } static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen) { struct group_filter *gsf = NULL; int err; if (optlen < GROUP_FILTER_SIZE(0)) return -EINVAL; if (optlen > READ_ONCE(sysctl_optmem_max)) return -ENOBUFS; gsf = memdup_sockptr(optval, optlen); if (IS_ERR(gsf)) return PTR_ERR(gsf); /* numsrc >= (4G-140)/128 overflow in 32 bits */ err = -ENOBUFS; if (gsf->gf_numsrc >= 0x1ffffff || gsf->gf_numsrc > READ_ONCE(sock_net(sk)->ipv4.sysctl_igmp_max_msf)) goto out_free_gsf; err = -EINVAL; if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) goto out_free_gsf; err = set_mcast_msfilter(sk, gsf->gf_interface, gsf->gf_numsrc, gsf->gf_fmode, &gsf->gf_group, gsf->gf_slist_flex); out_free_gsf: kfree(gsf); return err; } static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen) { const int size0 = offsetof(struct compat_group_filter, gf_slist_flex); struct compat_group_filter *gf32; unsigned int n; void *p; int err; if (optlen < size0) return -EINVAL; if (optlen > READ_ONCE(sysctl_optmem_max) - 4) return -ENOBUFS; p = kmalloc(optlen + 4, GFP_KERNEL); if (!p) return -ENOMEM; gf32 = p + 4; /* we want ->gf_group and ->gf_slist_flex aligned */ err = -EFAULT; if (copy_from_sockptr(gf32, optval, optlen)) goto out_free_gsf; /* numsrc >= (4G-140)/128 overflow in 32 bits */ n = gf32->gf_numsrc; err = -ENOBUFS; if (n >= 0x1ffffff) goto out_free_gsf; err = -EINVAL; if (offsetof(struct compat_group_filter, gf_slist_flex[n]) > optlen) goto out_free_gsf; /* numsrc >= (4G-140)/128 overflow in 32 bits */ err = -ENOBUFS; if (n > READ_ONCE(sock_net(sk)->ipv4.sysctl_igmp_max_msf)) goto out_free_gsf; err = set_mcast_msfilter(sk, gf32->gf_interface, n, gf32->gf_fmode, &gf32->gf_group, gf32->gf_slist_flex); out_free_gsf: kfree(p); return err; } static int ip_mcast_join_leave(struct sock *sk, int optname, sockptr_t optval, int optlen) { struct ip_mreqn mreq = { }; struct sockaddr_in *psin; struct group_req greq; if (optlen < sizeof(struct group_req)) return -EINVAL; if (copy_from_sockptr(&greq, optval, sizeof(greq))) return -EFAULT; psin = (struct sockaddr_in *)&greq.gr_group; if (psin->sin_family != AF_INET) return -EINVAL; mreq.imr_multiaddr = psin->sin_addr; mreq.imr_ifindex = greq.gr_interface; if (optname == MCAST_JOIN_GROUP) return ip_mc_join_group(sk, &mreq); return ip_mc_leave_group(sk, &mreq); } static int compat_ip_mcast_join_leave(struct sock *sk, int optname, sockptr_t optval, int optlen) { struct compat_group_req greq; struct ip_mreqn mreq = { }; struct sockaddr_in *psin; if (optlen < sizeof(struct compat_group_req)) return -EINVAL; if (copy_from_sockptr(&greq, optval, sizeof(greq))) return -EFAULT; psin = (struct sockaddr_in *)&greq.gr_group; if (psin->sin_family != AF_INET) return -EINVAL; mreq.imr_multiaddr = psin->sin_addr; mreq.imr_ifindex = greq.gr_interface; if (optname == MCAST_JOIN_GROUP) return ip_mc_join_group(sk, &mreq); return ip_mc_leave_group(sk, &mreq); } DEFINE_STATIC_KEY_FALSE(ip4_min_ttl); int do_ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); int val = 0, err; bool needs_rtnl = setsockopt_needs_rtnl(optname); switch (optname) { case IP_PKTINFO: case IP_RECVTTL: case IP_RECVOPTS: case IP_RECVTOS: case IP_RETOPTS: case IP_TOS: case IP_TTL: case IP_HDRINCL: case IP_MTU_DISCOVER: case IP_RECVERR: case IP_ROUTER_ALERT: case IP_FREEBIND: case IP_PASSSEC: case IP_TRANSPARENT: case IP_MINTTL: case IP_NODEFRAG: case IP_BIND_ADDRESS_NO_PORT: case IP_UNICAST_IF: case IP_MULTICAST_TTL: case IP_MULTICAST_ALL: case IP_MULTICAST_LOOP: case IP_RECVORIGDSTADDR: case IP_CHECKSUM: case IP_RECVFRAGSIZE: case IP_RECVERR_RFC4884: case IP_LOCAL_PORT_RANGE: if (optlen >= sizeof(int)) { if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; } else if (optlen >= sizeof(char)) { unsigned char ucval; if (copy_from_sockptr(&ucval, optval, sizeof(ucval))) return -EFAULT; val = (int) ucval; } } /* If optlen==0, it is equivalent to val == 0 */ if (optname == IP_ROUTER_ALERT) return ip_ra_control(sk, val ? 1 : 0, NULL); if (ip_mroute_opt(optname)) return ip_mroute_setsockopt(sk, optname, optval, optlen); err = 0; if (needs_rtnl) rtnl_lock(); sockopt_lock_sock(sk); switch (optname) { case IP_OPTIONS: { struct ip_options_rcu *old, *opt = NULL; if (optlen > 40) goto e_inval; err = ip_options_get(sock_net(sk), &opt, optval, optlen); if (err) break; old = rcu_dereference_protected(inet->inet_opt, lockdep_sock_is_held(sk)); if (inet->is_icsk) { struct inet_connection_sock *icsk = inet_csk(sk); #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == PF_INET || (!((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) && inet->inet_daddr != LOOPBACK4_IPV6)) { #endif if (old) icsk->icsk_ext_hdr_len -= old->opt.optlen; if (opt) icsk->icsk_ext_hdr_len += opt->opt.optlen; icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie); #if IS_ENABLED(CONFIG_IPV6) } #endif } rcu_assign_pointer(inet->inet_opt, opt); if (old) kfree_rcu(old, rcu); break; } case IP_PKTINFO: if (val) inet->cmsg_flags |= IP_CMSG_PKTINFO; else inet->cmsg_flags &= ~IP_CMSG_PKTINFO; break; case IP_RECVTTL: if (val) inet->cmsg_flags |= IP_CMSG_TTL; else inet->cmsg_flags &= ~IP_CMSG_TTL; break; case IP_RECVTOS: if (val) inet->cmsg_flags |= IP_CMSG_TOS; else inet->cmsg_flags &= ~IP_CMSG_TOS; break; case IP_RECVOPTS: if (val) inet->cmsg_flags |= IP_CMSG_RECVOPTS; else inet->cmsg_flags &= ~IP_CMSG_RECVOPTS; break; case IP_RETOPTS: if (val) inet->cmsg_flags |= IP_CMSG_RETOPTS; else inet->cmsg_flags &= ~IP_CMSG_RETOPTS; break; case IP_PASSSEC: if (val) inet->cmsg_flags |= IP_CMSG_PASSSEC; else inet->cmsg_flags &= ~IP_CMSG_PASSSEC; break; case IP_RECVORIGDSTADDR: if (val) inet->cmsg_flags |= IP_CMSG_ORIGDSTADDR; else inet->cmsg_flags &= ~IP_CMSG_ORIGDSTADDR; break; case IP_CHECKSUM: if (val) { if (!(inet->cmsg_flags & IP_CMSG_CHECKSUM)) { inet_inc_convert_csum(sk); inet->cmsg_flags |= IP_CMSG_CHECKSUM; } } else { if (inet->cmsg_flags & IP_CMSG_CHECKSUM) { inet_dec_convert_csum(sk); inet->cmsg_flags &= ~IP_CMSG_CHECKSUM; } } break; case IP_RECVFRAGSIZE: if (sk->sk_type != SOCK_RAW && sk->sk_type != SOCK_DGRAM) goto e_inval; if (val) inet->cmsg_flags |= IP_CMSG_RECVFRAGSIZE; else inet->cmsg_flags &= ~IP_CMSG_RECVFRAGSIZE; break; case IP_TOS: /* This sets both TOS and Precedence */ __ip_sock_set_tos(sk, val); break; case IP_TTL: if (optlen < 1) goto e_inval; if (val != -1 && (val < 1 || val > 255)) goto e_inval; inet->uc_ttl = val; break; case IP_HDRINCL: if (sk->sk_type != SOCK_RAW) { err = -ENOPROTOOPT; break; } inet->hdrincl = val ? 1 : 0; break; case IP_NODEFRAG: if (sk->sk_type != SOCK_RAW) { err = -ENOPROTOOPT; break; } inet->nodefrag = val ? 1 : 0; break; case IP_BIND_ADDRESS_NO_PORT: inet->bind_address_no_port = val ? 1 : 0; break; case IP_MTU_DISCOVER: if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT) goto e_inval; inet->pmtudisc = val; break; case IP_RECVERR: inet->recverr = !!val; if (!val) skb_queue_purge(&sk->sk_error_queue); break; case IP_RECVERR_RFC4884: if (val < 0 || val > 1) goto e_inval; inet->recverr_rfc4884 = !!val; break; case IP_MULTICAST_TTL: if (sk->sk_type == SOCK_STREAM) goto e_inval; if (optlen < 1) goto e_inval; if (val == -1) val = 1; if (val < 0 || val > 255) goto e_inval; inet->mc_ttl = val; break; case IP_MULTICAST_LOOP: if (optlen < 1) goto e_inval; inet->mc_loop = !!val; break; case IP_UNICAST_IF: { struct net_device *dev = NULL; int ifindex; int midx; if (optlen != sizeof(int)) goto e_inval; ifindex = (__force int)ntohl((__force __be32)val); if (ifindex == 0) { inet->uc_index = 0; err = 0; break; } dev = dev_get_by_index(sock_net(sk), ifindex); err = -EADDRNOTAVAIL; if (!dev) break; midx = l3mdev_master_ifindex(dev); dev_put(dev); err = -EINVAL; if (sk->sk_bound_dev_if && midx != sk->sk_bound_dev_if) break; inet->uc_index = ifindex; err = 0; break; } case IP_MULTICAST_IF: { struct ip_mreqn mreq; struct net_device *dev = NULL; int midx; if (sk->sk_type == SOCK_STREAM) goto e_inval; /* * Check the arguments are allowable */ if (optlen < sizeof(struct in_addr)) goto e_inval; err = -EFAULT; if (optlen >= sizeof(struct ip_mreqn)) { if (copy_from_sockptr(&mreq, optval, sizeof(mreq))) break; } else { memset(&mreq, 0, sizeof(mreq)); if (optlen >= sizeof(struct ip_mreq)) { if (copy_from_sockptr(&mreq, optval, sizeof(struct ip_mreq))) break; } else if (optlen >= sizeof(struct in_addr)) { if (copy_from_sockptr(&mreq.imr_address, optval, sizeof(struct in_addr))) break; } } if (!mreq.imr_ifindex) { if (mreq.imr_address.s_addr == htonl(INADDR_ANY)) { inet->mc_index = 0; inet->mc_addr = 0; err = 0; break; } dev = ip_dev_find(sock_net(sk), mreq.imr_address.s_addr); if (dev) mreq.imr_ifindex = dev->ifindex; } else dev = dev_get_by_index(sock_net(sk), mreq.imr_ifindex); err = -EADDRNOTAVAIL; if (!dev) break; midx = l3mdev_master_ifindex(dev); dev_put(dev); err = -EINVAL; if (sk->sk_bound_dev_if && mreq.imr_ifindex != sk->sk_bound_dev_if && midx != sk->sk_bound_dev_if) break; inet->mc_index = mreq.imr_ifindex; inet->mc_addr = mreq.imr_address.s_addr; err = 0; break; } case IP_ADD_MEMBERSHIP: case IP_DROP_MEMBERSHIP: { struct ip_mreqn mreq; err = -EPROTO; if (inet_sk(sk)->is_icsk) break; if (optlen < sizeof(struct ip_mreq)) goto e_inval; err = -EFAULT; if (optlen >= sizeof(struct ip_mreqn)) { if (copy_from_sockptr(&mreq, optval, sizeof(mreq))) break; } else { memset(&mreq, 0, sizeof(mreq)); if (copy_from_sockptr(&mreq, optval, sizeof(struct ip_mreq))) break; } if (optname == IP_ADD_MEMBERSHIP) err = ip_mc_join_group(sk, &mreq); else err = ip_mc_leave_group(sk, &mreq); break; } case IP_MSFILTER: { struct ip_msfilter *msf; if (optlen < IP_MSFILTER_SIZE(0)) goto e_inval; if (optlen > READ_ONCE(sysctl_optmem_max)) { err = -ENOBUFS; break; } msf = memdup_sockptr(optval, optlen); if (IS_ERR(msf)) { err = PTR_ERR(msf); break; } /* numsrc >= (1G-4) overflow in 32 bits */ if (msf->imsf_numsrc >= 0x3ffffffcU || msf->imsf_numsrc > READ_ONCE(net->ipv4.sysctl_igmp_max_msf)) { kfree(msf); err = -ENOBUFS; break; } if (IP_MSFILTER_SIZE(msf->imsf_numsrc) > optlen) { kfree(msf); err = -EINVAL; break; } err = ip_mc_msfilter(sk, msf, 0); kfree(msf); break; } case IP_BLOCK_SOURCE: case IP_UNBLOCK_SOURCE: case IP_ADD_SOURCE_MEMBERSHIP: case IP_DROP_SOURCE_MEMBERSHIP: { struct ip_mreq_source mreqs; int omode, add; if (optlen != sizeof(struct ip_mreq_source)) goto e_inval; if (copy_from_sockptr(&mreqs, optval, sizeof(mreqs))) { err = -EFAULT; break; } if (optname == IP_BLOCK_SOURCE) { omode = MCAST_EXCLUDE; add = 1; } else if (optname == IP_UNBLOCK_SOURCE) { omode = MCAST_EXCLUDE; add = 0; } else if (optname == IP_ADD_SOURCE_MEMBERSHIP) { struct ip_mreqn mreq; mreq.imr_multiaddr.s_addr = mreqs.imr_multiaddr; mreq.imr_address.s_addr = mreqs.imr_interface; mreq.imr_ifindex = 0; err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE); if (err && err != -EADDRINUSE) break; omode = MCAST_INCLUDE; add = 1; } else /* IP_DROP_SOURCE_MEMBERSHIP */ { omode = MCAST_INCLUDE; add = 0; } err = ip_mc_source(add, omode, sk, &mreqs, 0); break; } case MCAST_JOIN_GROUP: case MCAST_LEAVE_GROUP: if (in_compat_syscall()) err = compat_ip_mcast_join_leave(sk, optname, optval, optlen); else err = ip_mcast_join_leave(sk, optname, optval, optlen); break; case MCAST_JOIN_SOURCE_GROUP: case MCAST_LEAVE_SOURCE_GROUP: case MCAST_BLOCK_SOURCE: case MCAST_UNBLOCK_SOURCE: err = do_mcast_group_source(sk, optname, optval, optlen); break; case MCAST_MSFILTER: if (in_compat_syscall()) err = compat_ip_set_mcast_msfilter(sk, optval, optlen); else err = ip_set_mcast_msfilter(sk, optval, optlen); break; case IP_MULTICAST_ALL: if (optlen < 1) goto e_inval; if (val != 0 && val != 1) goto e_inval; inet->mc_all = val; break; case IP_FREEBIND: if (optlen < 1) goto e_inval; inet->freebind = !!val; break; case IP_IPSEC_POLICY: case IP_XFRM_POLICY: err = -EPERM; if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) break; err = xfrm_user_policy(sk, optname, optval, optlen); break; case IP_TRANSPARENT: if (!!val && !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) && !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { err = -EPERM; break; } if (optlen < 1) goto e_inval; inet->transparent = !!val; break; case IP_MINTTL: if (optlen < 1) goto e_inval; if (val < 0 || val > 255) goto e_inval; if (val) static_branch_enable(&ip4_min_ttl); /* tcp_v4_err() and tcp_v4_rcv() might read min_ttl * while we are changint it. */ WRITE_ONCE(inet->min_ttl, val); break; case IP_LOCAL_PORT_RANGE: { const __u16 lo = val; const __u16 hi = val >> 16; if (optlen != sizeof(__u32)) goto e_inval; if (lo != 0 && hi != 0 && lo > hi) goto e_inval; inet->local_port_range.lo = lo; inet->local_port_range.hi = hi; break; } default: err = -ENOPROTOOPT; break; } sockopt_release_sock(sk); if (needs_rtnl) rtnl_unlock(); return err; e_inval: sockopt_release_sock(sk); if (needs_rtnl) rtnl_unlock(); return -EINVAL; } /** * ipv4_pktinfo_prepare - transfer some info from rtable to skb * @sk: socket * @skb: buffer * @drop_dst: if true, drops skb dst * * To support IP_CMSG_PKTINFO option, we store rt_iif and specific * destination in skb->cb[] before dst drop. * This way, receiver doesn't make cache line misses to read rtable. */ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb, bool drop_dst) { struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb); bool prepare = (inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO) || ipv6_sk_rxinfo(sk); if (prepare && skb_rtable(skb)) { /* skb->cb is overloaded: prior to this point it is IP{6}CB * which has interface index (iif) as the first member of the * underlying inet{6}_skb_parm struct. This code then overlays * PKTINFO_SKB_CB and in_pktinfo also has iif as the first * element so the iif is picked up from the prior IPCB. If iif * is the loopback interface, then return the sending interface * (e.g., process binds socket to eth0 for Tx which is * redirected to loopback in the rtable/dst). */ struct rtable *rt = skb_rtable(skb); bool l3slave = ipv4_l3mdev_skb(IPCB(skb)->flags); if (pktinfo->ipi_ifindex == LOOPBACK_IFINDEX) pktinfo->ipi_ifindex = inet_iif(skb); else if (l3slave && rt && rt->rt_iif) pktinfo->ipi_ifindex = rt->rt_iif; pktinfo->ipi_spec_dst.s_addr = fib_compute_spec_dst(skb); } else { pktinfo->ipi_ifindex = 0; pktinfo->ipi_spec_dst.s_addr = 0; } if (drop_dst) skb_dst_drop(skb); } int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { int err; if (level != SOL_IP) return -ENOPROTOOPT; err = do_ip_setsockopt(sk, level, optname, optval, optlen); #if IS_ENABLED(CONFIG_BPFILTER_UMH) if (optname >= BPFILTER_IPT_SO_SET_REPLACE && optname < BPFILTER_IPT_SET_MAX) err = bpfilter_ip_set_sockopt(sk, optname, optval, optlen); #endif #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ if (err == -ENOPROTOOPT && optname != IP_HDRINCL && optname != IP_IPSEC_POLICY && optname != IP_XFRM_POLICY && !ip_mroute_opt(optname)) err = nf_setsockopt(sk, PF_INET, optname, optval, optlen); #endif return err; } EXPORT_SYMBOL(ip_setsockopt); /* * Get the options. Note for future reference. The GET of IP options gets * the _received_ ones. The set sets the _sent_ ones. */ static bool getsockopt_needs_rtnl(int optname) { switch (optname) { case IP_MSFILTER: case MCAST_MSFILTER: return true; } return false; } static int ip_get_mcast_msfilter(struct sock *sk, sockptr_t optval, sockptr_t optlen, int len) { const int size0 = offsetof(struct group_filter, gf_slist_flex); struct group_filter gsf; int num, gsf_size; int err; if (len < size0) return -EINVAL; if (copy_from_sockptr(&gsf, optval, size0)) return -EFAULT; num = gsf.gf_numsrc; err = ip_mc_gsfget(sk, &gsf, optval, offsetof(struct group_filter, gf_slist_flex)); if (err) return err; if (gsf.gf_numsrc < num) num = gsf.gf_numsrc; gsf_size = GROUP_FILTER_SIZE(num); if (copy_to_sockptr(optlen, &gsf_size, sizeof(int)) || copy_to_sockptr(optval, &gsf, size0)) return -EFAULT; return 0; } static int compat_ip_get_mcast_msfilter(struct sock *sk, sockptr_t optval, sockptr_t optlen, int len) { const int size0 = offsetof(struct compat_group_filter, gf_slist_flex); struct compat_group_filter gf32; struct group_filter gf; int num; int err; if (len < size0) return -EINVAL; if (copy_from_sockptr(&gf32, optval, size0)) return -EFAULT; gf.gf_interface = gf32.gf_interface; gf.gf_fmode = gf32.gf_fmode; num = gf.gf_numsrc = gf32.gf_numsrc; gf.gf_group = gf32.gf_group; err = ip_mc_gsfget(sk, &gf, optval, offsetof(struct compat_group_filter, gf_slist_flex)); if (err) return err; if (gf.gf_numsrc < num) num = gf.gf_numsrc; len = GROUP_FILTER_SIZE(num) - (sizeof(gf) - sizeof(gf32)); if (copy_to_sockptr(optlen, &len, sizeof(int)) || copy_to_sockptr_offset(optval, offsetof(struct compat_group_filter, gf_fmode), &gf.gf_fmode, sizeof(gf.gf_fmode)) || copy_to_sockptr_offset(optval, offsetof(struct compat_group_filter, gf_numsrc), &gf.gf_numsrc, sizeof(gf.gf_numsrc))) return -EFAULT; return 0; } int do_ip_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen) { struct inet_sock *inet = inet_sk(sk); bool needs_rtnl = getsockopt_needs_rtnl(optname); int val, err = 0; int len; if (level != SOL_IP) return -EOPNOTSUPP; if (ip_mroute_opt(optname)) return ip_mroute_getsockopt(sk, optname, optval, optlen); if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len < 0) return -EINVAL; if (needs_rtnl) rtnl_lock(); sockopt_lock_sock(sk); switch (optname) { case IP_OPTIONS: { unsigned char optbuf[sizeof(struct ip_options)+40]; struct ip_options *opt = (struct ip_options *)optbuf; struct ip_options_rcu *inet_opt; inet_opt = rcu_dereference_protected(inet->inet_opt, lockdep_sock_is_held(sk)); opt->optlen = 0; if (inet_opt) memcpy(optbuf, &inet_opt->opt, sizeof(struct ip_options) + inet_opt->opt.optlen); sockopt_release_sock(sk); if (opt->optlen == 0) { len = 0; return copy_to_sockptr(optlen, &len, sizeof(int)); } ip_options_undo(opt); len = min_t(unsigned int, len, opt->optlen); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, opt->__data, len)) return -EFAULT; return 0; } case IP_PKTINFO: val = (inet->cmsg_flags & IP_CMSG_PKTINFO) != 0; break; case IP_RECVTTL: val = (inet->cmsg_flags & IP_CMSG_TTL) != 0; break; case IP_RECVTOS: val = (inet->cmsg_flags & IP_CMSG_TOS) != 0; break; case IP_RECVOPTS: val = (inet->cmsg_flags & IP_CMSG_RECVOPTS) != 0; break; case IP_RETOPTS: val = (inet->cmsg_flags & IP_CMSG_RETOPTS) != 0; break; case IP_PASSSEC: val = (inet->cmsg_flags & IP_CMSG_PASSSEC) != 0; break; case IP_RECVORIGDSTADDR: val = (inet->cmsg_flags & IP_CMSG_ORIGDSTADDR) != 0; break; case IP_CHECKSUM: val = (inet->cmsg_flags & IP_CMSG_CHECKSUM) != 0; break; case IP_RECVFRAGSIZE: val = (inet->cmsg_flags & IP_CMSG_RECVFRAGSIZE) != 0; break; case IP_TOS: val = inet->tos; break; case IP_TTL: { struct net *net = sock_net(sk); val = (inet->uc_ttl == -1 ? READ_ONCE(net->ipv4.sysctl_ip_default_ttl) : inet->uc_ttl); break; } case IP_HDRINCL: val = inet->hdrincl; break; case IP_NODEFRAG: val = inet->nodefrag; break; case IP_BIND_ADDRESS_NO_PORT: val = inet->bind_address_no_port; break; case IP_MTU_DISCOVER: val = inet->pmtudisc; break; case IP_MTU: { struct dst_entry *dst; val = 0; dst = sk_dst_get(sk); if (dst) { val = dst_mtu(dst); dst_release(dst); } if (!val) { sockopt_release_sock(sk); return -ENOTCONN; } break; } case IP_RECVERR: val = inet->recverr; break; case IP_RECVERR_RFC4884: val = inet->recverr_rfc4884; break; case IP_MULTICAST_TTL: val = inet->mc_ttl; break; case IP_MULTICAST_LOOP: val = inet->mc_loop; break; case IP_UNICAST_IF: val = (__force int)htonl((__u32) inet->uc_index); break; case IP_MULTICAST_IF: { struct in_addr addr; len = min_t(unsigned int, len, sizeof(struct in_addr)); addr.s_addr = inet->mc_addr; sockopt_release_sock(sk); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &addr, len)) return -EFAULT; return 0; } case IP_MSFILTER: { struct ip_msfilter msf; if (len < IP_MSFILTER_SIZE(0)) { err = -EINVAL; goto out; } if (copy_from_sockptr(&msf, optval, IP_MSFILTER_SIZE(0))) { err = -EFAULT; goto out; } err = ip_mc_msfget(sk, &msf, optval, optlen); goto out; } case MCAST_MSFILTER: if (in_compat_syscall()) err = compat_ip_get_mcast_msfilter(sk, optval, optlen, len); else err = ip_get_mcast_msfilter(sk, optval, optlen, len); goto out; case IP_MULTICAST_ALL: val = inet->mc_all; break; case IP_PKTOPTIONS: { struct msghdr msg; sockopt_release_sock(sk); if (sk->sk_type != SOCK_STREAM) return -ENOPROTOOPT; if (optval.is_kernel) { msg.msg_control_is_user = false; msg.msg_control = optval.kernel; } else { msg.msg_control_is_user = true; msg.msg_control_user = optval.user; } msg.msg_controllen = len; msg.msg_flags = in_compat_syscall() ? MSG_CMSG_COMPAT : 0; if (inet->cmsg_flags & IP_CMSG_PKTINFO) { struct in_pktinfo info; info.ipi_addr.s_addr = inet->inet_rcv_saddr; info.ipi_spec_dst.s_addr = inet->inet_rcv_saddr; info.ipi_ifindex = inet->mc_index; put_cmsg(&msg, SOL_IP, IP_PKTINFO, sizeof(info), &info); } if (inet->cmsg_flags & IP_CMSG_TTL) { int hlim = inet->mc_ttl; put_cmsg(&msg, SOL_IP, IP_TTL, sizeof(hlim), &hlim); } if (inet->cmsg_flags & IP_CMSG_TOS) { int tos = inet->rcv_tos; put_cmsg(&msg, SOL_IP, IP_TOS, sizeof(tos), &tos); } len -= msg.msg_controllen; return copy_to_sockptr(optlen, &len, sizeof(int)); } case IP_FREEBIND: val = inet->freebind; break; case IP_TRANSPARENT: val = inet->transparent; break; case IP_MINTTL: val = inet->min_ttl; break; case IP_LOCAL_PORT_RANGE: val = inet->local_port_range.hi << 16 | inet->local_port_range.lo; break; case IP_PROTOCOL: val = inet_sk(sk)->inet_num; break; default: sockopt_release_sock(sk); return -ENOPROTOOPT; } sockopt_release_sock(sk); if (len < sizeof(int) && len > 0 && val >= 0 && val <= 255) { unsigned char ucval = (unsigned char)val; len = 1; if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &ucval, 1)) return -EFAULT; } else { len = min_t(unsigned int, sizeof(int), len); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &val, len)) return -EFAULT; } return 0; out: sockopt_release_sock(sk); if (needs_rtnl) rtnl_unlock(); return err; } int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { int err; err = do_ip_getsockopt(sk, level, optname, USER_SOCKPTR(optval), USER_SOCKPTR(optlen)); #if IS_ENABLED(CONFIG_BPFILTER_UMH) if (optname >= BPFILTER_IPT_SO_GET_INFO && optname < BPFILTER_IPT_GET_MAX) err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen); #endif #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS && !ip_mroute_opt(optname)) { int len; if (get_user(len, optlen)) return -EFAULT; err = nf_getsockopt(sk, PF_INET, optname, optval, &len); if (err >= 0) err = put_user(len, optlen); return err; } #endif return err; } EXPORT_SYMBOL(ip_getsockopt); |
| 5 5 10 10 27 21 2 9 9 3 5 5 6 1 5 5 5 5 7 7 6 7 2 2 4 16 16 16 2 2 2 2 6 3 3 3 2 1 2 1 1 24 1 24 6 1939 1942 1934 18 6 12 1676 1673 8 24 24 9 9 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 | // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf-cgroup.h> #include <linux/bpf.h> #include <linux/bpf_local_storage.h> #include <linux/btf.h> #include <linux/bug.h> #include <linux/filter.h> #include <linux/mm.h> #include <linux/rbtree.h> #include <linux/slab.h> #include <uapi/linux/btf.h> #include <linux/btf_ids.h> #ifdef CONFIG_CGROUP_BPF #include "../cgroup/cgroup-internal.h" #define LOCAL_STORAGE_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK) struct bpf_cgroup_storage_map { struct bpf_map map; spinlock_t lock; struct rb_root root; struct list_head list; }; static struct bpf_cgroup_storage_map *map_to_storage(struct bpf_map *map) { return container_of(map, struct bpf_cgroup_storage_map, map); } static bool attach_type_isolated(const struct bpf_map *map) { return map->key_size == sizeof(struct bpf_cgroup_storage_key); } static int bpf_cgroup_storage_key_cmp(const struct bpf_cgroup_storage_map *map, const void *_key1, const void *_key2) { if (attach_type_isolated(&map->map)) { const struct bpf_cgroup_storage_key *key1 = _key1; const struct bpf_cgroup_storage_key *key2 = _key2; if (key1->cgroup_inode_id < key2->cgroup_inode_id) return -1; else if (key1->cgroup_inode_id > key2->cgroup_inode_id) return 1; else if (key1->attach_type < key2->attach_type) return -1; else if (key1->attach_type > key2->attach_type) return 1; } else { const __u64 *cgroup_inode_id1 = _key1; const __u64 *cgroup_inode_id2 = _key2; if (*cgroup_inode_id1 < *cgroup_inode_id2) return -1; else if (*cgroup_inode_id1 > *cgroup_inode_id2) return 1; } return 0; } struct bpf_cgroup_storage * cgroup_storage_lookup(struct bpf_cgroup_storage_map *map, void *key, bool locked) { struct rb_root *root = &map->root; struct rb_node *node; if (!locked) spin_lock_bh(&map->lock); node = root->rb_node; while (node) { struct bpf_cgroup_storage *storage; storage = container_of(node, struct bpf_cgroup_storage, node); switch (bpf_cgroup_storage_key_cmp(map, key, &storage->key)) { case -1: node = node->rb_left; break; case 1: node = node->rb_right; break; default: if (!locked) spin_unlock_bh(&map->lock); return storage; } } if (!locked) spin_unlock_bh(&map->lock); return NULL; } static int cgroup_storage_insert(struct bpf_cgroup_storage_map *map, struct bpf_cgroup_storage *storage) { struct rb_root *root = &map->root; struct rb_node **new = &(root->rb_node), *parent = NULL; while (*new) { struct bpf_cgroup_storage *this; this = container_of(*new, struct bpf_cgroup_storage, node); parent = *new; switch (bpf_cgroup_storage_key_cmp(map, &storage->key, &this->key)) { case -1: new = &((*new)->rb_left); break; case 1: new = &((*new)->rb_right); break; default: return -EEXIST; } } rb_link_node(&storage->node, parent, new); rb_insert_color(&storage->node, root); return 0; } static void *cgroup_storage_lookup_elem(struct bpf_map *_map, void *key) { struct bpf_cgroup_storage_map *map = map_to_storage(_map); struct bpf_cgroup_storage *storage; storage = cgroup_storage_lookup(map, key, false); if (!storage) return NULL; return &READ_ONCE(storage->buf)->data[0]; } static int cgroup_storage_update_elem(struct bpf_map *map, void *key, void *value, u64 flags) { struct bpf_cgroup_storage *storage; struct bpf_storage_buffer *new; if (unlikely(flags & ~(BPF_F_LOCK | BPF_EXIST))) return -EINVAL; if (unlikely((flags & BPF_F_LOCK) && !map_value_has_spin_lock(map))) return -EINVAL; storage = cgroup_storage_lookup((struct bpf_cgroup_storage_map *)map, key, false); if (!storage) return -ENOENT; if (flags & BPF_F_LOCK) { copy_map_value_locked(map, storage->buf->data, value, false); return 0; } new = bpf_map_kmalloc_node(map, struct_size(new, data, map->value_size), __GFP_ZERO | GFP_NOWAIT | __GFP_NOWARN, map->numa_node); if (!new) return -ENOMEM; memcpy(&new->data[0], value, map->value_size); check_and_init_map_value(map, new->data); new = xchg(&storage->buf, new); kfree_rcu(new, rcu); return 0; } int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *key, void *value) { struct bpf_cgroup_storage_map *map = map_to_storage(_map); struct bpf_cgroup_storage *storage; int cpu, off = 0; u32 size; rcu_read_lock(); storage = cgroup_storage_lookup(map, key, false); if (!storage) { rcu_read_unlock(); return -ENOENT; } /* per_cpu areas are zero-filled and bpf programs can only * access 'value_size' of them, so copying rounded areas * will not leak any kernel data */ size = round_up(_map->value_size, 8); for_each_possible_cpu(cpu) { bpf_long_memcpy(value + off, per_cpu_ptr(storage->percpu_buf, cpu), size); off += size; } rcu_read_unlock(); return 0; } int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *key, void *value, u64 map_flags) { struct bpf_cgroup_storage_map *map = map_to_storage(_map); struct bpf_cgroup_storage *storage; int cpu, off = 0; u32 size; if (map_flags != BPF_ANY && map_flags != BPF_EXIST) return -EINVAL; rcu_read_lock(); storage = cgroup_storage_lookup(map, key, false); if (!storage) { rcu_read_unlock(); return -ENOENT; } /* the user space will provide round_up(value_size, 8) bytes that * will be copied into per-cpu area. bpf programs can only access * value_size of it. During lookup the same extra bytes will be * returned or zeros which were zero-filled by percpu_alloc, * so no kernel data leaks possible */ size = round_up(_map->value_size, 8); for_each_possible_cpu(cpu) { bpf_long_memcpy(per_cpu_ptr(storage->percpu_buf, cpu), value + off, size); off += size; } rcu_read_unlock(); return 0; } static int cgroup_storage_get_next_key(struct bpf_map *_map, void *key, void *_next_key) { struct bpf_cgroup_storage_map *map = map_to_storage(_map); struct bpf_cgroup_storage *storage; spin_lock_bh(&map->lock); if (list_empty(&map->list)) goto enoent; if (key) { storage = cgroup_storage_lookup(map, key, true); if (!storage) goto enoent; storage = list_next_entry(storage, list_map); if (!storage) goto enoent; } else { storage = list_first_entry(&map->list, struct bpf_cgroup_storage, list_map); } spin_unlock_bh(&map->lock); if (attach_type_isolated(&map->map)) { struct bpf_cgroup_storage_key *next = _next_key; *next = storage->key; } else { __u64 *next = _next_key; *next = storage->key.cgroup_inode_id; } return 0; enoent: spin_unlock_bh(&map->lock); return -ENOENT; } static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) { __u32 max_value_size = BPF_LOCAL_STORAGE_MAX_VALUE_SIZE; int numa_node = bpf_map_attr_numa_node(attr); struct bpf_cgroup_storage_map *map; /* percpu is bound by PCPU_MIN_UNIT_SIZE, non-percu * is the same as other local storages. */ if (attr->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) max_value_size = min_t(__u32, max_value_size, PCPU_MIN_UNIT_SIZE); if (attr->key_size != sizeof(struct bpf_cgroup_storage_key) && attr->key_size != sizeof(__u64)) return ERR_PTR(-EINVAL); if (attr->value_size == 0) return ERR_PTR(-EINVAL); if (attr->value_size > max_value_size) return ERR_PTR(-E2BIG); if (attr->map_flags & ~LOCAL_STORAGE_CREATE_FLAG_MASK || !bpf_map_flags_access_ok(attr->map_flags)) return ERR_PTR(-EINVAL); if (attr->max_entries) /* max_entries is not used and enforced to be 0 */ return ERR_PTR(-EINVAL); map = bpf_map_area_alloc(sizeof(struct bpf_cgroup_storage_map), numa_node); if (!map) return ERR_PTR(-ENOMEM); /* copy mandatory map attributes */ bpf_map_init_from_attr(&map->map, attr); spin_lock_init(&map->lock); map->root = RB_ROOT; INIT_LIST_HEAD(&map->list); return &map->map; } static void cgroup_storage_map_free(struct bpf_map *_map) { struct bpf_cgroup_storage_map *map = map_to_storage(_map); struct list_head *storages = &map->list; struct bpf_cgroup_storage *storage, *stmp; cgroup_lock(); list_for_each_entry_safe(storage, stmp, storages, list_map) { bpf_cgroup_storage_unlink(storage); bpf_cgroup_storage_free(storage); } cgroup_unlock(); WARN_ON(!RB_EMPTY_ROOT(&map->root)); WARN_ON(!list_empty(&map->list)); bpf_map_area_free(map); } static int cgroup_storage_delete_elem(struct bpf_map *map, void *key) { return -EINVAL; } static int cgroup_storage_check_btf(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { if (attach_type_isolated(map)) { struct btf_member *m; u32 offset, size; /* Key is expected to be of struct bpf_cgroup_storage_key type, * which is: * struct bpf_cgroup_storage_key { * __u64 cgroup_inode_id; * __u32 attach_type; * }; */ /* * Key_type must be a structure with two fields. */ if (BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT || BTF_INFO_VLEN(key_type->info) != 2) return -EINVAL; /* * The first field must be a 64 bit integer at 0 offset. */ m = (struct btf_member *)(key_type + 1); size = sizeof_field(struct bpf_cgroup_storage_key, cgroup_inode_id); if (!btf_member_is_reg_int(btf, key_type, m, 0, size)) return -EINVAL; /* * The second field must be a 32 bit integer at 64 bit offset. */ m++; offset = offsetof(struct bpf_cgroup_storage_key, attach_type); size = sizeof_field(struct bpf_cgroup_storage_key, attach_type); if (!btf_member_is_reg_int(btf, key_type, m, offset, size)) return -EINVAL; } else { u32 int_data; /* * Key is expected to be u64, which stores the cgroup_inode_id */ if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) return -EINVAL; int_data = *(u32 *)(key_type + 1); if (BTF_INT_BITS(int_data) != 64 || BTF_INT_OFFSET(int_data)) return -EINVAL; } return 0; } static void cgroup_storage_seq_show_elem(struct bpf_map *map, void *key, struct seq_file *m) { enum bpf_cgroup_storage_type stype; struct bpf_cgroup_storage *storage; int cpu; rcu_read_lock(); storage = cgroup_storage_lookup(map_to_storage(map), key, false); if (!storage) { rcu_read_unlock(); return; } btf_type_seq_show(map->btf, map->btf_key_type_id, key, m); stype = cgroup_storage_type(map); if (stype == BPF_CGROUP_STORAGE_SHARED) { seq_puts(m, ": "); btf_type_seq_show(map->btf, map->btf_value_type_id, &READ_ONCE(storage->buf)->data[0], m); seq_puts(m, "\n"); } else { seq_puts(m, ": {\n"); for_each_possible_cpu(cpu) { seq_printf(m, "\tcpu%d: ", cpu); btf_type_seq_show(map->btf, map->btf_value_type_id, per_cpu_ptr(storage->percpu_buf, cpu), m); seq_puts(m, "\n"); } seq_puts(m, "}\n"); } rcu_read_unlock(); } BTF_ID_LIST_SINGLE(cgroup_storage_map_btf_ids, struct, bpf_cgroup_storage_map) const struct bpf_map_ops cgroup_storage_map_ops = { .map_alloc = cgroup_storage_map_alloc, .map_free = cgroup_storage_map_free, .map_get_next_key = cgroup_storage_get_next_key, .map_lookup_elem = cgroup_storage_lookup_elem, .map_update_elem = cgroup_storage_update_elem, .map_delete_elem = cgroup_storage_delete_elem, .map_check_btf = cgroup_storage_check_btf, .map_seq_show_elem = cgroup_storage_seq_show_elem, .map_btf_id = &cgroup_storage_map_btf_ids[0], }; int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *_map) { enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map); if (aux->cgroup_storage[stype] && aux->cgroup_storage[stype] != _map) return -EBUSY; aux->cgroup_storage[stype] = _map; return 0; } static size_t bpf_cgroup_storage_calculate_size(struct bpf_map *map, u32 *pages) { size_t size; if (cgroup_storage_type(map) == BPF_CGROUP_STORAGE_SHARED) { size = sizeof(struct bpf_storage_buffer) + map->value_size; *pages = round_up(sizeof(struct bpf_cgroup_storage) + size, PAGE_SIZE) >> PAGE_SHIFT; } else { size = map->value_size; *pages = round_up(round_up(size, 8) * num_possible_cpus(), PAGE_SIZE) >> PAGE_SHIFT; } return size; } struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { const gfp_t gfp = __GFP_ZERO | GFP_USER; struct bpf_cgroup_storage *storage; struct bpf_map *map; size_t size; u32 pages; map = prog->aux->cgroup_storage[stype]; if (!map) return NULL; size = bpf_cgroup_storage_calculate_size(map, &pages); storage = bpf_map_kmalloc_node(map, sizeof(struct bpf_cgroup_storage), gfp, map->numa_node); if (!storage) goto enomem; if (stype == BPF_CGROUP_STORAGE_SHARED) { storage->buf = bpf_map_kmalloc_node(map, size, gfp, map->numa_node); if (!storage->buf) goto enomem; check_and_init_map_value(map, storage->buf->data); } else { storage->percpu_buf = bpf_map_alloc_percpu(map, size, 8, gfp); if (!storage->percpu_buf) goto enomem; } storage->map = (struct bpf_cgroup_storage_map *)map; return storage; enomem: kfree(storage); return ERR_PTR(-ENOMEM); } static void free_shared_cgroup_storage_rcu(struct rcu_head *rcu) { struct bpf_cgroup_storage *storage = container_of(rcu, struct bpf_cgroup_storage, rcu); kfree(storage->buf); kfree(storage); } static void free_percpu_cgroup_storage_rcu(struct rcu_head *rcu) { struct bpf_cgroup_storage *storage = container_of(rcu, struct bpf_cgroup_storage, rcu); free_percpu(storage->percpu_buf); kfree(storage); } void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage) { enum bpf_cgroup_storage_type stype; struct bpf_map *map; if (!storage) return; map = &storage->map->map; stype = cgroup_storage_type(map); if (stype == BPF_CGROUP_STORAGE_SHARED) call_rcu(&storage->rcu, free_shared_cgroup_storage_rcu); else call_rcu(&storage->rcu, free_percpu_cgroup_storage_rcu); } void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, struct cgroup *cgroup, enum bpf_attach_type type) { struct bpf_cgroup_storage_map *map; if (!storage) return; storage->key.attach_type = type; storage->key.cgroup_inode_id = cgroup_id(cgroup); map = storage->map; spin_lock_bh(&map->lock); WARN_ON(cgroup_storage_insert(map, storage)); list_add(&storage->list_map, &map->list); list_add(&storage->list_cg, &cgroup->bpf.storages); spin_unlock_bh(&map->lock); } void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage) { struct bpf_cgroup_storage_map *map; struct rb_root *root; if (!storage) return; map = storage->map; spin_lock_bh(&map->lock); root = &map->root; rb_erase(&storage->node, root); list_del(&storage->list_map); list_del(&storage->list_cg); spin_unlock_bh(&map->lock); } #endif |
| 490 100 102 102 27 8 7 9 16 19 19 99 99 99 96 11 99 99 1 10 7 29 27 101 101 101 101 101 34 34 7 27 34 34 105 105 6 99 98 98 31 74 99 7 99 465 464 72 465 464 465 1244 1244 1243 1244 1243 1243 804 804 785 785 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0+ /* * User-space Probes (UProbes) * * Copyright (C) IBM Corporation, 2008-2012 * Authors: * Srikar Dronamraju * Jim Keniston * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra */ #include <linux/kernel.h> #include <linux/highmem.h> #include <linux/pagemap.h> /* read_mapping_page */ #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/export.h> #include <linux/rmap.h> /* anon_vma_prepare */ #include <linux/mmu_notifier.h> /* set_pte_at_notify */ #include <linux/swap.h> /* folio_free_swap */ #include <linux/ptrace.h> /* user_enable_single_step */ #include <linux/kdebug.h> /* notifier mechanism */ #include "../../mm/internal.h" /* munlock_vma_page */ #include <linux/percpu-rwsem.h> #include <linux/task_work.h> #include <linux/shmem_fs.h> #include <linux/khugepaged.h> #include <linux/uprobes.h> #undef CREATE_TRACE_POINTS #include <trace/hooks/mm.h> #define UINSNS_PER_PAGE (PAGE_SIZE/UPROBE_XOL_SLOT_BYTES) #define MAX_UPROBE_XOL_SLOTS UINSNS_PER_PAGE static struct rb_root uprobes_tree = RB_ROOT; /* * allows us to skip the uprobe_mmap if there are no uprobe events active * at this time. Probably a fine grained per inode count is better? */ #define no_uprobe_events() RB_EMPTY_ROOT(&uprobes_tree) static DEFINE_SPINLOCK(uprobes_treelock); /* serialize rbtree access */ #define UPROBES_HASH_SZ 13 /* serialize uprobe->pending_list */ static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ]; #define uprobes_mmap_hash(v) (&uprobes_mmap_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ]) DEFINE_STATIC_PERCPU_RWSEM(dup_mmap_sem); /* Have a copy of original instruction */ #define UPROBE_COPY_INSN 0 struct uprobe { struct rb_node rb_node; /* node in the rb tree */ refcount_t ref; struct rw_semaphore register_rwsem; struct rw_semaphore consumer_rwsem; struct list_head pending_list; struct uprobe_consumer *consumers; struct inode *inode; /* Also hold a ref to inode */ loff_t offset; loff_t ref_ctr_offset; unsigned long flags; /* * The generic code assumes that it has two members of unknown type * owned by the arch-specific code: * * insn - copy_insn() saves the original instruction here for * arch_uprobe_analyze_insn(). * * ixol - potentially modified instruction to execute out of * line, copied to xol_area by xol_get_insn_slot(). */ struct arch_uprobe arch; }; struct delayed_uprobe { struct list_head list; struct uprobe *uprobe; struct mm_struct *mm; }; static DEFINE_MUTEX(delayed_uprobe_lock); static LIST_HEAD(delayed_uprobe_list); /* * Execute out of line area: anonymous executable mapping installed * by the probed task to execute the copy of the original instruction * mangled by set_swbp(). * * On a breakpoint hit, thread contests for a slot. It frees the * slot after singlestep. Currently a fixed number of slots are * allocated. */ struct xol_area { wait_queue_head_t wq; /* if all slots are busy */ atomic_t slot_count; /* number of in-use slots */ unsigned long *bitmap; /* 0 = free slot */ struct vm_special_mapping xol_mapping; struct page *pages[2]; /* * We keep the vma's vm_start rather than a pointer to the vma * itself. The probed process or a naughty kernel module could make * the vma go away, and we must handle that reasonably gracefully. */ unsigned long vaddr; /* Page(s) of instruction slots */ }; /* * valid_vma: Verify if the specified vma is an executable vma * Relax restrictions while unregistering: vm_flags might have * changed after breakpoint was inserted. * - is_register: indicates if we are in register context. * - Return 1 if the specified virtual address is in an * executable vma. */ static bool valid_vma(struct vm_area_struct *vma, bool is_register) { vm_flags_t flags = VM_HUGETLB | VM_MAYEXEC | VM_MAYSHARE; if (is_register) flags |= VM_WRITE; return vma->vm_file && (vma->vm_flags & flags) == VM_MAYEXEC; } static unsigned long offset_to_vaddr(struct vm_area_struct *vma, loff_t offset) { return vma->vm_start + offset - ((loff_t)vma->vm_pgoff << PAGE_SHIFT); } static loff_t vaddr_to_offset(struct vm_area_struct *vma, unsigned long vaddr) { return ((loff_t)vma->vm_pgoff << PAGE_SHIFT) + (vaddr - vma->vm_start); } /** * __replace_page - replace page in vma by new page. * based on replace_page in mm/ksm.c * * @vma: vma that holds the pte pointing to page * @addr: address the old @page is mapped at * @old_page: the page we are replacing by new_page * @new_page: the modified page we replace page by * * If @new_page is NULL, only unmap @old_page. * * Returns 0 on success, negative error code otherwise. */ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, struct page *old_page, struct page *new_page) { struct folio *old_folio = page_folio(old_page); struct folio *new_folio; struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, old_folio, vma, addr, 0); int err; struct mmu_notifier_range range; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, addr, addr + PAGE_SIZE); if (new_page) { new_folio = page_folio(new_page); err = mem_cgroup_charge(new_folio, vma->vm_mm, GFP_KERNEL); if (err) return err; } /* For folio_free_swap() below */ folio_lock(old_folio); mmu_notifier_invalidate_range_start(&range); err = -EAGAIN; if (!page_vma_mapped_walk(&pvmw)) goto unlock; VM_BUG_ON_PAGE(addr != pvmw.address, old_page); if (new_page) { folio_get(new_folio); page_add_new_anon_rmap(new_page, vma, addr); folio_add_lru_vma(new_folio, vma); trace_android_vh_uprobes_replace_page(new_folio, old_folio); } else /* no new page, just dec_mm_counter for old_page */ dec_mm_counter(mm, MM_ANONPAGES); if (!folio_test_anon(old_folio)) { dec_mm_counter(mm, mm_counter_file(old_page)); inc_mm_counter(mm, MM_ANONPAGES); } flush_cache_page(vma, addr, pte_pfn(*pvmw.pte)); ptep_clear_flush_notify(vma, addr, pvmw.pte); if (new_page) set_pte_at_notify(mm, addr, pvmw.pte, mk_pte(new_page, vma->vm_page_prot)); page_remove_rmap(old_page, vma, false); if (!folio_mapped(old_folio)) folio_free_swap(old_folio); page_vma_mapped_walk_done(&pvmw); folio_put(old_folio); err = 0; unlock: mmu_notifier_invalidate_range_end(&range); folio_unlock(old_folio); return err; } /** * is_swbp_insn - check if instruction is breakpoint instruction. * @insn: instruction to be checked. * Default implementation of is_swbp_insn * Returns true if @insn is a breakpoint instruction. */ bool __weak is_swbp_insn(uprobe_opcode_t *insn) { return *insn == UPROBE_SWBP_INSN; } /** * is_trap_insn - check if instruction is breakpoint instruction. * @insn: instruction to be checked. * Default implementation of is_trap_insn * Returns true if @insn is a breakpoint instruction. * * This function is needed for the case where an architecture has multiple * trap instructions (like powerpc). */ bool __weak is_trap_insn(uprobe_opcode_t *insn) { return is_swbp_insn(insn); } static void copy_from_page(struct page *page, unsigned long vaddr, void *dst, int len) { void *kaddr = kmap_atomic(page); memcpy(dst, kaddr + (vaddr & ~PAGE_MASK), len); kunmap_atomic(kaddr); } static void copy_to_page(struct page *page, unsigned long vaddr, const void *src, int len) { void *kaddr = kmap_atomic(page); memcpy(kaddr + (vaddr & ~PAGE_MASK), src, len); kunmap_atomic(kaddr); } static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t *new_opcode) { uprobe_opcode_t old_opcode; bool is_swbp; /* * Note: We only check if the old_opcode is UPROBE_SWBP_INSN here. * We do not check if it is any other 'trap variant' which could * be conditional trap instruction such as the one powerpc supports. * * The logic is that we do not care if the underlying instruction * is a trap variant; uprobes always wins over any other (gdb) * breakpoint. */ copy_from_page(page, vaddr, &old_opcode, UPROBE_SWBP_INSN_SIZE); is_swbp = is_swbp_insn(&old_opcode); if (is_swbp_insn(new_opcode)) { if (is_swbp) /* register: already installed? */ return 0; } else { if (!is_swbp) /* unregister: was it changed by us? */ return 0; } return 1; } static struct delayed_uprobe * delayed_uprobe_check(struct uprobe *uprobe, struct mm_struct *mm) { struct delayed_uprobe *du; list_for_each_entry(du, &delayed_uprobe_list, list) if (du->uprobe == uprobe && du->mm == mm) return du; return NULL; } static int delayed_uprobe_add(struct uprobe *uprobe, struct mm_struct *mm) { struct delayed_uprobe *du; if (delayed_uprobe_check(uprobe, mm)) return 0; du = kzalloc(sizeof(*du), GFP_KERNEL); if (!du) return -ENOMEM; du->uprobe = uprobe; du->mm = mm; list_add(&du->list, &delayed_uprobe_list); return 0; } static void delayed_uprobe_delete(struct delayed_uprobe *du) { if (WARN_ON(!du)) return; list_del(&du->list); kfree(du); } static void delayed_uprobe_remove(struct uprobe *uprobe, struct mm_struct *mm) { struct list_head *pos, *q; struct delayed_uprobe *du; if (!uprobe && !mm) return; list_for_each_safe(pos, q, &delayed_uprobe_list) { du = list_entry(pos, struct delayed_uprobe, list); if (uprobe && du->uprobe != uprobe) continue; if (mm && du->mm != mm) continue; delayed_uprobe_delete(du); } } static bool valid_ref_ctr_vma(struct uprobe *uprobe, struct vm_area_struct *vma) { unsigned long vaddr = offset_to_vaddr(vma, uprobe->ref_ctr_offset); return uprobe->ref_ctr_offset && vma->vm_file && file_inode(vma->vm_file) == uprobe->inode && (vma->vm_flags & (VM_WRITE|VM_SHARED)) == VM_WRITE && vma->vm_start <= vaddr && vma->vm_end > vaddr; } static struct vm_area_struct * find_ref_ctr_vma(struct uprobe *uprobe, struct mm_struct *mm) { VMA_ITERATOR(vmi, mm, 0); struct vm_area_struct *tmp; for_each_vma(vmi, tmp) if (valid_ref_ctr_vma(uprobe, tmp)) return tmp; return NULL; } static int __update_ref_ctr(struct mm_struct *mm, unsigned long vaddr, short d) { void *kaddr; struct page *page; struct vm_area_struct *vma; int ret; short *ptr; if (!vaddr || !d) return -EINVAL; ret = get_user_pages_remote(mm, vaddr, 1, FOLL_WRITE, &page, &vma, NULL); if (unlikely(ret <= 0)) { /* * We are asking for 1 page. If get_user_pages_remote() fails, * it may return 0, in that case we have to return error. */ return ret == 0 ? -EBUSY : ret; } kaddr = kmap_atomic(page); ptr = kaddr + (vaddr & ~PAGE_MASK); if (unlikely(*ptr + d < 0)) { pr_warn("ref_ctr going negative. vaddr: 0x%lx, " "curr val: %d, delta: %d\n", vaddr, *ptr, d); ret = -EINVAL; goto out; } *ptr += d; ret = 0; out: kunmap_atomic(kaddr); put_page(page); return ret; } static void update_ref_ctr_warn(struct uprobe *uprobe, struct mm_struct *mm, short d) { pr_warn("ref_ctr %s failed for inode: 0x%lx offset: " "0x%llx ref_ctr_offset: 0x%llx of mm: 0x%pK\n", d > 0 ? "increment" : "decrement", uprobe->inode->i_ino, (unsigned long long) uprobe->offset, (unsigned long long) uprobe->ref_ctr_offset, mm); } static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm, short d) { struct vm_area_struct *rc_vma; unsigned long rc_vaddr; int ret = 0; rc_vma = find_ref_ctr_vma(uprobe, mm); if (rc_vma) { rc_vaddr = offset_to_vaddr(rc_vma, uprobe->ref_ctr_offset); ret = __update_ref_ctr(mm, rc_vaddr, d); if (ret) update_ref_ctr_warn(uprobe, mm, d); if (d > 0) return ret; } mutex_lock(&delayed_uprobe_lock); if (d > 0) ret = delayed_uprobe_add(uprobe, mm); else delayed_uprobe_remove(uprobe, mm); mutex_unlock(&delayed_uprobe_lock); return ret; } /* * NOTE: * Expect the breakpoint instruction to be the smallest size instruction for * the architecture. If an arch has variable length instruction and the * breakpoint instruction is not of the smallest length instruction * supported by that architecture then we need to modify is_trap_at_addr and * uprobe_write_opcode accordingly. This would never be a problem for archs * that have fixed length instructions. * * uprobe_write_opcode - write the opcode at a given virtual address. * @auprobe: arch specific probepoint information. * @mm: the probed process address space. * @vaddr: the virtual address to store the opcode. * @opcode: opcode to be written at @vaddr. * * Called with mm->mmap_lock held for write. * Return 0 (success) or a negative errno. */ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t opcode) { struct uprobe *uprobe; struct page *old_page, *new_page; struct vm_area_struct *vma; int ret, is_register, ref_ctr_updated = 0; bool orig_page_huge = false; unsigned int gup_flags = FOLL_FORCE; is_register = is_swbp_insn(&opcode); uprobe = container_of(auprobe, struct uprobe, arch); retry: if (is_register) gup_flags |= FOLL_SPLIT_PMD; /* Read the page with vaddr into memory */ ret = get_user_pages_remote(mm, vaddr, 1, gup_flags, &old_page, &vma, NULL); if (ret <= 0) return ret; ret = verify_opcode(old_page, vaddr, &opcode); if (ret <= 0) goto put_old; if (WARN(!is_register && PageCompound(old_page), "uprobe unregister should never work on compound page\n")) { ret = -EINVAL; goto put_old; } /* We are going to replace instruction, update ref_ctr. */ if (!ref_ctr_updated && uprobe->ref_ctr_offset) { ret = update_ref_ctr(uprobe, mm, is_register ? 1 : -1); if (ret) goto put_old; ref_ctr_updated = 1; } ret = 0; if (!is_register && !PageAnon(old_page)) goto put_old; ret = anon_vma_prepare(vma); if (ret) goto put_old; ret = -ENOMEM; new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr); if (!new_page) goto put_old; __SetPageUptodate(new_page); copy_highpage(new_page, old_page); copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE); if (!is_register) { struct page *orig_page; pgoff_t index; VM_BUG_ON_PAGE(!PageAnon(old_page), old_page); index = vaddr_to_offset(vma, vaddr & PAGE_MASK) >> PAGE_SHIFT; orig_page = find_get_page(vma->vm_file->f_inode->i_mapping, index); if (orig_page) { if (PageUptodate(orig_page) && pages_identical(new_page, orig_page)) { /* let go new_page */ put_page(new_page); new_page = NULL; if (PageCompound(orig_page)) orig_page_huge = true; } put_page(orig_page); } } ret = __replace_page(vma, vaddr, old_page, new_page); if (new_page) put_page(new_page); put_old: put_page(old_page); if (unlikely(ret == -EAGAIN)) goto retry; /* Revert back reference counter if instruction update failed. */ if (ret && is_register && ref_ctr_updated) update_ref_ctr(uprobe, mm, -1); /* try collapse pmd for compound page */ if (!ret && orig_page_huge) collapse_pte_mapped_thp(mm, vaddr, false); return ret; } /** * set_swbp - store breakpoint at a given address. * @auprobe: arch specific probepoint information. * @mm: the probed process address space. * @vaddr: the virtual address to insert the opcode. * * For mm @mm, store the breakpoint instruction at @vaddr. * Return 0 (success) or a negative errno. */ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr) { return uprobe_write_opcode(auprobe, mm, vaddr, UPROBE_SWBP_INSN); } /** * set_orig_insn - Restore the original instruction. * @mm: the probed process address space. * @auprobe: arch specific probepoint information. * @vaddr: the virtual address to insert the opcode. * * For mm @mm, restore the original opcode (opcode) at @vaddr. * Return 0 (success) or a negative errno. */ int __weak set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr) { return uprobe_write_opcode(auprobe, mm, vaddr, *(uprobe_opcode_t *)&auprobe->insn); } static struct uprobe *get_uprobe(struct uprobe *uprobe) { refcount_inc(&uprobe->ref); return uprobe; } static void put_uprobe(struct uprobe *uprobe) { if (refcount_dec_and_test(&uprobe->ref)) { /* * If application munmap(exec_vma) before uprobe_unregister() * gets called, we don't get a chance to remove uprobe from * delayed_uprobe_list from remove_breakpoint(). Do it here. */ mutex_lock(&delayed_uprobe_lock); delayed_uprobe_remove(uprobe, NULL); mutex_unlock(&delayed_uprobe_lock); kfree(uprobe); } } static __always_inline int uprobe_cmp(const struct inode *l_inode, const loff_t l_offset, const struct uprobe *r) { if (l_inode < r->inode) return -1; if (l_inode > r->inode) return 1; if (l_offset < r->offset) return -1; if (l_offset > r->offset) return 1; return 0; } #define __node_2_uprobe(node) \ rb_entry((node), struct uprobe, rb_node) struct __uprobe_key { struct inode *inode; loff_t offset; }; static inline int __uprobe_cmp_key(const void *key, const struct rb_node *b) { const struct __uprobe_key *a = key; return uprobe_cmp(a->inode, a->offset, __node_2_uprobe(b)); } static inline int __uprobe_cmp(struct rb_node *a, const struct rb_node *b) { struct uprobe *u = __node_2_uprobe(a); return uprobe_cmp(u->inode, u->offset, __node_2_uprobe(b)); } static struct uprobe *__find_uprobe(struct inode *inode, loff_t offset) { struct __uprobe_key key = { .inode = inode, .offset = offset, }; struct rb_node *node = rb_find(&key, &uprobes_tree, __uprobe_cmp_key); if (node) return get_uprobe(__node_2_uprobe(node)); return NULL; } /* * Find a uprobe corresponding to a given inode:offset * Acquires uprobes_treelock */ static struct uprobe *find_uprobe(struct inode *inode, loff_t offset) { struct uprobe *uprobe; spin_lock(&uprobes_treelock); uprobe = __find_uprobe(inode, offset); spin_unlock(&uprobes_treelock); return uprobe; } static struct uprobe *__insert_uprobe(struct uprobe *uprobe) { struct rb_node *node; node = rb_find_add(&uprobe->rb_node, &uprobes_tree, __uprobe_cmp); if (node) return get_uprobe(__node_2_uprobe(node)); /* get access + creation ref */ refcount_set(&uprobe->ref, 2); return NULL; } /* * Acquire uprobes_treelock. * Matching uprobe already exists in rbtree; * increment (access refcount) and return the matching uprobe. * * No matching uprobe; insert the uprobe in rb_tree; * get a double refcount (access + creation) and return NULL. */ static struct uprobe *insert_uprobe(struct uprobe *uprobe) { struct uprobe *u; spin_lock(&uprobes_treelock); u = __insert_uprobe(uprobe); spin_unlock(&uprobes_treelock); return u; } static void ref_ctr_mismatch_warn(struct uprobe *cur_uprobe, struct uprobe *uprobe) { pr_warn("ref_ctr_offset mismatch. inode: 0x%lx offset: 0x%llx " "ref_ctr_offset(old): 0x%llx ref_ctr_offset(new): 0x%llx\n", uprobe->inode->i_ino, (unsigned long long) uprobe->offset, (unsigned long long) cur_uprobe->ref_ctr_offset, (unsigned long long) uprobe->ref_ctr_offset); } static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset, loff_t ref_ctr_offset) { struct uprobe *uprobe, *cur_uprobe; uprobe = kzalloc(sizeof(struct uprobe), GFP_KERNEL); if (!uprobe) return NULL; uprobe->inode = inode; uprobe->offset = offset; uprobe->ref_ctr_offset = ref_ctr_offset; init_rwsem(&uprobe->register_rwsem); init_rwsem(&uprobe->consumer_rwsem); /* add to uprobes_tree, sorted on inode:offset */ cur_uprobe = insert_uprobe(uprobe); /* a uprobe exists for this inode:offset combination */ if (cur_uprobe) { if (cur_uprobe->ref_ctr_offset != uprobe->ref_ctr_offset) { ref_ctr_mismatch_warn(cur_uprobe, uprobe); put_uprobe(cur_uprobe); kfree(uprobe); return ERR_PTR(-EINVAL); } kfree(uprobe); uprobe = cur_uprobe; } return uprobe; } static void consumer_add(struct uprobe *uprobe, struct uprobe_consumer *uc) { down_write(&uprobe->consumer_rwsem); uc->next = uprobe->consumers; uprobe->consumers = uc; up_write(&uprobe->consumer_rwsem); } /* * For uprobe @uprobe, delete the consumer @uc. * Return true if the @uc is deleted successfully * or return false. */ static bool consumer_del(struct uprobe *uprobe, struct uprobe_consumer *uc) { struct uprobe_consumer **con; bool ret = false; down_write(&uprobe->consumer_rwsem); for (con = &uprobe->consumers; *con; con = &(*con)->next) { if (*con == uc) { *con = uc->next; ret = true; break; } } up_write(&uprobe->consumer_rwsem); return ret; } static int __copy_insn(struct address_space *mapping, struct file *filp, void *insn, int nbytes, loff_t offset) { struct page *page; /* * Ensure that the page that has the original instruction is populated * and in page-cache. If ->read_folio == NULL it must be shmem_mapping(), * see uprobe_register(). */ if (mapping->a_ops->read_folio) page = read_mapping_page(mapping, offset >> PAGE_SHIFT, filp); else page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT); if (IS_ERR(page)) return PTR_ERR(page); copy_from_page(page, offset, insn, nbytes); put_page(page); return 0; } static int copy_insn(struct uprobe *uprobe, struct file *filp) { struct address_space *mapping = uprobe->inode->i_mapping; loff_t offs = uprobe->offset; void *insn = &uprobe->arch.insn; int size = sizeof(uprobe->arch.insn); int len, err = -EIO; /* Copy only available bytes, -EIO if nothing was read */ do { if (offs >= i_size_read(uprobe->inode)) break; len = min_t(int, size, PAGE_SIZE - (offs & ~PAGE_MASK)); err = __copy_insn(mapping, filp, insn, len, offs); if (err) break; insn += len; offs += len; size -= len; } while (size); return err; } static int prepare_uprobe(struct uprobe *uprobe, struct file *file, struct mm_struct *mm, unsigned long vaddr) { int ret = 0; if (test_bit(UPROBE_COPY_INSN, &uprobe->flags)) return ret; /* TODO: move this into _register, until then we abuse this sem. */ down_write(&uprobe->consumer_rwsem); if (test_bit(UPROBE_COPY_INSN, &uprobe->flags)) goto out; ret = copy_insn(uprobe, file); if (ret) goto out; ret = -ENOTSUPP; if (is_trap_insn((uprobe_opcode_t *)&uprobe->arch.insn)) goto out; ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr); if (ret) goto out; smp_wmb(); /* pairs with the smp_rmb() in handle_swbp() */ set_bit(UPROBE_COPY_INSN, &uprobe->flags); out: up_write(&uprobe->consumer_rwsem); return ret; } static inline bool consumer_filter(struct uprobe_consumer *uc, enum uprobe_filter_ctx ctx, struct mm_struct *mm) { return !uc->filter || uc->filter(uc, ctx, mm); } static bool filter_chain(struct uprobe *uprobe, enum uprobe_filter_ctx ctx, struct mm_struct *mm) { struct uprobe_consumer *uc; bool ret = false; down_read(&uprobe->consumer_rwsem); for (uc = uprobe->consumers; uc; uc = uc->next) { ret = consumer_filter(uc, ctx, mm); if (ret) break; } up_read(&uprobe->consumer_rwsem); return ret; } static int install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long vaddr) { bool first_uprobe; int ret; ret = prepare_uprobe(uprobe, vma->vm_file, mm, vaddr); if (ret) return ret; /* * set MMF_HAS_UPROBES in advance for uprobe_pre_sstep_notifier(), * the task can hit this breakpoint right after __replace_page(). */ first_uprobe = !test_bit(MMF_HAS_UPROBES, &mm->flags); if (first_uprobe) set_bit(MMF_HAS_UPROBES, &mm->flags); ret = set_swbp(&uprobe->arch, mm, vaddr); if (!ret) clear_bit(MMF_RECALC_UPROBES, &mm->flags); else if (first_uprobe) clear_bit(MMF_HAS_UPROBES, &mm->flags); return ret; } static int remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr) { set_bit(MMF_RECALC_UPROBES, &mm->flags); return set_orig_insn(&uprobe->arch, mm, vaddr); } static inline bool uprobe_is_active(struct uprobe *uprobe) { return !RB_EMPTY_NODE(&uprobe->rb_node); } /* * There could be threads that have already hit the breakpoint. They * will recheck the current insn and restart if find_uprobe() fails. * See find_active_uprobe(). */ static void delete_uprobe(struct uprobe *uprobe) { if (WARN_ON(!uprobe_is_active(uprobe))) return; spin_lock(&uprobes_treelock); rb_erase(&uprobe->rb_node, &uprobes_tree); spin_unlock(&uprobes_treelock); RB_CLEAR_NODE(&uprobe->rb_node); /* for uprobe_is_active() */ put_uprobe(uprobe); } struct map_info { struct map_info *next; struct mm_struct *mm; unsigned long vaddr; }; static inline struct map_info *free_map_info(struct map_info *info) { struct map_info *next = info->next; kfree(info); return next; } static struct map_info * build_map_info(struct address_space *mapping, loff_t offset, bool is_register) { unsigned long pgoff = offset >> PAGE_SHIFT; struct vm_area_struct *vma; struct map_info *curr = NULL; struct map_info *prev = NULL; struct map_info *info; int more = 0; again: i_mmap_lock_read(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { if (!valid_vma(vma, is_register)) continue; if (!prev && !more) { /* * Needs GFP_NOWAIT to avoid i_mmap_rwsem recursion through * reclaim. This is optimistic, no harm done if it fails. */ prev = kmalloc(sizeof(struct map_info), GFP_NOWAIT | __GFP_NOMEMALLOC | __GFP_NOWARN); if (prev) prev->next = NULL; } if (!prev) { more++; continue; } if (!mmget_not_zero(vma->vm_mm)) continue; info = prev; prev = prev->next; info->next = curr; curr = info; info->mm = vma->vm_mm; info->vaddr = offset_to_vaddr(vma, offset); } i_mmap_unlock_read(mapping); if (!more) goto out; prev = curr; while (curr) { mmput(curr->mm); curr = curr->next; } do { info = kmalloc(sizeof(struct map_info), GFP_KERNEL); if (!info) { curr = ERR_PTR(-ENOMEM); goto out; } info->next = prev; prev = info; } while (--more); goto again; out: while (prev) prev = free_map_info(prev); return curr; } static int register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new) { bool is_register = !!new; struct map_info *info; int err = 0; percpu_down_write(&dup_mmap_sem); info = build_map_info(uprobe->inode->i_mapping, uprobe->offset, is_register); if (IS_ERR(info)) { err = PTR_ERR(info); goto out; } while (info) { struct mm_struct *mm = info->mm; struct vm_area_struct *vma; if (err && is_register) goto free; mmap_write_lock(mm); vma = find_vma(mm, info->vaddr); if (!vma || !valid_vma(vma, is_register) || file_inode(vma->vm_file) != uprobe->inode) goto unlock; if (vma->vm_start > info->vaddr || vaddr_to_offset(vma, info->vaddr) != uprobe->offset) goto unlock; if (is_register) { /* consult only the "caller", new consumer. */ if (consumer_filter(new, UPROBE_FILTER_REGISTER, mm)) err = install_breakpoint(uprobe, mm, vma, info->vaddr); } else if (test_bit(MMF_HAS_UPROBES, &mm->flags)) { if (!filter_chain(uprobe, UPROBE_FILTER_UNREGISTER, mm)) err |= remove_breakpoint(uprobe, mm, info->vaddr); } unlock: mmap_write_unlock(mm); free: mmput(mm); info = free_map_info(info); } out: percpu_up_write(&dup_mmap_sem); return err; } static void __uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc) { int err; if (WARN_ON(!consumer_del(uprobe, uc))) return; err = register_for_each_vma(uprobe, NULL); /* TODO : cant unregister? schedule a worker thread */ if (!uprobe->consumers && !err) delete_uprobe(uprobe); } /* * uprobe_unregister - unregister an already registered probe. * @inode: the file in which the probe has to be removed. * @offset: offset from the start of the file. * @uc: identify which probe if multiple probes are colocated. */ void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) { struct uprobe *uprobe; uprobe = find_uprobe(inode, offset); if (WARN_ON(!uprobe)) return; down_write(&uprobe->register_rwsem); __uprobe_unregister(uprobe, uc); up_write(&uprobe->register_rwsem); put_uprobe(uprobe); } EXPORT_SYMBOL_GPL(uprobe_unregister); /* * __uprobe_register - register a probe * @inode: the file in which the probe has to be placed. * @offset: offset from the start of the file. * @uc: information on howto handle the probe.. * * Apart from the access refcount, __uprobe_register() takes a creation * refcount (thro alloc_uprobe) if and only if this @uprobe is getting * inserted into the rbtree (i.e first consumer for a @inode:@offset * tuple). Creation refcount stops uprobe_unregister from freeing the * @uprobe even before the register operation is complete. Creation * refcount is released when the last @uc for the @uprobe * unregisters. Caller of __uprobe_register() is required to keep @inode * (and the containing mount) referenced. * * Return errno if it cannot successully install probes * else return 0 (success) */ static int __uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc) { struct uprobe *uprobe; int ret; /* Uprobe must have at least one set consumer */ if (!uc->handler && !uc->ret_handler) return -EINVAL; /* copy_insn() uses read_mapping_page() or shmem_read_mapping_page() */ if (!inode->i_mapping->a_ops->read_folio && !shmem_mapping(inode->i_mapping)) return -EIO; /* Racy, just to catch the obvious mistakes */ if (offset > i_size_read(inode)) return -EINVAL; /* * This ensures that copy_from_page(), copy_to_page() and * __update_ref_ctr() can't cross page boundary. */ if (!IS_ALIGNED(offset, UPROBE_SWBP_INSN_SIZE)) return -EINVAL; if (!IS_ALIGNED(ref_ctr_offset, sizeof(short))) return -EINVAL; retry: uprobe = alloc_uprobe(inode, offset, ref_ctr_offset); if (!uprobe) return -ENOMEM; if (IS_ERR(uprobe)) return PTR_ERR(uprobe); /* * We can race with uprobe_unregister()->delete_uprobe(). * Check uprobe_is_active() and retry if it is false. */ down_write(&uprobe->register_rwsem); ret = -EAGAIN; if (likely(uprobe_is_active(uprobe))) { consumer_add(uprobe, uc); ret = register_for_each_vma(uprobe, uc); if (ret) __uprobe_unregister(uprobe, uc); } up_write(&uprobe->register_rwsem); put_uprobe(uprobe); if (unlikely(ret == -EAGAIN)) goto retry; return ret; } int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) { return __uprobe_register(inode, offset, 0, uc); } EXPORT_SYMBOL_GPL(uprobe_register); int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc) { return __uprobe_register(inode, offset, ref_ctr_offset, uc); } EXPORT_SYMBOL_GPL(uprobe_register_refctr); /* * uprobe_apply - unregister an already registered probe. * @inode: the file in which the probe has to be removed. * @offset: offset from the start of the file. * @uc: consumer which wants to add more or remove some breakpoints * @add: add or remove the breakpoints */ int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool add) { struct uprobe *uprobe; struct uprobe_consumer *con; int ret = -ENOENT; uprobe = find_uprobe(inode, offset); if (WARN_ON(!uprobe)) return ret; down_write(&uprobe->register_rwsem); for (con = uprobe->consumers; con && con != uc ; con = con->next) ; if (con) ret = register_for_each_vma(uprobe, add ? uc : NULL); up_write(&uprobe->register_rwsem); put_uprobe(uprobe); return ret; } static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm) { VMA_ITERATOR(vmi, mm, 0); struct vm_area_struct *vma; int err = 0; mmap_read_lock(mm); for_each_vma(vmi, vma) { unsigned long vaddr; loff_t offset; if (!valid_vma(vma, false) || file_inode(vma->vm_file) != uprobe->inode) continue; offset = (loff_t)vma->vm_pgoff << PAGE_SHIFT; if (uprobe->offset < offset || uprobe->offset >= offset + vma->vm_end - vma->vm_start) continue; vaddr = offset_to_vaddr(vma, uprobe->offset); err |= remove_breakpoint(uprobe, mm, vaddr); } mmap_read_unlock(mm); return err; } static struct rb_node * find_node_in_range(struct inode *inode, loff_t min, loff_t max) { struct rb_node *n = uprobes_tree.rb_node; while (n) { struct uprobe *u = rb_entry(n, struct uprobe, rb_node); if (inode < u->inode) { n = n->rb_left; } else if (inode > u->inode) { n = n->rb_right; } else { if (max < u->offset) n = n->rb_left; else if (min > u->offset) n = n->rb_right; else break; } } return n; } /* * For a given range in vma, build a list of probes that need to be inserted. */ static void build_probe_list(struct inode *inode, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *head) { loff_t min, max; struct rb_node *n, *t; struct uprobe *u; INIT_LIST_HEAD(head); min = vaddr_to_offset(vma, start); max = min + (end - start) - 1; spin_lock(&uprobes_treelock); n = find_node_in_range(inode, min, max); if (n) { for (t = n; t; t = rb_prev(t)) { u = rb_entry(t, struct uprobe, rb_node); if (u->inode != inode || u->offset < min) break; list_add(&u->pending_list, head); get_uprobe(u); } for (t = n; (t = rb_next(t)); ) { u = rb_entry(t, struct uprobe, rb_node); if (u->inode != inode || u->offset > max) break; list_add(&u->pending_list, head); get_uprobe(u); } } spin_unlock(&uprobes_treelock); } /* @vma contains reference counter, not the probed instruction. */ static int delayed_ref_ctr_inc(struct vm_area_struct *vma) { struct list_head *pos, *q; struct delayed_uprobe *du; unsigned long vaddr; int ret = 0, err = 0; mutex_lock(&delayed_uprobe_lock); list_for_each_safe(pos, q, &delayed_uprobe_list) { du = list_entry(pos, struct delayed_uprobe, list); if (du->mm != vma->vm_mm || !valid_ref_ctr_vma(du->uprobe, vma)) continue; vaddr = offset_to_vaddr(vma, du->uprobe->ref_ctr_offset); ret = __update_ref_ctr(vma->vm_mm, vaddr, 1); if (ret) { update_ref_ctr_warn(du->uprobe, vma->vm_mm, 1); if (!err) err = ret; } delayed_uprobe_delete(du); } mutex_unlock(&delayed_uprobe_lock); return err; } /* * Called from mmap_region/vma_adjust with mm->mmap_lock acquired. * * Currently we ignore all errors and always return 0, the callers * can't handle the failure anyway. */ int uprobe_mmap(struct vm_area_struct *vma) { struct list_head tmp_list; struct uprobe *uprobe, *u; struct inode *inode; if (no_uprobe_events()) return 0; if (vma->vm_file && (vma->vm_flags & (VM_WRITE|VM_SHARED)) == VM_WRITE && test_bit(MMF_HAS_UPROBES, &vma->vm_mm->flags)) delayed_ref_ctr_inc(vma); if (!valid_vma(vma, true)) return 0; inode = file_inode(vma->vm_file); if (!inode) return 0; mutex_lock(uprobes_mmap_hash(inode)); build_probe_list(inode, vma, vma->vm_start, vma->vm_end, &tmp_list); /* * We can race with uprobe_unregister(), this uprobe can be already * removed. But in this case filter_chain() must return false, all * consumers have gone away. */ list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) { if (!fatal_signal_pending(current) && filter_chain(uprobe, UPROBE_FILTER_MMAP, vma->vm_mm)) { unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset); install_breakpoint(uprobe, vma->vm_mm, vma, vaddr); } put_uprobe(uprobe); } mutex_unlock(uprobes_mmap_hash(inode)); return 0; } static bool vma_has_uprobes(struct vm_area_struct *vma, unsigned long start, unsigned long end) { loff_t min, max; struct inode *inode; struct rb_node *n; inode = file_inode(vma->vm_file); min = vaddr_to_offset(vma, start); max = min + (end - start) - 1; spin_lock(&uprobes_treelock); n = find_node_in_range(inode, min, max); spin_unlock(&uprobes_treelock); return !!n; } /* * Called in context of a munmap of a vma. */ void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end) { if (no_uprobe_events() || !valid_vma(vma, false)) return; if (!atomic_read(&vma->vm_mm->mm_users)) /* called by mmput() ? */ return; if (!test_bit(MMF_HAS_UPROBES, &vma->vm_mm->flags) || test_bit(MMF_RECALC_UPROBES, &vma->vm_mm->flags)) return; if (vma_has_uprobes(vma, start, end)) set_bit(MMF_RECALC_UPROBES, &vma->vm_mm->flags); } /* Slot allocation for XOL */ static int xol_add_vma(struct mm_struct *mm, struct xol_area *area) { struct vm_area_struct *vma; int ret; if (mmap_write_lock_killable(mm)) return -EINTR; if (mm->uprobes_state.xol_area) { ret = -EALREADY; goto fail; } if (!area->vaddr) { /* Try to map as high as possible, this is only a hint. */ area->vaddr = get_unmapped_area(NULL, TASK_SIZE - PAGE_SIZE, PAGE_SIZE, 0, 0); if (IS_ERR_VALUE(area->vaddr)) { ret = area->vaddr; goto fail; } } vma = _install_special_mapping(mm, area->vaddr, PAGE_SIZE, VM_EXEC|VM_MAYEXEC|VM_DONTCOPY|VM_IO, &area->xol_mapping); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto fail; } ret = 0; /* pairs with get_xol_area() */ smp_store_release(&mm->uprobes_state.xol_area, area); /* ^^^ */ fail: mmap_write_unlock(mm); return ret; } static struct xol_area *__create_xol_area(unsigned long vaddr) { struct mm_struct *mm = current->mm; uprobe_opcode_t insn = UPROBE_SWBP_INSN; struct xol_area *area; area = kzalloc(sizeof(*area), GFP_KERNEL); if (unlikely(!area)) goto out; area->bitmap = kcalloc(BITS_TO_LONGS(UINSNS_PER_PAGE), sizeof(long), GFP_KERNEL); if (!area->bitmap) goto free_area; area->xol_mapping.name = "[uprobes]"; area->xol_mapping.pages = area->pages; area->pages[0] = alloc_page(GFP_HIGHUSER | __GFP_ZERO); if (!area->pages[0]) goto free_bitmap; area->pages[1] = NULL; area->vaddr = vaddr; init_waitqueue_head(&area->wq); /* Reserve the 1st slot for get_trampoline_vaddr() */ set_bit(0, area->bitmap); atomic_set(&area->slot_count, 1); arch_uprobe_copy_ixol(area->pages[0], 0, &insn, UPROBE_SWBP_INSN_SIZE); if (!xol_add_vma(mm, area)) return area; __free_page(area->pages[0]); free_bitmap: kfree(area->bitmap); free_area: kfree(area); out: return NULL; } /* * get_xol_area - Allocate process's xol_area if necessary. * This area will be used for storing instructions for execution out of line. * * Returns the allocated area or NULL. */ static struct xol_area *get_xol_area(void) { struct mm_struct *mm = current->mm; struct xol_area *area; if (!mm->uprobes_state.xol_area) __create_xol_area(0); /* Pairs with xol_add_vma() smp_store_release() */ area = READ_ONCE(mm->uprobes_state.xol_area); /* ^^^ */ return area; } /* * uprobe_clear_state - Free the area allocated for slots. */ void uprobe_clear_state(struct mm_struct *mm) { struct xol_area *area = mm->uprobes_state.xol_area; mutex_lock(&delayed_uprobe_lock); delayed_uprobe_remove(NULL, mm); mutex_unlock(&delayed_uprobe_lock); if (!area) return; put_page(area->pages[0]); kfree(area->bitmap); kfree(area); } void uprobe_start_dup_mmap(void) { percpu_down_read(&dup_mmap_sem); } void uprobe_end_dup_mmap(void) { percpu_up_read(&dup_mmap_sem); } void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm) { if (test_bit(MMF_HAS_UPROBES, &oldmm->flags)) { set_bit(MMF_HAS_UPROBES, &newmm->flags); /* unconditionally, dup_mmap() skips VM_DONTCOPY vmas */ set_bit(MMF_RECALC_UPROBES, &newmm->flags); } } /* * - search for a free slot. */ static unsigned long xol_take_insn_slot(struct xol_area *area) { unsigned long slot_addr; int slot_nr; do { slot_nr = find_first_zero_bit(area->bitmap, UINSNS_PER_PAGE); if (slot_nr < UINSNS_PER_PAGE) { if (!test_and_set_bit(slot_nr, area->bitmap)) break; slot_nr = UINSNS_PER_PAGE; continue; } wait_event(area->wq, (atomic_read(&area->slot_count) < UINSNS_PER_PAGE)); } while (slot_nr >= UINSNS_PER_PAGE); slot_addr = area->vaddr + (slot_nr * UPROBE_XOL_SLOT_BYTES); atomic_inc(&area->slot_count); return slot_addr; } /* * xol_get_insn_slot - allocate a slot for xol. * Returns the allocated slot address or 0. */ static unsigned long xol_get_insn_slot(struct uprobe *uprobe) { struct xol_area *area; unsigned long xol_vaddr; area = get_xol_area(); if (!area) return 0; xol_vaddr = xol_take_insn_slot(area); if (unlikely(!xol_vaddr)) return 0; arch_uprobe_copy_ixol(area->pages[0], xol_vaddr, &uprobe->arch.ixol, sizeof(uprobe->arch.ixol)); return xol_vaddr; } /* * xol_free_insn_slot - If slot was earlier allocated by * @xol_get_insn_slot(), make the slot available for * subsequent requests. */ static void xol_free_insn_slot(struct task_struct *tsk) { struct xol_area *area; unsigned long vma_end; unsigned long slot_addr; if (!tsk->mm || !tsk->mm->uprobes_state.xol_area || !tsk->utask) return; slot_addr = tsk->utask->xol_vaddr; if (unlikely(!slot_addr)) return; area = tsk->mm->uprobes_state.xol_area; vma_end = area->vaddr + PAGE_SIZE; if (area->vaddr <= slot_addr && slot_addr < vma_end) { unsigned long offset; int slot_nr; offset = slot_addr - area->vaddr; slot_nr = offset / UPROBE_XOL_SLOT_BYTES; if (slot_nr >= UINSNS_PER_PAGE) return; clear_bit(slot_nr, area->bitmap); atomic_dec(&area->slot_count); smp_mb__after_atomic(); /* pairs with prepare_to_wait() */ if (waitqueue_active(&area->wq)) wake_up(&area->wq); tsk->utask->xol_vaddr = 0; } } void __weak arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, void *src, unsigned long len) { /* Initialize the slot */ copy_to_page(page, vaddr, src, len); /* * We probably need flush_icache_user_page() but it needs vma. * This should work on most of architectures by default. If * architecture needs to do something different it can define * its own version of the function. */ flush_dcache_page(page); } /** * uprobe_get_swbp_addr - compute address of swbp given post-swbp regs * @regs: Reflects the saved state of the task after it has hit a breakpoint * instruction. * Return the address of the breakpoint instruction. */ unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs) { return instruction_pointer(regs) - UPROBE_SWBP_INSN_SIZE; } unsigned long uprobe_get_trap_addr(struct pt_regs *regs) { struct uprobe_task *utask = current->utask; if (unlikely(utask && utask->active_uprobe)) return utask->vaddr; return instruction_pointer(regs); } static struct return_instance *free_ret_instance(struct return_instance *ri) { struct return_instance *next = ri->next; put_uprobe(ri->uprobe); kfree(ri); return next; } /* * Called with no locks held. * Called in context of an exiting or an exec-ing thread. */ void uprobe_free_utask(struct task_struct *t) { struct uprobe_task *utask = t->utask; struct return_instance *ri; if (!utask) return; if (utask->active_uprobe) put_uprobe(utask->active_uprobe); ri = utask->return_instances; while (ri) ri = free_ret_instance(ri); xol_free_insn_slot(t); kfree(utask); t->utask = NULL; } /* * Allocate a uprobe_task object for the task if necessary. * Called when the thread hits a breakpoint. * * Returns: * - pointer to new uprobe_task on success * - NULL otherwise */ static struct uprobe_task *get_utask(void) { if (!current->utask) current->utask = kzalloc(sizeof(struct uprobe_task), GFP_KERNEL); return current->utask; } static int dup_utask(struct task_struct *t, struct uprobe_task *o_utask) { struct uprobe_task *n_utask; struct return_instance **p, *o, *n; n_utask = kzalloc(sizeof(struct uprobe_task), GFP_KERNEL); if (!n_utask) return -ENOMEM; t->utask = n_utask; p = &n_utask->return_instances; for (o = o_utask->return_instances; o; o = o->next) { n = kmalloc(sizeof(struct return_instance), GFP_KERNEL); if (!n) return -ENOMEM; *n = *o; get_uprobe(n->uprobe); n->next = NULL; *p = n; p = &n->next; n_utask->depth++; } return 0; } static void uprobe_warn(struct task_struct *t, const char *msg) { pr_warn("uprobe: %s:%d failed to %s\n", current->comm, current->pid, msg); } static void dup_xol_work(struct callback_head *work) { if (current->flags & PF_EXITING) return; if (!__create_xol_area(current->utask->dup_xol_addr) && !fatal_signal_pending(current)) uprobe_warn(current, "dup xol area"); } /* * Called in context of a new clone/fork from copy_process. */ void uprobe_copy_process(struct task_struct *t, unsigned long flags) { struct uprobe_task *utask = current->utask; struct mm_struct *mm = current->mm; struct xol_area *area; t->utask = NULL; if (!utask || !utask->return_instances) return; if (mm == t->mm && !(flags & CLONE_VFORK)) return; if (dup_utask(t, utask)) return uprobe_warn(t, "dup ret instances"); /* The task can fork() after dup_xol_work() fails */ area = mm->uprobes_state.xol_area; if (!area) return uprobe_warn(t, "dup xol area"); if (mm == t->mm) return; t->utask->dup_xol_addr = area->vaddr; init_task_work(&t->utask->dup_xol_work, dup_xol_work); task_work_add(t, &t->utask->dup_xol_work, TWA_RESUME); } /* * Current area->vaddr notion assume the trampoline address is always * equal area->vaddr. * * Returns -1 in case the xol_area is not allocated. */ static unsigned long get_trampoline_vaddr(void) { struct xol_area *area; unsigned long trampoline_vaddr = -1; /* Pairs with xol_add_vma() smp_store_release() */ area = READ_ONCE(current->mm->uprobes_state.xol_area); /* ^^^ */ if (area) trampoline_vaddr = area->vaddr; return trampoline_vaddr; } static void cleanup_return_instances(struct uprobe_task *utask, bool chained, struct pt_regs *regs) { struct return_instance *ri = utask->return_instances; enum rp_check ctx = chained ? RP_CHECK_CHAIN_CALL : RP_CHECK_CALL; while (ri && !arch_uretprobe_is_alive(ri, ctx, regs)) { ri = free_ret_instance(ri); utask->depth--; } utask->return_instances = ri; } static void prepare_uretprobe(struct uprobe *uprobe, struct pt_regs *regs) { struct return_instance *ri; struct uprobe_task *utask; unsigned long orig_ret_vaddr, trampoline_vaddr; bool chained; if (!get_xol_area()) return; utask = get_utask(); if (!utask) return; if (utask->depth >= MAX_URETPROBE_DEPTH) { printk_ratelimited(KERN_INFO "uprobe: omit uretprobe due to" " nestedness limit pid/tgid=%d/%d\n", current->pid, current->tgid); return; } ri = kmalloc(sizeof(struct return_instance), GFP_KERNEL); if (!ri) return; trampoline_vaddr = get_trampoline_vaddr(); orig_ret_vaddr = arch_uretprobe_hijack_return_addr(trampoline_vaddr, regs); if (orig_ret_vaddr == -1) goto fail; /* drop the entries invalidated by longjmp() */ chained = (orig_ret_vaddr == trampoline_vaddr); cleanup_return_instances(utask, chained, regs); /* * We don't want to keep trampoline address in stack, rather keep the * original return address of first caller thru all the consequent * instances. This also makes breakpoint unwrapping easier. */ if (chained) { if (!utask->return_instances) { /* * This situation is not possible. Likely we have an * attack from user-space. */ uprobe_warn(current, "handle tail call"); goto fail; } orig_ret_vaddr = utask->return_instances->orig_ret_vaddr; } ri->uprobe = get_uprobe(uprobe); ri->func = instruction_pointer(regs); ri->stack = user_stack_pointer(regs); ri->orig_ret_vaddr = orig_ret_vaddr; ri->chained = chained; utask->depth++; ri->next = utask->return_instances; utask->return_instances = ri; return; fail: kfree(ri); } /* Prepare to single-step probed instruction out of line. */ static int pre_ssout(struct uprobe *uprobe, struct pt_regs *regs, unsigned long bp_vaddr) { struct uprobe_task *utask; unsigned long xol_vaddr; int err; utask = get_utask(); if (!utask) return -ENOMEM; xol_vaddr = xol_get_insn_slot(uprobe); if (!xol_vaddr) return -ENOMEM; utask->xol_vaddr = xol_vaddr; utask->vaddr = bp_vaddr; err = arch_uprobe_pre_xol(&uprobe->arch, regs); if (unlikely(err)) { xol_free_insn_slot(current); return err; } utask->active_uprobe = uprobe; utask->state = UTASK_SSTEP; return 0; } /* * If we are singlestepping, then ensure this thread is not connected to * non-fatal signals until completion of singlestep. When xol insn itself * triggers the signal, restart the original insn even if the task is * already SIGKILL'ed (since coredump should report the correct ip). This * is even more important if the task has a handler for SIGSEGV/etc, The * _same_ instruction should be repeated again after return from the signal * handler, and SSTEP can never finish in this case. */ bool uprobe_deny_signal(void) { struct task_struct *t = current; struct uprobe_task *utask = t->utask; if (likely(!utask || !utask->active_uprobe)) return false; WARN_ON_ONCE(utask->state != UTASK_SSTEP); if (task_sigpending(t)) { spin_lock_irq(&t->sighand->siglock); clear_tsk_thread_flag(t, TIF_SIGPENDING); spin_unlock_irq(&t->sighand->siglock); if (__fatal_signal_pending(t) || arch_uprobe_xol_was_trapped(t)) { utask->state = UTASK_SSTEP_TRAPPED; set_tsk_thread_flag(t, TIF_UPROBE); } } return true; } static void mmf_recalc_uprobes(struct mm_struct *mm) { VMA_ITERATOR(vmi, mm, 0); struct vm_area_struct *vma; for_each_vma(vmi, vma) { if (!valid_vma(vma, false)) continue; /* * This is not strictly accurate, we can race with * uprobe_unregister() and see the already removed * uprobe if delete_uprobe() was not yet called. * Or this uprobe can be filtered out. */ if (vma_has_uprobes(vma, vma->vm_start, vma->vm_end)) return; } clear_bit(MMF_HAS_UPROBES, &mm->flags); } static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr) { struct page *page; uprobe_opcode_t opcode; int result; if (WARN_ON_ONCE(!IS_ALIGNED(vaddr, UPROBE_SWBP_INSN_SIZE))) return -EINVAL; pagefault_disable(); result = __get_user(opcode, (uprobe_opcode_t __user *)vaddr); pagefault_enable(); if (likely(result == 0)) goto out; /* * The NULL 'tsk' here ensures that any faults that occur here * will not be accounted to the task. 'mm' *is* current->mm, * but we treat this as a 'remote' access since it is * essentially a kernel access to the memory. */ result = get_user_pages_remote(mm, vaddr, 1, FOLL_FORCE, &page, NULL, NULL); if (result < 0) return result; copy_from_page(page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE); put_page(page); out: /* This needs to return true for any variant of the trap insn */ return is_trap_insn(&opcode); } static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp) { struct mm_struct *mm = current->mm; struct uprobe *uprobe = NULL; struct vm_area_struct *vma; mmap_read_lock(mm); vma = vma_lookup(mm, bp_vaddr); if (vma) { if (valid_vma(vma, false)) { struct inode *inode = file_inode(vma->vm_file); loff_t offset = vaddr_to_offset(vma, bp_vaddr); uprobe = find_uprobe(inode, offset); } if (!uprobe) *is_swbp = is_trap_at_addr(mm, bp_vaddr); } else { *is_swbp = -EFAULT; } if (!uprobe && test_and_clear_bit(MMF_RECALC_UPROBES, &mm->flags)) mmf_recalc_uprobes(mm); mmap_read_unlock(mm); return uprobe; } static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs) { struct uprobe_consumer *uc; int remove = UPROBE_HANDLER_REMOVE; bool need_prep = false; /* prepare return uprobe, when needed */ down_read(&uprobe->register_rwsem); for (uc = uprobe->consumers; uc; uc = uc->next) { int rc = 0; if (uc->handler) { rc = uc->handler(uc, regs); WARN(rc & ~UPROBE_HANDLER_MASK, "bad rc=0x%x from %ps()\n", rc, uc->handler); } if (uc->ret_handler) need_prep = true; remove &= rc; } if (need_prep && !remove) prepare_uretprobe(uprobe, regs); /* put bp at return */ if (remove && uprobe->consumers) { WARN_ON(!uprobe_is_active(uprobe)); unapply_uprobe(uprobe, current->mm); } up_read(&uprobe->register_rwsem); } static void handle_uretprobe_chain(struct return_instance *ri, struct pt_regs *regs) { struct uprobe *uprobe = ri->uprobe; struct uprobe_consumer *uc; down_read(&uprobe->register_rwsem); for (uc = uprobe->consumers; uc; uc = uc->next) { if (uc->ret_handler) uc->ret_handler(uc, ri->func, regs); } up_read(&uprobe->register_rwsem); } static struct return_instance *find_next_ret_chain(struct return_instance *ri) { bool chained; do { chained = ri->chained; ri = ri->next; /* can't be NULL if chained */ } while (chained); return ri; } static void handle_trampoline(struct pt_regs *regs) { struct uprobe_task *utask; struct return_instance *ri, *next; bool valid; utask = current->utask; if (!utask) goto sigill; ri = utask->return_instances; if (!ri) goto sigill; do { /* * We should throw out the frames invalidated by longjmp(). * If this chain is valid, then the next one should be alive * or NULL; the latter case means that nobody but ri->func * could hit this trampoline on return. TODO: sigaltstack(). */ next = find_next_ret_chain(ri); valid = !next || arch_uretprobe_is_alive(next, RP_CHECK_RET, regs); instruction_pointer_set(regs, ri->orig_ret_vaddr); do { if (valid) handle_uretprobe_chain(ri, regs); ri = free_ret_instance(ri); utask->depth--; } while (ri != next); } while (!valid); utask->return_instances = ri; return; sigill: uprobe_warn(current, "handle uretprobe, sending SIGILL."); force_sig(SIGILL); } bool __weak arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs) { return false; } bool __weak arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx, struct pt_regs *regs) { return true; } /* * Run handler and ask thread to singlestep. * Ensure all non-fatal signals cannot interrupt thread while it singlesteps. */ static void handle_swbp(struct pt_regs *regs) { struct uprobe *uprobe; unsigned long bp_vaddr; int is_swbp; bp_vaddr = uprobe_get_swbp_addr(regs); if (bp_vaddr == get_trampoline_vaddr()) return handle_trampoline(regs); uprobe = find_active_uprobe(bp_vaddr, &is_swbp); if (!uprobe) { if (is_swbp > 0) { /* No matching uprobe; signal SIGTRAP. */ force_sig(SIGTRAP); } else { /* * Either we raced with uprobe_unregister() or we can't * access this memory. The latter is only possible if * another thread plays with our ->mm. In both cases * we can simply restart. If this vma was unmapped we * can pretend this insn was not executed yet and get * the (correct) SIGSEGV after restart. */ instruction_pointer_set(regs, bp_vaddr); } return; } /* change it in advance for ->handler() and restart */ instruction_pointer_set(regs, bp_vaddr); /* * TODO: move copy_insn/etc into _register and remove this hack. * After we hit the bp, _unregister + _register can install the * new and not-yet-analyzed uprobe at the same address, restart. */ if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags))) goto out; /* * Pairs with the smp_wmb() in prepare_uprobe(). * * Guarantees that if we see the UPROBE_COPY_INSN bit set, then * we must also see the stores to &uprobe->arch performed by the * prepare_uprobe() call. */ smp_rmb(); /* Tracing handlers use ->utask to communicate with fetch methods */ if (!get_utask()) goto out; if (arch_uprobe_ignore(&uprobe->arch, regs)) goto out; handler_chain(uprobe, regs); if (arch_uprobe_skip_sstep(&uprobe->arch, regs)) goto out; if (!pre_ssout(uprobe, regs, bp_vaddr)) return; /* arch_uprobe_skip_sstep() succeeded, or restart if can't singlestep */ out: put_uprobe(uprobe); } /* * Perform required fix-ups and disable singlestep. * Allow pending signals to take effect. */ static void handle_singlestep(struct uprobe_task *utask, struct pt_regs *regs) { struct uprobe *uprobe; int err = 0; uprobe = utask->active_uprobe; if (utask->state == UTASK_SSTEP_ACK) err = arch_uprobe_post_xol(&uprobe->arch, regs); else if (utask->state == UTASK_SSTEP_TRAPPED) arch_uprobe_abort_xol(&uprobe->arch, regs); else WARN_ON_ONCE(1); put_uprobe(uprobe); utask->active_uprobe = NULL; utask->state = UTASK_RUNNING; xol_free_insn_slot(current); spin_lock_irq(¤t->sighand->siglock); recalc_sigpending(); /* see uprobe_deny_signal() */ spin_unlock_irq(¤t->sighand->siglock); if (unlikely(err)) { uprobe_warn(current, "execute the probed insn, sending SIGILL."); force_sig(SIGILL); } } /* * On breakpoint hit, breakpoint notifier sets the TIF_UPROBE flag and * allows the thread to return from interrupt. After that handle_swbp() * sets utask->active_uprobe. * * On singlestep exception, singlestep notifier sets the TIF_UPROBE flag * and allows the thread to return from interrupt. * * While returning to userspace, thread notices the TIF_UPROBE flag and calls * uprobe_notify_resume(). */ void uprobe_notify_resume(struct pt_regs *regs) { struct uprobe_task *utask; clear_thread_flag(TIF_UPROBE); utask = current->utask; if (utask && utask->active_uprobe) handle_singlestep(utask, regs); else handle_swbp(regs); } /* * uprobe_pre_sstep_notifier gets called from interrupt context as part of * notifier mechanism. Set TIF_UPROBE flag and indicate breakpoint hit. */ int uprobe_pre_sstep_notifier(struct pt_regs *regs) { if (!current->mm) return 0; if (!test_bit(MMF_HAS_UPROBES, ¤t->mm->flags) && (!current->utask || !current->utask->return_instances)) return 0; set_thread_flag(TIF_UPROBE); return 1; } /* * uprobe_post_sstep_notifier gets called in interrupt context as part of notifier * mechanism. Set TIF_UPROBE flag and indicate completion of singlestep. */ int uprobe_post_sstep_notifier(struct pt_regs *regs) { struct uprobe_task *utask = current->utask; if (!current->mm || !utask || !utask->active_uprobe) /* task is currently not uprobed */ return 0; utask->state = UTASK_SSTEP_ACK; set_thread_flag(TIF_UPROBE); return 1; } static struct notifier_block uprobe_exception_nb = { .notifier_call = arch_uprobe_exception_notify, .priority = INT_MAX-1, /* notified after kprobes, kgdb */ }; void __init uprobes_init(void) { int i; for (i = 0; i < UPROBES_HASH_SZ; i++) mutex_init(&uprobes_mmap_mutex[i]); BUG_ON(register_die_notifier(&uprobe_exception_nb)); } |
| 65 65 4563 4563 3122 3 4563 4561 4567 65 4564 4561 111 4569 4564 4559 4152 1760 2320 9274 1269 8882 8872 161 65 65 65 2793 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* * Copyright (C) 2017-2022 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * Copyright Matt Mackall <mpm@selenic.com>, 2003, 2004, 2005 * Copyright Theodore Ts'o, 1994, 1995, 1996, 1997, 1998, 1999. All rights reserved. * * This driver produces cryptographically secure pseudorandom data. It is divided * into roughly six sections, each with a section header: * * - Initialization and readiness waiting. * - Fast key erasure RNG, the "crng". * - Entropy accumulation and extraction routines. * - Entropy collection routines. * - Userspace reader/writer interfaces. * - Sysctl interface. * * The high level overview is that there is one input pool, into which * various pieces of data are hashed. Prior to initialization, some of that * data is then "credited" as having a certain number of bits of entropy. * When enough bits of entropy are available, the hash is finalized and * handed as a key to a stream cipher that expands it indefinitely for * various consumers. This key is periodically refreshed as the various * entropy collectors, described below, add data to the input pool. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/utsname.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/major.h> #include <linux/string.h> #include <linux/fcntl.h> #include <linux/slab.h> #include <linux/random.h> #include <linux/poll.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/blkdev.h> #include <linux/interrupt.h> #include <linux/mm.h> #include <linux/nodemask.h> #include <linux/spinlock.h> #include <linux/kthread.h> #include <linux/percpu.h> #include <linux/ptrace.h> #include <linux/workqueue.h> #include <linux/irq.h> #include <linux/ratelimit.h> #include <linux/syscalls.h> #include <linux/completion.h> #include <linux/uuid.h> #include <linux/uaccess.h> #include <linux/suspend.h> #include <linux/siphash.h> #include <crypto/chacha.h> #include <crypto/blake2s.h> #include <asm/processor.h> #include <asm/irq.h> #include <asm/irq_regs.h> #include <asm/io.h> /********************************************************************* * * Initialization and readiness waiting. * * Much of the RNG infrastructure is devoted to various dependencies * being able to wait until the RNG has collected enough entropy and * is ready for safe consumption. * *********************************************************************/ /* * crng_init is protected by base_crng->lock, and only increases * its value (from empty->early->ready). */ static enum { CRNG_EMPTY = 0, /* Little to no entropy collected */ CRNG_EARLY = 1, /* At least POOL_EARLY_BITS collected */ CRNG_READY = 2 /* Fully initialized with POOL_READY_BITS collected */ } crng_init __read_mostly = CRNG_EMPTY; static DEFINE_STATIC_KEY_FALSE(crng_is_ready); #define crng_ready() (static_branch_likely(&crng_is_ready) || crng_init >= CRNG_READY) /* Various types of waiters for crng_init->CRNG_READY transition. */ static DECLARE_WAIT_QUEUE_HEAD(crng_init_wait); static struct fasync_struct *fasync; /* Control how we warn userspace. */ static struct ratelimit_state urandom_warning = RATELIMIT_STATE_INIT_FLAGS("urandom_warning", HZ, 3, RATELIMIT_MSG_ON_RELEASE); static int ratelimit_disable __read_mostly = IS_ENABLED(CONFIG_WARN_ALL_UNSEEDED_RANDOM); module_param_named(ratelimit_disable, ratelimit_disable, int, 0644); MODULE_PARM_DESC(ratelimit_disable, "Disable random ratelimit suppression"); /* * Returns whether or not the input pool has been seeded and thus guaranteed * to supply cryptographically secure random numbers. This applies to: the * /dev/urandom device, the get_random_bytes function, and the get_random_{u8, * u16,u32,u64,long} family of functions. * * Returns: true if the input pool has been seeded. * false if the input pool has not been seeded. */ bool rng_is_initialized(void) { return crng_ready(); } EXPORT_SYMBOL(rng_is_initialized); static void __cold crng_set_ready(struct work_struct *work) { static_branch_enable(&crng_is_ready); } /* Used by wait_for_random_bytes(), and considered an entropy collector, below. */ static void try_to_generate_entropy(void); /* * Wait for the input pool to be seeded and thus guaranteed to supply * cryptographically secure random numbers. This applies to: the /dev/urandom * device, the get_random_bytes function, and the get_random_{u8,u16,u32,u64, * int,long} family of functions. Using any of these functions without first * calling this function forfeits the guarantee of security. * * Returns: 0 if the input pool has been seeded. * -ERESTARTSYS if the function was interrupted by a signal. */ int wait_for_random_bytes(void) { while (!crng_ready()) { int ret; try_to_generate_entropy(); ret = wait_event_interruptible_timeout(crng_init_wait, crng_ready(), HZ); if (ret) return ret > 0 ? 0 : ret; } return 0; } EXPORT_SYMBOL(wait_for_random_bytes); #define warn_unseeded_randomness() \ if (IS_ENABLED(CONFIG_WARN_ALL_UNSEEDED_RANDOM) && !crng_ready()) \ printk_deferred(KERN_NOTICE "random: %s called from %pS with crng_init=%d\n", \ __func__, (void *)_RET_IP_, crng_init) /********************************************************************* * * Fast key erasure RNG, the "crng". * * These functions expand entropy from the entropy extractor into * long streams for external consumption using the "fast key erasure" * RNG described at <https://blog.cr.yp.to/20170723-random.html>. * * There are a few exported interfaces for use by other drivers: * * void get_random_bytes(void *buf, size_t len) * u8 get_random_u8() * u16 get_random_u16() * u32 get_random_u32() * u32 get_random_u32_below(u32 ceil) * u32 get_random_u32_above(u32 floor) * u32 get_random_u32_inclusive(u32 floor, u32 ceil) * u64 get_random_u64() * unsigned long get_random_long() * * These interfaces will return the requested number of random bytes * into the given buffer or as a return value. This is equivalent to * a read from /dev/urandom. The u8, u16, u32, u64, long family of * functions may be higher performance for one-off random integers, * because they do a bit of buffering and do not invoke reseeding * until the buffer is emptied. * *********************************************************************/ enum { CRNG_RESEED_START_INTERVAL = HZ, CRNG_RESEED_INTERVAL = 60 * HZ }; static struct { u8 key[CHACHA_KEY_SIZE] __aligned(__alignof__(long)); unsigned long birth; unsigned long generation; spinlock_t lock; } base_crng = { .lock = __SPIN_LOCK_UNLOCKED(base_crng.lock) }; struct crng { u8 key[CHACHA_KEY_SIZE]; unsigned long generation; local_lock_t lock; }; static DEFINE_PER_CPU(struct crng, crngs) = { .generation = ULONG_MAX, .lock = INIT_LOCAL_LOCK(crngs.lock), }; /* Used by crng_reseed() and crng_make_state() to extract a new seed from the input pool. */ static void extract_entropy(void *buf, size_t len); /* This extracts a new crng key from the input pool. */ static void crng_reseed(void) { unsigned long flags; unsigned long next_gen; u8 key[CHACHA_KEY_SIZE]; extract_entropy(key, sizeof(key)); /* * We copy the new key into the base_crng, overwriting the old one, * and update the generation counter. We avoid hitting ULONG_MAX, * because the per-cpu crngs are initialized to ULONG_MAX, so this * forces new CPUs that come online to always initialize. */ spin_lock_irqsave(&base_crng.lock, flags); memcpy(base_crng.key, key, sizeof(base_crng.key)); next_gen = base_crng.generation + 1; if (next_gen == ULONG_MAX) ++next_gen; WRITE_ONCE(base_crng.generation, next_gen); WRITE_ONCE(base_crng.birth, jiffies); if (!static_branch_likely(&crng_is_ready)) crng_init = CRNG_READY; spin_unlock_irqrestore(&base_crng.lock, flags); memzero_explicit(key, sizeof(key)); } /* * This generates a ChaCha block using the provided key, and then * immediately overwrites that key with half the block. It returns * the resultant ChaCha state to the user, along with the second * half of the block containing 32 bytes of random data that may * be used; random_data_len may not be greater than 32. * * The returned ChaCha state contains within it a copy of the old * key value, at index 4, so the state should always be zeroed out * immediately after using in order to maintain forward secrecy. * If the state cannot be erased in a timely manner, then it is * safer to set the random_data parameter to &chacha_state[4] so * that this function overwrites it before returning. */ static void crng_fast_key_erasure(u8 key[CHACHA_KEY_SIZE], u32 chacha_state[CHACHA_STATE_WORDS], u8 *random_data, size_t random_data_len) { u8 first_block[CHACHA_BLOCK_SIZE]; BUG_ON(random_data_len > 32); chacha_init_consts(chacha_state); memcpy(&chacha_state[4], key, CHACHA_KEY_SIZE); memset(&chacha_state[12], 0, sizeof(u32) * 4); chacha20_block(chacha_state, first_block); memcpy(key, first_block, CHACHA_KEY_SIZE); memcpy(random_data, first_block + CHACHA_KEY_SIZE, random_data_len); memzero_explicit(first_block, sizeof(first_block)); } /* * Return the interval until the next reseeding, which is normally * CRNG_RESEED_INTERVAL, but during early boot, it is at an interval * proportional to the uptime. */ static unsigned int crng_reseed_interval(void) { static bool early_boot = true; if (unlikely(READ_ONCE(early_boot))) { time64_t uptime = ktime_get_seconds(); if (uptime >= CRNG_RESEED_INTERVAL / HZ * 2) WRITE_ONCE(early_boot, false); else return max_t(unsigned int, CRNG_RESEED_START_INTERVAL, (unsigned int)uptime / 2 * HZ); } return CRNG_RESEED_INTERVAL; } /* * This function returns a ChaCha state that you may use for generating * random data. It also returns up to 32 bytes on its own of random data * that may be used; random_data_len may not be greater than 32. */ static void crng_make_state(u32 chacha_state[CHACHA_STATE_WORDS], u8 *random_data, size_t random_data_len) { unsigned long flags; struct crng *crng; BUG_ON(random_data_len > 32); /* * For the fast path, we check whether we're ready, unlocked first, and * then re-check once locked later. In the case where we're really not * ready, we do fast key erasure with the base_crng directly, extracting * when crng_init is CRNG_EMPTY. */ if (!crng_ready()) { bool ready; spin_lock_irqsave(&base_crng.lock, flags); ready = crng_ready(); if (!ready) { if (crng_init == CRNG_EMPTY) extract_entropy(base_crng.key, sizeof(base_crng.key)); crng_fast_key_erasure(base_crng.key, chacha_state, random_data, random_data_len); } spin_unlock_irqrestore(&base_crng.lock, flags); if (!ready) return; } /* * If the base_crng is old enough, we reseed, which in turn bumps the * generation counter that we check below. */ if (unlikely(time_is_before_jiffies(READ_ONCE(base_crng.birth) + crng_reseed_interval()))) crng_reseed(); local_lock_irqsave(&crngs.lock, flags); crng = raw_cpu_ptr(&crngs); /* * If our per-cpu crng is older than the base_crng, then it means * somebody reseeded the base_crng. In that case, we do fast key * erasure on the base_crng, and use its output as the new key * for our per-cpu crng. This brings us up to date with base_crng. */ if (unlikely(crng->generation != READ_ONCE(base_crng.generation))) { spin_lock(&base_crng.lock); crng_fast_key_erasure(base_crng.key, chacha_state, crng->key, sizeof(crng->key)); crng->generation = base_crng.generation; spin_unlock(&base_crng.lock); } /* * Finally, when we've made it this far, our per-cpu crng has an up * to date key, and we can do fast key erasure with it to produce * some random data and a ChaCha state for the caller. All other * branches of this function are "unlikely", so most of the time we * should wind up here immediately. */ crng_fast_key_erasure(crng->key, chacha_state, random_data, random_data_len); local_unlock_irqrestore(&crngs.lock, flags); } static void _get_random_bytes(void *buf, size_t len) { u32 chacha_state[CHACHA_STATE_WORDS]; u8 tmp[CHACHA_BLOCK_SIZE]; size_t first_block_len; if (!len) return; first_block_len = min_t(size_t, 32, len); crng_make_state(chacha_state, buf, first_block_len); len -= first_block_len; buf += first_block_len; while (len) { if (len < CHACHA_BLOCK_SIZE) { chacha20_block(chacha_state, tmp); memcpy(buf, tmp, len); memzero_explicit(tmp, sizeof(tmp)); break; } chacha20_block(chacha_state, buf); if (unlikely(chacha_state[12] == 0)) ++chacha_state[13]; len -= CHACHA_BLOCK_SIZE; buf += CHACHA_BLOCK_SIZE; } memzero_explicit(chacha_state, sizeof(chacha_state)); } /* * This function is the exported kernel interface. It returns some number of * good random numbers, suitable for key generation, seeding TCP sequence * numbers, etc. In order to ensure that the randomness returned by this * function is okay, the function wait_for_random_bytes() should be called and * return 0 at least once at any point prior. */ void get_random_bytes(void *buf, size_t len) { warn_unseeded_randomness(); _get_random_bytes(buf, len); } EXPORT_SYMBOL(get_random_bytes); static ssize_t get_random_bytes_user(struct iov_iter *iter) { u32 chacha_state[CHACHA_STATE_WORDS]; u8 block[CHACHA_BLOCK_SIZE]; size_t ret = 0, copied; if (unlikely(!iov_iter_count(iter))) return 0; /* * Immediately overwrite the ChaCha key at index 4 with random * bytes, in case userspace causes copy_to_iter() below to sleep * forever, so that we still retain forward secrecy in that case. */ crng_make_state(chacha_state, (u8 *)&chacha_state[4], CHACHA_KEY_SIZE); /* * However, if we're doing a read of len <= 32, we don't need to * use chacha_state after, so we can simply return those bytes to * the user directly. */ if (iov_iter_count(iter) <= CHACHA_KEY_SIZE) { ret = copy_to_iter(&chacha_state[4], CHACHA_KEY_SIZE, iter); goto out_zero_chacha; } for (;;) { chacha20_block(chacha_state, block); if (unlikely(chacha_state[12] == 0)) ++chacha_state[13]; copied = copy_to_iter(block, sizeof(block), iter); ret += copied; if (!iov_iter_count(iter) || copied != sizeof(block)) break; BUILD_BUG_ON(PAGE_SIZE % sizeof(block) != 0); if (ret % PAGE_SIZE == 0) { if (signal_pending(current)) break; cond_resched(); } } memzero_explicit(block, sizeof(block)); out_zero_chacha: memzero_explicit(chacha_state, sizeof(chacha_state)); return ret ? ret : -EFAULT; } /* * Batched entropy returns random integers. The quality of the random * number is good as /dev/urandom. In order to ensure that the randomness * provided by this function is okay, the function wait_for_random_bytes() * should be called and return 0 at least once at any point prior. */ #define DEFINE_BATCHED_ENTROPY(type) \ struct batch_ ##type { \ /* \ * We make this 1.5x a ChaCha block, so that we get the \ * remaining 32 bytes from fast key erasure, plus one full \ * block from the detached ChaCha state. We can increase \ * the size of this later if needed so long as we keep the \ * formula of (integer_blocks + 0.5) * CHACHA_BLOCK_SIZE. \ */ \ type entropy[CHACHA_BLOCK_SIZE * 3 / (2 * sizeof(type))]; \ local_lock_t lock; \ unsigned long generation; \ unsigned int position; \ }; \ \ static DEFINE_PER_CPU(struct batch_ ##type, batched_entropy_ ##type) = { \ .lock = INIT_LOCAL_LOCK(batched_entropy_ ##type.lock), \ .position = UINT_MAX \ }; \ \ type get_random_ ##type(void) \ { \ type ret; \ unsigned long flags; \ struct batch_ ##type *batch; \ unsigned long next_gen; \ \ warn_unseeded_randomness(); \ \ if (!crng_ready()) { \ _get_random_bytes(&ret, sizeof(ret)); \ return ret; \ } \ \ local_lock_irqsave(&batched_entropy_ ##type.lock, flags); \ batch = raw_cpu_ptr(&batched_entropy_##type); \ \ next_gen = READ_ONCE(base_crng.generation); \ if (batch->position >= ARRAY_SIZE(batch->entropy) || \ next_gen != batch->generation) { \ _get_random_bytes(batch->entropy, sizeof(batch->entropy)); \ batch->position = 0; \ batch->generation = next_gen; \ } \ \ ret = batch->entropy[batch->position]; \ batch->entropy[batch->position] = 0; \ ++batch->position; \ local_unlock_irqrestore(&batched_entropy_ ##type.lock, flags); \ return ret; \ } \ EXPORT_SYMBOL(get_random_ ##type); DEFINE_BATCHED_ENTROPY(u8) DEFINE_BATCHED_ENTROPY(u16) DEFINE_BATCHED_ENTROPY(u32) DEFINE_BATCHED_ENTROPY(u64) u32 __get_random_u32_below(u32 ceil) { /* * This is the slow path for variable ceil. It is still fast, most of * the time, by doing traditional reciprocal multiplication and * opportunistically comparing the lower half to ceil itself, before * falling back to computing a larger bound, and then rejecting samples * whose lower half would indicate a range indivisible by ceil. The use * of `-ceil % ceil` is analogous to `2^32 % ceil`, but is computable * in 32-bits. */ u32 rand = get_random_u32(); u64 mult; /* * This function is technically undefined for ceil == 0, and in fact * for the non-underscored constant version in the header, we build bug * on that. But for the non-constant case, it's convenient to have that * evaluate to being a straight call to get_random_u32(), so that * get_random_u32_inclusive() can work over its whole range without * undefined behavior. */ if (unlikely(!ceil)) return rand; mult = (u64)ceil * rand; if (unlikely((u32)mult < ceil)) { u32 bound = -ceil % ceil; while (unlikely((u32)mult < bound)) mult = (u64)ceil * get_random_u32(); } return mult >> 32; } EXPORT_SYMBOL(__get_random_u32_below); #ifdef CONFIG_SMP /* * This function is called when the CPU is coming up, with entry * CPUHP_RANDOM_PREPARE, which comes before CPUHP_WORKQUEUE_PREP. */ int __cold random_prepare_cpu(unsigned int cpu) { /* * When the cpu comes back online, immediately invalidate both * the per-cpu crng and all batches, so that we serve fresh * randomness. */ per_cpu_ptr(&crngs, cpu)->generation = ULONG_MAX; per_cpu_ptr(&batched_entropy_u8, cpu)->position = UINT_MAX; per_cpu_ptr(&batched_entropy_u16, cpu)->position = UINT_MAX; per_cpu_ptr(&batched_entropy_u32, cpu)->position = UINT_MAX; per_cpu_ptr(&batched_entropy_u64, cpu)->position = UINT_MAX; return 0; } #endif /********************************************************************** * * Entropy accumulation and extraction routines. * * Callers may add entropy via: * * static void mix_pool_bytes(const void *buf, size_t len) * * After which, if added entropy should be credited: * * static void credit_init_bits(size_t bits) * * Finally, extract entropy via: * * static void extract_entropy(void *buf, size_t len) * **********************************************************************/ enum { POOL_BITS = BLAKE2S_HASH_SIZE * 8, POOL_READY_BITS = POOL_BITS, /* When crng_init->CRNG_READY */ POOL_EARLY_BITS = POOL_READY_BITS / 2 /* When crng_init->CRNG_EARLY */ }; static struct { struct blake2s_state hash; spinlock_t lock; unsigned int init_bits; } input_pool = { .hash.h = { BLAKE2S_IV0 ^ (0x01010000 | BLAKE2S_HASH_SIZE), BLAKE2S_IV1, BLAKE2S_IV2, BLAKE2S_IV3, BLAKE2S_IV4, BLAKE2S_IV5, BLAKE2S_IV6, BLAKE2S_IV7 }, .hash.outlen = BLAKE2S_HASH_SIZE, .lock = __SPIN_LOCK_UNLOCKED(input_pool.lock), }; static void _mix_pool_bytes(const void *buf, size_t len) { blake2s_update(&input_pool.hash, buf, len); } /* * This function adds bytes into the input pool. It does not * update the initialization bit counter; the caller should call * credit_init_bits if this is appropriate. */ static void mix_pool_bytes(const void *buf, size_t len) { unsigned long flags; spin_lock_irqsave(&input_pool.lock, flags); _mix_pool_bytes(buf, len); spin_unlock_irqrestore(&input_pool.lock, flags); } /* * This is an HKDF-like construction for using the hashed collected entropy * as a PRF key, that's then expanded block-by-block. */ static void extract_entropy(void *buf, size_t len) { unsigned long flags; u8 seed[BLAKE2S_HASH_SIZE], next_key[BLAKE2S_HASH_SIZE]; struct { unsigned long rdseed[32 / sizeof(long)]; size_t counter; } block; size_t i, longs; for (i = 0; i < ARRAY_SIZE(block.rdseed);) { longs = arch_get_random_seed_longs(&block.rdseed[i], ARRAY_SIZE(block.rdseed) - i); if (longs) { i += longs; continue; } longs = arch_get_random_longs(&block.rdseed[i], ARRAY_SIZE(block.rdseed) - i); if (longs) { i += longs; continue; } block.rdseed[i++] = random_get_entropy(); } spin_lock_irqsave(&input_pool.lock, flags); /* seed = HASHPRF(last_key, entropy_input) */ blake2s_final(&input_pool.hash, seed); /* next_key = HASHPRF(seed, RDSEED || 0) */ block.counter = 0; blake2s(next_key, (u8 *)&block, seed, sizeof(next_key), sizeof(block), sizeof(seed)); blake2s_init_key(&input_pool.hash, BLAKE2S_HASH_SIZE, next_key, sizeof(next_key)); spin_unlock_irqrestore(&input_pool.lock, flags); memzero_explicit(next_key, sizeof(next_key)); while (len) { i = min_t(size_t, len, BLAKE2S_HASH_SIZE); /* output = HASHPRF(seed, RDSEED || ++counter) */ ++block.counter; blake2s(buf, (u8 *)&block, seed, i, sizeof(block), sizeof(seed)); len -= i; buf += i; } memzero_explicit(seed, sizeof(seed)); memzero_explicit(&block, sizeof(block)); } #define credit_init_bits(bits) if (!crng_ready()) _credit_init_bits(bits) static void __cold _credit_init_bits(size_t bits) { static DECLARE_WORK(set_ready, crng_set_ready); unsigned int new, orig, add; unsigned long flags; if (!bits) return; add = min_t(size_t, bits, POOL_BITS); orig = READ_ONCE(input_pool.init_bits); do { new = min_t(unsigned int, POOL_BITS, orig + add); } while (!try_cmpxchg(&input_pool.init_bits, &orig, new)); if (orig < POOL_READY_BITS && new >= POOL_READY_BITS) { crng_reseed(); /* Sets crng_init to CRNG_READY under base_crng.lock. */ if (static_key_initialized && system_unbound_wq) queue_work(system_unbound_wq, &set_ready); wake_up_interruptible(&crng_init_wait); kill_fasync(&fasync, SIGIO, POLL_IN); pr_notice("crng init done\n"); if (urandom_warning.missed) pr_notice("%d urandom warning(s) missed due to ratelimiting\n", urandom_warning.missed); } else if (orig < POOL_EARLY_BITS && new >= POOL_EARLY_BITS) { spin_lock_irqsave(&base_crng.lock, flags); /* Check if crng_init is CRNG_EMPTY, to avoid race with crng_reseed(). */ if (crng_init == CRNG_EMPTY) { extract_entropy(base_crng.key, sizeof(base_crng.key)); crng_init = CRNG_EARLY; } spin_unlock_irqrestore(&base_crng.lock, flags); } } /********************************************************************** * * Entropy collection routines. * * The following exported functions are used for pushing entropy into * the above entropy accumulation routines: * * void add_device_randomness(const void *buf, size_t len); * void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy); * void add_bootloader_randomness(const void *buf, size_t len); * void add_vmfork_randomness(const void *unique_vm_id, size_t len); * void add_interrupt_randomness(int irq); * void add_input_randomness(unsigned int type, unsigned int code, unsigned int value); * void add_disk_randomness(struct gendisk *disk); * * add_device_randomness() adds data to the input pool that * is likely to differ between two devices (or possibly even per boot). * This would be things like MAC addresses or serial numbers, or the * read-out of the RTC. This does *not* credit any actual entropy to * the pool, but it initializes the pool to different values for devices * that might otherwise be identical and have very little entropy * available to them (particularly common in the embedded world). * * add_hwgenerator_randomness() is for true hardware RNGs, and will credit * entropy as specified by the caller. If the entropy pool is full it will * block until more entropy is needed. * * add_bootloader_randomness() is called by bootloader drivers, such as EFI * and device tree, and credits its input depending on whether or not the * configuration option CONFIG_RANDOM_TRUST_BOOTLOADER is set. * * add_vmfork_randomness() adds a unique (but not necessarily secret) ID * representing the current instance of a VM to the pool, without crediting, * and then force-reseeds the crng so that it takes effect immediately. * * add_interrupt_randomness() uses the interrupt timing as random * inputs to the entropy pool. Using the cycle counters and the irq source * as inputs, it feeds the input pool roughly once a second or after 64 * interrupts, crediting 1 bit of entropy for whichever comes first. * * add_input_randomness() uses the input layer interrupt timing, as well * as the event type information from the hardware. * * add_disk_randomness() uses what amounts to the seek time of block * layer request events, on a per-disk_devt basis, as input to the * entropy pool. Note that high-speed solid state drives with very low * seek times do not make for good sources of entropy, as their seek * times are usually fairly consistent. * * The last two routines try to estimate how many bits of entropy * to credit. They do this by keeping track of the first and second * order deltas of the event timings. * **********************************************************************/ static bool trust_cpu __initdata = IS_ENABLED(CONFIG_RANDOM_TRUST_CPU); static bool trust_bootloader __initdata = IS_ENABLED(CONFIG_RANDOM_TRUST_BOOTLOADER); static int __init parse_trust_cpu(char *arg) { return kstrtobool(arg, &trust_cpu); } static int __init parse_trust_bootloader(char *arg) { return kstrtobool(arg, &trust_bootloader); } early_param("random.trust_cpu", parse_trust_cpu); early_param("random.trust_bootloader", parse_trust_bootloader); static int random_pm_notification(struct notifier_block *nb, unsigned long action, void *data) { unsigned long flags, entropy = random_get_entropy(); /* * Encode a representation of how long the system has been suspended, * in a way that is distinct from prior system suspends. */ ktime_t stamps[] = { ktime_get(), ktime_get_boottime(), ktime_get_real() }; spin_lock_irqsave(&input_pool.lock, flags); _mix_pool_bytes(&action, sizeof(action)); _mix_pool_bytes(stamps, sizeof(stamps)); _mix_pool_bytes(&entropy, sizeof(entropy)); spin_unlock_irqrestore(&input_pool.lock, flags); if (crng_ready() && (action == PM_RESTORE_PREPARE || (action == PM_POST_SUSPEND && !IS_ENABLED(CONFIG_PM_AUTOSLEEP) && !IS_ENABLED(CONFIG_PM_USERSPACE_AUTOSLEEP)))) { crng_reseed(); pr_notice("crng reseeded on system resumption\n"); } return 0; } static struct notifier_block pm_notifier = { .notifier_call = random_pm_notification }; /* * This is called extremely early, before time keeping functionality is * available, but arch randomness is. Interrupts are not yet enabled. */ void __init random_init_early(const char *command_line) { unsigned long entropy[BLAKE2S_BLOCK_SIZE / sizeof(long)]; size_t i, longs, arch_bits; #if defined(LATENT_ENTROPY_PLUGIN) static const u8 compiletime_seed[BLAKE2S_BLOCK_SIZE] __initconst __latent_entropy; _mix_pool_bytes(compiletime_seed, sizeof(compiletime_seed)); #endif for (i = 0, arch_bits = sizeof(entropy) * 8; i < ARRAY_SIZE(entropy);) { longs = arch_get_random_seed_longs_early(entropy, ARRAY_SIZE(entropy) - i); if (longs) { _mix_pool_bytes(entropy, sizeof(*entropy) * longs); i += longs; continue; } longs = arch_get_random_longs_early(entropy, ARRAY_SIZE(entropy) - i); if (longs) { _mix_pool_bytes(entropy, sizeof(*entropy) * longs); i += longs; continue; } arch_bits -= sizeof(*entropy) * 8; ++i; } _mix_pool_bytes(init_utsname(), sizeof(*(init_utsname()))); _mix_pool_bytes(command_line, strlen(command_line)); /* Reseed if already seeded by earlier phases. */ if (crng_ready()) crng_reseed(); else if (trust_cpu) _credit_init_bits(arch_bits); } /* * This is called a little bit after the prior function, and now there is * access to timestamps counters. Interrupts are not yet enabled. */ void __init random_init(void) { unsigned long entropy = random_get_entropy(); ktime_t now = ktime_get_real(); _mix_pool_bytes(&now, sizeof(now)); _mix_pool_bytes(&entropy, sizeof(entropy)); add_latent_entropy(); /* * If we were initialized by the cpu or bootloader before jump labels * or workqueues are initialized, then we should enable the static * branch here, where it's guaranteed that these have been initialized. */ if (!static_branch_likely(&crng_is_ready) && crng_init >= CRNG_READY) crng_set_ready(NULL); /* Reseed if already seeded by earlier phases. */ if (crng_ready()) crng_reseed(); WARN_ON(register_pm_notifier(&pm_notifier)); WARN(!entropy, "Missing cycle counter and fallback timer; RNG " "entropy collection will consequently suffer."); } /* * Add device- or boot-specific data to the input pool to help * initialize it. * * None of this adds any entropy; it is meant to avoid the problem of * the entropy pool having similar initial state across largely * identical devices. */ void add_device_randomness(const void *buf, size_t len) { unsigned long entropy = random_get_entropy(); unsigned long flags; spin_lock_irqsave(&input_pool.lock, flags); _mix_pool_bytes(&entropy, sizeof(entropy)); _mix_pool_bytes(buf, len); spin_unlock_irqrestore(&input_pool.lock, flags); } EXPORT_SYMBOL(add_device_randomness); /* * Interface for in-kernel drivers of true hardware RNGs. * Those devices may produce endless random bits and will be throttled * when our pool is full. */ void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy) { mix_pool_bytes(buf, len); credit_init_bits(entropy); /* * Throttle writing to once every reseed interval, unless we're not yet * initialized or no entropy is credited. */ if (!kthread_should_stop() && (crng_ready() || !entropy)) schedule_timeout_interruptible(crng_reseed_interval()); } EXPORT_SYMBOL_GPL(add_hwgenerator_randomness); /* * Handle random seed passed by bootloader, and credit it if * CONFIG_RANDOM_TRUST_BOOTLOADER is set. */ void __init add_bootloader_randomness(const void *buf, size_t len) { mix_pool_bytes(buf, len); if (trust_bootloader) credit_init_bits(len * 8); } #if IS_ENABLED(CONFIG_VMGENID) static BLOCKING_NOTIFIER_HEAD(vmfork_chain); /* * Handle a new unique VM ID, which is unique, not secret, so we * don't credit it, but we do immediately force a reseed after so * that it's used by the crng posthaste. */ void __cold add_vmfork_randomness(const void *unique_vm_id, size_t len) { add_device_randomness(unique_vm_id, len); if (crng_ready()) { crng_reseed(); pr_notice("crng reseeded due to virtual machine fork\n"); } blocking_notifier_call_chain(&vmfork_chain, 0, NULL); } #if IS_MODULE(CONFIG_VMGENID) EXPORT_SYMBOL_GPL(add_vmfork_randomness); #endif int __cold register_random_vmfork_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&vmfork_chain, nb); } EXPORT_SYMBOL_GPL(register_random_vmfork_notifier); int __cold unregister_random_vmfork_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&vmfork_chain, nb); } EXPORT_SYMBOL_GPL(unregister_random_vmfork_notifier); #endif struct fast_pool { unsigned long pool[4]; unsigned long last; unsigned int count; struct timer_list mix; }; static void mix_interrupt_randomness(struct timer_list *work); static DEFINE_PER_CPU(struct fast_pool, irq_randomness) = { #ifdef CONFIG_64BIT #define FASTMIX_PERM SIPHASH_PERMUTATION .pool = { SIPHASH_CONST_0, SIPHASH_CONST_1, SIPHASH_CONST_2, SIPHASH_CONST_3 }, #else #define FASTMIX_PERM HSIPHASH_PERMUTATION .pool = { HSIPHASH_CONST_0, HSIPHASH_CONST_1, HSIPHASH_CONST_2, HSIPHASH_CONST_3 }, #endif .mix = __TIMER_INITIALIZER(mix_interrupt_randomness, 0) }; /* * This is [Half]SipHash-1-x, starting from an empty key. Because * the key is fixed, it assumes that its inputs are non-malicious, * and therefore this has no security on its own. s represents the * four-word SipHash state, while v represents a two-word input. */ static void fast_mix(unsigned long s[4], unsigned long v1, unsigned long v2) { s[3] ^= v1; FASTMIX_PERM(s[0], s[1], s[2], s[3]); s[0] ^= v1; s[3] ^= v2; FASTMIX_PERM(s[0], s[1], s[2], s[3]); s[0] ^= v2; } #ifdef CONFIG_SMP /* * This function is called when the CPU has just come online, with * entry CPUHP_AP_RANDOM_ONLINE, just after CPUHP_AP_WORKQUEUE_ONLINE. */ int __cold random_online_cpu(unsigned int cpu) { /* * During CPU shutdown and before CPU onlining, add_interrupt_ * randomness() may schedule mix_interrupt_randomness(), and * set the MIX_INFLIGHT flag. However, because the worker can * be scheduled on a different CPU during this period, that * flag will never be cleared. For that reason, we zero out * the flag here, which runs just after workqueues are onlined * for the CPU again. This also has the effect of setting the * irq randomness count to zero so that new accumulated irqs * are fresh. */ per_cpu_ptr(&irq_randomness, cpu)->count = 0; return 0; } #endif static void mix_interrupt_randomness(struct timer_list *work) { struct fast_pool *fast_pool = container_of(work, struct fast_pool, mix); /* * The size of the copied stack pool is explicitly 2 longs so that we * only ever ingest half of the siphash output each time, retaining * the other half as the next "key" that carries over. The entropy is * supposed to be sufficiently dispersed between bits so on average * we don't wind up "losing" some. */ unsigned long pool[2]; unsigned int count; /* Check to see if we're running on the wrong CPU due to hotplug. */ local_irq_disable(); if (fast_pool != this_cpu_ptr(&irq_randomness)) { local_irq_enable(); return; } /* * Copy the pool to the stack so that the mixer always has a * consistent view, before we reenable irqs again. */ memcpy(pool, fast_pool->pool, sizeof(pool)); count = fast_pool->count; fast_pool->count = 0; fast_pool->last = jiffies; local_irq_enable(); mix_pool_bytes(pool, sizeof(pool)); credit_init_bits(clamp_t(unsigned int, (count & U16_MAX) / 64, 1, sizeof(pool) * 8)); memzero_explicit(pool, sizeof(pool)); } void add_interrupt_randomness(int irq) { enum { MIX_INFLIGHT = 1U << 31 }; unsigned long entropy = random_get_entropy(); struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness); struct pt_regs *regs = get_irq_regs(); unsigned int new_count; fast_mix(fast_pool->pool, entropy, (regs ? instruction_pointer(regs) : _RET_IP_) ^ swab(irq)); new_count = ++fast_pool->count; if (new_count & MIX_INFLIGHT) return; if (new_count < 1024 && !time_is_before_jiffies(fast_pool->last + HZ)) return; fast_pool->count |= MIX_INFLIGHT; if (!timer_pending(&fast_pool->mix)) { fast_pool->mix.expires = jiffies; add_timer_on(&fast_pool->mix, raw_smp_processor_id()); } } EXPORT_SYMBOL_GPL(add_interrupt_randomness); /* There is one of these per entropy source */ struct timer_rand_state { unsigned long last_time; long last_delta, last_delta2; }; /* * This function adds entropy to the entropy "pool" by using timing * delays. It uses the timer_rand_state structure to make an estimate * of how many bits of entropy this call has added to the pool. The * value "num" is also added to the pool; it should somehow describe * the type of event that just happened. */ static void add_timer_randomness(struct timer_rand_state *state, unsigned int num) { unsigned long entropy = random_get_entropy(), now = jiffies, flags; long delta, delta2, delta3; unsigned int bits; /* * If we're in a hard IRQ, add_interrupt_randomness() will be called * sometime after, so mix into the fast pool. */ if (in_hardirq()) { fast_mix(this_cpu_ptr(&irq_randomness)->pool, entropy, num); } else { spin_lock_irqsave(&input_pool.lock, flags); _mix_pool_bytes(&entropy, sizeof(entropy)); _mix_pool_bytes(&num, sizeof(num)); spin_unlock_irqrestore(&input_pool.lock, flags); } if (crng_ready()) return; /* * Calculate number of bits of randomness we probably added. * We take into account the first, second and third-order deltas * in order to make our estimate. */ delta = now - READ_ONCE(state->last_time); WRITE_ONCE(state->last_time, now); delta2 = delta - READ_ONCE(state->last_delta); WRITE_ONCE(state->last_delta, delta); delta3 = delta2 - READ_ONCE(state->last_delta2); WRITE_ONCE(state->last_delta2, delta2); if (delta < 0) delta = -delta; if (delta2 < 0) delta2 = -delta2; if (delta3 < 0) delta3 = -delta3; if (delta > delta2) delta = delta2; if (delta > delta3) delta = delta3; /* * delta is now minimum absolute delta. Round down by 1 bit * on general principles, and limit entropy estimate to 11 bits. */ bits = min(fls(delta >> 1), 11); /* * As mentioned above, if we're in a hard IRQ, add_interrupt_randomness() * will run after this, which uses a different crediting scheme of 1 bit * per every 64 interrupts. In order to let that function do accounting * close to the one in this function, we credit a full 64/64 bit per bit, * and then subtract one to account for the extra one added. */ if (in_hardirq()) this_cpu_ptr(&irq_randomness)->count += max(1u, bits * 64) - 1; else _credit_init_bits(bits); } void add_input_randomness(unsigned int type, unsigned int code, unsigned int value) { static unsigned char last_value; static struct timer_rand_state input_timer_state = { INITIAL_JIFFIES }; /* Ignore autorepeat and the like. */ if (value == last_value) return; last_value = value; add_timer_randomness(&input_timer_state, (type << 4) ^ code ^ (code >> 4) ^ value); } EXPORT_SYMBOL_GPL(add_input_randomness); #ifdef CONFIG_BLOCK void add_disk_randomness(struct gendisk *disk) { if (!disk || !disk->random) return; /* First major is 1, so we get >= 0x200 here. */ add_timer_randomness(disk->random, 0x100 + disk_devt(disk)); } EXPORT_SYMBOL_GPL(add_disk_randomness); void __cold rand_initialize_disk(struct gendisk *disk) { struct timer_rand_state *state; /* * If kzalloc returns null, we just won't use that entropy * source. */ state = kzalloc(sizeof(struct timer_rand_state), GFP_KERNEL); if (state) { state->last_time = INITIAL_JIFFIES; disk->random = state; } } #endif struct entropy_timer_state { unsigned long entropy; struct timer_list timer; unsigned int samples, samples_per_bit; }; /* * Each time the timer fires, we expect that we got an unpredictable * jump in the cycle counter. Even if the timer is running on another * CPU, the timer activity will be touching the stack of the CPU that is * generating entropy.. * * Note that we don't re-arm the timer in the timer itself - we are * happy to be scheduled away, since that just makes the load more * complex, but we do not want the timer to keep ticking unless the * entropy loop is running. * * So the re-arming always happens in the entropy loop itself. */ static void __cold entropy_timer(struct timer_list *timer) { struct entropy_timer_state *state = container_of(timer, struct entropy_timer_state, timer); if (++state->samples == state->samples_per_bit) { credit_init_bits(1); state->samples = 0; } } /* * If we have an actual cycle counter, see if we can * generate enough entropy with timing noise */ static void __cold try_to_generate_entropy(void) { enum { NUM_TRIAL_SAMPLES = 8192, MAX_SAMPLES_PER_BIT = HZ / 15 }; struct entropy_timer_state stack; unsigned int i, num_different = 0; unsigned long last = random_get_entropy(); for (i = 0; i < NUM_TRIAL_SAMPLES - 1; ++i) { stack.entropy = random_get_entropy(); if (stack.entropy != last) ++num_different; last = stack.entropy; } stack.samples_per_bit = DIV_ROUND_UP(NUM_TRIAL_SAMPLES, num_different + 1); if (stack.samples_per_bit > MAX_SAMPLES_PER_BIT) return; stack.samples = 0; timer_setup_on_stack(&stack.timer, entropy_timer, 0); while (!crng_ready() && !signal_pending(current)) { if (!timer_pending(&stack.timer)) mod_timer(&stack.timer, jiffies); mix_pool_bytes(&stack.entropy, sizeof(stack.entropy)); schedule(); stack.entropy = random_get_entropy(); } del_timer_sync(&stack.timer); destroy_timer_on_stack(&stack.timer); mix_pool_bytes(&stack.entropy, sizeof(stack.entropy)); } /********************************************************************** * * Userspace reader/writer interfaces. * * getrandom(2) is the primary modern interface into the RNG and should * be used in preference to anything else. * * Reading from /dev/random has the same functionality as calling * getrandom(2) with flags=0. In earlier versions, however, it had * vastly different semantics and should therefore be avoided, to * prevent backwards compatibility issues. * * Reading from /dev/urandom has the same functionality as calling * getrandom(2) with flags=GRND_INSECURE. Because it does not block * waiting for the RNG to be ready, it should not be used. * * Writing to either /dev/random or /dev/urandom adds entropy to * the input pool but does not credit it. * * Polling on /dev/random indicates when the RNG is initialized, on * the read side, and when it wants new entropy, on the write side. * * Both /dev/random and /dev/urandom have the same set of ioctls for * adding entropy, getting the entropy count, zeroing the count, and * reseeding the crng. * **********************************************************************/ SYSCALL_DEFINE3(getrandom, char __user *, ubuf, size_t, len, unsigned int, flags) { struct iov_iter iter; struct iovec iov; int ret; if (flags & ~(GRND_NONBLOCK | GRND_RANDOM | GRND_INSECURE)) return -EINVAL; /* * Requesting insecure and blocking randomness at the same time makes * no sense. */ if ((flags & (GRND_INSECURE | GRND_RANDOM)) == (GRND_INSECURE | GRND_RANDOM)) return -EINVAL; if (!crng_ready() && !(flags & GRND_INSECURE)) { if (flags & GRND_NONBLOCK) return -EAGAIN; ret = wait_for_random_bytes(); if (unlikely(ret)) return ret; } ret = import_single_range(ITER_DEST, ubuf, len, &iov, &iter); if (unlikely(ret)) return ret; return get_random_bytes_user(&iter); } static __poll_t random_poll(struct file *file, poll_table *wait) { poll_wait(file, &crng_init_wait, wait); return crng_ready() ? EPOLLIN | EPOLLRDNORM : EPOLLOUT | EPOLLWRNORM; } static ssize_t write_pool_user(struct iov_iter *iter) { u8 block[BLAKE2S_BLOCK_SIZE]; ssize_t ret = 0; size_t copied; if (unlikely(!iov_iter_count(iter))) return 0; for (;;) { copied = copy_from_iter(block, sizeof(block), iter); ret += copied; mix_pool_bytes(block, copied); if (!iov_iter_count(iter) || copied != sizeof(block)) break; BUILD_BUG_ON(PAGE_SIZE % sizeof(block) != 0); if (ret % PAGE_SIZE == 0) { if (signal_pending(current)) break; cond_resched(); } } memzero_explicit(block, sizeof(block)); return ret ? ret : -EFAULT; } static ssize_t random_write_iter(struct kiocb *kiocb, struct iov_iter *iter) { return write_pool_user(iter); } static ssize_t urandom_read_iter(struct kiocb *kiocb, struct iov_iter *iter) { static int maxwarn = 10; /* * Opportunistically attempt to initialize the RNG on platforms that * have fast cycle counters, but don't (for now) require it to succeed. */ if (!crng_ready()) try_to_generate_entropy(); if (!crng_ready()) { if (!ratelimit_disable && maxwarn <= 0) ++urandom_warning.missed; else if (ratelimit_disable || __ratelimit(&urandom_warning)) { --maxwarn; pr_notice("%s: uninitialized urandom read (%zu bytes read)\n", current->comm, iov_iter_count(iter)); } } return get_random_bytes_user(iter); } static ssize_t random_read_iter(struct kiocb *kiocb, struct iov_iter *iter) { int ret; if (!crng_ready() && ((kiocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO)) || (kiocb->ki_filp->f_flags & O_NONBLOCK))) return -EAGAIN; ret = wait_for_random_bytes(); if (ret != 0) return ret; return get_random_bytes_user(iter); } static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg) { int __user *p = (int __user *)arg; int ent_count; switch (cmd) { case RNDGETENTCNT: /* Inherently racy, no point locking. */ if (put_user(input_pool.init_bits, p)) return -EFAULT; return 0; case RNDADDTOENTCNT: if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (get_user(ent_count, p)) return -EFAULT; if (ent_count < 0) return -EINVAL; credit_init_bits(ent_count); return 0; case RNDADDENTROPY: { struct iov_iter iter; struct iovec iov; ssize_t ret; int len; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (get_user(ent_count, p++)) return -EFAULT; if (ent_count < 0) return -EINVAL; if (get_user(len, p++)) return -EFAULT; ret = import_single_range(ITER_SOURCE, p, len, &iov, &iter); if (unlikely(ret)) return ret; ret = write_pool_user(&iter); if (unlikely(ret < 0)) return ret; /* Since we're crediting, enforce that it was all written into the pool. */ if (unlikely(ret != len)) return -EFAULT; credit_init_bits(ent_count); return 0; } case RNDZAPENTCNT: case RNDCLEARPOOL: /* No longer has any effect. */ if (!capable(CAP_SYS_ADMIN)) return -EPERM; return 0; case RNDRESEEDCRNG: if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!crng_ready()) return -ENODATA; crng_reseed(); return 0; default: return -EINVAL; } } static int random_fasync(int fd, struct file *filp, int on) { return fasync_helper(fd, filp, on, &fasync); } const struct file_operations random_fops = { .read_iter = random_read_iter, .write_iter = random_write_iter, .poll = random_poll, .unlocked_ioctl = random_ioctl, .compat_ioctl = compat_ptr_ioctl, .fasync = random_fasync, .llseek = noop_llseek, .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, }; const struct file_operations urandom_fops = { .read_iter = urandom_read_iter, .write_iter = random_write_iter, .unlocked_ioctl = random_ioctl, .compat_ioctl = compat_ptr_ioctl, .fasync = random_fasync, .llseek = noop_llseek, .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, }; /******************************************************************** * * Sysctl interface. * * These are partly unused legacy knobs with dummy values to not break * userspace and partly still useful things. They are usually accessible * in /proc/sys/kernel/random/ and are as follows: * * - boot_id - a UUID representing the current boot. * * - uuid - a random UUID, different each time the file is read. * * - poolsize - the number of bits of entropy that the input pool can * hold, tied to the POOL_BITS constant. * * - entropy_avail - the number of bits of entropy currently in the * input pool. Always <= poolsize. * * - write_wakeup_threshold - the amount of entropy in the input pool * below which write polls to /dev/random will unblock, requesting * more entropy, tied to the POOL_READY_BITS constant. It is writable * to avoid breaking old userspaces, but writing to it does not * change any behavior of the RNG. * * - urandom_min_reseed_secs - fixed to the value CRNG_RESEED_INTERVAL. * It is writable to avoid breaking old userspaces, but writing * to it does not change any behavior of the RNG. * ********************************************************************/ #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> static int sysctl_random_min_urandom_seed = CRNG_RESEED_INTERVAL / HZ; static int sysctl_random_write_wakeup_bits = POOL_READY_BITS; static int sysctl_poolsize = POOL_BITS; static u8 sysctl_bootid[UUID_SIZE]; /* * This function is used to return both the bootid UUID, and random * UUID. The difference is in whether table->data is NULL; if it is, * then a new UUID is generated and returned to the user. */ static int proc_do_uuid(struct ctl_table *table, int write, void *buf, size_t *lenp, loff_t *ppos) { u8 tmp_uuid[UUID_SIZE], *uuid; char uuid_string[UUID_STRING_LEN + 1]; struct ctl_table fake_table = { .data = uuid_string, .maxlen = UUID_STRING_LEN }; if (write) return -EPERM; uuid = table->data; if (!uuid) { uuid = tmp_uuid; generate_random_uuid(uuid); } else { static DEFINE_SPINLOCK(bootid_spinlock); spin_lock(&bootid_spinlock); if (!uuid[8]) generate_random_uuid(uuid); spin_unlock(&bootid_spinlock); } snprintf(uuid_string, sizeof(uuid_string), "%pU", uuid); return proc_dostring(&fake_table, 0, buf, lenp, ppos); } /* The same as proc_dointvec, but writes don't change anything. */ static int proc_do_rointvec(struct ctl_table *table, int write, void *buf, size_t *lenp, loff_t *ppos) { return write ? 0 : proc_dointvec(table, 0, buf, lenp, ppos); } static struct ctl_table random_table[] = { { .procname = "poolsize", .data = &sysctl_poolsize, .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_dointvec, }, { .procname = "entropy_avail", .data = &input_pool.init_bits, .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_dointvec, }, { .procname = "write_wakeup_threshold", .data = &sysctl_random_write_wakeup_bits, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_rointvec, }, { .procname = "urandom_min_reseed_secs", .data = &sysctl_random_min_urandom_seed, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_rointvec, }, { .procname = "boot_id", .data = &sysctl_bootid, .mode = 0444, .proc_handler = proc_do_uuid, }, { .procname = "uuid", .mode = 0444, .proc_handler = proc_do_uuid, }, { } }; /* * random_init() is called before sysctl_init(), * so we cannot call register_sysctl_init() in random_init() */ static int __init random_sysctls_init(void) { register_sysctl_init("kernel/random", random_table); return 0; } device_initcall(random_sysctls_init); #endif |
| 54 54 53 640 640 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * NETLINK Generic Netlink Family * * Authors: Jamal Hadi Salim * Thomas Graf <tgraf@suug.ch> * Johannes Berg <johannes@sipsolutions.net> */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/string.h> #include <linux/skbuff.h> #include <linux/mutex.h> #include <linux/bitmap.h> #include <linux/rwsem.h> #include <linux/idr.h> #include <net/sock.h> #include <net/genetlink.h> static DEFINE_MUTEX(genl_mutex); /* serialization of message processing */ static DECLARE_RWSEM(cb_lock); atomic_t genl_sk_destructing_cnt = ATOMIC_INIT(0); DECLARE_WAIT_QUEUE_HEAD(genl_sk_destructing_waitq); void genl_lock(void) { mutex_lock(&genl_mutex); } EXPORT_SYMBOL(genl_lock); void genl_unlock(void) { mutex_unlock(&genl_mutex); } EXPORT_SYMBOL(genl_unlock); static void genl_lock_all(void) { down_write(&cb_lock); genl_lock(); } static void genl_unlock_all(void) { genl_unlock(); up_write(&cb_lock); } static DEFINE_IDR(genl_fam_idr); /* * Bitmap of multicast groups that are currently in use. * * To avoid an allocation at boot of just one unsigned long, * declare it global instead. * Bit 0 is marked as already used since group 0 is invalid. * Bit 1 is marked as already used since the drop-monitor code * abuses the API and thinks it can statically use group 1. * That group will typically conflict with other groups that * any proper users use. * Bit 16 is marked as used since it's used for generic netlink * and the code no longer marks pre-reserved IDs as used. * Bit 17 is marked as already used since the VFS quota code * also abused this API and relied on family == group ID, we * cater to that by giving it a static family and group ID. * Bit 18 is marked as already used since the PMCRAID driver * did the same thing as the VFS quota code (maybe copied?) */ static unsigned long mc_group_start = 0x3 | BIT(GENL_ID_CTRL) | BIT(GENL_ID_VFS_DQUOT) | BIT(GENL_ID_PMCRAID); static unsigned long *mc_groups = &mc_group_start; static unsigned long mc_groups_longs = 1; /* We need the last attribute with non-zero ID therefore a 2-entry array */ static struct nla_policy genl_policy_reject_all[] = { { .type = NLA_REJECT }, { .type = NLA_REJECT }, }; static int genl_ctrl_event(int event, const struct genl_family *family, const struct genl_multicast_group *grp, int grp_id); static void genl_op_fill_in_reject_policy(const struct genl_family *family, struct genl_ops *op) { BUILD_BUG_ON(ARRAY_SIZE(genl_policy_reject_all) - 1 != 1); if (op->policy || op->cmd < family->resv_start_op) return; op->policy = genl_policy_reject_all; op->maxattr = 1; } static const struct genl_family *genl_family_find_byid(unsigned int id) { return idr_find(&genl_fam_idr, id); } static const struct genl_family *genl_family_find_byname(char *name) { const struct genl_family *family; unsigned int id; idr_for_each_entry(&genl_fam_idr, family, id) if (strcmp(family->name, name) == 0) return family; return NULL; } static int genl_get_cmd_cnt(const struct genl_family *family) { return family->n_ops + family->n_small_ops; } static void genl_op_from_full(const struct genl_family *family, unsigned int i, struct genl_ops *op) { *op = family->ops[i]; if (!op->maxattr) op->maxattr = family->maxattr; if (!op->policy) op->policy = family->policy; genl_op_fill_in_reject_policy(family, op); } static int genl_get_cmd_full(u32 cmd, const struct genl_family *family, struct genl_ops *op) { int i; for (i = 0; i < family->n_ops; i++) if (family->ops[i].cmd == cmd) { genl_op_from_full(family, i, op); return 0; } return -ENOENT; } static void genl_op_from_small(const struct genl_family *family, unsigned int i, struct genl_ops *op) { memset(op, 0, sizeof(*op)); op->doit = family->small_ops[i].doit; op->dumpit = family->small_ops[i].dumpit; op->cmd = family->small_ops[i].cmd; op->internal_flags = family->small_ops[i].internal_flags; op->flags = family->small_ops[i].flags; op->validate = family->small_ops[i].validate; op->maxattr = family->maxattr; op->policy = family->policy; genl_op_fill_in_reject_policy(family, op); } static int genl_get_cmd_small(u32 cmd, const struct genl_family *family, struct genl_ops *op) { int i; for (i = 0; i < family->n_small_ops; i++) if (family->small_ops[i].cmd == cmd) { genl_op_from_small(family, i, op); return 0; } return -ENOENT; } static int genl_get_cmd(u32 cmd, const struct genl_family *family, struct genl_ops *op) { if (!genl_get_cmd_full(cmd, family, op)) return 0; return genl_get_cmd_small(cmd, family, op); } static void genl_get_cmd_by_index(unsigned int i, const struct genl_family *family, struct genl_ops *op) { if (i < family->n_ops) genl_op_from_full(family, i, op); else if (i < family->n_ops + family->n_small_ops) genl_op_from_small(family, i - family->n_ops, op); else WARN_ON_ONCE(1); } static int genl_allocate_reserve_groups(int n_groups, int *first_id) { unsigned long *new_groups; int start = 0; int i; int id; bool fits; do { if (start == 0) id = find_first_zero_bit(mc_groups, mc_groups_longs * BITS_PER_LONG); else id = find_next_zero_bit(mc_groups, mc_groups_longs * BITS_PER_LONG, start); fits = true; for (i = id; i < min_t(int, id + n_groups, mc_groups_longs * BITS_PER_LONG); i++) { if (test_bit(i, mc_groups)) { start = i; fits = false; break; } } if (id + n_groups > mc_groups_longs * BITS_PER_LONG) { unsigned long new_longs = mc_groups_longs + BITS_TO_LONGS(n_groups); size_t nlen = new_longs * sizeof(unsigned long); if (mc_groups == &mc_group_start) { new_groups = kzalloc(nlen, GFP_KERNEL); if (!new_groups) return -ENOMEM; mc_groups = new_groups; *mc_groups = mc_group_start; } else { new_groups = krealloc(mc_groups, nlen, GFP_KERNEL); if (!new_groups) return -ENOMEM; mc_groups = new_groups; for (i = 0; i < BITS_TO_LONGS(n_groups); i++) mc_groups[mc_groups_longs + i] = 0; } mc_groups_longs = new_longs; } } while (!fits); for (i = id; i < id + n_groups; i++) set_bit(i, mc_groups); *first_id = id; return 0; } static struct genl_family genl_ctrl; static int genl_validate_assign_mc_groups(struct genl_family *family) { int first_id; int n_groups = family->n_mcgrps; int err = 0, i; bool groups_allocated = false; if (!n_groups) return 0; for (i = 0; i < n_groups; i++) { const struct genl_multicast_group *grp = &family->mcgrps[i]; if (WARN_ON(grp->name[0] == '\0')) return -EINVAL; if (WARN_ON(memchr(grp->name, '\0', GENL_NAMSIZ) == NULL)) return -EINVAL; } /* special-case our own group and hacks */ if (family == &genl_ctrl) { first_id = GENL_ID_CTRL; BUG_ON(n_groups != 1); } else if (strcmp(family->name, "NET_DM") == 0) { first_id = 1; BUG_ON(n_groups != 1); } else if (family->id == GENL_ID_VFS_DQUOT) { first_id = GENL_ID_VFS_DQUOT; BUG_ON(n_groups != 1); } else if (family->id == GENL_ID_PMCRAID) { first_id = GENL_ID_PMCRAID; BUG_ON(n_groups != 1); } else { groups_allocated = true; err = genl_allocate_reserve_groups(n_groups, &first_id); if (err) return err; } family->mcgrp_offset = first_id; /* if still initializing, can't and don't need to realloc bitmaps */ if (!init_net.genl_sock) return 0; if (family->netnsok) { struct net *net; netlink_table_grab(); rcu_read_lock(); for_each_net_rcu(net) { err = __netlink_change_ngroups(net->genl_sock, mc_groups_longs * BITS_PER_LONG); if (err) { /* * No need to roll back, can only fail if * memory allocation fails and then the * number of _possible_ groups has been * increased on some sockets which is ok. */ break; } } rcu_read_unlock(); netlink_table_ungrab(); } else { err = netlink_change_ngroups(init_net.genl_sock, mc_groups_longs * BITS_PER_LONG); } if (groups_allocated && err) { for (i = 0; i < family->n_mcgrps; i++) clear_bit(family->mcgrp_offset + i, mc_groups); } return err; } static void genl_unregister_mc_groups(const struct genl_family *family) { struct net *net; int i; netlink_table_grab(); rcu_read_lock(); for_each_net_rcu(net) { for (i = 0; i < family->n_mcgrps; i++) __netlink_clear_multicast_users( net->genl_sock, family->mcgrp_offset + i); } rcu_read_unlock(); netlink_table_ungrab(); for (i = 0; i < family->n_mcgrps; i++) { int grp_id = family->mcgrp_offset + i; if (grp_id != 1) clear_bit(grp_id, mc_groups); genl_ctrl_event(CTRL_CMD_DELMCAST_GRP, family, &family->mcgrps[i], grp_id); } } static int genl_validate_ops(const struct genl_family *family) { int i, j; if (WARN_ON(family->n_ops && !family->ops) || WARN_ON(family->n_small_ops && !family->small_ops)) return -EINVAL; for (i = 0; i < genl_get_cmd_cnt(family); i++) { struct genl_ops op; genl_get_cmd_by_index(i, family, &op); if (op.dumpit == NULL && op.doit == NULL) return -EINVAL; if (WARN_ON(op.cmd >= family->resv_start_op && op.validate)) return -EINVAL; for (j = i + 1; j < genl_get_cmd_cnt(family); j++) { struct genl_ops op2; genl_get_cmd_by_index(j, family, &op2); if (op.cmd == op2.cmd) return -EINVAL; } } return 0; } /** * genl_register_family - register a generic netlink family * @family: generic netlink family * * Registers the specified family after validating it first. Only one * family may be registered with the same family name or identifier. * * The family's ops, multicast groups and module pointer must already * be assigned. * * Return 0 on success or a negative error code. */ int genl_register_family(struct genl_family *family) { int err, i; int start = GENL_START_ALLOC, end = GENL_MAX_ID; err = genl_validate_ops(family); if (err) return err; genl_lock_all(); if (genl_family_find_byname(family->name)) { err = -EEXIST; goto errout_locked; } /* * Sadly, a few cases need to be special-cased * due to them having previously abused the API * and having used their family ID also as their * multicast group ID, so we use reserved IDs * for both to be sure we can do that mapping. */ if (family == &genl_ctrl) { /* and this needs to be special for initial family lookups */ start = end = GENL_ID_CTRL; } else if (strcmp(family->name, "pmcraid") == 0) { start = end = GENL_ID_PMCRAID; } else if (strcmp(family->name, "VFS_DQUOT") == 0) { start = end = GENL_ID_VFS_DQUOT; } family->id = idr_alloc_cyclic(&genl_fam_idr, family, start, end + 1, GFP_KERNEL); if (family->id < 0) { err = family->id; goto errout_locked; } err = genl_validate_assign_mc_groups(family); if (err) goto errout_remove; genl_unlock_all(); /* send all events */ genl_ctrl_event(CTRL_CMD_NEWFAMILY, family, NULL, 0); for (i = 0; i < family->n_mcgrps; i++) genl_ctrl_event(CTRL_CMD_NEWMCAST_GRP, family, &family->mcgrps[i], family->mcgrp_offset + i); return 0; errout_remove: idr_remove(&genl_fam_idr, family->id); errout_locked: genl_unlock_all(); return err; } EXPORT_SYMBOL(genl_register_family); /** * genl_unregister_family - unregister generic netlink family * @family: generic netlink family * * Unregisters the specified family. * * Returns 0 on success or a negative error code. */ int genl_unregister_family(const struct genl_family *family) { genl_lock_all(); if (!genl_family_find_byid(family->id)) { genl_unlock_all(); return -ENOENT; } genl_unregister_mc_groups(family); idr_remove(&genl_fam_idr, family->id); up_write(&cb_lock); wait_event(genl_sk_destructing_waitq, atomic_read(&genl_sk_destructing_cnt) == 0); genl_unlock(); genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL, 0); return 0; } EXPORT_SYMBOL(genl_unregister_family); /** * genlmsg_put - Add generic netlink header to netlink message * @skb: socket buffer holding the message * @portid: netlink portid the message is addressed to * @seq: sequence number (usually the one of the sender) * @family: generic netlink family * @flags: netlink message flags * @cmd: generic netlink command * * Returns pointer to user specific header */ void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, const struct genl_family *family, int flags, u8 cmd) { struct nlmsghdr *nlh; struct genlmsghdr *hdr; nlh = nlmsg_put(skb, portid, seq, family->id, GENL_HDRLEN + family->hdrsize, flags); if (nlh == NULL) return NULL; hdr = nlmsg_data(nlh); hdr->cmd = cmd; hdr->version = family->version; hdr->reserved = 0; return (char *) hdr + GENL_HDRLEN; } EXPORT_SYMBOL(genlmsg_put); static struct genl_dumpit_info *genl_dumpit_info_alloc(void) { return kmalloc(sizeof(struct genl_dumpit_info), GFP_KERNEL); } static void genl_dumpit_info_free(const struct genl_dumpit_info *info) { kfree(info); } static struct nlattr ** genl_family_rcv_msg_attrs_parse(const struct genl_family *family, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, const struct genl_ops *ops, int hdrlen, enum genl_validate_flags no_strict_flag) { enum netlink_validation validate = ops->validate & no_strict_flag ? NL_VALIDATE_LIBERAL : NL_VALIDATE_STRICT; struct nlattr **attrbuf; int err; if (!ops->maxattr) return NULL; attrbuf = kmalloc_array(ops->maxattr + 1, sizeof(struct nlattr *), GFP_KERNEL); if (!attrbuf) return ERR_PTR(-ENOMEM); err = __nlmsg_parse(nlh, hdrlen, attrbuf, ops->maxattr, ops->policy, validate, extack); if (err) { kfree(attrbuf); return ERR_PTR(err); } return attrbuf; } static void genl_family_rcv_msg_attrs_free(struct nlattr **attrbuf) { kfree(attrbuf); } struct genl_start_context { const struct genl_family *family; struct nlmsghdr *nlh; struct netlink_ext_ack *extack; const struct genl_ops *ops; int hdrlen; }; static int genl_start(struct netlink_callback *cb) { struct genl_start_context *ctx = cb->data; const struct genl_ops *ops = ctx->ops; struct genl_dumpit_info *info; struct nlattr **attrs = NULL; int rc = 0; if (ops->validate & GENL_DONT_VALIDATE_DUMP) goto no_attrs; if (ctx->nlh->nlmsg_len < nlmsg_msg_size(ctx->hdrlen)) return -EINVAL; attrs = genl_family_rcv_msg_attrs_parse(ctx->family, ctx->nlh, ctx->extack, ops, ctx->hdrlen, GENL_DONT_VALIDATE_DUMP_STRICT); if (IS_ERR(attrs)) return PTR_ERR(attrs); no_attrs: info = genl_dumpit_info_alloc(); if (!info) { genl_family_rcv_msg_attrs_free(attrs); return -ENOMEM; } info->family = ctx->family; info->op = *ops; info->attrs = attrs; cb->data = info; if (ops->start) { if (!ctx->family->parallel_ops) genl_lock(); rc = ops->start(cb); if (!ctx->family->parallel_ops) genl_unlock(); } if (rc) { genl_family_rcv_msg_attrs_free(info->attrs); genl_dumpit_info_free(info); cb->data = NULL; } return rc; } static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { const struct genl_ops *ops = &genl_dumpit_info(cb)->op; int rc; genl_lock(); rc = ops->dumpit(skb, cb); genl_unlock(); return rc; } static int genl_lock_done(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); const struct genl_ops *ops = &info->op; int rc = 0; if (ops->done) { genl_lock(); rc = ops->done(cb); genl_unlock(); } genl_family_rcv_msg_attrs_free(info->attrs); genl_dumpit_info_free(info); return rc; } static int genl_parallel_done(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); const struct genl_ops *ops = &info->op; int rc = 0; if (ops->done) rc = ops->done(cb); genl_family_rcv_msg_attrs_free(info->attrs); genl_dumpit_info_free(info); return rc; } static int genl_family_rcv_msg_dumpit(const struct genl_family *family, struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, const struct genl_ops *ops, int hdrlen, struct net *net) { struct genl_start_context ctx; int err; if (!ops->dumpit) return -EOPNOTSUPP; ctx.family = family; ctx.nlh = nlh; ctx.extack = extack; ctx.ops = ops; ctx.hdrlen = hdrlen; if (!family->parallel_ops) { struct netlink_dump_control c = { .module = family->module, .data = &ctx, .start = genl_start, .dump = genl_lock_dumpit, .done = genl_lock_done, }; genl_unlock(); err = __netlink_dump_start(net->genl_sock, skb, nlh, &c); genl_lock(); } else { struct netlink_dump_control c = { .module = family->module, .data = &ctx, .start = genl_start, .dump = ops->dumpit, .done = genl_parallel_done, }; err = __netlink_dump_start(net->genl_sock, skb, nlh, &c); } return err; } static int genl_family_rcv_msg_doit(const struct genl_family *family, struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, const struct genl_ops *ops, int hdrlen, struct net *net) { struct nlattr **attrbuf; struct genl_info info; int err; if (!ops->doit) return -EOPNOTSUPP; attrbuf = genl_family_rcv_msg_attrs_parse(family, nlh, extack, ops, hdrlen, GENL_DONT_VALIDATE_STRICT); if (IS_ERR(attrbuf)) return PTR_ERR(attrbuf); info.snd_seq = nlh->nlmsg_seq; info.snd_portid = NETLINK_CB(skb).portid; info.nlhdr = nlh; info.genlhdr = nlmsg_data(nlh); info.userhdr = nlmsg_data(nlh) + GENL_HDRLEN; info.attrs = attrbuf; info.extack = extack; genl_info_net_set(&info, net); memset(&info.user_ptr, 0, sizeof(info.user_ptr)); if (family->pre_doit) { err = family->pre_doit(ops, skb, &info); if (err) goto out; } err = ops->doit(skb, &info); if (family->post_doit) family->post_doit(ops, skb, &info); out: genl_family_rcv_msg_attrs_free(attrbuf); return err; } static int genl_header_check(const struct genl_family *family, struct nlmsghdr *nlh, struct genlmsghdr *hdr, struct netlink_ext_ack *extack) { u16 flags; /* Only for commands added after we started validating */ if (hdr->cmd < family->resv_start_op) return 0; if (hdr->reserved) { NL_SET_ERR_MSG(extack, "genlmsghdr.reserved field is not 0"); return -EINVAL; } /* Old netlink flags have pretty loose semantics, allow only the flags * consumed by the core where we can enforce the meaning. */ flags = nlh->nlmsg_flags; if ((flags & NLM_F_DUMP) == NLM_F_DUMP) /* DUMP is 2 bits */ flags &= ~NLM_F_DUMP; if (flags & ~(NLM_F_REQUEST | NLM_F_ACK | NLM_F_ECHO)) { NL_SET_ERR_MSG(extack, "ambiguous or reserved bits set in nlmsg_flags"); return -EINVAL; } return 0; } static int genl_family_rcv_msg(const struct genl_family *family, struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct genlmsghdr *hdr = nlmsg_data(nlh); struct genl_ops op; int hdrlen; /* this family doesn't exist in this netns */ if (!family->netnsok && !net_eq(net, &init_net)) return -ENOENT; hdrlen = GENL_HDRLEN + family->hdrsize; if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) return -EINVAL; if (genl_header_check(family, nlh, hdr, extack)) return -EINVAL; if (genl_get_cmd(hdr->cmd, family, &op)) return -EOPNOTSUPP; if ((op.flags & GENL_ADMIN_PERM) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if ((op.flags & GENL_UNS_ADMIN_PERM) && !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) return -EPERM; if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP) return genl_family_rcv_msg_dumpit(family, skb, nlh, extack, &op, hdrlen, net); else return genl_family_rcv_msg_doit(family, skb, nlh, extack, &op, hdrlen, net); } static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { const struct genl_family *family; int err; family = genl_family_find_byid(nlh->nlmsg_type); if (family == NULL) return -ENOENT; if (!family->parallel_ops) genl_lock(); err = genl_family_rcv_msg(family, skb, nlh, extack); if (!family->parallel_ops) genl_unlock(); return err; } static void genl_rcv(struct sk_buff *skb) { down_read(&cb_lock); netlink_rcv_skb(skb, &genl_rcv_msg); up_read(&cb_lock); } /************************************************************************** * Controller **************************************************************************/ static struct genl_family genl_ctrl; static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq, u32 flags, struct sk_buff *skb, u8 cmd) { void *hdr; hdr = genlmsg_put(skb, portid, seq, &genl_ctrl, flags, cmd); if (hdr == NULL) return -1; if (nla_put_string(skb, CTRL_ATTR_FAMILY_NAME, family->name) || nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, family->id) || nla_put_u32(skb, CTRL_ATTR_VERSION, family->version) || nla_put_u32(skb, CTRL_ATTR_HDRSIZE, family->hdrsize) || nla_put_u32(skb, CTRL_ATTR_MAXATTR, family->maxattr)) goto nla_put_failure; if (genl_get_cmd_cnt(family)) { struct nlattr *nla_ops; int i; nla_ops = nla_nest_start_noflag(skb, CTRL_ATTR_OPS); if (nla_ops == NULL) goto nla_put_failure; for (i = 0; i < genl_get_cmd_cnt(family); i++) { struct nlattr *nest; struct genl_ops op; u32 op_flags; genl_get_cmd_by_index(i, family, &op); op_flags = op.flags; if (op.dumpit) op_flags |= GENL_CMD_CAP_DUMP; if (op.doit) op_flags |= GENL_CMD_CAP_DO; if (op.policy) op_flags |= GENL_CMD_CAP_HASPOL; nest = nla_nest_start_noflag(skb, i + 1); if (nest == NULL) goto nla_put_failure; if (nla_put_u32(skb, CTRL_ATTR_OP_ID, op.cmd) || nla_put_u32(skb, CTRL_ATTR_OP_FLAGS, op_flags)) goto nla_put_failure; nla_nest_end(skb, nest); } nla_nest_end(skb, nla_ops); } if (family->n_mcgrps) { struct nlattr *nla_grps; int i; nla_grps = nla_nest_start_noflag(skb, CTRL_ATTR_MCAST_GROUPS); if (nla_grps == NULL) goto nla_put_failure; for (i = 0; i < family->n_mcgrps; i++) { struct nlattr *nest; const struct genl_multicast_group *grp; grp = &family->mcgrps[i]; nest = nla_nest_start_noflag(skb, i + 1); if (nest == NULL) goto nla_put_failure; if (nla_put_u32(skb, CTRL_ATTR_MCAST_GRP_ID, family->mcgrp_offset + i) || nla_put_string(skb, CTRL_ATTR_MCAST_GRP_NAME, grp->name)) goto nla_put_failure; nla_nest_end(skb, nest); } nla_nest_end(skb, nla_grps); } genlmsg_end(skb, hdr); return 0; nla_put_failure: genlmsg_cancel(skb, hdr); return -EMSGSIZE; } static int ctrl_fill_mcgrp_info(const struct genl_family *family, const struct genl_multicast_group *grp, int grp_id, u32 portid, u32 seq, u32 flags, struct sk_buff *skb, u8 cmd) { void *hdr; struct nlattr *nla_grps; struct nlattr *nest; hdr = genlmsg_put(skb, portid, seq, &genl_ctrl, flags, cmd); if (hdr == NULL) return -1; if (nla_put_string(skb, CTRL_ATTR_FAMILY_NAME, family->name) || nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, family->id)) goto nla_put_failure; nla_grps = nla_nest_start_noflag(skb, CTRL_ATTR_MCAST_GROUPS); if (nla_grps == NULL) goto nla_put_failure; nest = nla_nest_start_noflag(skb, 1); if (nest == NULL) goto nla_put_failure; if (nla_put_u32(skb, CTRL_ATTR_MCAST_GRP_ID, grp_id) || nla_put_string(skb, CTRL_ATTR_MCAST_GRP_NAME, grp->name)) goto nla_put_failure; nla_nest_end(skb, nest); nla_nest_end(skb, nla_grps); genlmsg_end(skb, hdr); return 0; nla_put_failure: genlmsg_cancel(skb, hdr); return -EMSGSIZE; } static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) { int n = 0; struct genl_family *rt; struct net *net = sock_net(skb->sk); int fams_to_skip = cb->args[0]; unsigned int id; idr_for_each_entry(&genl_fam_idr, rt, id) { if (!rt->netnsok && !net_eq(net, &init_net)) continue; if (n++ < fams_to_skip) continue; if (ctrl_fill_info(rt, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, skb, CTRL_CMD_NEWFAMILY) < 0) { n--; break; } } cb->args[0] = n; return skb->len; } static struct sk_buff *ctrl_build_family_msg(const struct genl_family *family, u32 portid, int seq, u8 cmd) { struct sk_buff *skb; int err; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb == NULL) return ERR_PTR(-ENOBUFS); err = ctrl_fill_info(family, portid, seq, 0, skb, cmd); if (err < 0) { nlmsg_free(skb); return ERR_PTR(err); } return skb; } static struct sk_buff * ctrl_build_mcgrp_msg(const struct genl_family *family, const struct genl_multicast_group *grp, int grp_id, u32 portid, int seq, u8 cmd) { struct sk_buff *skb; int err; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb == NULL) return ERR_PTR(-ENOBUFS); err = ctrl_fill_mcgrp_info(family, grp, grp_id, portid, seq, 0, skb, cmd); if (err < 0) { nlmsg_free(skb); return ERR_PTR(err); } return skb; } static const struct nla_policy ctrl_policy_family[] = { [CTRL_ATTR_FAMILY_ID] = { .type = NLA_U16 }, [CTRL_ATTR_FAMILY_NAME] = { .type = NLA_NUL_STRING, .len = GENL_NAMSIZ - 1 }, }; static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; const struct genl_family *res = NULL; int err = -EINVAL; if (info->attrs[CTRL_ATTR_FAMILY_ID]) { u16 id = nla_get_u16(info->attrs[CTRL_ATTR_FAMILY_ID]); res = genl_family_find_byid(id); err = -ENOENT; } if (info->attrs[CTRL_ATTR_FAMILY_NAME]) { char *name; name = nla_data(info->attrs[CTRL_ATTR_FAMILY_NAME]); res = genl_family_find_byname(name); #ifdef CONFIG_MODULES if (res == NULL) { genl_unlock(); up_read(&cb_lock); request_module("net-pf-%d-proto-%d-family-%s", PF_NETLINK, NETLINK_GENERIC, name); down_read(&cb_lock); genl_lock(); res = genl_family_find_byname(name); } #endif err = -ENOENT; } if (res == NULL) return err; if (!res->netnsok && !net_eq(genl_info_net(info), &init_net)) { /* family doesn't exist here */ return -ENOENT; } msg = ctrl_build_family_msg(res, info->snd_portid, info->snd_seq, CTRL_CMD_NEWFAMILY); if (IS_ERR(msg)) return PTR_ERR(msg); return genlmsg_reply(msg, info); } static int genl_ctrl_event(int event, const struct genl_family *family, const struct genl_multicast_group *grp, int grp_id) { struct sk_buff *msg; /* genl is still initialising */ if (!init_net.genl_sock) return 0; switch (event) { case CTRL_CMD_NEWFAMILY: case CTRL_CMD_DELFAMILY: WARN_ON(grp); msg = ctrl_build_family_msg(family, 0, 0, event); break; case CTRL_CMD_NEWMCAST_GRP: case CTRL_CMD_DELMCAST_GRP: BUG_ON(!grp); msg = ctrl_build_mcgrp_msg(family, grp, grp_id, 0, 0, event); break; default: return -EINVAL; } if (IS_ERR(msg)) return PTR_ERR(msg); if (!family->netnsok) { genlmsg_multicast_netns(&genl_ctrl, &init_net, msg, 0, 0, GFP_KERNEL); } else { rcu_read_lock(); genlmsg_multicast_allns(&genl_ctrl, msg, 0, 0, GFP_ATOMIC); rcu_read_unlock(); } return 0; } struct ctrl_dump_policy_ctx { struct netlink_policy_dump_state *state; const struct genl_family *rt; unsigned int opidx; u32 op; u16 fam_id; u8 policies:1, single_op:1; }; static const struct nla_policy ctrl_policy_policy[] = { [CTRL_ATTR_FAMILY_ID] = { .type = NLA_U16 }, [CTRL_ATTR_FAMILY_NAME] = { .type = NLA_NUL_STRING, .len = GENL_NAMSIZ - 1 }, [CTRL_ATTR_OP] = { .type = NLA_U32 }, }; static int ctrl_dumppolicy_start(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; struct nlattr **tb = info->attrs; const struct genl_family *rt; struct genl_ops op; int err, i; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); if (!tb[CTRL_ATTR_FAMILY_ID] && !tb[CTRL_ATTR_FAMILY_NAME]) return -EINVAL; if (tb[CTRL_ATTR_FAMILY_ID]) { ctx->fam_id = nla_get_u16(tb[CTRL_ATTR_FAMILY_ID]); } else { rt = genl_family_find_byname( nla_data(tb[CTRL_ATTR_FAMILY_NAME])); if (!rt) return -ENOENT; ctx->fam_id = rt->id; } rt = genl_family_find_byid(ctx->fam_id); if (!rt) return -ENOENT; ctx->rt = rt; if (tb[CTRL_ATTR_OP]) { ctx->single_op = true; ctx->op = nla_get_u32(tb[CTRL_ATTR_OP]); err = genl_get_cmd(ctx->op, rt, &op); if (err) { NL_SET_BAD_ATTR(cb->extack, tb[CTRL_ATTR_OP]); return err; } if (!op.policy) return -ENODATA; return netlink_policy_dump_add_policy(&ctx->state, op.policy, op.maxattr); } for (i = 0; i < genl_get_cmd_cnt(rt); i++) { genl_get_cmd_by_index(i, rt, &op); if (op.policy) { err = netlink_policy_dump_add_policy(&ctx->state, op.policy, op.maxattr); if (err) goto err_free_state; } } if (!ctx->state) return -ENODATA; return 0; err_free_state: netlink_policy_dump_free(ctx->state); return err; } static void *ctrl_dumppolicy_prep(struct sk_buff *skb, struct netlink_callback *cb) { struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; void *hdr; hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &genl_ctrl, NLM_F_MULTI, CTRL_CMD_GETPOLICY); if (!hdr) return NULL; if (nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, ctx->fam_id)) return NULL; return hdr; } static int ctrl_dumppolicy_put_op(struct sk_buff *skb, struct netlink_callback *cb, struct genl_ops *op) { struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; struct nlattr *nest_pol, *nest_op; void *hdr; int idx; /* skip if we have nothing to show */ if (!op->policy) return 0; if (!op->doit && (!op->dumpit || op->validate & GENL_DONT_VALIDATE_DUMP)) return 0; hdr = ctrl_dumppolicy_prep(skb, cb); if (!hdr) return -ENOBUFS; nest_pol = nla_nest_start(skb, CTRL_ATTR_OP_POLICY); if (!nest_pol) goto err; nest_op = nla_nest_start(skb, op->cmd); if (!nest_op) goto err; /* for now both do/dump are always the same */ idx = netlink_policy_dump_get_policy_idx(ctx->state, op->policy, op->maxattr); if (op->doit && nla_put_u32(skb, CTRL_ATTR_POLICY_DO, idx)) goto err; if (op->dumpit && !(op->validate & GENL_DONT_VALIDATE_DUMP) && nla_put_u32(skb, CTRL_ATTR_POLICY_DUMP, idx)) goto err; nla_nest_end(skb, nest_op); nla_nest_end(skb, nest_pol); genlmsg_end(skb, hdr); return 0; err: genlmsg_cancel(skb, hdr); return -ENOBUFS; } static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb) { struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; void *hdr; if (!ctx->policies) { while (ctx->opidx < genl_get_cmd_cnt(ctx->rt)) { struct genl_ops op; if (ctx->single_op) { int err; err = genl_get_cmd(ctx->op, ctx->rt, &op); if (WARN_ON(err)) return skb->len; /* break out of the loop after this one */ ctx->opidx = genl_get_cmd_cnt(ctx->rt); } else { genl_get_cmd_by_index(ctx->opidx, ctx->rt, &op); } if (ctrl_dumppolicy_put_op(skb, cb, &op)) return skb->len; ctx->opidx++; } /* completed with the per-op policy index list */ ctx->policies = true; } while (netlink_policy_dump_loop(ctx->state)) { struct nlattr *nest; hdr = ctrl_dumppolicy_prep(skb, cb); if (!hdr) goto nla_put_failure; nest = nla_nest_start(skb, CTRL_ATTR_POLICY); if (!nest) goto nla_put_failure; if (netlink_policy_dump_write(skb, ctx->state)) goto nla_put_failure; nla_nest_end(skb, nest); genlmsg_end(skb, hdr); } return skb->len; nla_put_failure: genlmsg_cancel(skb, hdr); return skb->len; } static int ctrl_dumppolicy_done(struct netlink_callback *cb) { struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; netlink_policy_dump_free(ctx->state); return 0; } static const struct genl_ops genl_ctrl_ops[] = { { .cmd = CTRL_CMD_GETFAMILY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .policy = ctrl_policy_family, .maxattr = ARRAY_SIZE(ctrl_policy_family) - 1, .doit = ctrl_getfamily, .dumpit = ctrl_dumpfamily, }, { .cmd = CTRL_CMD_GETPOLICY, .policy = ctrl_policy_policy, .maxattr = ARRAY_SIZE(ctrl_policy_policy) - 1, .start = ctrl_dumppolicy_start, .dumpit = ctrl_dumppolicy, .done = ctrl_dumppolicy_done, }, }; static const struct genl_multicast_group genl_ctrl_groups[] = { { .name = "notify", }, }; static struct genl_family genl_ctrl __ro_after_init = { .module = THIS_MODULE, .ops = genl_ctrl_ops, .n_ops = ARRAY_SIZE(genl_ctrl_ops), .resv_start_op = CTRL_CMD_GETPOLICY + 1, .mcgrps = genl_ctrl_groups, .n_mcgrps = ARRAY_SIZE(genl_ctrl_groups), .id = GENL_ID_CTRL, .name = "nlctrl", .version = 0x2, .netnsok = true, }; static int genl_bind(struct net *net, int group) { const struct genl_family *family; unsigned int id; int ret = 0; down_read(&cb_lock); idr_for_each_entry(&genl_fam_idr, family, id) { const struct genl_multicast_group *grp; int i; if (family->n_mcgrps == 0) continue; i = group - family->mcgrp_offset; if (i < 0 || i >= family->n_mcgrps) continue; grp = &family->mcgrps[i]; if ((grp->flags & GENL_UNS_ADMIN_PERM) && !ns_capable(net->user_ns, CAP_NET_ADMIN)) ret = -EPERM; break; } up_read(&cb_lock); return ret; } static int __net_init genl_pernet_init(struct net *net) { struct netlink_kernel_cfg cfg = { .input = genl_rcv, .flags = NL_CFG_F_NONROOT_RECV, .bind = genl_bind, }; /* we'll bump the group number right afterwards */ net->genl_sock = netlink_kernel_create(net, NETLINK_GENERIC, &cfg); if (!net->genl_sock && net_eq(net, &init_net)) panic("GENL: Cannot initialize generic netlink\n"); if (!net->genl_sock) return -ENOMEM; return 0; } static void __net_exit genl_pernet_exit(struct net *net) { netlink_kernel_release(net->genl_sock); net->genl_sock = NULL; } static struct pernet_operations genl_pernet_ops = { .init = genl_pernet_init, .exit = genl_pernet_exit, }; static int __init genl_init(void) { int err; err = genl_register_family(&genl_ctrl); if (err < 0) goto problem; err = register_pernet_subsys(&genl_pernet_ops); if (err) goto problem; return 0; problem: panic("GENL: Cannot register controller: %d\n", err); } core_initcall(genl_init); static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group, gfp_t flags) { struct sk_buff *tmp; struct net *net, *prev = NULL; bool delivered = false; int err; for_each_net_rcu(net) { if (prev) { tmp = skb_clone(skb, flags); if (!tmp) { err = -ENOMEM; goto error; } err = nlmsg_multicast(prev->genl_sock, tmp, portid, group, flags); if (!err) delivered = true; else if (err != -ESRCH) goto error; } prev = net; } err = nlmsg_multicast(prev->genl_sock, skb, portid, group, flags); if (!err) delivered = true; else if (err != -ESRCH) return err; return delivered ? 0 : -ESRCH; error: kfree_skb(skb); return err; } int genlmsg_multicast_allns(const struct genl_family *family, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { if (WARN_ON_ONCE(group >= family->n_mcgrps)) return -EINVAL; group = family->mcgrp_offset + group; return genlmsg_mcast(skb, portid, group, flags); } EXPORT_SYMBOL(genlmsg_multicast_allns); void genl_notify(const struct genl_family *family, struct sk_buff *skb, struct genl_info *info, u32 group, gfp_t flags) { struct net *net = genl_info_net(info); struct sock *sk = net->genl_sock; if (WARN_ON_ONCE(group >= family->n_mcgrps)) return; group = family->mcgrp_offset + group; nlmsg_notify(sk, skb, info->snd_portid, group, nlmsg_report(info->nlhdr), flags); } EXPORT_SYMBOL(genl_notify); |
| 1244 1242 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Basic authentication token and access key management * * Copyright (C) 2004-2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/export.h> #include <linux/init.h> #include <linux/poison.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/workqueue.h> #include <linux/random.h> #include <linux/ima.h> #include <linux/err.h> #include "internal.h" struct kmem_cache *key_jar; struct rb_root key_serial_tree; /* tree of keys indexed by serial */ DEFINE_SPINLOCK(key_serial_lock); struct rb_root key_user_tree; /* tree of quota records indexed by UID */ DEFINE_SPINLOCK(key_user_lock); unsigned int key_quota_root_maxkeys = 1000000; /* root's key count quota */ unsigned int key_quota_root_maxbytes = 25000000; /* root's key space quota */ unsigned int key_quota_maxkeys = 200; /* general key count quota */ unsigned int key_quota_maxbytes = 20000; /* general key space quota */ static LIST_HEAD(key_types_list); static DECLARE_RWSEM(key_types_sem); /* We serialise key instantiation and link */ DEFINE_MUTEX(key_construction_mutex); #ifdef KEY_DEBUGGING void __key_check(const struct key *key) { printk("__key_check: key %p {%08x} should be {%08x}\n", key, key->magic, KEY_DEBUG_MAGIC); BUG(); } #endif /* * Get the key quota record for a user, allocating a new record if one doesn't * already exist. */ struct key_user *key_user_lookup(kuid_t uid) { struct key_user *candidate = NULL, *user; struct rb_node *parent, **p; try_again: parent = NULL; p = &key_user_tree.rb_node; spin_lock(&key_user_lock); /* search the tree for a user record with a matching UID */ while (*p) { parent = *p; user = rb_entry(parent, struct key_user, node); if (uid_lt(uid, user->uid)) p = &(*p)->rb_left; else if (uid_gt(uid, user->uid)) p = &(*p)->rb_right; else goto found; } /* if we get here, we failed to find a match in the tree */ if (!candidate) { /* allocate a candidate user record if we don't already have * one */ spin_unlock(&key_user_lock); user = NULL; candidate = kmalloc(sizeof(struct key_user), GFP_KERNEL); if (unlikely(!candidate)) goto out; /* the allocation may have scheduled, so we need to repeat the * search lest someone else added the record whilst we were * asleep */ goto try_again; } /* if we get here, then the user record still hadn't appeared on the * second pass - so we use the candidate record */ refcount_set(&candidate->usage, 1); atomic_set(&candidate->nkeys, 0); atomic_set(&candidate->nikeys, 0); candidate->uid = uid; candidate->qnkeys = 0; candidate->qnbytes = 0; spin_lock_init(&candidate->lock); mutex_init(&candidate->cons_lock); rb_link_node(&candidate->node, parent, p); rb_insert_color(&candidate->node, &key_user_tree); spin_unlock(&key_user_lock); user = candidate; goto out; /* okay - we found a user record for this UID */ found: refcount_inc(&user->usage); spin_unlock(&key_user_lock); kfree(candidate); out: return user; } /* * Dispose of a user structure */ void key_user_put(struct key_user *user) { if (refcount_dec_and_lock(&user->usage, &key_user_lock)) { rb_erase(&user->node, &key_user_tree); spin_unlock(&key_user_lock); kfree(user); } } /* * Allocate a serial number for a key. These are assigned randomly to avoid * security issues through covert channel problems. */ static inline void key_alloc_serial(struct key *key) { struct rb_node *parent, **p; struct key *xkey; /* propose a random serial number and look for a hole for it in the * serial number tree */ do { get_random_bytes(&key->serial, sizeof(key->serial)); key->serial >>= 1; /* negative numbers are not permitted */ } while (key->serial < 3); spin_lock(&key_serial_lock); attempt_insertion: parent = NULL; p = &key_serial_tree.rb_node; while (*p) { parent = *p; xkey = rb_entry(parent, struct key, serial_node); if (key->serial < xkey->serial) p = &(*p)->rb_left; else if (key->serial > xkey->serial) p = &(*p)->rb_right; else goto serial_exists; } /* we've found a suitable hole - arrange for this key to occupy it */ rb_link_node(&key->serial_node, parent, p); rb_insert_color(&key->serial_node, &key_serial_tree); spin_unlock(&key_serial_lock); return; /* we found a key with the proposed serial number - walk the tree from * that point looking for the next unused serial number */ serial_exists: for (;;) { key->serial++; if (key->serial < 3) { key->serial = 3; goto attempt_insertion; } parent = rb_next(parent); if (!parent) goto attempt_insertion; xkey = rb_entry(parent, struct key, serial_node); if (key->serial < xkey->serial) goto attempt_insertion; } } /** * key_alloc - Allocate a key of the specified type. * @type: The type of key to allocate. * @desc: The key description to allow the key to be searched out. * @uid: The owner of the new key. * @gid: The group ID for the new key's group permissions. * @cred: The credentials specifying UID namespace. * @perm: The permissions mask of the new key. * @flags: Flags specifying quota properties. * @restrict_link: Optional link restriction for new keyrings. * * Allocate a key of the specified type with the attributes given. The key is * returned in an uninstantiated state and the caller needs to instantiate the * key before returning. * * The restrict_link structure (if not NULL) will be freed when the * keyring is destroyed, so it must be dynamically allocated. * * The user's key count quota is updated to reflect the creation of the key and * the user's key data quota has the default for the key type reserved. The * instantiation function should amend this as necessary. If insufficient * quota is available, -EDQUOT will be returned. * * The LSM security modules can prevent a key being created, in which case * -EACCES will be returned. * * Returns a pointer to the new key if successful and an error code otherwise. * * Note that the caller needs to ensure the key type isn't uninstantiated. * Internally this can be done by locking key_types_sem. Externally, this can * be done by either never unregistering the key type, or making sure * key_alloc() calls don't race with module unloading. */ struct key *key_alloc(struct key_type *type, const char *desc, kuid_t uid, kgid_t gid, const struct cred *cred, key_perm_t perm, unsigned long flags, struct key_restriction *restrict_link) { struct key_user *user = NULL; struct key *key; size_t desclen, quotalen; int ret; key = ERR_PTR(-EINVAL); if (!desc || !*desc) goto error; if (type->vet_description) { ret = type->vet_description(desc); if (ret < 0) { key = ERR_PTR(ret); goto error; } } desclen = strlen(desc); quotalen = desclen + 1 + type->def_datalen; /* get hold of the key tracking for this user */ user = key_user_lookup(uid); if (!user) goto no_memory_1; /* check that the user's quota permits allocation of another key and * its description */ if (!(flags & KEY_ALLOC_NOT_IN_QUOTA)) { unsigned maxkeys = uid_eq(uid, GLOBAL_ROOT_UID) ? key_quota_root_maxkeys : key_quota_maxkeys; unsigned maxbytes = uid_eq(uid, GLOBAL_ROOT_UID) ? key_quota_root_maxbytes : key_quota_maxbytes; spin_lock(&user->lock); if (!(flags & KEY_ALLOC_QUOTA_OVERRUN)) { if (user->qnkeys + 1 > maxkeys || user->qnbytes + quotalen > maxbytes || user->qnbytes + quotalen < user->qnbytes) goto no_quota; } user->qnkeys++; user->qnbytes += quotalen; spin_unlock(&user->lock); } /* allocate and initialise the key and its description */ key = kmem_cache_zalloc(key_jar, GFP_KERNEL); if (!key) goto no_memory_2; key->index_key.desc_len = desclen; key->index_key.description = kmemdup(desc, desclen + 1, GFP_KERNEL); if (!key->index_key.description) goto no_memory_3; key->index_key.type = type; key_set_index_key(&key->index_key); refcount_set(&key->usage, 1); init_rwsem(&key->sem); lockdep_set_class(&key->sem, &type->lock_class); key->user = user; key->quotalen = quotalen; key->datalen = type->def_datalen; key->uid = uid; key->gid = gid; key->perm = perm; key->expiry = TIME64_MAX; key->restrict_link = restrict_link; key->last_used_at = ktime_get_real_seconds(); if (!(flags & KEY_ALLOC_NOT_IN_QUOTA)) key->flags |= 1 << KEY_FLAG_IN_QUOTA; if (flags & KEY_ALLOC_BUILT_IN) key->flags |= 1 << KEY_FLAG_BUILTIN; if (flags & KEY_ALLOC_UID_KEYRING) key->flags |= 1 << KEY_FLAG_UID_KEYRING; if (flags & KEY_ALLOC_SET_KEEP) key->flags |= 1 << KEY_FLAG_KEEP; #ifdef KEY_DEBUGGING key->magic = KEY_DEBUG_MAGIC; #endif /* let the security module know about the key */ ret = security_key_alloc(key, cred, flags); if (ret < 0) goto security_error; /* publish the key by giving it a serial number */ refcount_inc(&key->domain_tag->usage); atomic_inc(&user->nkeys); key_alloc_serial(key); error: return key; security_error: kfree(key->description); kmem_cache_free(key_jar, key); if (!(flags & KEY_ALLOC_NOT_IN_QUOTA)) { spin_lock(&user->lock); user->qnkeys--; user->qnbytes -= quotalen; spin_unlock(&user->lock); } key_user_put(user); key = ERR_PTR(ret); goto error; no_memory_3: kmem_cache_free(key_jar, key); no_memory_2: if (!(flags & KEY_ALLOC_NOT_IN_QUOTA)) { spin_lock(&user->lock); user->qnkeys--; user->qnbytes -= quotalen; spin_unlock(&user->lock); } key_user_put(user); no_memory_1: key = ERR_PTR(-ENOMEM); goto error; no_quota: spin_unlock(&user->lock); key_user_put(user); key = ERR_PTR(-EDQUOT); goto error; } EXPORT_SYMBOL(key_alloc); /** * key_payload_reserve - Adjust data quota reservation for the key's payload * @key: The key to make the reservation for. * @datalen: The amount of data payload the caller now wants. * * Adjust the amount of the owning user's key data quota that a key reserves. * If the amount is increased, then -EDQUOT may be returned if there isn't * enough free quota available. * * If successful, 0 is returned. */ int key_payload_reserve(struct key *key, size_t datalen) { int delta = (int)datalen - key->datalen; int ret = 0; key_check(key); /* contemplate the quota adjustment */ if (delta != 0 && test_bit(KEY_FLAG_IN_QUOTA, &key->flags)) { unsigned maxbytes = uid_eq(key->user->uid, GLOBAL_ROOT_UID) ? key_quota_root_maxbytes : key_quota_maxbytes; spin_lock(&key->user->lock); if (delta > 0 && (key->user->qnbytes + delta > maxbytes || key->user->qnbytes + delta < key->user->qnbytes)) { ret = -EDQUOT; } else { key->user->qnbytes += delta; key->quotalen += delta; } spin_unlock(&key->user->lock); } /* change the recorded data length if that didn't generate an error */ if (ret == 0) key->datalen = datalen; return ret; } EXPORT_SYMBOL(key_payload_reserve); /* * Change the key state to being instantiated. */ static void mark_key_instantiated(struct key *key, int reject_error) { /* Commit the payload before setting the state; barrier versus * key_read_state(). */ smp_store_release(&key->state, (reject_error < 0) ? reject_error : KEY_IS_POSITIVE); } /* * Instantiate a key and link it into the target keyring atomically. Must be * called with the target keyring's semaphore writelocked. The target key's * semaphore need not be locked as instantiation is serialised by * key_construction_mutex. */ static int __key_instantiate_and_link(struct key *key, struct key_preparsed_payload *prep, struct key *keyring, struct key *authkey, struct assoc_array_edit **_edit) { int ret, awaken; key_check(key); key_check(keyring); awaken = 0; ret = -EBUSY; mutex_lock(&key_construction_mutex); /* can't instantiate twice */ if (key->state == KEY_IS_UNINSTANTIATED) { /* instantiate the key */ ret = key->type->instantiate(key, prep); if (ret == 0) { /* mark the key as being instantiated */ atomic_inc(&key->user->nikeys); mark_key_instantiated(key, 0); notify_key(key, NOTIFY_KEY_INSTANTIATED, 0); if (test_and_clear_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags)) awaken = 1; /* and link it into the destination keyring */ if (keyring) { if (test_bit(KEY_FLAG_KEEP, &keyring->flags)) set_bit(KEY_FLAG_KEEP, &key->flags); __key_link(keyring, key, _edit); } /* disable the authorisation key */ if (authkey) key_invalidate(authkey); if (prep->expiry != TIME64_MAX) key_set_expiry(key, prep->expiry); } } mutex_unlock(&key_construction_mutex); /* wake up anyone waiting for a key to be constructed */ if (awaken) wake_up_bit(&key->flags, KEY_FLAG_USER_CONSTRUCT); return ret; } /** * key_instantiate_and_link - Instantiate a key and link it into the keyring. * @key: The key to instantiate. * @data: The data to use to instantiate the keyring. * @datalen: The length of @data. * @keyring: Keyring to create a link in on success (or NULL). * @authkey: The authorisation token permitting instantiation. * * Instantiate a key that's in the uninstantiated state using the provided data * and, if successful, link it in to the destination keyring if one is * supplied. * * If successful, 0 is returned, the authorisation token is revoked and anyone * waiting for the key is woken up. If the key was already instantiated, * -EBUSY will be returned. */ int key_instantiate_and_link(struct key *key, const void *data, size_t datalen, struct key *keyring, struct key *authkey) { struct key_preparsed_payload prep; struct assoc_array_edit *edit = NULL; int ret; memset(&prep, 0, sizeof(prep)); prep.orig_description = key->description; prep.data = data; prep.datalen = datalen; prep.quotalen = key->type->def_datalen; prep.expiry = TIME64_MAX; if (key->type->preparse) { ret = key->type->preparse(&prep); if (ret < 0) goto error; } if (keyring) { ret = __key_link_lock(keyring, &key->index_key); if (ret < 0) goto error; ret = __key_link_begin(keyring, &key->index_key, &edit); if (ret < 0) goto error_link_end; if (keyring->restrict_link && keyring->restrict_link->check) { struct key_restriction *keyres = keyring->restrict_link; ret = keyres->check(keyring, key->type, &prep.payload, keyres->key); if (ret < 0) goto error_link_end; } } ret = __key_instantiate_and_link(key, &prep, keyring, authkey, &edit); error_link_end: if (keyring) __key_link_end(keyring, &key->index_key, edit); error: if (key->type->preparse) key->type->free_preparse(&prep); return ret; } EXPORT_SYMBOL(key_instantiate_and_link); /** * key_reject_and_link - Negatively instantiate a key and link it into the keyring. * @key: The key to instantiate. * @timeout: The timeout on the negative key. * @error: The error to return when the key is hit. * @keyring: Keyring to create a link in on success (or NULL). * @authkey: The authorisation token permitting instantiation. * * Negatively instantiate a key that's in the uninstantiated state and, if * successful, set its timeout and stored error and link it in to the * destination keyring if one is supplied. The key and any links to the key * will be automatically garbage collected after the timeout expires. * * Negative keys are used to rate limit repeated request_key() calls by causing * them to return the stored error code (typically ENOKEY) until the negative * key expires. * * If successful, 0 is returned, the authorisation token is revoked and anyone * waiting for the key is woken up. If the key was already instantiated, * -EBUSY will be returned. */ int key_reject_and_link(struct key *key, unsigned timeout, unsigned error, struct key *keyring, struct key *authkey) { struct assoc_array_edit *edit = NULL; int ret, awaken, link_ret = 0; key_check(key); key_check(keyring); awaken = 0; ret = -EBUSY; if (keyring) { if (keyring->restrict_link) return -EPERM; link_ret = __key_link_lock(keyring, &key->index_key); if (link_ret == 0) { link_ret = __key_link_begin(keyring, &key->index_key, &edit); if (link_ret < 0) __key_link_end(keyring, &key->index_key, edit); } } mutex_lock(&key_construction_mutex); /* can't instantiate twice */ if (key->state == KEY_IS_UNINSTANTIATED) { /* mark the key as being negatively instantiated */ atomic_inc(&key->user->nikeys); mark_key_instantiated(key, -error); notify_key(key, NOTIFY_KEY_INSTANTIATED, -error); key_set_expiry(key, ktime_get_real_seconds() + timeout); if (test_and_clear_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags)) awaken = 1; ret = 0; /* and link it into the destination keyring */ if (keyring && link_ret == 0) __key_link(keyring, key, &edit); /* disable the authorisation key */ if (authkey) key_invalidate(authkey); } mutex_unlock(&key_construction_mutex); if (keyring && link_ret == 0) __key_link_end(keyring, &key->index_key, edit); /* wake up anyone waiting for a key to be constructed */ if (awaken) wake_up_bit(&key->flags, KEY_FLAG_USER_CONSTRUCT); return ret == 0 ? link_ret : ret; } EXPORT_SYMBOL(key_reject_and_link); /** * key_put - Discard a reference to a key. * @key: The key to discard a reference from. * * Discard a reference to a key, and when all the references are gone, we * schedule the cleanup task to come and pull it out of the tree in process * context at some later time. */ void key_put(struct key *key) { if (key) { key_check(key); if (refcount_dec_and_test(&key->usage)) schedule_work(&key_gc_work); } } EXPORT_SYMBOL(key_put); /* * Find a key by its serial number. */ struct key *key_lookup(key_serial_t id) { struct rb_node *n; struct key *key; spin_lock(&key_serial_lock); /* search the tree for the specified key */ n = key_serial_tree.rb_node; while (n) { key = rb_entry(n, struct key, serial_node); if (id < key->serial) n = n->rb_left; else if (id > key->serial) n = n->rb_right; else goto found; } not_found: key = ERR_PTR(-ENOKEY); goto error; found: /* A key is allowed to be looked up only if someone still owns a * reference to it - otherwise it's awaiting the gc. */ if (!refcount_inc_not_zero(&key->usage)) goto not_found; error: spin_unlock(&key_serial_lock); return key; } /* * Find and lock the specified key type against removal. * * We return with the sem read-locked if successful. If the type wasn't * available -ENOKEY is returned instead. */ struct key_type *key_type_lookup(const char *type) { struct key_type *ktype; down_read(&key_types_sem); /* look up the key type to see if it's one of the registered kernel * types */ list_for_each_entry(ktype, &key_types_list, link) { if (strcmp(ktype->name, type) == 0) goto found_kernel_type; } up_read(&key_types_sem); ktype = ERR_PTR(-ENOKEY); found_kernel_type: return ktype; } void key_set_timeout(struct key *key, unsigned timeout) { time64_t expiry = TIME64_MAX; /* make the changes with the locks held to prevent races */ down_write(&key->sem); if (timeout > 0) expiry = ktime_get_real_seconds() + timeout; key_set_expiry(key, expiry); up_write(&key->sem); } EXPORT_SYMBOL_GPL(key_set_timeout); /* * Unlock a key type locked by key_type_lookup(). */ void key_type_put(struct key_type *ktype) { up_read(&key_types_sem); } /* * Attempt to update an existing key. * * The key is given to us with an incremented refcount that we need to discard * if we get an error. */ static inline key_ref_t __key_update(key_ref_t key_ref, struct key_preparsed_payload *prep) { struct key *key = key_ref_to_ptr(key_ref); int ret; /* need write permission on the key to update it */ ret = key_permission(key_ref, KEY_NEED_WRITE); if (ret < 0) goto error; ret = -EEXIST; if (!key->type->update) goto error; down_write(&key->sem); ret = key->type->update(key, prep); if (ret == 0) { /* Updating a negative key positively instantiates it */ mark_key_instantiated(key, 0); notify_key(key, NOTIFY_KEY_UPDATED, 0); } up_write(&key->sem); if (ret < 0) goto error; out: return key_ref; error: key_put(key); key_ref = ERR_PTR(ret); goto out; } /** * key_create_or_update - Update or create and instantiate a key. * @keyring_ref: A pointer to the destination keyring with possession flag. * @type: The type of key. * @description: The searchable description for the key. * @payload: The data to use to instantiate or update the key. * @plen: The length of @payload. * @perm: The permissions mask for a new key. * @flags: The quota flags for a new key. * * Search the destination keyring for a key of the same description and if one * is found, update it, otherwise create and instantiate a new one and create a * link to it from that keyring. * * If perm is KEY_PERM_UNDEF then an appropriate key permissions mask will be * concocted. * * Returns a pointer to the new key if successful, -ENODEV if the key type * wasn't available, -ENOTDIR if the keyring wasn't a keyring, -EACCES if the * caller isn't permitted to modify the keyring or the LSM did not permit * creation of the key. * * On success, the possession flag from the keyring ref will be tacked on to * the key ref before it is returned. */ key_ref_t key_create_or_update(key_ref_t keyring_ref, const char *type, const char *description, const void *payload, size_t plen, key_perm_t perm, unsigned long flags) { struct keyring_index_key index_key = { .description = description, }; struct key_preparsed_payload prep; struct assoc_array_edit *edit = NULL; const struct cred *cred = current_cred(); struct key *keyring, *key = NULL; key_ref_t key_ref; int ret; struct key_restriction *restrict_link = NULL; /* look up the key type to see if it's one of the registered kernel * types */ index_key.type = key_type_lookup(type); if (IS_ERR(index_key.type)) { key_ref = ERR_PTR(-ENODEV); goto error; } key_ref = ERR_PTR(-EINVAL); if (!index_key.type->instantiate || (!index_key.description && !index_key.type->preparse)) goto error_put_type; keyring = key_ref_to_ptr(keyring_ref); key_check(keyring); if (!(flags & KEY_ALLOC_BYPASS_RESTRICTION)) restrict_link = keyring->restrict_link; key_ref = ERR_PTR(-ENOTDIR); if (keyring->type != &key_type_keyring) goto error_put_type; memset(&prep, 0, sizeof(prep)); prep.orig_description = description; prep.data = payload; prep.datalen = plen; prep.quotalen = index_key.type->def_datalen; prep.expiry = TIME64_MAX; if (index_key.type->preparse) { ret = index_key.type->preparse(&prep); if (ret < 0) { key_ref = ERR_PTR(ret); goto error_free_prep; } if (!index_key.description) index_key.description = prep.description; key_ref = ERR_PTR(-EINVAL); if (!index_key.description) goto error_free_prep; } index_key.desc_len = strlen(index_key.description); key_set_index_key(&index_key); ret = __key_link_lock(keyring, &index_key); if (ret < 0) { key_ref = ERR_PTR(ret); goto error_free_prep; } ret = __key_link_begin(keyring, &index_key, &edit); if (ret < 0) { key_ref = ERR_PTR(ret); goto error_link_end; } if (restrict_link && restrict_link->check) { ret = restrict_link->check(keyring, index_key.type, &prep.payload, restrict_link->key); if (ret < 0) { key_ref = ERR_PTR(ret); goto error_link_end; } } /* if we're going to allocate a new key, we're going to have * to modify the keyring */ ret = key_permission(keyring_ref, KEY_NEED_WRITE); if (ret < 0) { key_ref = ERR_PTR(ret); goto error_link_end; } /* if it's possible to update this type of key, search for an existing * key of the same type and description in the destination keyring and * update that instead if possible */ if (index_key.type->update) { key_ref = find_key_to_update(keyring_ref, &index_key); if (key_ref) goto found_matching_key; } /* if the client doesn't provide, decide on the permissions we want */ if (perm == KEY_PERM_UNDEF) { perm = KEY_POS_VIEW | KEY_POS_SEARCH | KEY_POS_LINK | KEY_POS_SETATTR; perm |= KEY_USR_VIEW; if (index_key.type->read) perm |= KEY_POS_READ; if (index_key.type == &key_type_keyring || index_key.type->update) perm |= KEY_POS_WRITE; } /* allocate a new key */ key = key_alloc(index_key.type, index_key.description, cred->fsuid, cred->fsgid, cred, perm, flags, NULL); if (IS_ERR(key)) { key_ref = ERR_CAST(key); goto error_link_end; } /* instantiate it and link it into the target keyring */ ret = __key_instantiate_and_link(key, &prep, keyring, NULL, &edit); if (ret < 0) { key_put(key); key_ref = ERR_PTR(ret); goto error_link_end; } ima_post_key_create_or_update(keyring, key, payload, plen, flags, true); key_ref = make_key_ref(key, is_key_possessed(keyring_ref)); error_link_end: __key_link_end(keyring, &index_key, edit); error_free_prep: if (index_key.type->preparse) index_key.type->free_preparse(&prep); error_put_type: key_type_put(index_key.type); error: return key_ref; found_matching_key: /* we found a matching key, so we're going to try to update it * - we can drop the locks first as we have the key pinned */ __key_link_end(keyring, &index_key, edit); key = key_ref_to_ptr(key_ref); if (test_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags)) { ret = wait_for_key_construction(key, true); if (ret < 0) { key_ref_put(key_ref); key_ref = ERR_PTR(ret); goto error_free_prep; } } key_ref = __key_update(key_ref, &prep); if (!IS_ERR(key_ref)) ima_post_key_create_or_update(keyring, key, payload, plen, flags, false); goto error_free_prep; } EXPORT_SYMBOL(key_create_or_update); /** * key_update - Update a key's contents. * @key_ref: The pointer (plus possession flag) to the key. * @payload: The data to be used to update the key. * @plen: The length of @payload. * * Attempt to update the contents of a key with the given payload data. The * caller must be granted Write permission on the key. Negative keys can be * instantiated by this method. * * Returns 0 on success, -EACCES if not permitted and -EOPNOTSUPP if the key * type does not support updating. The key type may return other errors. */ int key_update(key_ref_t key_ref, const void *payload, size_t plen) { struct key_preparsed_payload prep; struct key *key = key_ref_to_ptr(key_ref); int ret; key_check(key); /* the key must be writable */ ret = key_permission(key_ref, KEY_NEED_WRITE); if (ret < 0) return ret; /* attempt to update it if supported */ if (!key->type->update) return -EOPNOTSUPP; memset(&prep, 0, sizeof(prep)); prep.data = payload; prep.datalen = plen; prep.quotalen = key->type->def_datalen; prep.expiry = TIME64_MAX; if (key->type->preparse) { ret = key->type->preparse(&prep); if (ret < 0) goto error; } down_write(&key->sem); ret = key->type->update(key, &prep); if (ret == 0) { /* Updating a negative key positively instantiates it */ mark_key_instantiated(key, 0); notify_key(key, NOTIFY_KEY_UPDATED, 0); } up_write(&key->sem); error: if (key->type->preparse) key->type->free_preparse(&prep); return ret; } EXPORT_SYMBOL(key_update); /** * key_revoke - Revoke a key. * @key: The key to be revoked. * * Mark a key as being revoked and ask the type to free up its resources. The * revocation timeout is set and the key and all its links will be * automatically garbage collected after key_gc_delay amount of time if they * are not manually dealt with first. */ void key_revoke(struct key *key) { time64_t time; key_check(key); /* make sure no one's trying to change or use the key when we mark it * - we tell lockdep that we might nest because we might be revoking an * authorisation key whilst holding the sem on a key we've just * instantiated */ down_write_nested(&key->sem, 1); if (!test_and_set_bit(KEY_FLAG_REVOKED, &key->flags)) { notify_key(key, NOTIFY_KEY_REVOKED, 0); if (key->type->revoke) key->type->revoke(key); /* set the death time to no more than the expiry time */ time = ktime_get_real_seconds(); if (key->revoked_at == 0 || key->revoked_at > time) { key->revoked_at = time; key_schedule_gc(key->revoked_at + key_gc_delay); } } up_write(&key->sem); } EXPORT_SYMBOL(key_revoke); /** * key_invalidate - Invalidate a key. * @key: The key to be invalidated. * * Mark a key as being invalidated and have it cleaned up immediately. The key * is ignored by all searches and other operations from this point. */ void key_invalidate(struct key *key) { kenter("%d", key_serial(key)); key_check(key); if (!test_bit(KEY_FLAG_INVALIDATED, &key->flags)) { down_write_nested(&key->sem, 1); if (!test_and_set_bit(KEY_FLAG_INVALIDATED, &key->flags)) { notify_key(key, NOTIFY_KEY_INVALIDATED, 0); key_schedule_gc_links(); } up_write(&key->sem); } } EXPORT_SYMBOL(key_invalidate); /** * generic_key_instantiate - Simple instantiation of a key from preparsed data * @key: The key to be instantiated * @prep: The preparsed data to load. * * Instantiate a key from preparsed data. We assume we can just copy the data * in directly and clear the old pointers. * * This can be pointed to directly by the key type instantiate op pointer. */ int generic_key_instantiate(struct key *key, struct key_preparsed_payload *prep) { int ret; pr_devel("==>%s()\n", __func__); ret = key_payload_reserve(key, prep->quotalen); if (ret == 0) { rcu_assign_keypointer(key, prep->payload.data[0]); key->payload.data[1] = prep->payload.data[1]; key->payload.data[2] = prep->payload.data[2]; key->payload.data[3] = prep->payload.data[3]; prep->payload.data[0] = NULL; prep->payload.data[1] = NULL; prep->payload.data[2] = NULL; prep->payload.data[3] = NULL; } pr_devel("<==%s() = %d\n", __func__, ret); return ret; } EXPORT_SYMBOL(generic_key_instantiate); /** * register_key_type - Register a type of key. * @ktype: The new key type. * * Register a new key type. * * Returns 0 on success or -EEXIST if a type of this name already exists. */ int register_key_type(struct key_type *ktype) { struct key_type *p; int ret; memset(&ktype->lock_class, 0, sizeof(ktype->lock_class)); ret = -EEXIST; down_write(&key_types_sem); /* disallow key types with the same name */ list_for_each_entry(p, &key_types_list, link) { if (strcmp(p->name, ktype->name) == 0) goto out; } /* store the type */ list_add(&ktype->link, &key_types_list); pr_notice("Key type %s registered\n", ktype->name); ret = 0; out: up_write(&key_types_sem); return ret; } EXPORT_SYMBOL(register_key_type); /** * unregister_key_type - Unregister a type of key. * @ktype: The key type. * * Unregister a key type and mark all the extant keys of this type as dead. * Those keys of this type are then destroyed to get rid of their payloads and * they and their links will be garbage collected as soon as possible. */ void unregister_key_type(struct key_type *ktype) { down_write(&key_types_sem); list_del_init(&ktype->link); downgrade_write(&key_types_sem); key_gc_keytype(ktype); pr_notice("Key type %s unregistered\n", ktype->name); up_read(&key_types_sem); } EXPORT_SYMBOL(unregister_key_type); /* * Initialise the key management state. */ void __init key_init(void) { /* allocate a slab in which we can store keys */ key_jar = kmem_cache_create("key_jar", sizeof(struct key), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); /* add the special key types */ list_add_tail(&key_type_keyring.link, &key_types_list); list_add_tail(&key_type_dead.link, &key_types_list); list_add_tail(&key_type_user.link, &key_types_list); list_add_tail(&key_type_logon.link, &key_types_list); /* record the root user tracking */ rb_link_node(&root_key_user.node, NULL, &key_user_tree.rb_node); rb_insert_color(&root_key_user.node, &key_user_tree); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * pm_runtime.h - Device run-time power management helper functions. * * Copyright (C) 2009 Rafael J. Wysocki <rjw@sisk.pl> */ #ifndef _LINUX_PM_RUNTIME_H #define _LINUX_PM_RUNTIME_H #include <linux/device.h> #include <linux/notifier.h> #include <linux/pm.h> #include <linux/jiffies.h> /* Runtime PM flag argument bits */ #define RPM_ASYNC 0x01 /* Request is asynchronous */ #define RPM_NOWAIT 0x02 /* Don't wait for concurrent state change */ #define RPM_GET_PUT 0x04 /* Increment/decrement the usage_count */ #define RPM_AUTO 0x08 /* Use autosuspend_delay */ /* * Use this for defining a set of PM operations to be used in all situations * (system suspend, hibernation or runtime PM). * * Note that the behaviour differs from the deprecated UNIVERSAL_DEV_PM_OPS() * macro, which uses the provided callbacks for both runtime PM and system * sleep, while DEFINE_RUNTIME_DEV_PM_OPS() uses pm_runtime_force_suspend() * and pm_runtime_force_resume() for its system sleep callbacks. * * If the underlying dev_pm_ops struct symbol has to be exported, use * EXPORT_RUNTIME_DEV_PM_OPS() or EXPORT_GPL_RUNTIME_DEV_PM_OPS() instead. */ #define DEFINE_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ _DEFINE_DEV_PM_OPS(name, pm_runtime_force_suspend, \ pm_runtime_force_resume, suspend_fn, \ resume_fn, idle_fn) #define EXPORT_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ EXPORT_DEV_PM_OPS(name) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #define EXPORT_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ EXPORT_GPL_DEV_PM_OPS(name) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #define EXPORT_NS_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ EXPORT_NS_DEV_PM_OPS(name, ns) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #define EXPORT_NS_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ EXPORT_NS_GPL_DEV_PM_OPS(name, ns) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #ifdef CONFIG_PM extern struct workqueue_struct *pm_wq; static inline bool queue_pm_work(struct work_struct *work) { return queue_work(pm_wq, work); } extern int pm_generic_runtime_suspend(struct device *dev); extern int pm_generic_runtime_resume(struct device *dev); extern int pm_runtime_force_suspend(struct device *dev); extern int pm_runtime_force_resume(struct device *dev); extern int __pm_runtime_idle(struct device *dev, int rpmflags); extern int __pm_runtime_suspend(struct device *dev, int rpmflags); extern int __pm_runtime_resume(struct device *dev, int rpmflags); extern int pm_runtime_get_if_active(struct device *dev, bool ign_usage_count); extern int pm_schedule_suspend(struct device *dev, unsigned int delay); extern int __pm_runtime_set_status(struct device *dev, unsigned int status); extern int pm_runtime_barrier(struct device *dev); extern void pm_runtime_enable(struct device *dev); extern void __pm_runtime_disable(struct device *dev, bool check_resume); extern void pm_runtime_allow(struct device *dev); extern void pm_runtime_forbid(struct device *dev); extern void pm_runtime_no_callbacks(struct device *dev); extern void pm_runtime_irq_safe(struct device *dev); extern void __pm_runtime_use_autosuspend(struct device *dev, bool use); extern void pm_runtime_set_autosuspend_delay(struct device *dev, int delay); extern u64 pm_runtime_autosuspend_expiration(struct device *dev); extern void pm_runtime_update_max_time_suspended(struct device *dev, s64 delta_ns); extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable); extern void pm_runtime_get_suppliers(struct device *dev); extern void pm_runtime_put_suppliers(struct device *dev); extern void pm_runtime_new_link(struct device *dev); extern void pm_runtime_drop_link(struct device_link *link); extern void pm_runtime_release_supplier(struct device_link *link); extern int devm_pm_runtime_enable(struct device *dev); /** * pm_runtime_get_if_in_use - Conditionally bump up runtime PM usage counter. * @dev: Target device. * * Increment the runtime PM usage counter of @dev if its runtime PM status is * %RPM_ACTIVE and its runtime PM usage counter is greater than 0. */ static inline int pm_runtime_get_if_in_use(struct device *dev) { return pm_runtime_get_if_active(dev, false); } /** * pm_suspend_ignore_children - Set runtime PM behavior regarding children. * @dev: Target device. * @enable: Whether or not to ignore possible dependencies on children. * * The dependencies of @dev on its children will not be taken into account by * the runtime PM framework going forward if @enable is %true, or they will * be taken into account otherwise. */ static inline void pm_suspend_ignore_children(struct device *dev, bool enable) { dev->power.ignore_children = enable; } /** * pm_runtime_get_noresume - Bump up runtime PM usage counter of a device. * @dev: Target device. */ static inline void pm_runtime_get_noresume(struct device *dev) { atomic_inc(&dev->power.usage_count); } /** * pm_runtime_put_noidle - Drop runtime PM usage counter of a device. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev unless it is 0 already. */ static inline void pm_runtime_put_noidle(struct device *dev) { atomic_add_unless(&dev->power.usage_count, -1, 0); } /** * pm_runtime_suspended - Check whether or not a device is runtime-suspended. * @dev: Target device. * * Return %true if runtime PM is enabled for @dev and its runtime PM status is * %RPM_SUSPENDED, or %false otherwise. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which * runtime PM cannot be either disabled or enabled for @dev and its runtime PM * status cannot change. */ static inline bool pm_runtime_suspended(struct device *dev) { return dev->power.runtime_status == RPM_SUSPENDED && !dev->power.disable_depth; } /** * pm_runtime_active - Check whether or not a device is runtime-active. * @dev: Target device. * * Return %true if runtime PM is disabled for @dev or its runtime PM status is * %RPM_ACTIVE, or %false otherwise. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which * runtime PM cannot be either disabled or enabled for @dev and its runtime PM * status cannot change. */ static inline bool pm_runtime_active(struct device *dev) { return dev->power.runtime_status == RPM_ACTIVE || dev->power.disable_depth; } /** * pm_runtime_status_suspended - Check if runtime PM status is "suspended". * @dev: Target device. * * Return %true if the runtime PM status of @dev is %RPM_SUSPENDED, or %false * otherwise, regardless of whether or not runtime PM has been enabled for @dev. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which the * runtime PM status of @dev cannot change. */ static inline bool pm_runtime_status_suspended(struct device *dev) { return dev->power.runtime_status == RPM_SUSPENDED; } /** * pm_runtime_enabled - Check if runtime PM is enabled. * @dev: Target device. * * Return %true if runtime PM is enabled for @dev or %false otherwise. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which * runtime PM cannot be either disabled or enabled for @dev. */ static inline bool pm_runtime_enabled(struct device *dev) { return !dev->power.disable_depth; } /** * pm_runtime_has_no_callbacks - Check if runtime PM callbacks may be present. * @dev: Target device. * * Return %true if @dev is a special device without runtime PM callbacks or * %false otherwise. */ static inline bool pm_runtime_has_no_callbacks(struct device *dev) { return dev->power.no_callbacks; } /** * pm_runtime_mark_last_busy - Update the last access time of a device. * @dev: Target device. * * Update the last access time of @dev used by the runtime PM autosuspend * mechanism to the current time as returned by ktime_get_mono_fast_ns(). */ static inline void pm_runtime_mark_last_busy(struct device *dev) { WRITE_ONCE(dev->power.last_busy, ktime_get_mono_fast_ns()); } /** * pm_runtime_is_irq_safe - Check if runtime PM can work in interrupt context. * @dev: Target device. * * Return %true if @dev has been marked as an "IRQ-safe" device (with respect * to runtime PM), in which case its runtime PM callabcks can be expected to * work correctly when invoked from interrupt handlers. */ static inline bool pm_runtime_is_irq_safe(struct device *dev) { return dev->power.irq_safe; } extern u64 pm_runtime_suspended_time(struct device *dev); #else /* !CONFIG_PM */ static inline bool queue_pm_work(struct work_struct *work) { return false; } static inline int pm_generic_runtime_suspend(struct device *dev) { return 0; } static inline int pm_generic_runtime_resume(struct device *dev) { return 0; } static inline int pm_runtime_force_suspend(struct device *dev) { return 0; } static inline int pm_runtime_force_resume(struct device *dev) { return 0; } static inline int __pm_runtime_idle(struct device *dev, int rpmflags) { return -ENOSYS; } static inline int __pm_runtime_suspend(struct device *dev, int rpmflags) { return -ENOSYS; } static inline int __pm_runtime_resume(struct device *dev, int rpmflags) { return 1; } static inline int pm_schedule_suspend(struct device *dev, unsigned int delay) { return -ENOSYS; } static inline int pm_runtime_get_if_in_use(struct device *dev) { return -EINVAL; } static inline int pm_runtime_get_if_active(struct device *dev, bool ign_usage_count) { return -EINVAL; } static inline int __pm_runtime_set_status(struct device *dev, unsigned int status) { return 0; } static inline int pm_runtime_barrier(struct device *dev) { return 0; } static inline void pm_runtime_enable(struct device *dev) {} static inline void __pm_runtime_disable(struct device *dev, bool c) {} static inline void pm_runtime_allow(struct device *dev) {} static inline void pm_runtime_forbid(struct device *dev) {} static inline int devm_pm_runtime_enable(struct device *dev) { return 0; } static inline void pm_suspend_ignore_children(struct device *dev, bool enable) {} static inline void pm_runtime_get_noresume(struct device *dev) {} static inline void pm_runtime_put_noidle(struct device *dev) {} static inline bool pm_runtime_suspended(struct device *dev) { return false; } static inline bool pm_runtime_active(struct device *dev) { return true; } static inline bool pm_runtime_status_suspended(struct device *dev) { return false; } static inline bool pm_runtime_enabled(struct device *dev) { return false; } static inline void pm_runtime_no_callbacks(struct device *dev) {} static inline void pm_runtime_irq_safe(struct device *dev) {} static inline bool pm_runtime_is_irq_safe(struct device *dev) { return false; } static inline bool pm_runtime_has_no_callbacks(struct device *dev) { return false; } static inline void pm_runtime_mark_last_busy(struct device *dev) {} static inline void __pm_runtime_use_autosuspend(struct device *dev, bool use) {} static inline void pm_runtime_set_autosuspend_delay(struct device *dev, int delay) {} static inline u64 pm_runtime_autosuspend_expiration( struct device *dev) { return 0; } static inline void pm_runtime_set_memalloc_noio(struct device *dev, bool enable){} static inline void pm_runtime_get_suppliers(struct device *dev) {} static inline void pm_runtime_put_suppliers(struct device *dev) {} static inline void pm_runtime_new_link(struct device *dev) {} static inline void pm_runtime_drop_link(struct device_link *link) {} static inline void pm_runtime_release_supplier(struct device_link *link) {} #endif /* !CONFIG_PM */ /** * pm_runtime_idle - Conditionally set up autosuspend of a device or suspend it. * @dev: Target device. * * Invoke the "idle check" callback of @dev and, depending on its return value, * set up autosuspend of @dev or suspend it (depending on whether or not * autosuspend has been enabled for it). */ static inline int pm_runtime_idle(struct device *dev) { return __pm_runtime_idle(dev, 0); } /** * pm_runtime_suspend - Suspend a device synchronously. * @dev: Target device. */ static inline int pm_runtime_suspend(struct device *dev) { return __pm_runtime_suspend(dev, 0); } /** * pm_runtime_autosuspend - Set up autosuspend of a device or suspend it. * @dev: Target device. * * Set up autosuspend of @dev or suspend it (depending on whether or not * autosuspend is enabled for it) without engaging its "idle check" callback. */ static inline int pm_runtime_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_AUTO); } /** * pm_runtime_resume - Resume a device synchronously. * @dev: Target device. */ static inline int pm_runtime_resume(struct device *dev) { return __pm_runtime_resume(dev, 0); } /** * pm_request_idle - Queue up "idle check" execution for a device. * @dev: Target device. * * Queue up a work item to run an equivalent of pm_runtime_idle() for @dev * asynchronously. */ static inline int pm_request_idle(struct device *dev) { return __pm_runtime_idle(dev, RPM_ASYNC); } /** * pm_request_resume - Queue up runtime-resume of a device. * @dev: Target device. */ static inline int pm_request_resume(struct device *dev) { return __pm_runtime_resume(dev, RPM_ASYNC); } /** * pm_request_autosuspend - Queue up autosuspend of a device. * @dev: Target device. * * Queue up a work item to run an equivalent pm_runtime_autosuspend() for @dev * asynchronously. */ static inline int pm_request_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_ASYNC | RPM_AUTO); } /** * pm_runtime_get - Bump up usage counter and queue up resume of a device. * @dev: Target device. * * Bump up the runtime PM usage counter of @dev and queue up a work item to * carry out runtime-resume of it. */ static inline int pm_runtime_get(struct device *dev) { return __pm_runtime_resume(dev, RPM_GET_PUT | RPM_ASYNC); } /** * pm_runtime_get_sync - Bump up usage counter of a device and resume it. * @dev: Target device. * * Bump up the runtime PM usage counter of @dev and carry out runtime-resume of * it synchronously. * * The possible return values of this function are the same as for * pm_runtime_resume() and the runtime PM usage counter of @dev remains * incremented in all cases, even if it returns an error code. * Consider using pm_runtime_resume_and_get() instead of it, especially * if its return value is checked by the caller, as this is likely to result * in cleaner code. */ static inline int pm_runtime_get_sync(struct device *dev) { return __pm_runtime_resume(dev, RPM_GET_PUT); } /** * pm_runtime_resume_and_get - Bump up usage counter of a device and resume it. * @dev: Target device. * * Resume @dev synchronously and if that is successful, increment its runtime * PM usage counter. Return 0 if the runtime PM usage counter of @dev has been * incremented or a negative error code otherwise. */ static inline int pm_runtime_resume_and_get(struct device *dev) { int ret; ret = __pm_runtime_resume(dev, RPM_GET_PUT); if (ret < 0) { pm_runtime_put_noidle(dev); return ret; } return 0; } /** * pm_runtime_put - Drop device usage counter and queue up "idle check" if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, queue up a work item for @dev like in pm_request_idle(). */ static inline int pm_runtime_put(struct device *dev) { return __pm_runtime_idle(dev, RPM_GET_PUT | RPM_ASYNC); } /** * pm_runtime_put_autosuspend - Drop device usage counter and queue autosuspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, queue up a work item for @dev like in pm_request_autosuspend(). */ static inline int pm_runtime_put_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_ASYNC | RPM_AUTO); } /** * pm_runtime_put_sync - Drop device usage counter and run "idle check" if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, invoke the "idle check" callback of @dev and, depending on its * return value, set up autosuspend of @dev or suspend it (depending on whether * or not autosuspend has been enabled for it). * * The possible return values of this function are the same as for * pm_runtime_idle() and the runtime PM usage counter of @dev remains * decremented in all cases, even if it returns an error code. */ static inline int pm_runtime_put_sync(struct device *dev) { return __pm_runtime_idle(dev, RPM_GET_PUT); } /** * pm_runtime_put_sync_suspend - Drop device usage counter and suspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, carry out runtime-suspend of @dev synchronously. * * The possible return values of this function are the same as for * pm_runtime_suspend() and the runtime PM usage counter of @dev remains * decremented in all cases, even if it returns an error code. */ static inline int pm_runtime_put_sync_suspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT); } /** * pm_runtime_put_sync_autosuspend - Drop device usage counter and autosuspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, set up autosuspend of @dev or suspend it synchronously (depending * on whether or not autosuspend has been enabled for it). * * The possible return values of this function are the same as for * pm_runtime_autosuspend() and the runtime PM usage counter of @dev remains * decremented in all cases, even if it returns an error code. */ static inline int pm_runtime_put_sync_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_AUTO); } /** * pm_runtime_set_active - Set runtime PM status to "active". * @dev: Target device. * * Set the runtime PM status of @dev to %RPM_ACTIVE and ensure that dependencies * of it will be taken into account. * * It is not valid to call this function for devices with runtime PM enabled. */ static inline int pm_runtime_set_active(struct device *dev) { return __pm_runtime_set_status(dev, RPM_ACTIVE); } /** * pm_runtime_set_suspended - Set runtime PM status to "suspended". * @dev: Target device. * * Set the runtime PM status of @dev to %RPM_SUSPENDED and ensure that * dependencies of it will be taken into account. * * It is not valid to call this function for devices with runtime PM enabled. */ static inline int pm_runtime_set_suspended(struct device *dev) { return __pm_runtime_set_status(dev, RPM_SUSPENDED); } /** * pm_runtime_disable - Disable runtime PM for a device. * @dev: Target device. * * Prevent the runtime PM framework from working with @dev (by incrementing its * "blocking" counter). * * For each invocation of this function for @dev there must be a matching * pm_runtime_enable() call in order for runtime PM to be enabled for it. */ static inline void pm_runtime_disable(struct device *dev) { __pm_runtime_disable(dev, true); } /** * pm_runtime_use_autosuspend - Allow autosuspend to be used for a device. * @dev: Target device. * * Allow the runtime PM autosuspend mechanism to be used for @dev whenever * requested (or "autosuspend" will be handled as direct runtime-suspend for * it). * * NOTE: It's important to undo this with pm_runtime_dont_use_autosuspend() * at driver exit time unless your driver initially enabled pm_runtime * with devm_pm_runtime_enable() (which handles it for you). */ static inline void pm_runtime_use_autosuspend(struct device *dev) { __pm_runtime_use_autosuspend(dev, true); } /** * pm_runtime_dont_use_autosuspend - Prevent autosuspend from being used. * @dev: Target device. * * Prevent the runtime PM autosuspend mechanism from being used for @dev which * means that "autosuspend" will be handled as direct runtime-suspend for it * going forward. */ static inline void pm_runtime_dont_use_autosuspend(struct device *dev) { __pm_runtime_use_autosuspend(dev, false); } #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 | // SPDX-License-Identifier: GPL-2.0 /* * consolidates trace point definitions * * Copyright (C) 2009 Neil Horman <nhorman@tuxdriver.com> */ #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/string.h> #include <linux/if_arp.h> #include <linux/inetdevice.h> #include <linux/inet.h> #include <linux/interrupt.h> #include <linux/export.h> #include <linux/netpoll.h> #include <linux/sched.h> #include <linux/delay.h> #include <linux/rcupdate.h> #include <linux/types.h> #include <linux/workqueue.h> #include <linux/netlink.h> #include <linux/net_dropmon.h> #include <linux/slab.h> #include <asm/unaligned.h> #include <asm/bitops.h> #define CREATE_TRACE_POINTS #include <trace/events/skb.h> #include <trace/events/net.h> #include <trace/events/napi.h> #include <trace/events/sock.h> #include <trace/events/udp.h> #include <trace/events/tcp.h> #include <trace/events/fib.h> #include <trace/events/qdisc.h> #include <trace/events/bridge.h> EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_add); EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_external_learn_add); EXPORT_TRACEPOINT_SYMBOL_GPL(fdb_delete); EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_update); #if IS_ENABLED(CONFIG_PAGE_POOL) #include <trace/events/page_pool.h> #endif #include <trace/events/neigh.h> EXPORT_TRACEPOINT_SYMBOL_GPL(neigh_update); EXPORT_TRACEPOINT_SYMBOL_GPL(neigh_update_done); EXPORT_TRACEPOINT_SYMBOL_GPL(neigh_timer_handler); EXPORT_TRACEPOINT_SYMBOL_GPL(neigh_event_send_done); EXPORT_TRACEPOINT_SYMBOL_GPL(neigh_event_send_dead); EXPORT_TRACEPOINT_SYMBOL_GPL(neigh_cleanup_and_release); EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb); EXPORT_TRACEPOINT_SYMBOL_GPL(consume_skb); EXPORT_TRACEPOINT_SYMBOL_GPL(napi_poll); EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_send_reset); EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_bad_csum); EXPORT_TRACEPOINT_SYMBOL_GPL(net_dev_queue); EXPORT_TRACEPOINT_SYMBOL_GPL(net_dev_xmit); EXPORT_TRACEPOINT_SYMBOL_GPL(netif_receive_skb); EXPORT_TRACEPOINT_SYMBOL_GPL(netif_rx); |
| 418 101 332 1174 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM mmap_lock #if !defined(_TRACE_MMAP_LOCK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_MMAP_LOCK_H #include <linux/tracepoint.h> #include <linux/types.h> struct mm_struct; extern int trace_mmap_lock_reg(void); extern void trace_mmap_lock_unreg(void); DECLARE_EVENT_CLASS(mmap_lock, TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write), TP_ARGS(mm, memcg_path, write), TP_STRUCT__entry( __field(struct mm_struct *, mm) __string(memcg_path, memcg_path) __field(bool, write) ), TP_fast_assign( __entry->mm = mm; __assign_str(memcg_path, memcg_path); __entry->write = write; ), TP_printk( "mm=%p memcg_path=%s write=%s", __entry->mm, __get_str(memcg_path), __entry->write ? "true" : "false" ) ); #define DEFINE_MMAP_LOCK_EVENT(name) \ DEFINE_EVENT_FN(mmap_lock, name, \ TP_PROTO(struct mm_struct *mm, const char *memcg_path, \ bool write), \ TP_ARGS(mm, memcg_path, write), \ trace_mmap_lock_reg, trace_mmap_lock_unreg) DEFINE_MMAP_LOCK_EVENT(mmap_lock_start_locking); DEFINE_MMAP_LOCK_EVENT(mmap_lock_released); TRACE_EVENT_FN(mmap_lock_acquire_returned, TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write, bool success), TP_ARGS(mm, memcg_path, write, success), TP_STRUCT__entry( __field(struct mm_struct *, mm) __string(memcg_path, memcg_path) __field(bool, write) __field(bool, success) ), TP_fast_assign( __entry->mm = mm; __assign_str(memcg_path, memcg_path); __entry->write = write; __entry->success = success; ), TP_printk( "mm=%p memcg_path=%s write=%s success=%s", __entry->mm, __get_str(memcg_path), __entry->write ? "true" : "false", __entry->success ? "true" : "false" ), trace_mmap_lock_reg, trace_mmap_lock_unreg ); #endif /* _TRACE_MMAP_LOCK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 31 31 31 31 31 31 31 34 2 1 31 30 31 31 640 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/key/af_key.c An implementation of PF_KEYv2 sockets. * * Authors: Maxim Giryaev <gem@asplinux.ru> * David S. Miller <davem@redhat.com> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * Kunihiro Ishiguro <kunihiro@ipinfusion.com> * Kazunori MIYAZAWA / USAGI Project <miyazawa@linux-ipv6.org> * Derek Atkins <derek@ihtfp.com> */ #include <linux/capability.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/socket.h> #include <linux/pfkeyv2.h> #include <linux/ipsec.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/proc_fs.h> #include <linux/init.h> #include <linux/slab.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/xfrm.h> #include <net/sock.h> #define _X2KEY(x) ((x) == XFRM_INF ? 0 : (x)) #define _KEY2X(x) ((x) == 0 ? XFRM_INF : (x)) static unsigned int pfkey_net_id __read_mostly; struct netns_pfkey { /* List of all pfkey sockets. */ struct hlist_head table; atomic_t socks_nr; }; static DEFINE_MUTEX(pfkey_mutex); #define DUMMY_MARK 0 static const struct xfrm_mark dummy_mark = {0, 0}; struct pfkey_sock { /* struct sock must be the first member of struct pfkey_sock */ struct sock sk; int registered; int promisc; struct { uint8_t msg_version; uint32_t msg_portid; int (*dump)(struct pfkey_sock *sk); void (*done)(struct pfkey_sock *sk); union { struct xfrm_policy_walk policy; struct xfrm_state_walk state; } u; struct sk_buff *skb; } dump; struct mutex dump_lock; }; static int parse_sockaddr_pair(struct sockaddr *sa, int ext_len, xfrm_address_t *saddr, xfrm_address_t *daddr, u16 *family); static inline struct pfkey_sock *pfkey_sk(struct sock *sk) { return (struct pfkey_sock *)sk; } static int pfkey_can_dump(const struct sock *sk) { if (3 * atomic_read(&sk->sk_rmem_alloc) <= 2 * sk->sk_rcvbuf) return 1; return 0; } static void pfkey_terminate_dump(struct pfkey_sock *pfk) { if (pfk->dump.dump) { if (pfk->dump.skb) { kfree_skb(pfk->dump.skb); pfk->dump.skb = NULL; } pfk->dump.done(pfk); pfk->dump.dump = NULL; pfk->dump.done = NULL; } } static void pfkey_sock_destruct(struct sock *sk) { struct net *net = sock_net(sk); struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); pfkey_terminate_dump(pfkey_sk(sk)); skb_queue_purge(&sk->sk_receive_queue); if (!sock_flag(sk, SOCK_DEAD)) { pr_err("Attempt to release alive pfkey socket: %p\n", sk); return; } WARN_ON(atomic_read(&sk->sk_rmem_alloc)); WARN_ON(refcount_read(&sk->sk_wmem_alloc)); atomic_dec(&net_pfkey->socks_nr); } static const struct proto_ops pfkey_ops; static void pfkey_insert(struct sock *sk) { struct net *net = sock_net(sk); struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); mutex_lock(&pfkey_mutex); sk_add_node_rcu(sk, &net_pfkey->table); mutex_unlock(&pfkey_mutex); } static void pfkey_remove(struct sock *sk) { mutex_lock(&pfkey_mutex); sk_del_node_init_rcu(sk); mutex_unlock(&pfkey_mutex); } static struct proto key_proto = { .name = "KEY", .owner = THIS_MODULE, .obj_size = sizeof(struct pfkey_sock), }; static int pfkey_create(struct net *net, struct socket *sock, int protocol, int kern) { struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); struct sock *sk; struct pfkey_sock *pfk; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (sock->type != SOCK_RAW) return -ESOCKTNOSUPPORT; if (protocol != PF_KEY_V2) return -EPROTONOSUPPORT; sk = sk_alloc(net, PF_KEY, GFP_KERNEL, &key_proto, kern); if (sk == NULL) return -ENOMEM; pfk = pfkey_sk(sk); mutex_init(&pfk->dump_lock); sock->ops = &pfkey_ops; sock_init_data(sock, sk); sk->sk_family = PF_KEY; sk->sk_destruct = pfkey_sock_destruct; atomic_inc(&net_pfkey->socks_nr); pfkey_insert(sk); return 0; } static int pfkey_release(struct socket *sock) { struct sock *sk = sock->sk; if (!sk) return 0; pfkey_remove(sk); sock_orphan(sk); sock->sk = NULL; skb_queue_purge(&sk->sk_write_queue); synchronize_rcu(); sock_put(sk); return 0; } static int pfkey_broadcast_one(struct sk_buff *skb, gfp_t allocation, struct sock *sk) { int err = -ENOBUFS; if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) return err; skb = skb_clone(skb, allocation); if (skb) { skb_set_owner_r(skb, sk); skb_queue_tail(&sk->sk_receive_queue, skb); sk->sk_data_ready(sk); err = 0; } return err; } /* Send SKB to all pfkey sockets matching selected criteria. */ #define BROADCAST_ALL 0 #define BROADCAST_ONE 1 #define BROADCAST_REGISTERED 2 #define BROADCAST_PROMISC_ONLY 4 static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, int broadcast_flags, struct sock *one_sk, struct net *net) { struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); struct sock *sk; int err = -ESRCH; /* XXX Do we need something like netlink_overrun? I think * XXX PF_KEY socket apps will not mind current behavior. */ if (!skb) return -ENOMEM; rcu_read_lock(); sk_for_each_rcu(sk, &net_pfkey->table) { struct pfkey_sock *pfk = pfkey_sk(sk); int err2; /* Yes, it means that if you are meant to receive this * pfkey message you receive it twice as promiscuous * socket. */ if (pfk->promisc) pfkey_broadcast_one(skb, GFP_ATOMIC, sk); /* the exact target will be processed later */ if (sk == one_sk) continue; if (broadcast_flags != BROADCAST_ALL) { if (broadcast_flags & BROADCAST_PROMISC_ONLY) continue; if ((broadcast_flags & BROADCAST_REGISTERED) && !pfk->registered) continue; if (broadcast_flags & BROADCAST_ONE) continue; } err2 = pfkey_broadcast_one(skb, GFP_ATOMIC, sk); /* Error is cleared after successful sending to at least one * registered KM */ if ((broadcast_flags & BROADCAST_REGISTERED) && err) err = err2; } rcu_read_unlock(); if (one_sk != NULL) err = pfkey_broadcast_one(skb, allocation, one_sk); kfree_skb(skb); return err; } static int pfkey_do_dump(struct pfkey_sock *pfk) { struct sadb_msg *hdr; int rc; mutex_lock(&pfk->dump_lock); if (!pfk->dump.dump) { rc = 0; goto out; } rc = pfk->dump.dump(pfk); if (rc == -ENOBUFS) { rc = 0; goto out; } if (pfk->dump.skb) { if (!pfkey_can_dump(&pfk->sk)) { rc = 0; goto out; } hdr = (struct sadb_msg *) pfk->dump.skb->data; hdr->sadb_msg_seq = 0; hdr->sadb_msg_errno = rc; pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE, &pfk->sk, sock_net(&pfk->sk)); pfk->dump.skb = NULL; } pfkey_terminate_dump(pfk); out: mutex_unlock(&pfk->dump_lock); return rc; } static inline void pfkey_hdr_dup(struct sadb_msg *new, const struct sadb_msg *orig) { *new = *orig; } static int pfkey_error(const struct sadb_msg *orig, int err, struct sock *sk) { struct sk_buff *skb = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_KERNEL); struct sadb_msg *hdr; if (!skb) return -ENOBUFS; /* Woe be to the platform trying to support PFKEY yet * having normal errnos outside the 1-255 range, inclusive. */ err = -err; if (err == ERESTARTSYS || err == ERESTARTNOHAND || err == ERESTARTNOINTR) err = EINTR; if (err >= 512) err = EINVAL; BUG_ON(err <= 0 || err >= 256); hdr = skb_put(skb, sizeof(struct sadb_msg)); pfkey_hdr_dup(hdr, orig); hdr->sadb_msg_errno = (uint8_t) err; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); pfkey_broadcast(skb, GFP_KERNEL, BROADCAST_ONE, sk, sock_net(sk)); return 0; } static const u8 sadb_ext_min_len[] = { [SADB_EXT_RESERVED] = (u8) 0, [SADB_EXT_SA] = (u8) sizeof(struct sadb_sa), [SADB_EXT_LIFETIME_CURRENT] = (u8) sizeof(struct sadb_lifetime), [SADB_EXT_LIFETIME_HARD] = (u8) sizeof(struct sadb_lifetime), [SADB_EXT_LIFETIME_SOFT] = (u8) sizeof(struct sadb_lifetime), [SADB_EXT_ADDRESS_SRC] = (u8) sizeof(struct sadb_address), [SADB_EXT_ADDRESS_DST] = (u8) sizeof(struct sadb_address), [SADB_EXT_ADDRESS_PROXY] = (u8) sizeof(struct sadb_address), [SADB_EXT_KEY_AUTH] = (u8) sizeof(struct sadb_key), [SADB_EXT_KEY_ENCRYPT] = (u8) sizeof(struct sadb_key), [SADB_EXT_IDENTITY_SRC] = (u8) sizeof(struct sadb_ident), [SADB_EXT_IDENTITY_DST] = (u8) sizeof(struct sadb_ident), [SADB_EXT_SENSITIVITY] = (u8) sizeof(struct sadb_sens), [SADB_EXT_PROPOSAL] = (u8) sizeof(struct sadb_prop), [SADB_EXT_SUPPORTED_AUTH] = (u8) sizeof(struct sadb_supported), [SADB_EXT_SUPPORTED_ENCRYPT] = (u8) sizeof(struct sadb_supported), [SADB_EXT_SPIRANGE] = (u8) sizeof(struct sadb_spirange), [SADB_X_EXT_KMPRIVATE] = (u8) sizeof(struct sadb_x_kmprivate), [SADB_X_EXT_POLICY] = (u8) sizeof(struct sadb_x_policy), [SADB_X_EXT_SA2] = (u8) sizeof(struct sadb_x_sa2), [SADB_X_EXT_NAT_T_TYPE] = (u8) sizeof(struct sadb_x_nat_t_type), [SADB_X_EXT_NAT_T_SPORT] = (u8) sizeof(struct sadb_x_nat_t_port), [SADB_X_EXT_NAT_T_DPORT] = (u8) sizeof(struct sadb_x_nat_t_port), [SADB_X_EXT_NAT_T_OA] = (u8) sizeof(struct sadb_address), [SADB_X_EXT_SEC_CTX] = (u8) sizeof(struct sadb_x_sec_ctx), [SADB_X_EXT_KMADDRESS] = (u8) sizeof(struct sadb_x_kmaddress), [SADB_X_EXT_FILTER] = (u8) sizeof(struct sadb_x_filter), }; /* Verify sadb_address_{len,prefixlen} against sa_family. */ static int verify_address_len(const void *p) { const struct sadb_address *sp = p; const struct sockaddr *addr = (const struct sockaddr *)(sp + 1); const struct sockaddr_in *sin; #if IS_ENABLED(CONFIG_IPV6) const struct sockaddr_in6 *sin6; #endif int len; if (sp->sadb_address_len < DIV_ROUND_UP(sizeof(*sp) + offsetofend(typeof(*addr), sa_family), sizeof(uint64_t))) return -EINVAL; switch (addr->sa_family) { case AF_INET: len = DIV_ROUND_UP(sizeof(*sp) + sizeof(*sin), sizeof(uint64_t)); if (sp->sadb_address_len != len || sp->sadb_address_prefixlen > 32) return -EINVAL; break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: len = DIV_ROUND_UP(sizeof(*sp) + sizeof(*sin6), sizeof(uint64_t)); if (sp->sadb_address_len != len || sp->sadb_address_prefixlen > 128) return -EINVAL; break; #endif default: /* It is user using kernel to keep track of security * associations for another protocol, such as * OSPF/RSVP/RIPV2/MIP. It is user's job to verify * lengths. * * XXX Actually, association/policy database is not yet * XXX able to cope with arbitrary sockaddr families. * XXX When it can, remove this -EINVAL. -DaveM */ return -EINVAL; } return 0; } static inline int sadb_key_len(const struct sadb_key *key) { int key_bytes = DIV_ROUND_UP(key->sadb_key_bits, 8); return DIV_ROUND_UP(sizeof(struct sadb_key) + key_bytes, sizeof(uint64_t)); } static int verify_key_len(const void *p) { const struct sadb_key *key = p; if (sadb_key_len(key) > key->sadb_key_len) return -EINVAL; return 0; } static inline int pfkey_sec_ctx_len(const struct sadb_x_sec_ctx *sec_ctx) { return DIV_ROUND_UP(sizeof(struct sadb_x_sec_ctx) + sec_ctx->sadb_x_ctx_len, sizeof(uint64_t)); } static inline int verify_sec_ctx_len(const void *p) { const struct sadb_x_sec_ctx *sec_ctx = p; int len = sec_ctx->sadb_x_ctx_len; if (len > PAGE_SIZE) return -EINVAL; len = pfkey_sec_ctx_len(sec_ctx); if (sec_ctx->sadb_x_sec_len != len) return -EINVAL; return 0; } static inline struct xfrm_user_sec_ctx *pfkey_sadb2xfrm_user_sec_ctx(const struct sadb_x_sec_ctx *sec_ctx, gfp_t gfp) { struct xfrm_user_sec_ctx *uctx = NULL; int ctx_size = sec_ctx->sadb_x_ctx_len; uctx = kmalloc((sizeof(*uctx)+ctx_size), gfp); if (!uctx) return NULL; uctx->len = pfkey_sec_ctx_len(sec_ctx); uctx->exttype = sec_ctx->sadb_x_sec_exttype; uctx->ctx_doi = sec_ctx->sadb_x_ctx_doi; uctx->ctx_alg = sec_ctx->sadb_x_ctx_alg; uctx->ctx_len = sec_ctx->sadb_x_ctx_len; memcpy(uctx + 1, sec_ctx + 1, uctx->ctx_len); return uctx; } static int present_and_same_family(const struct sadb_address *src, const struct sadb_address *dst) { const struct sockaddr *s_addr, *d_addr; if (!src || !dst) return 0; s_addr = (const struct sockaddr *)(src + 1); d_addr = (const struct sockaddr *)(dst + 1); if (s_addr->sa_family != d_addr->sa_family) return 0; if (s_addr->sa_family != AF_INET #if IS_ENABLED(CONFIG_IPV6) && s_addr->sa_family != AF_INET6 #endif ) return 0; return 1; } static int parse_exthdrs(struct sk_buff *skb, const struct sadb_msg *hdr, void **ext_hdrs) { const char *p = (char *) hdr; int len = skb->len; len -= sizeof(*hdr); p += sizeof(*hdr); while (len > 0) { const struct sadb_ext *ehdr = (const struct sadb_ext *) p; uint16_t ext_type; int ext_len; if (len < sizeof(*ehdr)) return -EINVAL; ext_len = ehdr->sadb_ext_len; ext_len *= sizeof(uint64_t); ext_type = ehdr->sadb_ext_type; if (ext_len < sizeof(uint64_t) || ext_len > len || ext_type == SADB_EXT_RESERVED) return -EINVAL; if (ext_type <= SADB_EXT_MAX) { int min = (int) sadb_ext_min_len[ext_type]; if (ext_len < min) return -EINVAL; if (ext_hdrs[ext_type-1] != NULL) return -EINVAL; switch (ext_type) { case SADB_EXT_ADDRESS_SRC: case SADB_EXT_ADDRESS_DST: case SADB_EXT_ADDRESS_PROXY: case SADB_X_EXT_NAT_T_OA: if (verify_address_len(p)) return -EINVAL; break; case SADB_X_EXT_SEC_CTX: if (verify_sec_ctx_len(p)) return -EINVAL; break; case SADB_EXT_KEY_AUTH: case SADB_EXT_KEY_ENCRYPT: if (verify_key_len(p)) return -EINVAL; break; default: break; } ext_hdrs[ext_type-1] = (void *) p; } p += ext_len; len -= ext_len; } return 0; } static uint16_t pfkey_satype2proto(uint8_t satype) { switch (satype) { case SADB_SATYPE_UNSPEC: return IPSEC_PROTO_ANY; case SADB_SATYPE_AH: return IPPROTO_AH; case SADB_SATYPE_ESP: return IPPROTO_ESP; case SADB_X_SATYPE_IPCOMP: return IPPROTO_COMP; default: return 0; } /* NOTREACHED */ } static uint8_t pfkey_proto2satype(uint16_t proto) { switch (proto) { case IPPROTO_AH: return SADB_SATYPE_AH; case IPPROTO_ESP: return SADB_SATYPE_ESP; case IPPROTO_COMP: return SADB_X_SATYPE_IPCOMP; default: return 0; } /* NOTREACHED */ } /* BTW, this scheme means that there is no way with PFKEY2 sockets to * say specifically 'just raw sockets' as we encode them as 255. */ static uint8_t pfkey_proto_to_xfrm(uint8_t proto) { return proto == IPSEC_PROTO_ANY ? 0 : proto; } static uint8_t pfkey_proto_from_xfrm(uint8_t proto) { return proto ? proto : IPSEC_PROTO_ANY; } static inline int pfkey_sockaddr_len(sa_family_t family) { switch (family) { case AF_INET: return sizeof(struct sockaddr_in); #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: return sizeof(struct sockaddr_in6); #endif } return 0; } static int pfkey_sockaddr_extract(const struct sockaddr *sa, xfrm_address_t *xaddr) { switch (sa->sa_family) { case AF_INET: xaddr->a4 = ((struct sockaddr_in *)sa)->sin_addr.s_addr; return AF_INET; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: memcpy(xaddr->a6, &((struct sockaddr_in6 *)sa)->sin6_addr, sizeof(struct in6_addr)); return AF_INET6; #endif } return 0; } static int pfkey_sadb_addr2xfrm_addr(const struct sadb_address *addr, xfrm_address_t *xaddr) { return pfkey_sockaddr_extract((struct sockaddr *)(addr + 1), xaddr); } static struct xfrm_state *pfkey_xfrm_state_lookup(struct net *net, const struct sadb_msg *hdr, void * const *ext_hdrs) { const struct sadb_sa *sa; const struct sadb_address *addr; uint16_t proto; unsigned short family; xfrm_address_t *xaddr; sa = ext_hdrs[SADB_EXT_SA - 1]; if (sa == NULL) return NULL; proto = pfkey_satype2proto(hdr->sadb_msg_satype); if (proto == 0) return NULL; /* sadb_address_len should be checked by caller */ addr = ext_hdrs[SADB_EXT_ADDRESS_DST - 1]; if (addr == NULL) return NULL; family = ((const struct sockaddr *)(addr + 1))->sa_family; switch (family) { case AF_INET: xaddr = (xfrm_address_t *)&((const struct sockaddr_in *)(addr + 1))->sin_addr; break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: xaddr = (xfrm_address_t *)&((const struct sockaddr_in6 *)(addr + 1))->sin6_addr; break; #endif default: xaddr = NULL; } if (!xaddr) return NULL; return xfrm_state_lookup(net, DUMMY_MARK, xaddr, sa->sadb_sa_spi, proto, family); } #define PFKEY_ALIGN8(a) (1 + (((a) - 1) | (8 - 1))) static int pfkey_sockaddr_size(sa_family_t family) { return PFKEY_ALIGN8(pfkey_sockaddr_len(family)); } static inline int pfkey_mode_from_xfrm(int mode) { switch(mode) { case XFRM_MODE_TRANSPORT: return IPSEC_MODE_TRANSPORT; case XFRM_MODE_TUNNEL: return IPSEC_MODE_TUNNEL; case XFRM_MODE_BEET: return IPSEC_MODE_BEET; default: return -1; } } static inline int pfkey_mode_to_xfrm(int mode) { switch(mode) { case IPSEC_MODE_ANY: /*XXX*/ case IPSEC_MODE_TRANSPORT: return XFRM_MODE_TRANSPORT; case IPSEC_MODE_TUNNEL: return XFRM_MODE_TUNNEL; case IPSEC_MODE_BEET: return XFRM_MODE_BEET; default: return -1; } } static unsigned int pfkey_sockaddr_fill(const xfrm_address_t *xaddr, __be16 port, struct sockaddr *sa, unsigned short family) { switch (family) { case AF_INET: { struct sockaddr_in *sin = (struct sockaddr_in *)sa; sin->sin_family = AF_INET; sin->sin_port = port; sin->sin_addr.s_addr = xaddr->a4; memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); return 32; } #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sa; sin6->sin6_family = AF_INET6; sin6->sin6_port = port; sin6->sin6_flowinfo = 0; sin6->sin6_addr = xaddr->in6; sin6->sin6_scope_id = 0; return 128; } #endif } return 0; } static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x, int add_keys, int hsc) { struct sk_buff *skb; struct sadb_msg *hdr; struct sadb_sa *sa; struct sadb_lifetime *lifetime; struct sadb_address *addr; struct sadb_key *key; struct sadb_x_sa2 *sa2; struct sadb_x_sec_ctx *sec_ctx; struct xfrm_sec_ctx *xfrm_ctx; int ctx_size = 0; int size; int auth_key_size = 0; int encrypt_key_size = 0; int sockaddr_size; struct xfrm_encap_tmpl *natt = NULL; int mode; /* address family check */ sockaddr_size = pfkey_sockaddr_size(x->props.family); if (!sockaddr_size) return ERR_PTR(-EINVAL); /* base, SA, (lifetime (HSC),) address(SD), (address(P),) key(AE), (identity(SD),) (sensitivity)> */ size = sizeof(struct sadb_msg) +sizeof(struct sadb_sa) + sizeof(struct sadb_lifetime) + ((hsc & 1) ? sizeof(struct sadb_lifetime) : 0) + ((hsc & 2) ? sizeof(struct sadb_lifetime) : 0) + sizeof(struct sadb_address)*2 + sockaddr_size*2 + sizeof(struct sadb_x_sa2); if ((xfrm_ctx = x->security)) { ctx_size = PFKEY_ALIGN8(xfrm_ctx->ctx_len); size += sizeof(struct sadb_x_sec_ctx) + ctx_size; } /* identity & sensitivity */ if (!xfrm_addr_equal(&x->sel.saddr, &x->props.saddr, x->props.family)) size += sizeof(struct sadb_address) + sockaddr_size; if (add_keys) { if (x->aalg && x->aalg->alg_key_len) { auth_key_size = PFKEY_ALIGN8((x->aalg->alg_key_len + 7) / 8); size += sizeof(struct sadb_key) + auth_key_size; } if (x->ealg && x->ealg->alg_key_len) { encrypt_key_size = PFKEY_ALIGN8((x->ealg->alg_key_len+7) / 8); size += sizeof(struct sadb_key) + encrypt_key_size; } } if (x->encap) natt = x->encap; if (natt && natt->encap_type) { size += sizeof(struct sadb_x_nat_t_type); size += sizeof(struct sadb_x_nat_t_port); size += sizeof(struct sadb_x_nat_t_port); } skb = alloc_skb(size + 16, GFP_ATOMIC); if (skb == NULL) return ERR_PTR(-ENOBUFS); /* call should fill header later */ hdr = skb_put(skb, sizeof(struct sadb_msg)); memset(hdr, 0, size); /* XXX do we need this ? */ hdr->sadb_msg_len = size / sizeof(uint64_t); /* sa */ sa = skb_put(skb, sizeof(struct sadb_sa)); sa->sadb_sa_len = sizeof(struct sadb_sa)/sizeof(uint64_t); sa->sadb_sa_exttype = SADB_EXT_SA; sa->sadb_sa_spi = x->id.spi; sa->sadb_sa_replay = x->props.replay_window; switch (x->km.state) { case XFRM_STATE_VALID: sa->sadb_sa_state = x->km.dying ? SADB_SASTATE_DYING : SADB_SASTATE_MATURE; break; case XFRM_STATE_ACQ: sa->sadb_sa_state = SADB_SASTATE_LARVAL; break; default: sa->sadb_sa_state = SADB_SASTATE_DEAD; break; } sa->sadb_sa_auth = 0; if (x->aalg) { struct xfrm_algo_desc *a = xfrm_aalg_get_byname(x->aalg->alg_name, 0); sa->sadb_sa_auth = (a && a->pfkey_supported) ? a->desc.sadb_alg_id : 0; } sa->sadb_sa_encrypt = 0; BUG_ON(x->ealg && x->calg); if (x->ealg) { struct xfrm_algo_desc *a = xfrm_ealg_get_byname(x->ealg->alg_name, 0); sa->sadb_sa_encrypt = (a && a->pfkey_supported) ? a->desc.sadb_alg_id : 0; } /* KAME compatible: sadb_sa_encrypt is overloaded with calg id */ if (x->calg) { struct xfrm_algo_desc *a = xfrm_calg_get_byname(x->calg->alg_name, 0); sa->sadb_sa_encrypt = (a && a->pfkey_supported) ? a->desc.sadb_alg_id : 0; } sa->sadb_sa_flags = 0; if (x->props.flags & XFRM_STATE_NOECN) sa->sadb_sa_flags |= SADB_SAFLAGS_NOECN; if (x->props.flags & XFRM_STATE_DECAP_DSCP) sa->sadb_sa_flags |= SADB_SAFLAGS_DECAP_DSCP; if (x->props.flags & XFRM_STATE_NOPMTUDISC) sa->sadb_sa_flags |= SADB_SAFLAGS_NOPMTUDISC; /* hard time */ if (hsc & 2) { lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_HARD; lifetime->sadb_lifetime_allocations = _X2KEY(x->lft.hard_packet_limit); lifetime->sadb_lifetime_bytes = _X2KEY(x->lft.hard_byte_limit); lifetime->sadb_lifetime_addtime = x->lft.hard_add_expires_seconds; lifetime->sadb_lifetime_usetime = x->lft.hard_use_expires_seconds; } /* soft time */ if (hsc & 1) { lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_SOFT; lifetime->sadb_lifetime_allocations = _X2KEY(x->lft.soft_packet_limit); lifetime->sadb_lifetime_bytes = _X2KEY(x->lft.soft_byte_limit); lifetime->sadb_lifetime_addtime = x->lft.soft_add_expires_seconds; lifetime->sadb_lifetime_usetime = x->lft.soft_use_expires_seconds; } /* current time */ lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_CURRENT; lifetime->sadb_lifetime_allocations = x->curlft.packets; lifetime->sadb_lifetime_bytes = x->curlft.bytes; lifetime->sadb_lifetime_addtime = x->curlft.add_time; lifetime->sadb_lifetime_usetime = x->curlft.use_time; /* src address */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_SRC; /* "if the ports are non-zero, then the sadb_address_proto field, normally zero, MUST be filled in with the transport protocol's number." - RFC2367 */ addr->sadb_address_proto = 0; addr->sadb_address_reserved = 0; addr->sadb_address_prefixlen = pfkey_sockaddr_fill(&x->props.saddr, 0, (struct sockaddr *) (addr + 1), x->props.family); BUG_ON(!addr->sadb_address_prefixlen); /* dst address */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_DST; addr->sadb_address_proto = 0; addr->sadb_address_reserved = 0; addr->sadb_address_prefixlen = pfkey_sockaddr_fill(&x->id.daddr, 0, (struct sockaddr *) (addr + 1), x->props.family); BUG_ON(!addr->sadb_address_prefixlen); if (!xfrm_addr_equal(&x->sel.saddr, &x->props.saddr, x->props.family)) { addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_PROXY; addr->sadb_address_proto = pfkey_proto_from_xfrm(x->sel.proto); addr->sadb_address_prefixlen = x->sel.prefixlen_s; addr->sadb_address_reserved = 0; pfkey_sockaddr_fill(&x->sel.saddr, x->sel.sport, (struct sockaddr *) (addr + 1), x->props.family); } /* auth key */ if (add_keys && auth_key_size) { key = skb_put(skb, sizeof(struct sadb_key) + auth_key_size); key->sadb_key_len = (sizeof(struct sadb_key) + auth_key_size) / sizeof(uint64_t); key->sadb_key_exttype = SADB_EXT_KEY_AUTH; key->sadb_key_bits = x->aalg->alg_key_len; key->sadb_key_reserved = 0; memcpy(key + 1, x->aalg->alg_key, (x->aalg->alg_key_len+7)/8); } /* encrypt key */ if (add_keys && encrypt_key_size) { key = skb_put(skb, sizeof(struct sadb_key) + encrypt_key_size); key->sadb_key_len = (sizeof(struct sadb_key) + encrypt_key_size) / sizeof(uint64_t); key->sadb_key_exttype = SADB_EXT_KEY_ENCRYPT; key->sadb_key_bits = x->ealg->alg_key_len; key->sadb_key_reserved = 0; memcpy(key + 1, x->ealg->alg_key, (x->ealg->alg_key_len+7)/8); } /* sa */ sa2 = skb_put(skb, sizeof(struct sadb_x_sa2)); sa2->sadb_x_sa2_len = sizeof(struct sadb_x_sa2)/sizeof(uint64_t); sa2->sadb_x_sa2_exttype = SADB_X_EXT_SA2; if ((mode = pfkey_mode_from_xfrm(x->props.mode)) < 0) { kfree_skb(skb); return ERR_PTR(-EINVAL); } sa2->sadb_x_sa2_mode = mode; sa2->sadb_x_sa2_reserved1 = 0; sa2->sadb_x_sa2_reserved2 = 0; sa2->sadb_x_sa2_sequence = 0; sa2->sadb_x_sa2_reqid = x->props.reqid; if (natt && natt->encap_type) { struct sadb_x_nat_t_type *n_type; struct sadb_x_nat_t_port *n_port; /* type */ n_type = skb_put(skb, sizeof(*n_type)); n_type->sadb_x_nat_t_type_len = sizeof(*n_type)/sizeof(uint64_t); n_type->sadb_x_nat_t_type_exttype = SADB_X_EXT_NAT_T_TYPE; n_type->sadb_x_nat_t_type_type = natt->encap_type; n_type->sadb_x_nat_t_type_reserved[0] = 0; n_type->sadb_x_nat_t_type_reserved[1] = 0; n_type->sadb_x_nat_t_type_reserved[2] = 0; /* source port */ n_port = skb_put(skb, sizeof(*n_port)); n_port->sadb_x_nat_t_port_len = sizeof(*n_port)/sizeof(uint64_t); n_port->sadb_x_nat_t_port_exttype = SADB_X_EXT_NAT_T_SPORT; n_port->sadb_x_nat_t_port_port = natt->encap_sport; n_port->sadb_x_nat_t_port_reserved = 0; /* dest port */ n_port = skb_put(skb, sizeof(*n_port)); n_port->sadb_x_nat_t_port_len = sizeof(*n_port)/sizeof(uint64_t); n_port->sadb_x_nat_t_port_exttype = SADB_X_EXT_NAT_T_DPORT; n_port->sadb_x_nat_t_port_port = natt->encap_dport; n_port->sadb_x_nat_t_port_reserved = 0; } /* security context */ if (xfrm_ctx) { sec_ctx = skb_put(skb, sizeof(struct sadb_x_sec_ctx) + ctx_size); sec_ctx->sadb_x_sec_len = (sizeof(struct sadb_x_sec_ctx) + ctx_size) / sizeof(uint64_t); sec_ctx->sadb_x_sec_exttype = SADB_X_EXT_SEC_CTX; sec_ctx->sadb_x_ctx_doi = xfrm_ctx->ctx_doi; sec_ctx->sadb_x_ctx_alg = xfrm_ctx->ctx_alg; sec_ctx->sadb_x_ctx_len = xfrm_ctx->ctx_len; memcpy(sec_ctx + 1, xfrm_ctx->ctx_str, xfrm_ctx->ctx_len); } return skb; } static inline struct sk_buff *pfkey_xfrm_state2msg(const struct xfrm_state *x) { struct sk_buff *skb; skb = __pfkey_xfrm_state2msg(x, 1, 3); return skb; } static inline struct sk_buff *pfkey_xfrm_state2msg_expire(const struct xfrm_state *x, int hsc) { return __pfkey_xfrm_state2msg(x, 0, hsc); } static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct xfrm_state *x; const struct sadb_lifetime *lifetime; const struct sadb_sa *sa; const struct sadb_key *key; const struct sadb_x_sec_ctx *sec_ctx; uint16_t proto; int err; sa = ext_hdrs[SADB_EXT_SA - 1]; if (!sa || !present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1])) return ERR_PTR(-EINVAL); if (hdr->sadb_msg_satype == SADB_SATYPE_ESP && !ext_hdrs[SADB_EXT_KEY_ENCRYPT-1]) return ERR_PTR(-EINVAL); if (hdr->sadb_msg_satype == SADB_SATYPE_AH && !ext_hdrs[SADB_EXT_KEY_AUTH-1]) return ERR_PTR(-EINVAL); if (!!ext_hdrs[SADB_EXT_LIFETIME_HARD-1] != !!ext_hdrs[SADB_EXT_LIFETIME_SOFT-1]) return ERR_PTR(-EINVAL); proto = pfkey_satype2proto(hdr->sadb_msg_satype); if (proto == 0) return ERR_PTR(-EINVAL); /* default error is no buffer space */ err = -ENOBUFS; /* RFC2367: Only SADB_SASTATE_MATURE SAs may be submitted in an SADB_ADD message. SADB_SASTATE_LARVAL SAs are created by SADB_GETSPI and it is not sensible to add a new SA in the DYING or SADB_SASTATE_DEAD state. Therefore, the sadb_sa_state field of all submitted SAs MUST be SADB_SASTATE_MATURE and the kernel MUST return an error if this is not true. However, KAME setkey always uses SADB_SASTATE_LARVAL. Hence, we have to _ignore_ sadb_sa_state, which is also reasonable. */ if (sa->sadb_sa_auth > SADB_AALG_MAX || (hdr->sadb_msg_satype == SADB_X_SATYPE_IPCOMP && sa->sadb_sa_encrypt > SADB_X_CALG_MAX) || sa->sadb_sa_encrypt > SADB_EALG_MAX) return ERR_PTR(-EINVAL); key = ext_hdrs[SADB_EXT_KEY_AUTH - 1]; if (key != NULL && sa->sadb_sa_auth != SADB_X_AALG_NULL && key->sadb_key_bits == 0) return ERR_PTR(-EINVAL); key = ext_hdrs[SADB_EXT_KEY_ENCRYPT-1]; if (key != NULL && sa->sadb_sa_encrypt != SADB_EALG_NULL && key->sadb_key_bits == 0) return ERR_PTR(-EINVAL); x = xfrm_state_alloc(net); if (x == NULL) return ERR_PTR(-ENOBUFS); x->id.proto = proto; x->id.spi = sa->sadb_sa_spi; x->props.replay_window = min_t(unsigned int, sa->sadb_sa_replay, (sizeof(x->replay.bitmap) * 8)); if (sa->sadb_sa_flags & SADB_SAFLAGS_NOECN) x->props.flags |= XFRM_STATE_NOECN; if (sa->sadb_sa_flags & SADB_SAFLAGS_DECAP_DSCP) x->props.flags |= XFRM_STATE_DECAP_DSCP; if (sa->sadb_sa_flags & SADB_SAFLAGS_NOPMTUDISC) x->props.flags |= XFRM_STATE_NOPMTUDISC; lifetime = ext_hdrs[SADB_EXT_LIFETIME_HARD - 1]; if (lifetime != NULL) { x->lft.hard_packet_limit = _KEY2X(lifetime->sadb_lifetime_allocations); x->lft.hard_byte_limit = _KEY2X(lifetime->sadb_lifetime_bytes); x->lft.hard_add_expires_seconds = lifetime->sadb_lifetime_addtime; x->lft.hard_use_expires_seconds = lifetime->sadb_lifetime_usetime; } lifetime = ext_hdrs[SADB_EXT_LIFETIME_SOFT - 1]; if (lifetime != NULL) { x->lft.soft_packet_limit = _KEY2X(lifetime->sadb_lifetime_allocations); x->lft.soft_byte_limit = _KEY2X(lifetime->sadb_lifetime_bytes); x->lft.soft_add_expires_seconds = lifetime->sadb_lifetime_addtime; x->lft.soft_use_expires_seconds = lifetime->sadb_lifetime_usetime; } sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1]; if (sec_ctx != NULL) { struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_KERNEL); if (!uctx) goto out; err = security_xfrm_state_alloc(x, uctx); kfree(uctx); if (err) goto out; } err = -ENOBUFS; key = ext_hdrs[SADB_EXT_KEY_AUTH - 1]; if (sa->sadb_sa_auth) { int keysize = 0; struct xfrm_algo_desc *a = xfrm_aalg_get_byid(sa->sadb_sa_auth); if (!a || !a->pfkey_supported) { err = -ENOSYS; goto out; } if (key) keysize = (key->sadb_key_bits + 7) / 8; x->aalg = kmalloc(sizeof(*x->aalg) + keysize, GFP_KERNEL); if (!x->aalg) { err = -ENOMEM; goto out; } strcpy(x->aalg->alg_name, a->name); x->aalg->alg_key_len = 0; if (key) { x->aalg->alg_key_len = key->sadb_key_bits; memcpy(x->aalg->alg_key, key+1, keysize); } x->aalg->alg_trunc_len = a->uinfo.auth.icv_truncbits; x->props.aalgo = sa->sadb_sa_auth; /* x->algo.flags = sa->sadb_sa_flags; */ } if (sa->sadb_sa_encrypt) { if (hdr->sadb_msg_satype == SADB_X_SATYPE_IPCOMP) { struct xfrm_algo_desc *a = xfrm_calg_get_byid(sa->sadb_sa_encrypt); if (!a || !a->pfkey_supported) { err = -ENOSYS; goto out; } x->calg = kmalloc(sizeof(*x->calg), GFP_KERNEL); if (!x->calg) { err = -ENOMEM; goto out; } strcpy(x->calg->alg_name, a->name); x->props.calgo = sa->sadb_sa_encrypt; } else { int keysize = 0; struct xfrm_algo_desc *a = xfrm_ealg_get_byid(sa->sadb_sa_encrypt); if (!a || !a->pfkey_supported) { err = -ENOSYS; goto out; } key = (struct sadb_key*) ext_hdrs[SADB_EXT_KEY_ENCRYPT-1]; if (key) keysize = (key->sadb_key_bits + 7) / 8; x->ealg = kmalloc(sizeof(*x->ealg) + keysize, GFP_KERNEL); if (!x->ealg) { err = -ENOMEM; goto out; } strcpy(x->ealg->alg_name, a->name); x->ealg->alg_key_len = 0; if (key) { x->ealg->alg_key_len = key->sadb_key_bits; memcpy(x->ealg->alg_key, key+1, keysize); } x->props.ealgo = sa->sadb_sa_encrypt; x->geniv = a->uinfo.encr.geniv; } } /* x->algo.flags = sa->sadb_sa_flags; */ x->props.family = pfkey_sadb_addr2xfrm_addr((struct sadb_address *) ext_hdrs[SADB_EXT_ADDRESS_SRC-1], &x->props.saddr); pfkey_sadb_addr2xfrm_addr((struct sadb_address *) ext_hdrs[SADB_EXT_ADDRESS_DST-1], &x->id.daddr); if (ext_hdrs[SADB_X_EXT_SA2-1]) { const struct sadb_x_sa2 *sa2 = ext_hdrs[SADB_X_EXT_SA2-1]; int mode = pfkey_mode_to_xfrm(sa2->sadb_x_sa2_mode); if (mode < 0) { err = -EINVAL; goto out; } x->props.mode = mode; x->props.reqid = sa2->sadb_x_sa2_reqid; } if (ext_hdrs[SADB_EXT_ADDRESS_PROXY-1]) { const struct sadb_address *addr = ext_hdrs[SADB_EXT_ADDRESS_PROXY-1]; /* Nobody uses this, but we try. */ x->sel.family = pfkey_sadb_addr2xfrm_addr(addr, &x->sel.saddr); x->sel.prefixlen_s = addr->sadb_address_prefixlen; } if (!x->sel.family) x->sel.family = x->props.family; if (ext_hdrs[SADB_X_EXT_NAT_T_TYPE-1]) { const struct sadb_x_nat_t_type* n_type; struct xfrm_encap_tmpl *natt; x->encap = kmalloc(sizeof(*x->encap), GFP_KERNEL); if (!x->encap) { err = -ENOMEM; goto out; } natt = x->encap; n_type = ext_hdrs[SADB_X_EXT_NAT_T_TYPE-1]; natt->encap_type = n_type->sadb_x_nat_t_type_type; if (ext_hdrs[SADB_X_EXT_NAT_T_SPORT-1]) { const struct sadb_x_nat_t_port *n_port = ext_hdrs[SADB_X_EXT_NAT_T_SPORT-1]; natt->encap_sport = n_port->sadb_x_nat_t_port_port; } if (ext_hdrs[SADB_X_EXT_NAT_T_DPORT-1]) { const struct sadb_x_nat_t_port *n_port = ext_hdrs[SADB_X_EXT_NAT_T_DPORT-1]; natt->encap_dport = n_port->sadb_x_nat_t_port_port; } memset(&natt->encap_oa, 0, sizeof(natt->encap_oa)); } err = xfrm_init_state(x); if (err) goto out; x->km.seq = hdr->sadb_msg_seq; return x; out: x->km.state = XFRM_STATE_DEAD; xfrm_state_put(x); return ERR_PTR(err); } static int pfkey_reserved(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { return -EOPNOTSUPP; } static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); struct sk_buff *resp_skb; struct sadb_x_sa2 *sa2; struct sadb_address *saddr, *daddr; struct sadb_msg *out_hdr; struct sadb_spirange *range; struct xfrm_state *x = NULL; int mode; int err; u32 min_spi, max_spi; u32 reqid; u8 proto; unsigned short family; xfrm_address_t *xsaddr = NULL, *xdaddr = NULL; if (!present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1])) return -EINVAL; proto = pfkey_satype2proto(hdr->sadb_msg_satype); if (proto == 0) return -EINVAL; if ((sa2 = ext_hdrs[SADB_X_EXT_SA2-1]) != NULL) { mode = pfkey_mode_to_xfrm(sa2->sadb_x_sa2_mode); if (mode < 0) return -EINVAL; reqid = sa2->sadb_x_sa2_reqid; } else { mode = 0; reqid = 0; } saddr = ext_hdrs[SADB_EXT_ADDRESS_SRC-1]; daddr = ext_hdrs[SADB_EXT_ADDRESS_DST-1]; family = ((struct sockaddr *)(saddr + 1))->sa_family; switch (family) { case AF_INET: xdaddr = (xfrm_address_t *)&((struct sockaddr_in *)(daddr + 1))->sin_addr.s_addr; xsaddr = (xfrm_address_t *)&((struct sockaddr_in *)(saddr + 1))->sin_addr.s_addr; break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: xdaddr = (xfrm_address_t *)&((struct sockaddr_in6 *)(daddr + 1))->sin6_addr; xsaddr = (xfrm_address_t *)&((struct sockaddr_in6 *)(saddr + 1))->sin6_addr; break; #endif } if (hdr->sadb_msg_seq) { x = xfrm_find_acq_byseq(net, DUMMY_MARK, hdr->sadb_msg_seq); if (x && !xfrm_addr_equal(&x->id.daddr, xdaddr, family)) { xfrm_state_put(x); x = NULL; } } if (!x) x = xfrm_find_acq(net, &dummy_mark, mode, reqid, 0, proto, xdaddr, xsaddr, 1, family); if (x == NULL) return -ENOENT; min_spi = 0x100; max_spi = 0x0fffffff; range = ext_hdrs[SADB_EXT_SPIRANGE-1]; if (range) { min_spi = range->sadb_spirange_min; max_spi = range->sadb_spirange_max; } err = verify_spi_info(x->id.proto, min_spi, max_spi); if (err) { xfrm_state_put(x); return err; } err = xfrm_alloc_spi(x, min_spi, max_spi); resp_skb = err ? ERR_PTR(err) : pfkey_xfrm_state2msg(x); if (IS_ERR(resp_skb)) { xfrm_state_put(x); return PTR_ERR(resp_skb); } out_hdr = (struct sadb_msg *) resp_skb->data; out_hdr->sadb_msg_version = hdr->sadb_msg_version; out_hdr->sadb_msg_type = SADB_GETSPI; out_hdr->sadb_msg_satype = pfkey_proto2satype(proto); out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_reserved = 0; out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; xfrm_state_put(x); pfkey_broadcast(resp_skb, GFP_KERNEL, BROADCAST_ONE, sk, net); return 0; } static int pfkey_acquire(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); struct xfrm_state *x; if (hdr->sadb_msg_len != sizeof(struct sadb_msg)/8) return -EOPNOTSUPP; if (hdr->sadb_msg_seq == 0 || hdr->sadb_msg_errno == 0) return 0; x = xfrm_find_acq_byseq(net, DUMMY_MARK, hdr->sadb_msg_seq); if (x == NULL) return 0; spin_lock_bh(&x->lock); if (x->km.state == XFRM_STATE_ACQ) x->km.state = XFRM_STATE_ERROR; spin_unlock_bh(&x->lock); xfrm_state_put(x); return 0; } static inline int event2poltype(int event) { switch (event) { case XFRM_MSG_DELPOLICY: return SADB_X_SPDDELETE; case XFRM_MSG_NEWPOLICY: return SADB_X_SPDADD; case XFRM_MSG_UPDPOLICY: return SADB_X_SPDUPDATE; case XFRM_MSG_POLEXPIRE: // return SADB_X_SPDEXPIRE; default: pr_err("pfkey: Unknown policy event %d\n", event); break; } return 0; } static inline int event2keytype(int event) { switch (event) { case XFRM_MSG_DELSA: return SADB_DELETE; case XFRM_MSG_NEWSA: return SADB_ADD; case XFRM_MSG_UPDSA: return SADB_UPDATE; case XFRM_MSG_EXPIRE: return SADB_EXPIRE; default: pr_err("pfkey: Unknown SA event %d\n", event); break; } return 0; } /* ADD/UPD/DEL */ static int key_notify_sa(struct xfrm_state *x, const struct km_event *c) { struct sk_buff *skb; struct sadb_msg *hdr; skb = pfkey_xfrm_state2msg(x); if (IS_ERR(skb)) return PTR_ERR(skb); hdr = (struct sadb_msg *) skb->data; hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_type = event2keytype(c->event); hdr->sadb_msg_satype = pfkey_proto2satype(x->id.proto); hdr->sadb_msg_errno = 0; hdr->sadb_msg_reserved = 0; hdr->sadb_msg_seq = c->seq; hdr->sadb_msg_pid = c->portid; pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, xs_net(x)); return 0; } static int pfkey_add(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); struct xfrm_state *x; int err; struct km_event c; x = pfkey_msg2xfrm_state(net, hdr, ext_hdrs); if (IS_ERR(x)) return PTR_ERR(x); xfrm_state_hold(x); if (hdr->sadb_msg_type == SADB_ADD) err = xfrm_state_add(x); else err = xfrm_state_update(x); xfrm_audit_state_add(x, err ? 0 : 1, true); if (err < 0) { x->km.state = XFRM_STATE_DEAD; __xfrm_state_put(x); goto out; } if (hdr->sadb_msg_type == SADB_ADD) c.event = XFRM_MSG_NEWSA; else c.event = XFRM_MSG_UPDSA; c.seq = hdr->sadb_msg_seq; c.portid = hdr->sadb_msg_pid; km_state_notify(x, &c); out: xfrm_state_put(x); return err; } static int pfkey_delete(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); struct xfrm_state *x; struct km_event c; int err; if (!ext_hdrs[SADB_EXT_SA-1] || !present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1])) return -EINVAL; x = pfkey_xfrm_state_lookup(net, hdr, ext_hdrs); if (x == NULL) return -ESRCH; if ((err = security_xfrm_state_delete(x))) goto out; if (xfrm_state_kern(x)) { err = -EPERM; goto out; } err = xfrm_state_delete(x); if (err < 0) goto out; c.seq = hdr->sadb_msg_seq; c.portid = hdr->sadb_msg_pid; c.event = XFRM_MSG_DELSA; km_state_notify(x, &c); out: xfrm_audit_state_delete(x, err ? 0 : 1, true); xfrm_state_put(x); return err; } static int pfkey_get(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); __u8 proto; struct sk_buff *out_skb; struct sadb_msg *out_hdr; struct xfrm_state *x; if (!ext_hdrs[SADB_EXT_SA-1] || !present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1])) return -EINVAL; x = pfkey_xfrm_state_lookup(net, hdr, ext_hdrs); if (x == NULL) return -ESRCH; out_skb = pfkey_xfrm_state2msg(x); proto = x->id.proto; xfrm_state_put(x); if (IS_ERR(out_skb)) return PTR_ERR(out_skb); out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = hdr->sadb_msg_version; out_hdr->sadb_msg_type = SADB_GET; out_hdr->sadb_msg_satype = pfkey_proto2satype(proto); out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_reserved = 0; out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk, sock_net(sk)); return 0; } static struct sk_buff *compose_sadb_supported(const struct sadb_msg *orig, gfp_t allocation) { struct sk_buff *skb; struct sadb_msg *hdr; int len, auth_len, enc_len, i; auth_len = xfrm_count_pfkey_auth_supported(); if (auth_len) { auth_len *= sizeof(struct sadb_alg); auth_len += sizeof(struct sadb_supported); } enc_len = xfrm_count_pfkey_enc_supported(); if (enc_len) { enc_len *= sizeof(struct sadb_alg); enc_len += sizeof(struct sadb_supported); } len = enc_len + auth_len + sizeof(struct sadb_msg); skb = alloc_skb(len + 16, allocation); if (!skb) goto out_put_algs; hdr = skb_put(skb, sizeof(*hdr)); pfkey_hdr_dup(hdr, orig); hdr->sadb_msg_errno = 0; hdr->sadb_msg_len = len / sizeof(uint64_t); if (auth_len) { struct sadb_supported *sp; struct sadb_alg *ap; sp = skb_put(skb, auth_len); ap = (struct sadb_alg *) (sp + 1); sp->sadb_supported_len = auth_len / sizeof(uint64_t); sp->sadb_supported_exttype = SADB_EXT_SUPPORTED_AUTH; for (i = 0; ; i++) { struct xfrm_algo_desc *aalg = xfrm_aalg_get_byidx(i); if (!aalg) break; if (!aalg->pfkey_supported) continue; if (aalg->available) *ap++ = aalg->desc; } } if (enc_len) { struct sadb_supported *sp; struct sadb_alg *ap; sp = skb_put(skb, enc_len); ap = (struct sadb_alg *) (sp + 1); sp->sadb_supported_len = enc_len / sizeof(uint64_t); sp->sadb_supported_exttype = SADB_EXT_SUPPORTED_ENCRYPT; for (i = 0; ; i++) { struct xfrm_algo_desc *ealg = xfrm_ealg_get_byidx(i); if (!ealg) break; if (!ealg->pfkey_supported) continue; if (ealg->available) *ap++ = ealg->desc; } } out_put_algs: return skb; } static int pfkey_register(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct pfkey_sock *pfk = pfkey_sk(sk); struct sk_buff *supp_skb; if (hdr->sadb_msg_satype > SADB_SATYPE_MAX) return -EINVAL; if (hdr->sadb_msg_satype != SADB_SATYPE_UNSPEC) { if (pfk->registered&(1<<hdr->sadb_msg_satype)) return -EEXIST; pfk->registered |= (1<<hdr->sadb_msg_satype); } mutex_lock(&pfkey_mutex); xfrm_probe_algs(); supp_skb = compose_sadb_supported(hdr, GFP_KERNEL | __GFP_ZERO); mutex_unlock(&pfkey_mutex); if (!supp_skb) { if (hdr->sadb_msg_satype != SADB_SATYPE_UNSPEC) pfk->registered &= ~(1<<hdr->sadb_msg_satype); return -ENOBUFS; } pfkey_broadcast(supp_skb, GFP_KERNEL, BROADCAST_REGISTERED, sk, sock_net(sk)); return 0; } static int unicast_flush_resp(struct sock *sk, const struct sadb_msg *ihdr) { struct sk_buff *skb; struct sadb_msg *hdr; skb = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_ATOMIC); if (!skb) return -ENOBUFS; hdr = skb_put_data(skb, ihdr, sizeof(struct sadb_msg)); hdr->sadb_msg_errno = (uint8_t) 0; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ONE, sk, sock_net(sk)); } static int key_notify_sa_flush(const struct km_event *c) { struct sk_buff *skb; struct sadb_msg *hdr; skb = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_ATOMIC); if (!skb) return -ENOBUFS; hdr = skb_put(skb, sizeof(struct sadb_msg)); hdr->sadb_msg_satype = pfkey_proto2satype(c->data.proto); hdr->sadb_msg_type = SADB_FLUSH; hdr->sadb_msg_seq = c->seq; hdr->sadb_msg_pid = c->portid; hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_errno = (uint8_t) 0; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); hdr->sadb_msg_reserved = 0; pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net); return 0; } static int pfkey_flush(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); unsigned int proto; struct km_event c; int err, err2; proto = pfkey_satype2proto(hdr->sadb_msg_satype); if (proto == 0) return -EINVAL; err = xfrm_state_flush(net, proto, true, false); err2 = unicast_flush_resp(sk, hdr); if (err || err2) { if (err == -ESRCH) /* empty table - go quietly */ err = 0; return err ? err : err2; } c.data.proto = proto; c.seq = hdr->sadb_msg_seq; c.portid = hdr->sadb_msg_pid; c.event = XFRM_MSG_FLUSHSA; c.net = net; km_state_notify(NULL, &c); return 0; } static int dump_sa(struct xfrm_state *x, int count, void *ptr) { struct pfkey_sock *pfk = ptr; struct sk_buff *out_skb; struct sadb_msg *out_hdr; if (!pfkey_can_dump(&pfk->sk)) return -ENOBUFS; out_skb = pfkey_xfrm_state2msg(x); if (IS_ERR(out_skb)) return PTR_ERR(out_skb); out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = pfk->dump.msg_version; out_hdr->sadb_msg_type = SADB_DUMP; out_hdr->sadb_msg_satype = pfkey_proto2satype(x->id.proto); out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_reserved = 0; out_hdr->sadb_msg_seq = count + 1; out_hdr->sadb_msg_pid = pfk->dump.msg_portid; if (pfk->dump.skb) pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE, &pfk->sk, sock_net(&pfk->sk)); pfk->dump.skb = out_skb; return 0; } static int pfkey_dump_sa(struct pfkey_sock *pfk) { struct net *net = sock_net(&pfk->sk); return xfrm_state_walk(net, &pfk->dump.u.state, dump_sa, (void *) pfk); } static void pfkey_dump_sa_done(struct pfkey_sock *pfk) { struct net *net = sock_net(&pfk->sk); xfrm_state_walk_done(&pfk->dump.u.state, net); } static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { u8 proto; struct xfrm_address_filter *filter = NULL; struct pfkey_sock *pfk = pfkey_sk(sk); mutex_lock(&pfk->dump_lock); if (pfk->dump.dump != NULL) { mutex_unlock(&pfk->dump_lock); return -EBUSY; } proto = pfkey_satype2proto(hdr->sadb_msg_satype); if (proto == 0) { mutex_unlock(&pfk->dump_lock); return -EINVAL; } if (ext_hdrs[SADB_X_EXT_FILTER - 1]) { struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1]; if ((xfilter->sadb_x_filter_splen > (sizeof(xfrm_address_t) << 3)) || (xfilter->sadb_x_filter_dplen > (sizeof(xfrm_address_t) << 3))) { mutex_unlock(&pfk->dump_lock); return -EINVAL; } filter = kmalloc(sizeof(*filter), GFP_KERNEL); if (filter == NULL) { mutex_unlock(&pfk->dump_lock); return -ENOMEM; } memcpy(&filter->saddr, &xfilter->sadb_x_filter_saddr, sizeof(xfrm_address_t)); memcpy(&filter->daddr, &xfilter->sadb_x_filter_daddr, sizeof(xfrm_address_t)); filter->family = xfilter->sadb_x_filter_family; filter->splen = xfilter->sadb_x_filter_splen; filter->dplen = xfilter->sadb_x_filter_dplen; } pfk->dump.msg_version = hdr->sadb_msg_version; pfk->dump.msg_portid = hdr->sadb_msg_pid; pfk->dump.dump = pfkey_dump_sa; pfk->dump.done = pfkey_dump_sa_done; xfrm_state_walk_init(&pfk->dump.u.state, proto, filter); mutex_unlock(&pfk->dump_lock); return pfkey_do_dump(pfk); } static int pfkey_promisc(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct pfkey_sock *pfk = pfkey_sk(sk); int satype = hdr->sadb_msg_satype; bool reset_errno = false; if (hdr->sadb_msg_len == (sizeof(*hdr) / sizeof(uint64_t))) { reset_errno = true; if (satype != 0 && satype != 1) return -EINVAL; pfk->promisc = satype; } if (reset_errno && skb_cloned(skb)) skb = skb_copy(skb, GFP_KERNEL); else skb = skb_clone(skb, GFP_KERNEL); if (reset_errno && skb) { struct sadb_msg *new_hdr = (struct sadb_msg *) skb->data; new_hdr->sadb_msg_errno = 0; } pfkey_broadcast(skb, GFP_KERNEL, BROADCAST_ALL, NULL, sock_net(sk)); return 0; } static int check_reqid(struct xfrm_policy *xp, int dir, int count, void *ptr) { int i; u32 reqid = *(u32*)ptr; for (i=0; i<xp->xfrm_nr; i++) { if (xp->xfrm_vec[i].reqid == reqid) return -EEXIST; } return 0; } static u32 gen_reqid(struct net *net) { struct xfrm_policy_walk walk; u32 start; int rc; static u32 reqid = IPSEC_MANUAL_REQID_MAX; start = reqid; do { ++reqid; if (reqid == 0) reqid = IPSEC_MANUAL_REQID_MAX+1; xfrm_policy_walk_init(&walk, XFRM_POLICY_TYPE_MAIN); rc = xfrm_policy_walk(net, &walk, check_reqid, (void*)&reqid); xfrm_policy_walk_done(&walk, net); if (rc != -EEXIST) return reqid; } while (reqid != start); return 0; } static int parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_policy *pol, struct sadb_x_ipsecrequest *rq) { struct net *net = xp_net(xp); struct xfrm_tmpl *t = xp->xfrm_vec + xp->xfrm_nr; int mode; if (xp->xfrm_nr >= XFRM_MAX_DEPTH) return -ELOOP; if (rq->sadb_x_ipsecrequest_mode == 0) return -EINVAL; if (!xfrm_id_proto_valid(rq->sadb_x_ipsecrequest_proto)) return -EINVAL; t->id.proto = rq->sadb_x_ipsecrequest_proto; if ((mode = pfkey_mode_to_xfrm(rq->sadb_x_ipsecrequest_mode)) < 0) return -EINVAL; t->mode = mode; if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_USE) { if ((mode == XFRM_MODE_TUNNEL || mode == XFRM_MODE_BEET) && pol->sadb_x_policy_dir == IPSEC_DIR_OUTBOUND) return -EINVAL; t->optional = 1; } else if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_UNIQUE) { t->reqid = rq->sadb_x_ipsecrequest_reqid; if (t->reqid > IPSEC_MANUAL_REQID_MAX) t->reqid = 0; if (!t->reqid && !(t->reqid = gen_reqid(net))) return -ENOBUFS; } /* addresses present only in tunnel mode */ if (t->mode == XFRM_MODE_TUNNEL) { int err; err = parse_sockaddr_pair( (struct sockaddr *)(rq + 1), rq->sadb_x_ipsecrequest_len - sizeof(*rq), &t->saddr, &t->id.daddr, &t->encap_family); if (err) return err; } else t->encap_family = xp->family; /* No way to set this via kame pfkey */ t->allalgs = 1; xp->xfrm_nr++; return 0; } static int parse_ipsecrequests(struct xfrm_policy *xp, struct sadb_x_policy *pol) { int err; int len = pol->sadb_x_policy_len*8 - sizeof(struct sadb_x_policy); struct sadb_x_ipsecrequest *rq = (void*)(pol+1); if (pol->sadb_x_policy_len * 8 < sizeof(struct sadb_x_policy)) return -EINVAL; while (len >= sizeof(*rq)) { if (len < rq->sadb_x_ipsecrequest_len || rq->sadb_x_ipsecrequest_len < sizeof(*rq)) return -EINVAL; if ((err = parse_ipsecrequest(xp, pol, rq)) < 0) return err; len -= rq->sadb_x_ipsecrequest_len; rq = (void*)((u8*)rq + rq->sadb_x_ipsecrequest_len); } return 0; } static inline int pfkey_xfrm_policy2sec_ctx_size(const struct xfrm_policy *xp) { struct xfrm_sec_ctx *xfrm_ctx = xp->security; if (xfrm_ctx) { int len = sizeof(struct sadb_x_sec_ctx); len += xfrm_ctx->ctx_len; return PFKEY_ALIGN8(len); } return 0; } static int pfkey_xfrm_policy2msg_size(const struct xfrm_policy *xp) { const struct xfrm_tmpl *t; int sockaddr_size = pfkey_sockaddr_size(xp->family); int socklen = 0; int i; for (i=0; i<xp->xfrm_nr; i++) { t = xp->xfrm_vec + i; socklen += pfkey_sockaddr_len(t->encap_family); } return sizeof(struct sadb_msg) + (sizeof(struct sadb_lifetime) * 3) + (sizeof(struct sadb_address) * 2) + (sockaddr_size * 2) + sizeof(struct sadb_x_policy) + (xp->xfrm_nr * sizeof(struct sadb_x_ipsecrequest)) + (socklen * 2) + pfkey_xfrm_policy2sec_ctx_size(xp); } static struct sk_buff * pfkey_xfrm_policy2msg_prep(const struct xfrm_policy *xp) { struct sk_buff *skb; int size; size = pfkey_xfrm_policy2msg_size(xp); skb = alloc_skb(size + 16, GFP_ATOMIC); if (skb == NULL) return ERR_PTR(-ENOBUFS); return skb; } static int pfkey_xfrm_policy2msg(struct sk_buff *skb, const struct xfrm_policy *xp, int dir) { struct sadb_msg *hdr; struct sadb_address *addr; struct sadb_lifetime *lifetime; struct sadb_x_policy *pol; struct sadb_x_sec_ctx *sec_ctx; struct xfrm_sec_ctx *xfrm_ctx; int i; int size; int sockaddr_size = pfkey_sockaddr_size(xp->family); int socklen = pfkey_sockaddr_len(xp->family); size = pfkey_xfrm_policy2msg_size(xp); /* call should fill header later */ hdr = skb_put(skb, sizeof(struct sadb_msg)); memset(hdr, 0, size); /* XXX do we need this ? */ /* src address */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_SRC; addr->sadb_address_proto = pfkey_proto_from_xfrm(xp->selector.proto); addr->sadb_address_prefixlen = xp->selector.prefixlen_s; addr->sadb_address_reserved = 0; if (!pfkey_sockaddr_fill(&xp->selector.saddr, xp->selector.sport, (struct sockaddr *) (addr + 1), xp->family)) BUG(); /* dst address */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_DST; addr->sadb_address_proto = pfkey_proto_from_xfrm(xp->selector.proto); addr->sadb_address_prefixlen = xp->selector.prefixlen_d; addr->sadb_address_reserved = 0; pfkey_sockaddr_fill(&xp->selector.daddr, xp->selector.dport, (struct sockaddr *) (addr + 1), xp->family); /* hard time */ lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_HARD; lifetime->sadb_lifetime_allocations = _X2KEY(xp->lft.hard_packet_limit); lifetime->sadb_lifetime_bytes = _X2KEY(xp->lft.hard_byte_limit); lifetime->sadb_lifetime_addtime = xp->lft.hard_add_expires_seconds; lifetime->sadb_lifetime_usetime = xp->lft.hard_use_expires_seconds; /* soft time */ lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_SOFT; lifetime->sadb_lifetime_allocations = _X2KEY(xp->lft.soft_packet_limit); lifetime->sadb_lifetime_bytes = _X2KEY(xp->lft.soft_byte_limit); lifetime->sadb_lifetime_addtime = xp->lft.soft_add_expires_seconds; lifetime->sadb_lifetime_usetime = xp->lft.soft_use_expires_seconds; /* current time */ lifetime = skb_put(skb, sizeof(struct sadb_lifetime)); lifetime->sadb_lifetime_len = sizeof(struct sadb_lifetime)/sizeof(uint64_t); lifetime->sadb_lifetime_exttype = SADB_EXT_LIFETIME_CURRENT; lifetime->sadb_lifetime_allocations = xp->curlft.packets; lifetime->sadb_lifetime_bytes = xp->curlft.bytes; lifetime->sadb_lifetime_addtime = xp->curlft.add_time; lifetime->sadb_lifetime_usetime = xp->curlft.use_time; pol = skb_put(skb, sizeof(struct sadb_x_policy)); pol->sadb_x_policy_len = sizeof(struct sadb_x_policy)/sizeof(uint64_t); pol->sadb_x_policy_exttype = SADB_X_EXT_POLICY; pol->sadb_x_policy_type = IPSEC_POLICY_DISCARD; if (xp->action == XFRM_POLICY_ALLOW) { if (xp->xfrm_nr) pol->sadb_x_policy_type = IPSEC_POLICY_IPSEC; else pol->sadb_x_policy_type = IPSEC_POLICY_NONE; } pol->sadb_x_policy_dir = dir+1; pol->sadb_x_policy_reserved = 0; pol->sadb_x_policy_id = xp->index; pol->sadb_x_policy_priority = xp->priority; for (i=0; i<xp->xfrm_nr; i++) { const struct xfrm_tmpl *t = xp->xfrm_vec + i; struct sadb_x_ipsecrequest *rq; int req_size; int mode; req_size = sizeof(struct sadb_x_ipsecrequest); if (t->mode == XFRM_MODE_TUNNEL) { socklen = pfkey_sockaddr_len(t->encap_family); req_size += socklen * 2; } else { size -= 2*socklen; } rq = skb_put(skb, req_size); pol->sadb_x_policy_len += req_size/8; memset(rq, 0, sizeof(*rq)); rq->sadb_x_ipsecrequest_len = req_size; rq->sadb_x_ipsecrequest_proto = t->id.proto; if ((mode = pfkey_mode_from_xfrm(t->mode)) < 0) return -EINVAL; rq->sadb_x_ipsecrequest_mode = mode; rq->sadb_x_ipsecrequest_level = IPSEC_LEVEL_REQUIRE; if (t->reqid) rq->sadb_x_ipsecrequest_level = IPSEC_LEVEL_UNIQUE; if (t->optional) rq->sadb_x_ipsecrequest_level = IPSEC_LEVEL_USE; rq->sadb_x_ipsecrequest_reqid = t->reqid; if (t->mode == XFRM_MODE_TUNNEL) { u8 *sa = (void *)(rq + 1); pfkey_sockaddr_fill(&t->saddr, 0, (struct sockaddr *)sa, t->encap_family); pfkey_sockaddr_fill(&t->id.daddr, 0, (struct sockaddr *) (sa + socklen), t->encap_family); } } /* security context */ if ((xfrm_ctx = xp->security)) { int ctx_size = pfkey_xfrm_policy2sec_ctx_size(xp); sec_ctx = skb_put(skb, ctx_size); sec_ctx->sadb_x_sec_len = ctx_size / sizeof(uint64_t); sec_ctx->sadb_x_sec_exttype = SADB_X_EXT_SEC_CTX; sec_ctx->sadb_x_ctx_doi = xfrm_ctx->ctx_doi; sec_ctx->sadb_x_ctx_alg = xfrm_ctx->ctx_alg; sec_ctx->sadb_x_ctx_len = xfrm_ctx->ctx_len; memcpy(sec_ctx + 1, xfrm_ctx->ctx_str, xfrm_ctx->ctx_len); } hdr->sadb_msg_len = size / sizeof(uint64_t); hdr->sadb_msg_reserved = refcount_read(&xp->refcnt); return 0; } static int key_notify_policy(struct xfrm_policy *xp, int dir, const struct km_event *c) { struct sk_buff *out_skb; struct sadb_msg *out_hdr; int err; out_skb = pfkey_xfrm_policy2msg_prep(xp); if (IS_ERR(out_skb)) return PTR_ERR(out_skb); err = pfkey_xfrm_policy2msg(out_skb, xp, dir); if (err < 0) { kfree_skb(out_skb); return err; } out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = PF_KEY_V2; if (c->data.byid && c->event == XFRM_MSG_DELPOLICY) out_hdr->sadb_msg_type = SADB_X_SPDDELETE2; else out_hdr->sadb_msg_type = event2poltype(c->event); out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_seq = c->seq; out_hdr->sadb_msg_pid = c->portid; pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, NULL, xp_net(xp)); return 0; } static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); int err = 0; struct sadb_lifetime *lifetime; struct sadb_address *sa; struct sadb_x_policy *pol; struct xfrm_policy *xp; struct km_event c; struct sadb_x_sec_ctx *sec_ctx; if (!present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1]) || !ext_hdrs[SADB_X_EXT_POLICY-1]) return -EINVAL; pol = ext_hdrs[SADB_X_EXT_POLICY-1]; if (pol->sadb_x_policy_type > IPSEC_POLICY_IPSEC) return -EINVAL; if (!pol->sadb_x_policy_dir || pol->sadb_x_policy_dir >= IPSEC_DIR_MAX) return -EINVAL; xp = xfrm_policy_alloc(net, GFP_KERNEL); if (xp == NULL) return -ENOBUFS; xp->action = (pol->sadb_x_policy_type == IPSEC_POLICY_DISCARD ? XFRM_POLICY_BLOCK : XFRM_POLICY_ALLOW); xp->priority = pol->sadb_x_policy_priority; sa = ext_hdrs[SADB_EXT_ADDRESS_SRC-1]; xp->family = pfkey_sadb_addr2xfrm_addr(sa, &xp->selector.saddr); xp->selector.family = xp->family; xp->selector.prefixlen_s = sa->sadb_address_prefixlen; xp->selector.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); xp->selector.sport = ((struct sockaddr_in *)(sa+1))->sin_port; if (xp->selector.sport) xp->selector.sport_mask = htons(0xffff); sa = ext_hdrs[SADB_EXT_ADDRESS_DST-1]; pfkey_sadb_addr2xfrm_addr(sa, &xp->selector.daddr); xp->selector.prefixlen_d = sa->sadb_address_prefixlen; /* Amusing, we set this twice. KAME apps appear to set same value * in both addresses. */ xp->selector.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); xp->selector.dport = ((struct sockaddr_in *)(sa+1))->sin_port; if (xp->selector.dport) xp->selector.dport_mask = htons(0xffff); sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1]; if (sec_ctx != NULL) { struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_KERNEL); if (!uctx) { err = -ENOBUFS; goto out; } err = security_xfrm_policy_alloc(&xp->security, uctx, GFP_KERNEL); kfree(uctx); if (err) goto out; } xp->lft.soft_byte_limit = XFRM_INF; xp->lft.hard_byte_limit = XFRM_INF; xp->lft.soft_packet_limit = XFRM_INF; xp->lft.hard_packet_limit = XFRM_INF; if ((lifetime = ext_hdrs[SADB_EXT_LIFETIME_HARD-1]) != NULL) { xp->lft.hard_packet_limit = _KEY2X(lifetime->sadb_lifetime_allocations); xp->lft.hard_byte_limit = _KEY2X(lifetime->sadb_lifetime_bytes); xp->lft.hard_add_expires_seconds = lifetime->sadb_lifetime_addtime; xp->lft.hard_use_expires_seconds = lifetime->sadb_lifetime_usetime; } if ((lifetime = ext_hdrs[SADB_EXT_LIFETIME_SOFT-1]) != NULL) { xp->lft.soft_packet_limit = _KEY2X(lifetime->sadb_lifetime_allocations); xp->lft.soft_byte_limit = _KEY2X(lifetime->sadb_lifetime_bytes); xp->lft.soft_add_expires_seconds = lifetime->sadb_lifetime_addtime; xp->lft.soft_use_expires_seconds = lifetime->sadb_lifetime_usetime; } xp->xfrm_nr = 0; if (pol->sadb_x_policy_type == IPSEC_POLICY_IPSEC && (err = parse_ipsecrequests(xp, pol)) < 0) goto out; err = xfrm_policy_insert(pol->sadb_x_policy_dir-1, xp, hdr->sadb_msg_type != SADB_X_SPDUPDATE); xfrm_audit_policy_add(xp, err ? 0 : 1, true); if (err) goto out; if (hdr->sadb_msg_type == SADB_X_SPDUPDATE) c.event = XFRM_MSG_UPDPOLICY; else c.event = XFRM_MSG_NEWPOLICY; c.seq = hdr->sadb_msg_seq; c.portid = hdr->sadb_msg_pid; km_policy_notify(xp, pol->sadb_x_policy_dir-1, &c); xfrm_pol_put(xp); return 0; out: xp->walk.dead = 1; xfrm_policy_destroy(xp); return err; } static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); int err; struct sadb_address *sa; struct sadb_x_policy *pol; struct xfrm_policy *xp; struct xfrm_selector sel; struct km_event c; struct sadb_x_sec_ctx *sec_ctx; struct xfrm_sec_ctx *pol_ctx = NULL; if (!present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1]) || !ext_hdrs[SADB_X_EXT_POLICY-1]) return -EINVAL; pol = ext_hdrs[SADB_X_EXT_POLICY-1]; if (!pol->sadb_x_policy_dir || pol->sadb_x_policy_dir >= IPSEC_DIR_MAX) return -EINVAL; memset(&sel, 0, sizeof(sel)); sa = ext_hdrs[SADB_EXT_ADDRESS_SRC-1]; sel.family = pfkey_sadb_addr2xfrm_addr(sa, &sel.saddr); sel.prefixlen_s = sa->sadb_address_prefixlen; sel.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); sel.sport = ((struct sockaddr_in *)(sa+1))->sin_port; if (sel.sport) sel.sport_mask = htons(0xffff); sa = ext_hdrs[SADB_EXT_ADDRESS_DST-1]; pfkey_sadb_addr2xfrm_addr(sa, &sel.daddr); sel.prefixlen_d = sa->sadb_address_prefixlen; sel.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); sel.dport = ((struct sockaddr_in *)(sa+1))->sin_port; if (sel.dport) sel.dport_mask = htons(0xffff); sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1]; if (sec_ctx != NULL) { struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_KERNEL); if (!uctx) return -ENOMEM; err = security_xfrm_policy_alloc(&pol_ctx, uctx, GFP_KERNEL); kfree(uctx); if (err) return err; } xp = xfrm_policy_bysel_ctx(net, &dummy_mark, 0, XFRM_POLICY_TYPE_MAIN, pol->sadb_x_policy_dir - 1, &sel, pol_ctx, 1, &err); security_xfrm_policy_free(pol_ctx); if (xp == NULL) return -ENOENT; xfrm_audit_policy_delete(xp, err ? 0 : 1, true); if (err) goto out; c.seq = hdr->sadb_msg_seq; c.portid = hdr->sadb_msg_pid; c.data.byid = 0; c.event = XFRM_MSG_DELPOLICY; km_policy_notify(xp, pol->sadb_x_policy_dir-1, &c); out: xfrm_pol_put(xp); return err; } static int key_pol_get_resp(struct sock *sk, struct xfrm_policy *xp, const struct sadb_msg *hdr, int dir) { int err; struct sk_buff *out_skb; struct sadb_msg *out_hdr; err = 0; out_skb = pfkey_xfrm_policy2msg_prep(xp); if (IS_ERR(out_skb)) { err = PTR_ERR(out_skb); goto out; } err = pfkey_xfrm_policy2msg(out_skb, xp, dir); if (err < 0) { kfree_skb(out_skb); goto out; } out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = hdr->sadb_msg_version; out_hdr->sadb_msg_type = hdr->sadb_msg_type; out_hdr->sadb_msg_satype = 0; out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk, xp_net(xp)); err = 0; out: return err; } static int pfkey_sockaddr_pair_size(sa_family_t family) { return PFKEY_ALIGN8(pfkey_sockaddr_len(family) * 2); } static int parse_sockaddr_pair(struct sockaddr *sa, int ext_len, xfrm_address_t *saddr, xfrm_address_t *daddr, u16 *family) { int af, socklen; if (ext_len < 2 || ext_len < pfkey_sockaddr_pair_size(sa->sa_family)) return -EINVAL; af = pfkey_sockaddr_extract(sa, saddr); if (!af) return -EINVAL; socklen = pfkey_sockaddr_len(af); if (pfkey_sockaddr_extract((struct sockaddr *) (((u8 *)sa) + socklen), daddr) != af) return -EINVAL; *family = af; return 0; } #ifdef CONFIG_NET_KEY_MIGRATE static int ipsecrequests_to_migrate(struct sadb_x_ipsecrequest *rq1, int len, struct xfrm_migrate *m) { int err; struct sadb_x_ipsecrequest *rq2; int mode; if (len < sizeof(*rq1) || len < rq1->sadb_x_ipsecrequest_len || rq1->sadb_x_ipsecrequest_len < sizeof(*rq1)) return -EINVAL; /* old endoints */ err = parse_sockaddr_pair((struct sockaddr *)(rq1 + 1), rq1->sadb_x_ipsecrequest_len - sizeof(*rq1), &m->old_saddr, &m->old_daddr, &m->old_family); if (err) return err; rq2 = (struct sadb_x_ipsecrequest *)((u8 *)rq1 + rq1->sadb_x_ipsecrequest_len); len -= rq1->sadb_x_ipsecrequest_len; if (len <= sizeof(*rq2) || len < rq2->sadb_x_ipsecrequest_len || rq2->sadb_x_ipsecrequest_len < sizeof(*rq2)) return -EINVAL; /* new endpoints */ err = parse_sockaddr_pair((struct sockaddr *)(rq2 + 1), rq2->sadb_x_ipsecrequest_len - sizeof(*rq2), &m->new_saddr, &m->new_daddr, &m->new_family); if (err) return err; if (rq1->sadb_x_ipsecrequest_proto != rq2->sadb_x_ipsecrequest_proto || rq1->sadb_x_ipsecrequest_mode != rq2->sadb_x_ipsecrequest_mode || rq1->sadb_x_ipsecrequest_reqid != rq2->sadb_x_ipsecrequest_reqid) return -EINVAL; m->proto = rq1->sadb_x_ipsecrequest_proto; if ((mode = pfkey_mode_to_xfrm(rq1->sadb_x_ipsecrequest_mode)) < 0) return -EINVAL; m->mode = mode; m->reqid = rq1->sadb_x_ipsecrequest_reqid; return ((int)(rq1->sadb_x_ipsecrequest_len + rq2->sadb_x_ipsecrequest_len)); } static int pfkey_migrate(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { int i, len, ret, err = -EINVAL; u8 dir; struct sadb_address *sa; struct sadb_x_kmaddress *kma; struct sadb_x_policy *pol; struct sadb_x_ipsecrequest *rq; struct xfrm_selector sel; struct xfrm_migrate m[XFRM_MAX_DEPTH]; struct xfrm_kmaddress k; struct net *net = sock_net(sk); if (!present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC - 1], ext_hdrs[SADB_EXT_ADDRESS_DST - 1]) || !ext_hdrs[SADB_X_EXT_POLICY - 1]) { err = -EINVAL; goto out; } kma = ext_hdrs[SADB_X_EXT_KMADDRESS - 1]; pol = ext_hdrs[SADB_X_EXT_POLICY - 1]; if (pol->sadb_x_policy_dir >= IPSEC_DIR_MAX) { err = -EINVAL; goto out; } if (kma) { /* convert sadb_x_kmaddress to xfrm_kmaddress */ k.reserved = kma->sadb_x_kmaddress_reserved; ret = parse_sockaddr_pair((struct sockaddr *)(kma + 1), 8*(kma->sadb_x_kmaddress_len) - sizeof(*kma), &k.local, &k.remote, &k.family); if (ret < 0) { err = ret; goto out; } } dir = pol->sadb_x_policy_dir - 1; memset(&sel, 0, sizeof(sel)); /* set source address info of selector */ sa = ext_hdrs[SADB_EXT_ADDRESS_SRC - 1]; sel.family = pfkey_sadb_addr2xfrm_addr(sa, &sel.saddr); sel.prefixlen_s = sa->sadb_address_prefixlen; sel.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); sel.sport = ((struct sockaddr_in *)(sa + 1))->sin_port; if (sel.sport) sel.sport_mask = htons(0xffff); /* set destination address info of selector */ sa = ext_hdrs[SADB_EXT_ADDRESS_DST - 1]; pfkey_sadb_addr2xfrm_addr(sa, &sel.daddr); sel.prefixlen_d = sa->sadb_address_prefixlen; sel.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); sel.dport = ((struct sockaddr_in *)(sa + 1))->sin_port; if (sel.dport) sel.dport_mask = htons(0xffff); rq = (struct sadb_x_ipsecrequest *)(pol + 1); /* extract ipsecrequests */ i = 0; len = pol->sadb_x_policy_len * 8 - sizeof(struct sadb_x_policy); while (len > 0 && i < XFRM_MAX_DEPTH) { ret = ipsecrequests_to_migrate(rq, len, &m[i]); if (ret < 0) { err = ret; goto out; } else { rq = (struct sadb_x_ipsecrequest *)((u8 *)rq + ret); len -= ret; i++; } } if (!i || len > 0) { err = -EINVAL; goto out; } return xfrm_migrate(&sel, dir, XFRM_POLICY_TYPE_MAIN, m, i, kma ? &k : NULL, net, NULL, 0); out: return err; } #else static int pfkey_migrate(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { return -ENOPROTOOPT; } #endif static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); unsigned int dir; int err = 0, delete; struct sadb_x_policy *pol; struct xfrm_policy *xp; struct km_event c; if ((pol = ext_hdrs[SADB_X_EXT_POLICY-1]) == NULL) return -EINVAL; dir = xfrm_policy_id2dir(pol->sadb_x_policy_id); if (dir >= XFRM_POLICY_MAX) return -EINVAL; delete = (hdr->sadb_msg_type == SADB_X_SPDDELETE2); xp = xfrm_policy_byid(net, &dummy_mark, 0, XFRM_POLICY_TYPE_MAIN, dir, pol->sadb_x_policy_id, delete, &err); if (xp == NULL) return -ENOENT; if (delete) { xfrm_audit_policy_delete(xp, err ? 0 : 1, true); if (err) goto out; c.seq = hdr->sadb_msg_seq; c.portid = hdr->sadb_msg_pid; c.data.byid = 1; c.event = XFRM_MSG_DELPOLICY; km_policy_notify(xp, dir, &c); } else { err = key_pol_get_resp(sk, xp, hdr, dir); } out: xfrm_pol_put(xp); return err; } static int dump_sp(struct xfrm_policy *xp, int dir, int count, void *ptr) { struct pfkey_sock *pfk = ptr; struct sk_buff *out_skb; struct sadb_msg *out_hdr; int err; if (!pfkey_can_dump(&pfk->sk)) return -ENOBUFS; out_skb = pfkey_xfrm_policy2msg_prep(xp); if (IS_ERR(out_skb)) return PTR_ERR(out_skb); err = pfkey_xfrm_policy2msg(out_skb, xp, dir); if (err < 0) { kfree_skb(out_skb); return err; } out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = pfk->dump.msg_version; out_hdr->sadb_msg_type = SADB_X_SPDDUMP; out_hdr->sadb_msg_satype = SADB_SATYPE_UNSPEC; out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_seq = count + 1; out_hdr->sadb_msg_pid = pfk->dump.msg_portid; if (pfk->dump.skb) pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE, &pfk->sk, sock_net(&pfk->sk)); pfk->dump.skb = out_skb; return 0; } static int pfkey_dump_sp(struct pfkey_sock *pfk) { struct net *net = sock_net(&pfk->sk); return xfrm_policy_walk(net, &pfk->dump.u.policy, dump_sp, (void *) pfk); } static void pfkey_dump_sp_done(struct pfkey_sock *pfk) { struct net *net = sock_net((struct sock *)pfk); xfrm_policy_walk_done(&pfk->dump.u.policy, net); } static int pfkey_spddump(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct pfkey_sock *pfk = pfkey_sk(sk); mutex_lock(&pfk->dump_lock); if (pfk->dump.dump != NULL) { mutex_unlock(&pfk->dump_lock); return -EBUSY; } pfk->dump.msg_version = hdr->sadb_msg_version; pfk->dump.msg_portid = hdr->sadb_msg_pid; pfk->dump.dump = pfkey_dump_sp; pfk->dump.done = pfkey_dump_sp_done; xfrm_policy_walk_init(&pfk->dump.u.policy, XFRM_POLICY_TYPE_MAIN); mutex_unlock(&pfk->dump_lock); return pfkey_do_dump(pfk); } static int key_notify_policy_flush(const struct km_event *c) { struct sk_buff *skb_out; struct sadb_msg *hdr; skb_out = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_ATOMIC); if (!skb_out) return -ENOBUFS; hdr = skb_put(skb_out, sizeof(struct sadb_msg)); hdr->sadb_msg_type = SADB_X_SPDFLUSH; hdr->sadb_msg_seq = c->seq; hdr->sadb_msg_pid = c->portid; hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_errno = (uint8_t) 0; hdr->sadb_msg_satype = SADB_SATYPE_UNSPEC; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); hdr->sadb_msg_reserved = 0; pfkey_broadcast(skb_out, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net); return 0; } static int pfkey_spdflush(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { struct net *net = sock_net(sk); struct km_event c; int err, err2; err = xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, true); err2 = unicast_flush_resp(sk, hdr); if (err || err2) { if (err == -ESRCH) /* empty table - old silent behavior */ return 0; return err; } c.data.type = XFRM_POLICY_TYPE_MAIN; c.event = XFRM_MSG_FLUSHPOLICY; c.portid = hdr->sadb_msg_pid; c.seq = hdr->sadb_msg_seq; c.net = net; km_policy_notify(NULL, 0, &c); return 0; } typedef int (*pfkey_handler)(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs); static const pfkey_handler pfkey_funcs[SADB_MAX + 1] = { [SADB_RESERVED] = pfkey_reserved, [SADB_GETSPI] = pfkey_getspi, [SADB_UPDATE] = pfkey_add, [SADB_ADD] = pfkey_add, [SADB_DELETE] = pfkey_delete, [SADB_GET] = pfkey_get, [SADB_ACQUIRE] = pfkey_acquire, [SADB_REGISTER] = pfkey_register, [SADB_EXPIRE] = NULL, [SADB_FLUSH] = pfkey_flush, [SADB_DUMP] = pfkey_dump, [SADB_X_PROMISC] = pfkey_promisc, [SADB_X_PCHANGE] = NULL, [SADB_X_SPDUPDATE] = pfkey_spdadd, [SADB_X_SPDADD] = pfkey_spdadd, [SADB_X_SPDDELETE] = pfkey_spddelete, [SADB_X_SPDGET] = pfkey_spdget, [SADB_X_SPDACQUIRE] = NULL, [SADB_X_SPDDUMP] = pfkey_spddump, [SADB_X_SPDFLUSH] = pfkey_spdflush, [SADB_X_SPDSETIDX] = pfkey_spdadd, [SADB_X_SPDDELETE2] = pfkey_spdget, [SADB_X_MIGRATE] = pfkey_migrate, }; static int pfkey_process(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr) { void *ext_hdrs[SADB_EXT_MAX]; int err; /* Non-zero return value of pfkey_broadcast() does not always signal * an error and even on an actual error we may still want to process * the message so rather ignore the return value. */ pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL, BROADCAST_PROMISC_ONLY, NULL, sock_net(sk)); memset(ext_hdrs, 0, sizeof(ext_hdrs)); err = parse_exthdrs(skb, hdr, ext_hdrs); if (!err) { err = -EOPNOTSUPP; if (pfkey_funcs[hdr->sadb_msg_type]) err = pfkey_funcs[hdr->sadb_msg_type](sk, skb, hdr, ext_hdrs); } return err; } static struct sadb_msg *pfkey_get_base_msg(struct sk_buff *skb, int *errp) { struct sadb_msg *hdr = NULL; if (skb->len < sizeof(*hdr)) { *errp = -EMSGSIZE; } else { hdr = (struct sadb_msg *) skb->data; if (hdr->sadb_msg_version != PF_KEY_V2 || hdr->sadb_msg_reserved != 0 || (hdr->sadb_msg_type <= SADB_RESERVED || hdr->sadb_msg_type > SADB_MAX)) { hdr = NULL; *errp = -EINVAL; } else if (hdr->sadb_msg_len != (skb->len / sizeof(uint64_t)) || hdr->sadb_msg_len < (sizeof(struct sadb_msg) / sizeof(uint64_t))) { hdr = NULL; *errp = -EMSGSIZE; } else { *errp = 0; } } return hdr; } static inline int aalg_tmpl_set(const struct xfrm_tmpl *t, const struct xfrm_algo_desc *d) { unsigned int id = d->desc.sadb_alg_id; if (id >= sizeof(t->aalgos) * 8) return 0; return (t->aalgos >> id) & 1; } static inline int ealg_tmpl_set(const struct xfrm_tmpl *t, const struct xfrm_algo_desc *d) { unsigned int id = d->desc.sadb_alg_id; if (id >= sizeof(t->ealgos) * 8) return 0; return (t->ealgos >> id) & 1; } static int count_ah_combs(const struct xfrm_tmpl *t) { int i, sz = 0; for (i = 0; ; i++) { const struct xfrm_algo_desc *aalg = xfrm_aalg_get_byidx(i); if (!aalg) break; if (!aalg->pfkey_supported) continue; if (aalg_tmpl_set(t, aalg)) sz += sizeof(struct sadb_comb); } return sz + sizeof(struct sadb_prop); } static int count_esp_combs(const struct xfrm_tmpl *t) { int i, k, sz = 0; for (i = 0; ; i++) { const struct xfrm_algo_desc *ealg = xfrm_ealg_get_byidx(i); if (!ealg) break; if (!ealg->pfkey_supported) continue; if (!(ealg_tmpl_set(t, ealg))) continue; for (k = 1; ; k++) { const struct xfrm_algo_desc *aalg = xfrm_aalg_get_byidx(k); if (!aalg) break; if (!aalg->pfkey_supported) continue; if (aalg_tmpl_set(t, aalg)) sz += sizeof(struct sadb_comb); } } return sz + sizeof(struct sadb_prop); } static int dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) { struct sadb_prop *p; int sz = 0; int i; p = skb_put(skb, sizeof(struct sadb_prop)); p->sadb_prop_len = sizeof(struct sadb_prop)/8; p->sadb_prop_exttype = SADB_EXT_PROPOSAL; p->sadb_prop_replay = 32; memset(p->sadb_prop_reserved, 0, sizeof(p->sadb_prop_reserved)); for (i = 0; ; i++) { const struct xfrm_algo_desc *aalg = xfrm_aalg_get_byidx(i); if (!aalg) break; if (!aalg->pfkey_supported) continue; if (aalg_tmpl_set(t, aalg) && aalg->available) { struct sadb_comb *c; c = skb_put_zero(skb, sizeof(struct sadb_comb)); p->sadb_prop_len += sizeof(struct sadb_comb)/8; c->sadb_comb_auth = aalg->desc.sadb_alg_id; c->sadb_comb_auth_minbits = aalg->desc.sadb_alg_minbits; c->sadb_comb_auth_maxbits = aalg->desc.sadb_alg_maxbits; c->sadb_comb_hard_addtime = 24*60*60; c->sadb_comb_soft_addtime = 20*60*60; c->sadb_comb_hard_usetime = 8*60*60; c->sadb_comb_soft_usetime = 7*60*60; sz += sizeof(*c); } } return sz + sizeof(*p); } static int dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) { struct sadb_prop *p; int sz = 0; int i, k; p = skb_put(skb, sizeof(struct sadb_prop)); p->sadb_prop_len = sizeof(struct sadb_prop)/8; p->sadb_prop_exttype = SADB_EXT_PROPOSAL; p->sadb_prop_replay = 32; memset(p->sadb_prop_reserved, 0, sizeof(p->sadb_prop_reserved)); for (i=0; ; i++) { const struct xfrm_algo_desc *ealg = xfrm_ealg_get_byidx(i); if (!ealg) break; if (!ealg->pfkey_supported) continue; if (!(ealg_tmpl_set(t, ealg) && ealg->available)) continue; for (k = 1; ; k++) { struct sadb_comb *c; const struct xfrm_algo_desc *aalg = xfrm_aalg_get_byidx(k); if (!aalg) break; if (!aalg->pfkey_supported) continue; if (!(aalg_tmpl_set(t, aalg) && aalg->available)) continue; c = skb_put(skb, sizeof(struct sadb_comb)); memset(c, 0, sizeof(*c)); p->sadb_prop_len += sizeof(struct sadb_comb)/8; c->sadb_comb_auth = aalg->desc.sadb_alg_id; c->sadb_comb_auth_minbits = aalg->desc.sadb_alg_minbits; c->sadb_comb_auth_maxbits = aalg->desc.sadb_alg_maxbits; c->sadb_comb_encrypt = ealg->desc.sadb_alg_id; c->sadb_comb_encrypt_minbits = ealg->desc.sadb_alg_minbits; c->sadb_comb_encrypt_maxbits = ealg->desc.sadb_alg_maxbits; c->sadb_comb_hard_addtime = 24*60*60; c->sadb_comb_soft_addtime = 20*60*60; c->sadb_comb_hard_usetime = 8*60*60; c->sadb_comb_soft_usetime = 7*60*60; sz += sizeof(*c); } } return sz + sizeof(*p); } static int key_notify_policy_expire(struct xfrm_policy *xp, const struct km_event *c) { return 0; } static int key_notify_sa_expire(struct xfrm_state *x, const struct km_event *c) { struct sk_buff *out_skb; struct sadb_msg *out_hdr; int hard; int hsc; hard = c->data.hard; if (hard) hsc = 2; else hsc = 1; out_skb = pfkey_xfrm_state2msg_expire(x, hsc); if (IS_ERR(out_skb)) return PTR_ERR(out_skb); out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = PF_KEY_V2; out_hdr->sadb_msg_type = SADB_EXPIRE; out_hdr->sadb_msg_satype = pfkey_proto2satype(x->id.proto); out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_reserved = 0; out_hdr->sadb_msg_seq = 0; out_hdr->sadb_msg_pid = 0; pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL, xs_net(x)); return 0; } static int pfkey_send_notify(struct xfrm_state *x, const struct km_event *c) { struct net *net = x ? xs_net(x) : c->net; struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); if (atomic_read(&net_pfkey->socks_nr) == 0) return 0; switch (c->event) { case XFRM_MSG_EXPIRE: return key_notify_sa_expire(x, c); case XFRM_MSG_DELSA: case XFRM_MSG_NEWSA: case XFRM_MSG_UPDSA: return key_notify_sa(x, c); case XFRM_MSG_FLUSHSA: return key_notify_sa_flush(c); case XFRM_MSG_NEWAE: /* not yet supported */ break; default: pr_err("pfkey: Unknown SA event %d\n", c->event); break; } return 0; } static int pfkey_send_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c) { if (xp && xp->type != XFRM_POLICY_TYPE_MAIN) return 0; switch (c->event) { case XFRM_MSG_POLEXPIRE: return key_notify_policy_expire(xp, c); case XFRM_MSG_DELPOLICY: case XFRM_MSG_NEWPOLICY: case XFRM_MSG_UPDPOLICY: return key_notify_policy(xp, dir, c); case XFRM_MSG_FLUSHPOLICY: if (c->data.type != XFRM_POLICY_TYPE_MAIN) break; return key_notify_policy_flush(c); default: pr_err("pfkey: Unknown policy event %d\n", c->event); break; } return 0; } static u32 get_acqseq(void) { u32 res; static atomic_t acqseq; do { res = atomic_inc_return(&acqseq); } while (!res); return res; } static bool pfkey_is_alive(const struct km_event *c) { struct netns_pfkey *net_pfkey = net_generic(c->net, pfkey_net_id); struct sock *sk; bool is_alive = false; rcu_read_lock(); sk_for_each_rcu(sk, &net_pfkey->table) { if (pfkey_sk(sk)->registered) { is_alive = true; break; } } rcu_read_unlock(); return is_alive; } static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *xp) { struct sk_buff *skb; struct sadb_msg *hdr; struct sadb_address *addr; struct sadb_x_policy *pol; int sockaddr_size; int size; struct sadb_x_sec_ctx *sec_ctx; struct xfrm_sec_ctx *xfrm_ctx; int ctx_size = 0; int alg_size = 0; sockaddr_size = pfkey_sockaddr_size(x->props.family); if (!sockaddr_size) return -EINVAL; size = sizeof(struct sadb_msg) + (sizeof(struct sadb_address) * 2) + (sockaddr_size * 2) + sizeof(struct sadb_x_policy); if (x->id.proto == IPPROTO_AH) alg_size = count_ah_combs(t); else if (x->id.proto == IPPROTO_ESP) alg_size = count_esp_combs(t); if ((xfrm_ctx = x->security)) { ctx_size = PFKEY_ALIGN8(xfrm_ctx->ctx_len); size += sizeof(struct sadb_x_sec_ctx) + ctx_size; } skb = alloc_skb(size + alg_size + 16, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; hdr = skb_put(skb, sizeof(struct sadb_msg)); hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_type = SADB_ACQUIRE; hdr->sadb_msg_satype = pfkey_proto2satype(x->id.proto); hdr->sadb_msg_len = size / sizeof(uint64_t); hdr->sadb_msg_errno = 0; hdr->sadb_msg_reserved = 0; hdr->sadb_msg_seq = x->km.seq = get_acqseq(); hdr->sadb_msg_pid = 0; /* src address */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_SRC; addr->sadb_address_proto = 0; addr->sadb_address_reserved = 0; addr->sadb_address_prefixlen = pfkey_sockaddr_fill(&x->props.saddr, 0, (struct sockaddr *) (addr + 1), x->props.family); if (!addr->sadb_address_prefixlen) BUG(); /* dst address */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_DST; addr->sadb_address_proto = 0; addr->sadb_address_reserved = 0; addr->sadb_address_prefixlen = pfkey_sockaddr_fill(&x->id.daddr, 0, (struct sockaddr *) (addr + 1), x->props.family); if (!addr->sadb_address_prefixlen) BUG(); pol = skb_put(skb, sizeof(struct sadb_x_policy)); pol->sadb_x_policy_len = sizeof(struct sadb_x_policy)/sizeof(uint64_t); pol->sadb_x_policy_exttype = SADB_X_EXT_POLICY; pol->sadb_x_policy_type = IPSEC_POLICY_IPSEC; pol->sadb_x_policy_dir = XFRM_POLICY_OUT + 1; pol->sadb_x_policy_reserved = 0; pol->sadb_x_policy_id = xp->index; pol->sadb_x_policy_priority = xp->priority; /* Set sadb_comb's. */ alg_size = 0; if (x->id.proto == IPPROTO_AH) alg_size = dump_ah_combs(skb, t); else if (x->id.proto == IPPROTO_ESP) alg_size = dump_esp_combs(skb, t); hdr->sadb_msg_len += alg_size / 8; /* security context */ if (xfrm_ctx) { sec_ctx = skb_put(skb, sizeof(struct sadb_x_sec_ctx) + ctx_size); sec_ctx->sadb_x_sec_len = (sizeof(struct sadb_x_sec_ctx) + ctx_size) / sizeof(uint64_t); sec_ctx->sadb_x_sec_exttype = SADB_X_EXT_SEC_CTX; sec_ctx->sadb_x_ctx_doi = xfrm_ctx->ctx_doi; sec_ctx->sadb_x_ctx_alg = xfrm_ctx->ctx_alg; sec_ctx->sadb_x_ctx_len = xfrm_ctx->ctx_len; memcpy(sec_ctx + 1, xfrm_ctx->ctx_str, xfrm_ctx->ctx_len); } return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL, xs_net(x)); } static struct xfrm_policy *pfkey_compile_policy(struct sock *sk, int opt, u8 *data, int len, int *dir) { struct net *net = sock_net(sk); struct xfrm_policy *xp; struct sadb_x_policy *pol = (struct sadb_x_policy*)data; struct sadb_x_sec_ctx *sec_ctx; switch (sk->sk_family) { case AF_INET: if (opt != IP_IPSEC_POLICY) { *dir = -EOPNOTSUPP; return NULL; } break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: if (opt != IPV6_IPSEC_POLICY) { *dir = -EOPNOTSUPP; return NULL; } break; #endif default: *dir = -EINVAL; return NULL; } *dir = -EINVAL; if (len < sizeof(struct sadb_x_policy) || pol->sadb_x_policy_len*8 > len || pol->sadb_x_policy_type > IPSEC_POLICY_BYPASS || (!pol->sadb_x_policy_dir || pol->sadb_x_policy_dir > IPSEC_DIR_OUTBOUND)) return NULL; xp = xfrm_policy_alloc(net, GFP_ATOMIC); if (xp == NULL) { *dir = -ENOBUFS; return NULL; } xp->action = (pol->sadb_x_policy_type == IPSEC_POLICY_DISCARD ? XFRM_POLICY_BLOCK : XFRM_POLICY_ALLOW); xp->lft.soft_byte_limit = XFRM_INF; xp->lft.hard_byte_limit = XFRM_INF; xp->lft.soft_packet_limit = XFRM_INF; xp->lft.hard_packet_limit = XFRM_INF; xp->family = sk->sk_family; xp->xfrm_nr = 0; if (pol->sadb_x_policy_type == IPSEC_POLICY_IPSEC && (*dir = parse_ipsecrequests(xp, pol)) < 0) goto out; /* security context too */ if (len >= (pol->sadb_x_policy_len*8 + sizeof(struct sadb_x_sec_ctx))) { char *p = (char *)pol; struct xfrm_user_sec_ctx *uctx; p += pol->sadb_x_policy_len*8; sec_ctx = (struct sadb_x_sec_ctx *)p; if (len < pol->sadb_x_policy_len*8 + sec_ctx->sadb_x_sec_len*8) { *dir = -EINVAL; goto out; } if ((*dir = verify_sec_ctx_len(p))) goto out; uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx, GFP_ATOMIC); *dir = security_xfrm_policy_alloc(&xp->security, uctx, GFP_ATOMIC); kfree(uctx); if (*dir) goto out; } *dir = pol->sadb_x_policy_dir-1; return xp; out: xp->walk.dead = 1; xfrm_policy_destroy(xp); return NULL; } static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport) { struct sk_buff *skb; struct sadb_msg *hdr; struct sadb_sa *sa; struct sadb_address *addr; struct sadb_x_nat_t_port *n_port; int sockaddr_size; int size; __u8 satype = (x->id.proto == IPPROTO_ESP ? SADB_SATYPE_ESP : 0); struct xfrm_encap_tmpl *natt = NULL; sockaddr_size = pfkey_sockaddr_size(x->props.family); if (!sockaddr_size) return -EINVAL; if (!satype) return -EINVAL; if (!x->encap) return -EINVAL; natt = x->encap; /* Build an SADB_X_NAT_T_NEW_MAPPING message: * * HDR | SA | ADDRESS_SRC (old addr) | NAT_T_SPORT (old port) | * ADDRESS_DST (new addr) | NAT_T_DPORT (new port) */ size = sizeof(struct sadb_msg) + sizeof(struct sadb_sa) + (sizeof(struct sadb_address) * 2) + (sockaddr_size * 2) + (sizeof(struct sadb_x_nat_t_port) * 2); skb = alloc_skb(size + 16, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; hdr = skb_put(skb, sizeof(struct sadb_msg)); hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_type = SADB_X_NAT_T_NEW_MAPPING; hdr->sadb_msg_satype = satype; hdr->sadb_msg_len = size / sizeof(uint64_t); hdr->sadb_msg_errno = 0; hdr->sadb_msg_reserved = 0; hdr->sadb_msg_seq = x->km.seq; hdr->sadb_msg_pid = 0; /* SA */ sa = skb_put(skb, sizeof(struct sadb_sa)); sa->sadb_sa_len = sizeof(struct sadb_sa)/sizeof(uint64_t); sa->sadb_sa_exttype = SADB_EXT_SA; sa->sadb_sa_spi = x->id.spi; sa->sadb_sa_replay = 0; sa->sadb_sa_state = 0; sa->sadb_sa_auth = 0; sa->sadb_sa_encrypt = 0; sa->sadb_sa_flags = 0; /* ADDRESS_SRC (old addr) */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_SRC; addr->sadb_address_proto = 0; addr->sadb_address_reserved = 0; addr->sadb_address_prefixlen = pfkey_sockaddr_fill(&x->props.saddr, 0, (struct sockaddr *) (addr + 1), x->props.family); if (!addr->sadb_address_prefixlen) BUG(); /* NAT_T_SPORT (old port) */ n_port = skb_put(skb, sizeof(*n_port)); n_port->sadb_x_nat_t_port_len = sizeof(*n_port)/sizeof(uint64_t); n_port->sadb_x_nat_t_port_exttype = SADB_X_EXT_NAT_T_SPORT; n_port->sadb_x_nat_t_port_port = natt->encap_sport; n_port->sadb_x_nat_t_port_reserved = 0; /* ADDRESS_DST (new addr) */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); addr->sadb_address_len = (sizeof(struct sadb_address)+sockaddr_size)/ sizeof(uint64_t); addr->sadb_address_exttype = SADB_EXT_ADDRESS_DST; addr->sadb_address_proto = 0; addr->sadb_address_reserved = 0; addr->sadb_address_prefixlen = pfkey_sockaddr_fill(ipaddr, 0, (struct sockaddr *) (addr + 1), x->props.family); if (!addr->sadb_address_prefixlen) BUG(); /* NAT_T_DPORT (new port) */ n_port = skb_put(skb, sizeof(*n_port)); n_port->sadb_x_nat_t_port_len = sizeof(*n_port)/sizeof(uint64_t); n_port->sadb_x_nat_t_port_exttype = SADB_X_EXT_NAT_T_DPORT; n_port->sadb_x_nat_t_port_port = sport; n_port->sadb_x_nat_t_port_reserved = 0; return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL, xs_net(x)); } #ifdef CONFIG_NET_KEY_MIGRATE static int set_sadb_address(struct sk_buff *skb, int sasize, int type, const struct xfrm_selector *sel) { struct sadb_address *addr; addr = skb_put(skb, sizeof(struct sadb_address) + sasize); addr->sadb_address_len = (sizeof(struct sadb_address) + sasize)/8; addr->sadb_address_exttype = type; addr->sadb_address_proto = sel->proto; addr->sadb_address_reserved = 0; switch (type) { case SADB_EXT_ADDRESS_SRC: addr->sadb_address_prefixlen = sel->prefixlen_s; pfkey_sockaddr_fill(&sel->saddr, 0, (struct sockaddr *)(addr + 1), sel->family); break; case SADB_EXT_ADDRESS_DST: addr->sadb_address_prefixlen = sel->prefixlen_d; pfkey_sockaddr_fill(&sel->daddr, 0, (struct sockaddr *)(addr + 1), sel->family); break; default: return -EINVAL; } return 0; } static int set_sadb_kmaddress(struct sk_buff *skb, const struct xfrm_kmaddress *k) { struct sadb_x_kmaddress *kma; u8 *sa; int family = k->family; int socklen = pfkey_sockaddr_len(family); int size_req; size_req = (sizeof(struct sadb_x_kmaddress) + pfkey_sockaddr_pair_size(family)); kma = skb_put_zero(skb, size_req); kma->sadb_x_kmaddress_len = size_req / 8; kma->sadb_x_kmaddress_exttype = SADB_X_EXT_KMADDRESS; kma->sadb_x_kmaddress_reserved = k->reserved; sa = (u8 *)(kma + 1); if (!pfkey_sockaddr_fill(&k->local, 0, (struct sockaddr *)sa, family) || !pfkey_sockaddr_fill(&k->remote, 0, (struct sockaddr *)(sa+socklen), family)) return -EINVAL; return 0; } static int set_ipsecrequest(struct sk_buff *skb, uint8_t proto, uint8_t mode, int level, uint32_t reqid, uint8_t family, const xfrm_address_t *src, const xfrm_address_t *dst) { struct sadb_x_ipsecrequest *rq; u8 *sa; int socklen = pfkey_sockaddr_len(family); int size_req; size_req = sizeof(struct sadb_x_ipsecrequest) + pfkey_sockaddr_pair_size(family); rq = skb_put_zero(skb, size_req); rq->sadb_x_ipsecrequest_len = size_req; rq->sadb_x_ipsecrequest_proto = proto; rq->sadb_x_ipsecrequest_mode = mode; rq->sadb_x_ipsecrequest_level = level; rq->sadb_x_ipsecrequest_reqid = reqid; sa = (u8 *) (rq + 1); if (!pfkey_sockaddr_fill(src, 0, (struct sockaddr *)sa, family) || !pfkey_sockaddr_fill(dst, 0, (struct sockaddr *)(sa + socklen), family)) return -EINVAL; return 0; } #endif #ifdef CONFIG_NET_KEY_MIGRATE static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, const struct xfrm_kmaddress *k, const struct xfrm_encap_tmpl *encap) { int i; int sasize_sel; int size = 0; int size_pol = 0; struct sk_buff *skb; struct sadb_msg *hdr; struct sadb_x_policy *pol; const struct xfrm_migrate *mp; if (type != XFRM_POLICY_TYPE_MAIN) return 0; if (num_bundles <= 0 || num_bundles > XFRM_MAX_DEPTH) return -EINVAL; if (k != NULL) { /* addresses for KM */ size += PFKEY_ALIGN8(sizeof(struct sadb_x_kmaddress) + pfkey_sockaddr_pair_size(k->family)); } /* selector */ sasize_sel = pfkey_sockaddr_size(sel->family); if (!sasize_sel) return -EINVAL; size += (sizeof(struct sadb_address) + sasize_sel) * 2; /* policy info */ size_pol += sizeof(struct sadb_x_policy); /* ipsecrequests */ for (i = 0, mp = m; i < num_bundles; i++, mp++) { /* old locator pair */ size_pol += sizeof(struct sadb_x_ipsecrequest) + pfkey_sockaddr_pair_size(mp->old_family); /* new locator pair */ size_pol += sizeof(struct sadb_x_ipsecrequest) + pfkey_sockaddr_pair_size(mp->new_family); } size += sizeof(struct sadb_msg) + size_pol; /* alloc buffer */ skb = alloc_skb(size, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; hdr = skb_put(skb, sizeof(struct sadb_msg)); hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_type = SADB_X_MIGRATE; hdr->sadb_msg_satype = pfkey_proto2satype(m->proto); hdr->sadb_msg_len = size / 8; hdr->sadb_msg_errno = 0; hdr->sadb_msg_reserved = 0; hdr->sadb_msg_seq = 0; hdr->sadb_msg_pid = 0; /* Addresses to be used by KM for negotiation, if ext is available */ if (k != NULL && (set_sadb_kmaddress(skb, k) < 0)) goto err; /* selector src */ set_sadb_address(skb, sasize_sel, SADB_EXT_ADDRESS_SRC, sel); /* selector dst */ set_sadb_address(skb, sasize_sel, SADB_EXT_ADDRESS_DST, sel); /* policy information */ pol = skb_put(skb, sizeof(struct sadb_x_policy)); pol->sadb_x_policy_len = size_pol / 8; pol->sadb_x_policy_exttype = SADB_X_EXT_POLICY; pol->sadb_x_policy_type = IPSEC_POLICY_IPSEC; pol->sadb_x_policy_dir = dir + 1; pol->sadb_x_policy_reserved = 0; pol->sadb_x_policy_id = 0; pol->sadb_x_policy_priority = 0; for (i = 0, mp = m; i < num_bundles; i++, mp++) { /* old ipsecrequest */ int mode = pfkey_mode_from_xfrm(mp->mode); if (mode < 0) goto err; if (set_ipsecrequest(skb, mp->proto, mode, (mp->reqid ? IPSEC_LEVEL_UNIQUE : IPSEC_LEVEL_REQUIRE), mp->reqid, mp->old_family, &mp->old_saddr, &mp->old_daddr) < 0) goto err; /* new ipsecrequest */ if (set_ipsecrequest(skb, mp->proto, mode, (mp->reqid ? IPSEC_LEVEL_UNIQUE : IPSEC_LEVEL_REQUIRE), mp->reqid, mp->new_family, &mp->new_saddr, &mp->new_daddr) < 0) goto err; } /* broadcast migrate message to sockets */ pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, &init_net); return 0; err: kfree_skb(skb); return -EINVAL; } #else static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, const struct xfrm_kmaddress *k, const struct xfrm_encap_tmpl *encap) { return -ENOPROTOOPT; } #endif static int pfkey_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct sk_buff *skb = NULL; struct sadb_msg *hdr = NULL; int err; struct net *net = sock_net(sk); err = -EOPNOTSUPP; if (msg->msg_flags & MSG_OOB) goto out; err = -EMSGSIZE; if ((unsigned int)len > sk->sk_sndbuf - 32) goto out; err = -ENOBUFS; skb = alloc_skb(len, GFP_KERNEL); if (skb == NULL) goto out; err = -EFAULT; if (memcpy_from_msg(skb_put(skb,len), msg, len)) goto out; hdr = pfkey_get_base_msg(skb, &err); if (!hdr) goto out; mutex_lock(&net->xfrm.xfrm_cfg_mutex); err = pfkey_process(sk, skb, hdr); mutex_unlock(&net->xfrm.xfrm_cfg_mutex); out: if (err && hdr && pfkey_error(hdr, err, sk) == 0) err = 0; kfree_skb(skb); return err ? : len; } static int pfkey_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct pfkey_sock *pfk = pfkey_sk(sk); struct sk_buff *skb; int copied, err; err = -EINVAL; if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT)) goto out; skb = skb_recv_datagram(sk, flags, &err); if (skb == NULL) goto out; copied = skb->len; if (copied > len) { msg->msg_flags |= MSG_TRUNC; copied = len; } skb_reset_transport_header(skb); err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto out_free; sock_recv_cmsgs(msg, sk, skb); err = (flags & MSG_TRUNC) ? skb->len : copied; if (pfk->dump.dump != NULL && 3 * atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) pfkey_do_dump(pfk); out_free: skb_free_datagram(sk, skb); out: return err; } static const struct proto_ops pfkey_ops = { .family = PF_KEY, .owner = THIS_MODULE, /* Operations that make no sense on pfkey sockets. */ .bind = sock_no_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = sock_no_getname, .ioctl = sock_no_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, /* Now the operations that really occur. */ .release = pfkey_release, .poll = datagram_poll, .sendmsg = pfkey_sendmsg, .recvmsg = pfkey_recvmsg, }; static const struct net_proto_family pfkey_family_ops = { .family = PF_KEY, .create = pfkey_create, .owner = THIS_MODULE, }; #ifdef CONFIG_PROC_FS static int pfkey_seq_show(struct seq_file *f, void *v) { struct sock *s = sk_entry(v); if (v == SEQ_START_TOKEN) seq_printf(f ,"sk RefCnt Rmem Wmem User Inode\n"); else seq_printf(f, "%pK %-6d %-6u %-6u %-6u %-6lu\n", s, refcount_read(&s->sk_refcnt), sk_rmem_alloc_get(s), sk_wmem_alloc_get(s), from_kuid_munged(seq_user_ns(f), sock_i_uid(s)), sock_i_ino(s) ); return 0; } static void *pfkey_seq_start(struct seq_file *f, loff_t *ppos) __acquires(rcu) { struct net *net = seq_file_net(f); struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); rcu_read_lock(); return seq_hlist_start_head_rcu(&net_pfkey->table, *ppos); } static void *pfkey_seq_next(struct seq_file *f, void *v, loff_t *ppos) { struct net *net = seq_file_net(f); struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); return seq_hlist_next_rcu(v, &net_pfkey->table, ppos); } static void pfkey_seq_stop(struct seq_file *f, void *v) __releases(rcu) { rcu_read_unlock(); } static const struct seq_operations pfkey_seq_ops = { .start = pfkey_seq_start, .next = pfkey_seq_next, .stop = pfkey_seq_stop, .show = pfkey_seq_show, }; static int __net_init pfkey_init_proc(struct net *net) { struct proc_dir_entry *e; e = proc_create_net("pfkey", 0, net->proc_net, &pfkey_seq_ops, sizeof(struct seq_net_private)); if (e == NULL) return -ENOMEM; return 0; } static void __net_exit pfkey_exit_proc(struct net *net) { remove_proc_entry("pfkey", net->proc_net); } #else static inline int pfkey_init_proc(struct net *net) { return 0; } static inline void pfkey_exit_proc(struct net *net) { } #endif static struct xfrm_mgr pfkeyv2_mgr = { .notify = pfkey_send_notify, .acquire = pfkey_send_acquire, .compile_policy = pfkey_compile_policy, .new_mapping = pfkey_send_new_mapping, .notify_policy = pfkey_send_policy_notify, .migrate = pfkey_send_migrate, .is_alive = pfkey_is_alive, }; static int __net_init pfkey_net_init(struct net *net) { struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); int rv; INIT_HLIST_HEAD(&net_pfkey->table); atomic_set(&net_pfkey->socks_nr, 0); rv = pfkey_init_proc(net); return rv; } static void __net_exit pfkey_net_exit(struct net *net) { struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); pfkey_exit_proc(net); WARN_ON(!hlist_empty(&net_pfkey->table)); } static struct pernet_operations pfkey_net_ops = { .init = pfkey_net_init, .exit = pfkey_net_exit, .id = &pfkey_net_id, .size = sizeof(struct netns_pfkey), }; static void __exit ipsec_pfkey_exit(void) { xfrm_unregister_km(&pfkeyv2_mgr); sock_unregister(PF_KEY); unregister_pernet_subsys(&pfkey_net_ops); proto_unregister(&key_proto); } static int __init ipsec_pfkey_init(void) { int err = proto_register(&key_proto, 0); if (err != 0) goto out; err = register_pernet_subsys(&pfkey_net_ops); if (err != 0) goto out_unregister_key_proto; err = sock_register(&pfkey_family_ops); if (err != 0) goto out_unregister_pernet; xfrm_register_km(&pfkeyv2_mgr); out: return err; out_unregister_pernet: unregister_pernet_subsys(&pfkey_net_ops); out_unregister_key_proto: proto_unregister(&key_proto); goto out; } module_init(ipsec_pfkey_init); module_exit(ipsec_pfkey_exit); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_KEY); |
| 4 4 1 2 2 19 19 12 1 644 643 643 643 643 640 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux NET3: IP/IP protocol decoder. * * Authors: * Sam Lantinga (slouken@cs.ucdavis.edu) 02/01/95 * * Fixes: * Alan Cox : Merged and made usable non modular (its so tiny its silly as * a module taking up 2 pages). * Alan Cox : Fixed bug with 1.3.18 and IPIP not working (now needs to set skb->h.iph) * to keep ip_forward happy. * Alan Cox : More fixes for 1.3.21, and firewall fix. Maybe this will work soon 8). * Kai Schulte : Fixed #defines for IP_FIREWALL->FIREWALL * David Woodhouse : Perform some basic ICMP handling. * IPIP Routing without decapsulation. * Carlos Picoto : GRE over IP support * Alexey Kuznetsov: Reworked. Really, now it is truncated version of ipv4/ip_gre.c. * I do not want to merge them together. */ /* tunnel.c: an IP tunnel driver The purpose of this driver is to provide an IP tunnel through which you can tunnel network traffic transparently across subnets. This was written by looking at Nick Holloway's dummy driver Thanks for the great code! -Sam Lantinga (slouken@cs.ucdavis.edu) 02/01/95 Minor tweaks: Cleaned up the code a little and added some pre-1.3.0 tweaks. dev->hard_header/hard_header_len changed to use no headers. Comments/bracketing tweaked. Made the tunnels use dev->name not tunnel: when error reporting. Added tx_dropped stat -Alan Cox (alan@lxorguk.ukuu.org.uk) 21 March 95 Reworked: Changed to tunnel to destination gateway in addition to the tunnel's pointopoint address Almost completely rewritten Note: There is currently no firewall or ICMP handling done. -Sam Lantinga (slouken@cs.ucdavis.edu) 02/13/96 */ /* Things I wish I had known when writing the tunnel driver: When the tunnel_xmit() function is called, the skb contains the packet to be sent (plus a great deal of extra info), and dev contains the tunnel device that _we_ are. When we are passed a packet, we are expected to fill in the source address with our source IP address. What is the proper way to allocate, copy and free a buffer? After you allocate it, it is a "0 length" chunk of memory starting at zero. If you want to add headers to the buffer later, you'll have to call "skb_reserve(skb, amount)" with the amount of memory you want reserved. Then, you call "skb_put(skb, amount)" with the amount of space you want in the buffer. skb_put() returns a pointer to the top (#0) of that buffer. skb->len is set to the amount of space you have "allocated" with skb_put(). You can then write up to skb->len bytes to that buffer. If you need more, you can call skb_put() again with the additional amount of space you need. You can find out how much more space you can allocate by calling "skb_tailroom(skb)". Now, to add header space, call "skb_push(skb, header_len)". This creates space at the beginning of the buffer and returns a pointer to this new space. If later you need to strip a header from a buffer, call "skb_pull(skb, header_len)". skb_headroom() will return how much space is left at the top of the buffer (before the main data). Remember, this headroom space must be reserved before the skb_put() function is called. */ /* This version of net/ipv4/ipip.c is cloned of net/ipv4/ip_gre.c For comments look at net/ipv4/ip_gre.c --ANK */ #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/netfilter_ipv4.h> #include <linux/if_ether.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/ip_tunnels.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/dst_metadata.h> static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); static unsigned int ipip_net_id __read_mostly; static int ipip_tunnel_init(struct net_device *dev); static struct rtnl_link_ops ipip_link_ops __read_mostly; static int ipip_err(struct sk_buff *skb, u32 info) { /* All the routers (except for Linux) return only * 8 bytes of packet payload. It means, that precise relaying of * ICMP in the real Internet is absolutely infeasible. */ struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, ipip_net_id); const struct iphdr *iph = (const struct iphdr *)skb->data; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct ip_tunnel *t; int err = 0; t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, iph->daddr, iph->saddr, 0); if (!t) { err = -ENOENT; goto out; } switch (type) { case ICMP_DEST_UNREACH: switch (code) { case ICMP_SR_FAILED: /* Impossible event. */ goto out; default: /* All others are translated to HOST_UNREACH. * rfc2003 contains "deep thoughts" about NET_UNREACH, * I believe they are just ether pollution. --ANK */ break; } break; case ICMP_TIME_EXCEEDED: if (code != ICMP_EXC_TTL) goto out; break; case ICMP_REDIRECT: break; default: goto out; } if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, net, info, t->parms.link, iph->protocol); goto out; } if (type == ICMP_REDIRECT) { ipv4_redirect(skb, net, t->parms.link, iph->protocol); goto out; } if (t->parms.iph.daddr == 0) { err = -ENOENT; goto out; } if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) goto out; if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO)) t->err_count++; else t->err_count = 1; t->err_time = jiffies; out: return err; } static const struct tnl_ptk_info ipip_tpi = { /* no tunnel info required for ipip. */ .proto = htons(ETH_P_IP), }; #if IS_ENABLED(CONFIG_MPLS) static const struct tnl_ptk_info mplsip_tpi = { /* no tunnel info required for mplsip. */ .proto = htons(ETH_P_MPLS_UC), }; #endif static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto) { struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, ipip_net_id); struct metadata_dst *tun_dst = NULL; struct ip_tunnel *tunnel; const struct iphdr *iph; iph = ip_hdr(skb); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, iph->saddr, iph->daddr, 0); if (tunnel) { const struct tnl_ptk_info *tpi; if (tunnel->parms.iph.protocol != ipproto && tunnel->parms.iph.protocol != 0) goto drop; if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; #if IS_ENABLED(CONFIG_MPLS) if (ipproto == IPPROTO_MPLS) tpi = &mplsip_tpi; else #endif tpi = &ipip_tpi; if (iptunnel_pull_header(skb, 0, tpi->proto, false)) goto drop; if (tunnel->collect_md) { tun_dst = ip_tun_rx_dst(skb, 0, 0, 0); if (!tun_dst) return 0; } skb_reset_mac_header(skb); return ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); } return -1; drop: kfree_skb(skb); return 0; } static int ipip_rcv(struct sk_buff *skb) { return ipip_tunnel_rcv(skb, IPPROTO_IPIP); } #if IS_ENABLED(CONFIG_MPLS) static int mplsip_rcv(struct sk_buff *skb) { return ipip_tunnel_rcv(skb, IPPROTO_MPLS); } #endif /* * This function assumes it is being called from dev_queue_xmit() * and that skb is filled properly by that function. */ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tiph = &tunnel->parms.iph; u8 ipproto; if (!pskb_inet_may_pull(skb)) goto tx_error; switch (skb->protocol) { case htons(ETH_P_IP): ipproto = IPPROTO_IPIP; break; #if IS_ENABLED(CONFIG_MPLS) case htons(ETH_P_MPLS_UC): ipproto = IPPROTO_MPLS; break; #endif default: goto tx_error; } if (tiph->protocol != ipproto && tiph->protocol != 0) goto tx_error; if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4)) goto tx_error; skb_set_inner_ipproto(skb, ipproto); if (tunnel->collect_md) ip_md_tunnel_xmit(skb, dev, ipproto, 0); else ip_tunnel_xmit(skb, dev, tiph, ipproto); return NETDEV_TX_OK; tx_error: kfree_skb(skb); dev->stats.tx_errors++; return NETDEV_TX_OK; } static bool ipip_tunnel_ioctl_verify_protocol(u8 ipproto) { switch (ipproto) { case 0: case IPPROTO_IPIP: #if IS_ENABLED(CONFIG_MPLS) case IPPROTO_MPLS: #endif return true; } return false; } static int ipip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) { if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { if (p->iph.version != 4 || !ipip_tunnel_ioctl_verify_protocol(p->iph.protocol) || p->iph.ihl != 5 || (p->iph.frag_off & htons(~IP_DF))) return -EINVAL; } p->i_key = p->o_key = 0; p->i_flags = p->o_flags = 0; return ip_tunnel_ctl(dev, p, cmd); } static const struct net_device_ops ipip_netdev_ops = { .ndo_init = ipip_tunnel_init, .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = ipip_tunnel_xmit, .ndo_siocdevprivate = ip_tunnel_siocdevprivate, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_tunnel_ctl = ipip_tunnel_ctl, }; #define IPIP_FEATURES (NETIF_F_SG | \ NETIF_F_FRAGLIST | \ NETIF_F_HIGHDMA | \ NETIF_F_GSO_SOFTWARE | \ NETIF_F_HW_CSUM) static void ipip_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipip_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; dev->type = ARPHRD_TUNNEL; dev->flags = IFF_NOARP; dev->addr_len = 4; dev->features |= NETIF_F_LLTX; netif_keep_dst(dev); dev->features |= IPIP_FEATURES; dev->hw_features |= IPIP_FEATURES; ip_tunnel_setup(dev, ipip_net_id); } static int ipip_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); __dev_addr_set(dev, &tunnel->parms.iph.saddr, 4); memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); tunnel->tun_hlen = 0; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; return ip_tunnel_init(dev); } static int ipip_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { u8 proto; if (!data || !data[IFLA_IPTUN_PROTO]) return 0; proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); if (proto != IPPROTO_IPIP && proto != IPPROTO_MPLS && proto != 0) return -EINVAL; return 0; } static void ipip_netlink_parms(struct nlattr *data[], struct ip_tunnel_parm *parms, bool *collect_md, __u32 *fwmark) { memset(parms, 0, sizeof(*parms)); parms->iph.version = 4; parms->iph.protocol = IPPROTO_IPIP; parms->iph.ihl = 5; *collect_md = false; if (!data) return; ip_tunnel_netlink_parms(data, parms); if (data[IFLA_IPTUN_COLLECT_METADATA]) *collect_md = true; if (data[IFLA_IPTUN_FWMARK]) *fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]); } static int ipip_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; __u32 fwmark = 0; if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { int err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) return err; } ipip_netlink_parms(data, &p, &t->collect_md, &fwmark); return ip_tunnel_newlink(dev, tb, &p, fwmark); } static int ipip_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; bool collect_md; __u32 fwmark = t->fwmark; if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { int err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) return err; } ipip_netlink_parms(data, &p, &collect_md, &fwmark); if (collect_md) return -EINVAL; if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) || (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr)) return -EINVAL; return ip_tunnel_changelink(dev, tb, &p, fwmark); } static size_t ipip_get_size(const struct net_device *dev) { return /* IFLA_IPTUN_LINK */ nla_total_size(4) + /* IFLA_IPTUN_LOCAL */ nla_total_size(4) + /* IFLA_IPTUN_REMOTE */ nla_total_size(4) + /* IFLA_IPTUN_TTL */ nla_total_size(1) + /* IFLA_IPTUN_TOS */ nla_total_size(1) + /* IFLA_IPTUN_PROTO */ nla_total_size(1) + /* IFLA_IPTUN_PMTUDISC */ nla_total_size(1) + /* IFLA_IPTUN_ENCAP_TYPE */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_FLAGS */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_SPORT */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_DPORT */ nla_total_size(2) + /* IFLA_IPTUN_COLLECT_METADATA */ nla_total_size(0) + /* IFLA_IPTUN_FWMARK */ nla_total_size(4) + 0; } static int ipip_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_parm *parm = &tunnel->parms; if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || nla_put_in_addr(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) || nla_put_in_addr(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) || nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) || nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) || nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->iph.protocol) || nla_put_u8(skb, IFLA_IPTUN_PMTUDISC, !!(parm->iph.frag_off & htons(IP_DF))) || nla_put_u32(skb, IFLA_IPTUN_FWMARK, tunnel->fwmark)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE, tunnel->encap.type) || nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT, tunnel->encap.sport) || nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT, tunnel->encap.dport) || nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS, tunnel->encap.flags)) goto nla_put_failure; if (tunnel->collect_md) if (nla_put_flag(skb, IFLA_IPTUN_COLLECT_METADATA)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static const struct nla_policy ipip_policy[IFLA_IPTUN_MAX + 1] = { [IFLA_IPTUN_LINK] = { .type = NLA_U32 }, [IFLA_IPTUN_LOCAL] = { .type = NLA_U32 }, [IFLA_IPTUN_REMOTE] = { .type = NLA_U32 }, [IFLA_IPTUN_TTL] = { .type = NLA_U8 }, [IFLA_IPTUN_TOS] = { .type = NLA_U8 }, [IFLA_IPTUN_PROTO] = { .type = NLA_U8 }, [IFLA_IPTUN_PMTUDISC] = { .type = NLA_U8 }, [IFLA_IPTUN_ENCAP_TYPE] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_FLAGS] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_SPORT] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_DPORT] = { .type = NLA_U16 }, [IFLA_IPTUN_COLLECT_METADATA] = { .type = NLA_FLAG }, [IFLA_IPTUN_FWMARK] = { .type = NLA_U32 }, }; static struct rtnl_link_ops ipip_link_ops __read_mostly = { .kind = "ipip", .maxtype = IFLA_IPTUN_MAX, .policy = ipip_policy, .priv_size = sizeof(struct ip_tunnel), .setup = ipip_tunnel_setup, .validate = ipip_tunnel_validate, .newlink = ipip_newlink, .changelink = ipip_changelink, .dellink = ip_tunnel_dellink, .get_size = ipip_get_size, .fill_info = ipip_fill_info, .get_link_net = ip_tunnel_get_link_net, }; static struct xfrm_tunnel ipip_handler __read_mostly = { .handler = ipip_rcv, .err_handler = ipip_err, .priority = 1, }; #if IS_ENABLED(CONFIG_MPLS) static struct xfrm_tunnel mplsip_handler __read_mostly = { .handler = mplsip_rcv, .err_handler = ipip_err, .priority = 1, }; #endif static int __net_init ipip_init_net(struct net *net) { return ip_tunnel_init_net(net, ipip_net_id, &ipip_link_ops, "tunl0"); } static void __net_exit ipip_exit_batch_net(struct list_head *list_net) { ip_tunnel_delete_nets(list_net, ipip_net_id, &ipip_link_ops); } static struct pernet_operations ipip_net_ops = { .init = ipip_init_net, .exit_batch = ipip_exit_batch_net, .id = &ipip_net_id, .size = sizeof(struct ip_tunnel_net), }; static int __init ipip_init(void) { int err; pr_info("ipip: IPv4 and MPLS over IPv4 tunneling driver\n"); err = register_pernet_device(&ipip_net_ops); if (err < 0) return err; err = xfrm4_tunnel_register(&ipip_handler, AF_INET); if (err < 0) { pr_info("%s: can't register tunnel\n", __func__); goto xfrm_tunnel_ipip_failed; } #if IS_ENABLED(CONFIG_MPLS) err = xfrm4_tunnel_register(&mplsip_handler, AF_MPLS); if (err < 0) { pr_info("%s: can't register tunnel\n", __func__); goto xfrm_tunnel_mplsip_failed; } #endif err = rtnl_link_register(&ipip_link_ops); if (err < 0) goto rtnl_link_failed; out: return err; rtnl_link_failed: #if IS_ENABLED(CONFIG_MPLS) xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS); xfrm_tunnel_mplsip_failed: #endif xfrm4_tunnel_deregister(&ipip_handler, AF_INET); xfrm_tunnel_ipip_failed: unregister_pernet_device(&ipip_net_ops); goto out; } static void __exit ipip_fini(void) { rtnl_link_unregister(&ipip_link_ops); if (xfrm4_tunnel_deregister(&ipip_handler, AF_INET)) pr_info("%s: can't deregister tunnel\n", __func__); #if IS_ENABLED(CONFIG_MPLS) if (xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS)) pr_info("%s: can't deregister tunnel\n", __func__); #endif unregister_pernet_device(&ipip_net_ops); } module_init(ipip_init); module_exit(ipip_fini); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("ipip"); MODULE_ALIAS_NETDEV("tunl0"); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_IO_H #define _ASM_X86_IO_H /* * This file contains the definitions for the x86 IO instructions * inb/inw/inl/outb/outw/outl and the "string versions" of the same * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing" * versions of the single-IO instructions (inb_p/inw_p/..). * * This file is not meant to be obfuscating: it's just complicated * to (a) handle it all in a way that makes gcc able to optimize it * as well as possible and (b) trying to avoid writing the same thing * over and over again with slight variations and possibly making a * mistake somewhere. */ /* * Thanks to James van Artsdalen for a better timing-fix than * the two short jumps: using outb's to a nonexistent port seems * to guarantee better timings even on fast machines. * * On the other hand, I'd like to be sure of a non-existent port: * I feel a bit unsafe about using 0x80 (should be safe, though) * * Linus */ /* * Bit simplified and optimized by Jan Hubicka * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999. * * isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added, * isa_read[wl] and isa_write[wl] fixed * - Arnaldo Carvalho de Melo <acme@conectiva.com.br> */ #define ARCH_HAS_IOREMAP_WC #define ARCH_HAS_IOREMAP_WT #include <linux/string.h> #include <linux/compiler.h> #include <linux/cc_platform.h> #include <asm/page.h> #include <asm/early_ioremap.h> #include <asm/pgtable_types.h> #include <asm/shared/io.h> #define build_mmio_read(name, size, type, reg, barrier) \ static inline type name(const volatile void __iomem *addr) \ { type ret; asm volatile("mov" size " %1,%0":reg (ret) \ :"m" (*(volatile type __force *)addr) barrier); return ret; } #define build_mmio_write(name, size, type, reg, barrier) \ static inline void name(type val, volatile void __iomem *addr) \ { asm volatile("mov" size " %0,%1": :reg (val), \ "m" (*(volatile type __force *)addr) barrier); } build_mmio_read(readb, "b", unsigned char, "=q", :"memory") build_mmio_read(readw, "w", unsigned short, "=r", :"memory") build_mmio_read(readl, "l", unsigned int, "=r", :"memory") build_mmio_read(__readb, "b", unsigned char, "=q", ) build_mmio_read(__readw, "w", unsigned short, "=r", ) build_mmio_read(__readl, "l", unsigned int, "=r", ) build_mmio_write(writeb, "b", unsigned char, "q", :"memory") build_mmio_write(writew, "w", unsigned short, "r", :"memory") build_mmio_write(writel, "l", unsigned int, "r", :"memory") build_mmio_write(__writeb, "b", unsigned char, "q", ) build_mmio_write(__writew, "w", unsigned short, "r", ) build_mmio_write(__writel, "l", unsigned int, "r", ) #define readb readb #define readw readw #define readl readl #define readb_relaxed(a) __readb(a) #define readw_relaxed(a) __readw(a) #define readl_relaxed(a) __readl(a) #define __raw_readb __readb #define __raw_readw __readw #define __raw_readl __readl #define writeb writeb #define writew writew #define writel writel #define writeb_relaxed(v, a) __writeb(v, a) #define writew_relaxed(v, a) __writew(v, a) #define writel_relaxed(v, a) __writel(v, a) #define __raw_writeb __writeb #define __raw_writew __writew #define __raw_writel __writel #ifdef CONFIG_X86_64 build_mmio_read(readq, "q", u64, "=r", :"memory") build_mmio_read(__readq, "q", u64, "=r", ) build_mmio_write(writeq, "q", u64, "r", :"memory") build_mmio_write(__writeq, "q", u64, "r", ) #define readq_relaxed(a) __readq(a) #define writeq_relaxed(v, a) __writeq(v, a) #define __raw_readq __readq #define __raw_writeq __writeq /* Let people know that we have them */ #define readq readq #define writeq writeq #endif #define ARCH_HAS_VALID_PHYS_ADDR_RANGE extern int valid_phys_addr_range(phys_addr_t addr, size_t size); extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size); /** * virt_to_phys - map virtual addresses to physical * @address: address to remap * * The returned physical address is the physical (CPU) mapping for * the memory address given. It is only valid to use this function on * addresses directly mapped or allocated via kmalloc. * * This function does not give bus mappings for DMA transfers. In * almost all conceivable cases a device driver should not be using * this function */ static inline phys_addr_t virt_to_phys(volatile void *address) { return __pa(address); } #define virt_to_phys virt_to_phys /** * phys_to_virt - map physical address to virtual * @address: address to remap * * The returned virtual address is a current CPU mapping for * the memory address given. It is only valid to use this function on * addresses that have a kernel mapping * * This function does not handle bus mappings for DMA transfers. In * almost all conceivable cases a device driver should not be using * this function */ static inline void *phys_to_virt(phys_addr_t address) { return __va(address); } #define phys_to_virt phys_to_virt /* * Change "struct page" to physical address. */ #define page_to_phys(page) ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT) /* * ISA I/O bus memory addresses are 1:1 with the physical address. * However, we truncate the address to unsigned int to avoid undesirable * promotions in legacy drivers. */ static inline unsigned int isa_virt_to_bus(volatile void *address) { return (unsigned int)virt_to_phys(address); } #define isa_bus_to_virt phys_to_virt /* * The default ioremap() behavior is non-cached; if you need something * else, you probably want one of the following. */ extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size); #define ioremap_uc ioremap_uc extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size); #define ioremap_cache ioremap_cache extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, unsigned long prot_val); #define ioremap_prot ioremap_prot extern void __iomem *ioremap_encrypted(resource_size_t phys_addr, unsigned long size); #define ioremap_encrypted ioremap_encrypted /** * ioremap - map bus memory into CPU space * @offset: bus address of the memory * @size: size of the resource to map * * ioremap performs a platform specific sequence of operations to * make bus memory CPU accessible via the readb/readw/readl/writeb/ * writew/writel functions and the other mmio helpers. The returned * address is not guaranteed to be usable directly as a virtual * address. * * If the area you are trying to map is a PCI BAR you should have a * look at pci_iomap(). */ void __iomem *ioremap(resource_size_t offset, unsigned long size); #define ioremap ioremap extern void iounmap(volatile void __iomem *addr); #define iounmap iounmap #ifdef __KERNEL__ void memcpy_fromio(void *, const volatile void __iomem *, size_t); void memcpy_toio(volatile void __iomem *, const void *, size_t); void memset_io(volatile void __iomem *, int, size_t); #define memcpy_fromio memcpy_fromio #define memcpy_toio memcpy_toio #define memset_io memset_io #include <asm-generic/iomap.h> /* * ISA space is 'always mapped' on a typical x86 system, no need to * explicitly ioremap() it. The fact that the ISA IO space is mapped * to PAGE_OFFSET is pure coincidence - it does not mean ISA values * are physical addresses. The following constant pointer can be * used as the IO-area pointer (it can be iounmapped as well, so the * analogy with PCI is quite large): */ #define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET)) #endif /* __KERNEL__ */ extern void native_io_delay(void); extern int io_delay_type; extern void io_delay_init(void); #if defined(CONFIG_PARAVIRT) #include <asm/paravirt.h> #else static inline void slow_down_io(void) { native_io_delay(); #ifdef REALLY_SLOW_IO native_io_delay(); native_io_delay(); native_io_delay(); #endif } #endif #define BUILDIO(bwl, bw, type) \ static inline void out##bwl##_p(type value, u16 port) \ { \ out##bwl(value, port); \ slow_down_io(); \ } \ \ static inline type in##bwl##_p(u16 port) \ { \ type value = in##bwl(port); \ slow_down_io(); \ return value; \ } \ \ static inline void outs##bwl(u16 port, const void *addr, unsigned long count) \ { \ if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) { \ type *value = (type *)addr; \ while (count) { \ out##bwl(*value, port); \ value++; \ count--; \ } \ } else { \ asm volatile("rep; outs" #bwl \ : "+S"(addr), "+c"(count) \ : "d"(port) : "memory"); \ } \ } \ \ static inline void ins##bwl(u16 port, void *addr, unsigned long count) \ { \ if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) { \ type *value = (type *)addr; \ while (count) { \ *value = in##bwl(port); \ value++; \ count--; \ } \ } else { \ asm volatile("rep; ins" #bwl \ : "+D"(addr), "+c"(count) \ : "d"(port) : "memory"); \ } \ } BUILDIO(b, b, u8) BUILDIO(w, w, u16) BUILDIO(l, , u32) #undef BUILDIO #define inb_p inb_p #define inw_p inw_p #define inl_p inl_p #define insb insb #define insw insw #define insl insl #define outb_p outb_p #define outw_p outw_p #define outl_p outl_p #define outsb outsb #define outsw outsw #define outsl outsl extern void *xlate_dev_mem_ptr(phys_addr_t phys); extern void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr); #define xlate_dev_mem_ptr xlate_dev_mem_ptr #define unxlate_dev_mem_ptr unxlate_dev_mem_ptr extern int ioremap_change_attr(unsigned long vaddr, unsigned long size, enum page_cache_mode pcm); extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size); #define ioremap_wc ioremap_wc extern void __iomem *ioremap_wt(resource_size_t offset, unsigned long size); #define ioremap_wt ioremap_wt extern bool is_early_ioremap_ptep(pte_t *ptep); #define IO_SPACE_LIMIT 0xffff #include <asm-generic/io.h> #undef PCI_IOBASE #ifdef CONFIG_MTRR extern int __must_check arch_phys_wc_index(int handle); #define arch_phys_wc_index arch_phys_wc_index extern int __must_check arch_phys_wc_add(unsigned long base, unsigned long size); extern void arch_phys_wc_del(int handle); #define arch_phys_wc_add arch_phys_wc_add #endif #ifdef CONFIG_X86_PAT extern int arch_io_reserve_memtype_wc(resource_size_t start, resource_size_t size); extern void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size); #define arch_io_reserve_memtype_wc arch_io_reserve_memtype_wc #endif #ifdef CONFIG_AMD_MEM_ENCRYPT extern bool arch_memremap_can_ram_remap(resource_size_t offset, unsigned long size, unsigned long flags); #define arch_memremap_can_ram_remap arch_memremap_can_ram_remap extern bool phys_mem_access_encrypted(unsigned long phys_addr, unsigned long size); #else static inline bool phys_mem_access_encrypted(unsigned long phys_addr, unsigned long size) { return true; } #endif /** * iosubmit_cmds512 - copy data to single MMIO location, in 512-bit units * @dst: destination, in MMIO space (must be 512-bit aligned) * @src: source * @count: number of 512 bits quantities to submit * * Submit data from kernel space to MMIO space, in units of 512 bits at a * time. Order of access is not guaranteed, nor is a memory barrier * performed afterwards. * * Warning: Do not use this helper unless your driver has checked that the CPU * instruction is supported on the platform. */ static inline void iosubmit_cmds512(void __iomem *dst, const void *src, size_t count) { const u8 *from = src; const u8 *end = from + count * 64; while (from < end) { movdir64b(dst, from); from += 64; } } #endif /* _ASM_X86_IO_H */ |
| 576 251 44 260 20 261 623 603 593 612 94 20 602 21 384 4 9 8 289 299 298 306 12 14 5 275 247 12 235 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 | // SPDX-License-Identifier: GPL-2.0 /* * Convert integer string representation to an integer. * If an integer doesn't fit into specified type, -E is returned. * * Integer starts with optional sign. * kstrtou*() functions do not accept sign "-". * * Radix 0 means autodetection: leading "0x" implies radix 16, * leading "0" implies radix 8, otherwise radix is 10. * Autodetection hints work after optional sign, but not before. * * If -E is returned, result is not touched. */ #include <linux/ctype.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/kstrtox.h> #include <linux/math64.h> #include <linux/types.h> #include <linux/uaccess.h> #include "kstrtox.h" noinline const char *_parse_integer_fixup_radix(const char *s, unsigned int *base) { if (*base == 0) { if (s[0] == '0') { if (_tolower(s[1]) == 'x' && isxdigit(s[2])) *base = 16; else *base = 8; } else *base = 10; } if (*base == 16 && s[0] == '0' && _tolower(s[1]) == 'x') s += 2; return s; } /* * Convert non-negative integer string representation in explicitly given radix * to an integer. A maximum of max_chars characters will be converted. * * Return number of characters consumed maybe or-ed with overflow bit. * If overflow occurs, result integer (incorrect) is still returned. * * Don't you dare use this function. */ noinline unsigned int _parse_integer_limit(const char *s, unsigned int base, unsigned long long *p, size_t max_chars) { unsigned long long res; unsigned int rv; res = 0; rv = 0; while (max_chars--) { unsigned int c = *s; unsigned int lc = c | 0x20; /* don't tolower() this line */ unsigned int val; if ('0' <= c && c <= '9') val = c - '0'; else if ('a' <= lc && lc <= 'f') val = lc - 'a' + 10; else break; if (val >= base) break; /* * Check for overflow only if we are within range of * it in the max base we support (16) */ if (unlikely(res & (~0ull << 60))) { if (res > div_u64(ULLONG_MAX - val, base)) rv |= KSTRTOX_OVERFLOW; } res = res * base + val; rv++; s++; } *p = res; return rv; } noinline unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long *p) { return _parse_integer_limit(s, base, p, INT_MAX); } static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res) { unsigned long long _res; unsigned int rv; s = _parse_integer_fixup_radix(s, &base); rv = _parse_integer(s, base, &_res); if (rv & KSTRTOX_OVERFLOW) return -ERANGE; if (rv == 0) return -EINVAL; s += rv; if (*s == '\n') s++; if (*s) return -EINVAL; *res = _res; return 0; } /** * kstrtoull - convert a string to an unsigned long long * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign, but not a minus sign. * @base: The number base to use. The maximum supported base is 16. If base is * given as 0, then the base of the string is automatically detected with the * conventional semantics - If it begins with 0x the number will be parsed as a * hexadecimal (case insensitive), if it otherwise begins with 0, it will be * parsed as an octal number. Otherwise it will be parsed as a decimal. * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtoull(). Return code must be checked. */ noinline int kstrtoull(const char *s, unsigned int base, unsigned long long *res) { if (s[0] == '+') s++; return _kstrtoull(s, base, res); } EXPORT_SYMBOL(kstrtoull); /** * kstrtoll - convert a string to a long long * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign or a minus sign. * @base: The number base to use. The maximum supported base is 16. If base is * given as 0, then the base of the string is automatically detected with the * conventional semantics - If it begins with 0x the number will be parsed as a * hexadecimal (case insensitive), if it otherwise begins with 0, it will be * parsed as an octal number. Otherwise it will be parsed as a decimal. * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtoll(). Return code must be checked. */ noinline int kstrtoll(const char *s, unsigned int base, long long *res) { unsigned long long tmp; int rv; if (s[0] == '-') { rv = _kstrtoull(s + 1, base, &tmp); if (rv < 0) return rv; if ((long long)-tmp > 0) return -ERANGE; *res = -tmp; } else { rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if ((long long)tmp < 0) return -ERANGE; *res = tmp; } return 0; } EXPORT_SYMBOL(kstrtoll); /* Internal, do not use. */ int _kstrtoul(const char *s, unsigned int base, unsigned long *res) { unsigned long long tmp; int rv; rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if (tmp != (unsigned long)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(_kstrtoul); /* Internal, do not use. */ int _kstrtol(const char *s, unsigned int base, long *res) { long long tmp; int rv; rv = kstrtoll(s, base, &tmp); if (rv < 0) return rv; if (tmp != (long)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(_kstrtol); /** * kstrtouint - convert a string to an unsigned int * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign, but not a minus sign. * @base: The number base to use. The maximum supported base is 16. If base is * given as 0, then the base of the string is automatically detected with the * conventional semantics - If it begins with 0x the number will be parsed as a * hexadecimal (case insensitive), if it otherwise begins with 0, it will be * parsed as an octal number. Otherwise it will be parsed as a decimal. * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtoul(). Return code must be checked. */ noinline int kstrtouint(const char *s, unsigned int base, unsigned int *res) { unsigned long long tmp; int rv; rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if (tmp != (unsigned int)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtouint); /** * kstrtoint - convert a string to an int * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign or a minus sign. * @base: The number base to use. The maximum supported base is 16. If base is * given as 0, then the base of the string is automatically detected with the * conventional semantics - If it begins with 0x the number will be parsed as a * hexadecimal (case insensitive), if it otherwise begins with 0, it will be * parsed as an octal number. Otherwise it will be parsed as a decimal. * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtol(). Return code must be checked. */ noinline int kstrtoint(const char *s, unsigned int base, int *res) { long long tmp; int rv; rv = kstrtoll(s, base, &tmp); if (rv < 0) return rv; if (tmp != (int)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtoint); noinline int kstrtou16(const char *s, unsigned int base, u16 *res) { unsigned long long tmp; int rv; rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if (tmp != (u16)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtou16); noinline int kstrtos16(const char *s, unsigned int base, s16 *res) { long long tmp; int rv; rv = kstrtoll(s, base, &tmp); if (rv < 0) return rv; if (tmp != (s16)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtos16); noinline int kstrtou8(const char *s, unsigned int base, u8 *res) { unsigned long long tmp; int rv; rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if (tmp != (u8)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtou8); noinline int kstrtos8(const char *s, unsigned int base, s8 *res) { long long tmp; int rv; rv = kstrtoll(s, base, &tmp); if (rv < 0) return rv; if (tmp != (s8)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtos8); /** * kstrtobool - convert common user inputs into boolean values * @s: input string * @res: result * * This routine returns 0 iff the first character is one of 'YyTt1NnFf0', or * [oO][NnFf] for "on" and "off". Otherwise it will return -EINVAL. Value * pointed to by res is updated upon finding a match. */ noinline int kstrtobool(const char *s, bool *res) { if (!s) return -EINVAL; switch (s[0]) { case 'y': case 'Y': case 't': case 'T': case '1': *res = true; return 0; case 'n': case 'N': case 'f': case 'F': case '0': *res = false; return 0; case 'o': case 'O': switch (s[1]) { case 'n': case 'N': *res = true; return 0; case 'f': case 'F': *res = false; return 0; default: break; } break; default: break; } return -EINVAL; } EXPORT_SYMBOL(kstrtobool); /* * Since "base" would be a nonsense argument, this open-codes the * _from_user helper instead of using the helper macro below. */ int kstrtobool_from_user(const char __user *s, size_t count, bool *res) { /* Longest string needed to differentiate, newline, terminator */ char buf[4]; count = min(count, sizeof(buf) - 1); if (copy_from_user(buf, s, count)) return -EFAULT; buf[count] = '\0'; return kstrtobool(buf, res); } EXPORT_SYMBOL(kstrtobool_from_user); #define kstrto_from_user(f, g, type) \ int f(const char __user *s, size_t count, unsigned int base, type *res) \ { \ /* sign, base 2 representation, newline, terminator */ \ char buf[1 + sizeof(type) * 8 + 1 + 1]; \ \ count = min(count, sizeof(buf) - 1); \ if (copy_from_user(buf, s, count)) \ return -EFAULT; \ buf[count] = '\0'; \ return g(buf, base, res); \ } \ EXPORT_SYMBOL(f) kstrto_from_user(kstrtoull_from_user, kstrtoull, unsigned long long); kstrto_from_user(kstrtoll_from_user, kstrtoll, long long); kstrto_from_user(kstrtoul_from_user, kstrtoul, unsigned long); kstrto_from_user(kstrtol_from_user, kstrtol, long); kstrto_from_user(kstrtouint_from_user, kstrtouint, unsigned int); kstrto_from_user(kstrtoint_from_user, kstrtoint, int); kstrto_from_user(kstrtou16_from_user, kstrtou16, u16); kstrto_from_user(kstrtos16_from_user, kstrtos16, s16); kstrto_from_user(kstrtou8_from_user, kstrtou8, u8); kstrto_from_user(kstrtos8_from_user, kstrtos8, s8); |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Declarations for error reporting tracepoints. * * Copyright (C) 2021, Google LLC. */ #undef TRACE_SYSTEM #define TRACE_SYSTEM error_report #if !defined(_TRACE_ERROR_REPORT_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_ERROR_REPORT_H #include <linux/tracepoint.h> #ifndef __ERROR_REPORT_DECLARE_TRACE_ENUMS_ONCE_ONLY #define __ERROR_REPORT_DECLARE_TRACE_ENUMS_ONCE_ONLY enum error_detector { ERROR_DETECTOR_KFENCE, ERROR_DETECTOR_KASAN, ERROR_DETECTOR_WARN, }; #endif /* __ERROR_REPORT_DECLARE_TRACE_ENUMS_ONCE_ONLY */ #define error_detector_list \ EM(ERROR_DETECTOR_KFENCE, "kfence") \ EM(ERROR_DETECTOR_KASAN, "kasan") \ EMe(ERROR_DETECTOR_WARN, "warning") /* Always end the list with an EMe. */ #undef EM #undef EMe #define EM(a, b) TRACE_DEFINE_ENUM(a); #define EMe(a, b) TRACE_DEFINE_ENUM(a); error_detector_list #undef EM #undef EMe #define EM(a, b) { a, b }, #define EMe(a, b) { a, b } #define show_error_detector_list(val) \ __print_symbolic(val, error_detector_list) DECLARE_EVENT_CLASS(error_report_template, TP_PROTO(enum error_detector error_detector, unsigned long id), TP_ARGS(error_detector, id), TP_STRUCT__entry(__field(enum error_detector, error_detector) __field(unsigned long, id)), TP_fast_assign(__entry->error_detector = error_detector; __entry->id = id;), TP_printk("[%s] %lx", show_error_detector_list(__entry->error_detector), __entry->id)); /** * error_report_end - called after printing the error report * @error_detector: short string describing the error detection tool * @id: pseudo-unique descriptor identifying the report * (e.g. the memory access address) * * This event occurs right after a debugging tool finishes printing the error * report. */ DEFINE_EVENT(error_report_template, error_report_end, TP_PROTO(enum error_detector error_detector, unsigned long id), TP_ARGS(error_detector, id)); #endif /* _TRACE_ERROR_REPORT_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1636 1635 1636 1636 1636 515 515 543 16 16 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 | // SPDX-License-Identifier: GPL-2.0 /* * fs/sysfs/symlink.c - sysfs symlink implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007 Tejun Heo <teheo@suse.de> * * Please see Documentation/filesystems/sysfs.rst for more information. */ #include <linux/fs.h> #include <linux/module.h> #include <linux/kobject.h> #include <linux/mutex.h> #include <linux/security.h> #include "sysfs.h" static int sysfs_do_create_link_sd(struct kernfs_node *parent, struct kobject *target_kobj, const char *name, int warn) { struct kernfs_node *kn, *target = NULL; if (WARN_ON(!name || !parent)) return -EINVAL; /* * We don't own @target_kobj and it may be removed at any time. * Synchronize using sysfs_symlink_target_lock. See * sysfs_remove_dir() for details. */ spin_lock(&sysfs_symlink_target_lock); if (target_kobj->sd) { target = target_kobj->sd; kernfs_get(target); } spin_unlock(&sysfs_symlink_target_lock); if (!target) return -ENOENT; kn = kernfs_create_link(parent, name, target); kernfs_put(target); if (!IS_ERR(kn)) return 0; if (warn && PTR_ERR(kn) == -EEXIST) sysfs_warn_dup(parent, name); return PTR_ERR(kn); } /** * sysfs_create_link_sd - create symlink to a given object. * @kn: directory we're creating the link in. * @target: object we're pointing to. * @name: name of the symlink. */ int sysfs_create_link_sd(struct kernfs_node *kn, struct kobject *target, const char *name) { return sysfs_do_create_link_sd(kn, target, name, 1); } static int sysfs_do_create_link(struct kobject *kobj, struct kobject *target, const char *name, int warn) { struct kernfs_node *parent = NULL; if (!kobj) parent = sysfs_root_kn; else parent = kobj->sd; if (!parent) return -EFAULT; return sysfs_do_create_link_sd(parent, target, name, warn); } /** * sysfs_create_link - create symlink between two objects. * @kobj: object whose directory we're creating the link in. * @target: object we're pointing to. * @name: name of the symlink. */ int sysfs_create_link(struct kobject *kobj, struct kobject *target, const char *name) { return sysfs_do_create_link(kobj, target, name, 1); } EXPORT_SYMBOL_GPL(sysfs_create_link); /** * sysfs_create_link_nowarn - create symlink between two objects. * @kobj: object whose directory we're creating the link in. * @target: object we're pointing to. * @name: name of the symlink. * * This function does the same as sysfs_create_link(), but it * doesn't warn if the link already exists. */ int sysfs_create_link_nowarn(struct kobject *kobj, struct kobject *target, const char *name) { return sysfs_do_create_link(kobj, target, name, 0); } EXPORT_SYMBOL_GPL(sysfs_create_link_nowarn); /** * sysfs_delete_link - remove symlink in object's directory. * @kobj: object we're acting for. * @targ: object we're pointing to. * @name: name of the symlink to remove. * * Unlike sysfs_remove_link sysfs_delete_link has enough information * to successfully delete symlinks in tagged directories. */ void sysfs_delete_link(struct kobject *kobj, struct kobject *targ, const char *name) { const void *ns = NULL; /* * We don't own @target and it may be removed at any time. * Synchronize using sysfs_symlink_target_lock. See * sysfs_remove_dir() for details. */ spin_lock(&sysfs_symlink_target_lock); if (targ->sd && kernfs_ns_enabled(kobj->sd)) ns = targ->sd->ns; spin_unlock(&sysfs_symlink_target_lock); kernfs_remove_by_name_ns(kobj->sd, name, ns); } /** * sysfs_remove_link - remove symlink in object's directory. * @kobj: object we're acting for. * @name: name of the symlink to remove. */ void sysfs_remove_link(struct kobject *kobj, const char *name) { struct kernfs_node *parent = NULL; if (!kobj) parent = sysfs_root_kn; else parent = kobj->sd; kernfs_remove_by_name(parent, name); } EXPORT_SYMBOL_GPL(sysfs_remove_link); /** * sysfs_rename_link_ns - rename symlink in object's directory. * @kobj: object we're acting for. * @targ: object we're pointing to. * @old: previous name of the symlink. * @new: new name of the symlink. * @new_ns: new namespace of the symlink. * * A helper function for the common rename symlink idiom. */ int sysfs_rename_link_ns(struct kobject *kobj, struct kobject *targ, const char *old, const char *new, const void *new_ns) { struct kernfs_node *parent, *kn = NULL; const void *old_ns = NULL; int result; if (!kobj) parent = sysfs_root_kn; else parent = kobj->sd; if (targ->sd) old_ns = targ->sd->ns; result = -ENOENT; kn = kernfs_find_and_get_ns(parent, old, old_ns); if (!kn) goto out; result = -EINVAL; if (kernfs_type(kn) != KERNFS_LINK) goto out; if (kn->symlink.target_kn->priv != targ) goto out; result = kernfs_rename_ns(kn, parent, new, new_ns); out: kernfs_put(kn); return result; } EXPORT_SYMBOL_GPL(sysfs_rename_link_ns); |
| 1992 10 1439 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_GENERIC_PGALLOC_H #define __ASM_GENERIC_PGALLOC_H #ifdef CONFIG_MMU #define GFP_PGTABLE_KERNEL (GFP_KERNEL | __GFP_ZERO) #define GFP_PGTABLE_USER (GFP_PGTABLE_KERNEL | __GFP_ACCOUNT) /** * __pte_alloc_one_kernel - allocate a page for PTE-level kernel page table * @mm: the mm_struct of the current context * * This function is intended for architectures that need * anything beyond simple page allocation. * * Return: pointer to the allocated memory or %NULL on error */ static inline pte_t *__pte_alloc_one_kernel(struct mm_struct *mm) { return (pte_t *)__get_free_page(GFP_PGTABLE_KERNEL); } #ifndef __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL /** * pte_alloc_one_kernel - allocate a page for PTE-level kernel page table * @mm: the mm_struct of the current context * * Return: pointer to the allocated memory or %NULL on error */ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) { return __pte_alloc_one_kernel(mm); } #endif /** * pte_free_kernel - free PTE-level kernel page table page * @mm: the mm_struct of the current context * @pte: pointer to the memory containing the page table */ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { free_page((unsigned long)pte); } /** * __pte_alloc_one - allocate a page for PTE-level user page table * @mm: the mm_struct of the current context * @gfp: GFP flags to use for the allocation * * Allocates a page and runs the pgtable_pte_page_ctor(). * * This function is intended for architectures that need * anything beyond simple page allocation or must have custom GFP flags. * * Return: `struct page` initialized as page table or %NULL on error */ static inline pgtable_t __pte_alloc_one(struct mm_struct *mm, gfp_t gfp) { struct page *pte; pte = alloc_page(gfp); if (!pte) return NULL; if (!pgtable_pte_page_ctor(pte)) { __free_page(pte); return NULL; } return pte; } #ifndef __HAVE_ARCH_PTE_ALLOC_ONE /** * pte_alloc_one - allocate a page for PTE-level user page table * @mm: the mm_struct of the current context * * Allocates a page and runs the pgtable_pte_page_ctor(). * * Return: `struct page` initialized as page table or %NULL on error */ static inline pgtable_t pte_alloc_one(struct mm_struct *mm) { return __pte_alloc_one(mm, GFP_PGTABLE_USER); } #endif /* * Should really implement gc for free page table pages. This could be * done with a reference count in struct page. */ /** * pte_free - free PTE-level user page table page * @mm: the mm_struct of the current context * @pte_page: the `struct page` representing the page table */ static inline void pte_free(struct mm_struct *mm, struct page *pte_page) { pgtable_pte_page_dtor(pte_page); __free_page(pte_page); } #if CONFIG_PGTABLE_LEVELS > 2 #ifndef __HAVE_ARCH_PMD_ALLOC_ONE /** * pmd_alloc_one - allocate a page for PMD-level page table * @mm: the mm_struct of the current context * * Allocates a page and runs the pgtable_pmd_page_ctor(). * Allocations use %GFP_PGTABLE_USER in user context and * %GFP_PGTABLE_KERNEL in kernel context. * * Return: pointer to the allocated memory or %NULL on error */ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { struct page *page; gfp_t gfp = GFP_PGTABLE_USER; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; page = alloc_pages(gfp, 0); if (!page) return NULL; if (!pgtable_pmd_page_ctor(page)) { __free_pages(page, 0); return NULL; } return (pmd_t *)page_address(page); } #endif #ifndef __HAVE_ARCH_PMD_FREE static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); pgtable_pmd_page_dtor(virt_to_page(pmd)); free_page((unsigned long)pmd); } #endif #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 static inline pud_t *__pud_alloc_one(struct mm_struct *mm, unsigned long addr) { gfp_t gfp = GFP_PGTABLE_USER; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; return (pud_t *)get_zeroed_page(gfp); } #ifndef __HAVE_ARCH_PUD_ALLOC_ONE /** * pud_alloc_one - allocate a page for PUD-level page table * @mm: the mm_struct of the current context * * Allocates a page using %GFP_PGTABLE_USER for user context and * %GFP_PGTABLE_KERNEL for kernel context. * * Return: pointer to the allocated memory or %NULL on error */ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { return __pud_alloc_one(mm, addr); } #endif static inline void __pud_free(struct mm_struct *mm, pud_t *pud) { BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); free_page((unsigned long)pud); } #ifndef __HAVE_ARCH_PUD_FREE static inline void pud_free(struct mm_struct *mm, pud_t *pud) { __pud_free(mm, pud); } #endif #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #ifndef __HAVE_ARCH_PGD_FREE static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { free_page((unsigned long)pgd); } #endif #endif /* CONFIG_MMU */ #endif /* __ASM_GENERIC_PGALLOC_H */ |
| 1890 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM kmem #if !defined(_TRACE_KMEM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_KMEM_H #include <linux/types.h> #include <linux/tracepoint.h> #include <trace/events/mmflags.h> TRACE_EVENT(kmem_cache_alloc, TP_PROTO(unsigned long call_site, const void *ptr, struct kmem_cache *s, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, s, gfp_flags, node), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) __field( int, node ) __field( bool, accounted ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __entry->bytes_req = s->object_size; __entry->bytes_alloc = s->size; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; __entry->accounted = IS_ENABLED(CONFIG_MEMCG_KMEM) ? ((gfp_flags & __GFP_ACCOUNT) || (s->flags & SLAB_ACCOUNT)) : false; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s", (void *)__entry->call_site, __entry->ptr, __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), __entry->node, __entry->accounted ? "true" : "false") ); TRACE_EVENT(kmalloc, TP_PROTO(unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) __field( int, node ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __entry->bytes_req = bytes_req; __entry->bytes_alloc = bytes_alloc; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s", (void *)__entry->call_site, __entry->ptr, __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), __entry->node, (IS_ENABLED(CONFIG_MEMCG_KMEM) && (__entry->gfp_flags & (__force unsigned long)__GFP_ACCOUNT)) ? "true" : "false") ); TRACE_EVENT(kfree, TP_PROTO(unsigned long call_site, const void *ptr), TP_ARGS(call_site, ptr), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; ), TP_printk("call_site=%pS ptr=%p", (void *)__entry->call_site, __entry->ptr) ); TRACE_EVENT(kmem_cache_free, TP_PROTO(unsigned long call_site, const void *ptr, const struct kmem_cache *s), TP_ARGS(call_site, ptr, s), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __string( name, s->name ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __assign_str(name, s->name); ), TP_printk("call_site=%pS ptr=%p name=%s", (void *)__entry->call_site, __entry->ptr, __get_str(name)) ); TRACE_EVENT(mm_page_free, TP_PROTO(struct page *page, unsigned int order), TP_ARGS(page, order), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->order = order; ), TP_printk("page=%p pfn=0x%lx order=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order) ); TRACE_EVENT(mm_page_free_batched, TP_PROTO(struct page *page), TP_ARGS(page), TP_STRUCT__entry( __field( unsigned long, pfn ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); ), TP_printk("page=%p pfn=0x%lx order=0", pfn_to_page(__entry->pfn), __entry->pfn) ); TRACE_EVENT(mm_page_alloc, TP_PROTO(struct page *page, unsigned int order, gfp_t gfp_flags, int migratetype), TP_ARGS(page, order, gfp_flags, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( unsigned long, gfp_flags ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=0x%lx order=%d migratetype=%d gfp_flags=%s", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, show_gfp_flags(__entry->gfp_flags)) ); DECLARE_EVENT_CLASS(mm_page, TP_PROTO(struct page *page, unsigned int order, int migratetype, int percpu_refill), TP_ARGS(page, order, migratetype, percpu_refill), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) __field( int, percpu_refill ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; __entry->percpu_refill = percpu_refill; ), TP_printk("page=%p pfn=0x%lx order=%u migratetype=%d percpu_refill=%d", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, __entry->percpu_refill) ); DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked, TP_PROTO(struct page *page, unsigned int order, int migratetype, int percpu_refill), TP_ARGS(page, order, migratetype, percpu_refill) ); TRACE_EVENT(mm_page_pcpu_drain, TP_PROTO(struct page *page, unsigned int order, int migratetype), TP_ARGS(page, order, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=0x%lx order=%d migratetype=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order, __entry->migratetype) ); TRACE_EVENT(mm_page_alloc_extfrag, TP_PROTO(struct page *page, int alloc_order, int fallback_order, int alloc_migratetype, int fallback_migratetype), TP_ARGS(page, alloc_order, fallback_order, alloc_migratetype, fallback_migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( int, alloc_order ) __field( int, fallback_order ) __field( int, alloc_migratetype ) __field( int, fallback_migratetype ) __field( int, change_ownership ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->alloc_order = alloc_order; __entry->fallback_order = fallback_order; __entry->alloc_migratetype = alloc_migratetype; __entry->fallback_migratetype = fallback_migratetype; __entry->change_ownership = (alloc_migratetype == get_pageblock_migratetype(page)); ), TP_printk("page=%p pfn=0x%lx alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->alloc_order, __entry->fallback_order, pageblock_order, __entry->alloc_migratetype, __entry->fallback_migratetype, __entry->fallback_order < pageblock_order, __entry->change_ownership) ); TRACE_EVENT(mm_alloc_contig_migrate_range_info, TP_PROTO(unsigned long start, unsigned long end, unsigned long nr_migrated, unsigned long nr_reclaimed, unsigned long nr_mapped, int migratetype), TP_ARGS(start, end, nr_migrated, nr_reclaimed, nr_mapped, migratetype), TP_STRUCT__entry( __field(unsigned long, start) __field(unsigned long, end) __field(unsigned long, nr_migrated) __field(unsigned long, nr_reclaimed) __field(unsigned long, nr_mapped) __field(int, migratetype) ), TP_fast_assign( __entry->start = start; __entry->end = end; __entry->nr_migrated = nr_migrated; __entry->nr_reclaimed = nr_reclaimed; __entry->nr_mapped = nr_mapped; __entry->migratetype = migratetype; ), TP_printk("start=0x%lx end=0x%lx migratetype=%d nr_migrated=%lu nr_reclaimed=%lu nr_mapped=%lu", __entry->start, __entry->end, __entry->migratetype, __entry->nr_migrated, __entry->nr_reclaimed, __entry->nr_mapped) ); /* * Required for uniquely and securely identifying mm in rss_stat tracepoint. */ #ifndef __PTR_TO_HASHVAL static unsigned int __maybe_unused mm_ptr_to_hash(const void *ptr) { int ret; unsigned long hashval; ret = ptr_to_hashval(ptr, &hashval); if (ret) return 0; /* The hashed value is only 32-bit */ return (unsigned int)hashval; } #define __PTR_TO_HASHVAL #endif #define TRACE_MM_PAGES \ EM(MM_FILEPAGES) \ EM(MM_ANONPAGES) \ EM(MM_SWAPENTS) \ EMe(MM_SHMEMPAGES) #undef EM #undef EMe #define EM(a) TRACE_DEFINE_ENUM(a); #define EMe(a) TRACE_DEFINE_ENUM(a); TRACE_MM_PAGES #undef EM #undef EMe #define EM(a) { a, #a }, #define EMe(a) { a, #a } TRACE_EVENT(rss_stat, TP_PROTO(struct mm_struct *mm, int member, long count), TP_ARGS(mm, member, count), TP_STRUCT__entry( __field(unsigned int, mm_id) __field(unsigned int, curr) __field(int, member) __field(long, size) ), TP_fast_assign( __entry->mm_id = mm_ptr_to_hash(mm); __entry->curr = !!(current->mm == mm); __entry->member = member; __entry->size = (count << PAGE_SHIFT); ), TP_printk("mm_id=%u curr=%d type=%s size=%ldB", __entry->mm_id, __entry->curr, __print_symbolic(__entry->member, TRACE_MM_PAGES), __entry->size) ); #endif /* _TRACE_KMEM_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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the RAW-IP module. * * Version: @(#)raw.h 1.0.2 05/07/93 * * Author: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _RAW_H #define _RAW_H #include <net/inet_sock.h> #include <net/protocol.h> #include <net/netns/hash.h> #include <linux/hash.h> #include <linux/icmp.h> extern struct proto raw_prot; extern struct raw_hashinfo raw_v4_hashinfo; bool raw_v4_match(struct net *net, struct sock *sk, unsigned short num, __be32 raddr, __be32 laddr, int dif, int sdif); int raw_abort(struct sock *sk, int err); void raw_icmp_error(struct sk_buff *, int, u32); int raw_local_deliver(struct sk_buff *, int); int raw_rcv(struct sock *, struct sk_buff *); #define RAW_HTABLE_LOG 8 #define RAW_HTABLE_SIZE (1U << RAW_HTABLE_LOG) struct raw_hashinfo { spinlock_t lock; struct hlist_head ht[RAW_HTABLE_SIZE] ____cacheline_aligned; }; static inline u32 raw_hashfunc(const struct net *net, u32 proto) { return hash_32(net_hash_mix(net) ^ proto, RAW_HTABLE_LOG); } static inline void raw_hashinfo_init(struct raw_hashinfo *hashinfo) { int i; spin_lock_init(&hashinfo->lock); for (i = 0; i < RAW_HTABLE_SIZE; i++) INIT_HLIST_HEAD(&hashinfo->ht[i]); } #ifdef CONFIG_PROC_FS int raw_proc_init(void); void raw_proc_exit(void); struct raw_iter_state { struct seq_net_private p; int bucket; }; static inline struct raw_iter_state *raw_seq_private(struct seq_file *seq) { return seq->private; } void *raw_seq_start(struct seq_file *seq, loff_t *pos); void *raw_seq_next(struct seq_file *seq, void *v, loff_t *pos); void raw_seq_stop(struct seq_file *seq, void *v); #endif int raw_hash_sk(struct sock *sk); void raw_unhash_sk(struct sock *sk); void raw_init(void); struct raw_sock { /* inet_sock has to be the first member */ struct inet_sock inet; struct icmp_filter filter; u32 ipmr_table; }; static inline struct raw_sock *raw_sk(const struct sock *sk) { return (struct raw_sock *)sk; } static inline bool raw_sk_bound_dev_eq(struct net *net, int bound_dev_if, int dif, int sdif) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) return inet_bound_dev_eq(READ_ONCE(net->ipv4.sysctl_raw_l3mdev_accept), bound_dev_if, dif, sdif); #else return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); #endif } #endif /* _RAW_H */ |
| 1589 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 | // SPDX-License-Identifier: GPL-2.0-or-later /* delayacct.c - per-task delay accounting * * Copyright (C) Shailabh Nagar, IBM Corp. 2006 */ #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/sched/cputime.h> #include <linux/sched/clock.h> #include <linux/slab.h> #include <linux/taskstats.h> #include <linux/sysctl.h> #include <linux/delayacct.h> #include <linux/module.h> #ifdef CONFIG_TASK_DELAY_ACCT DEFINE_STATIC_KEY_FALSE(delayacct_key); int delayacct_on __read_mostly; /* Delay accounting turned on/off */ struct kmem_cache *delayacct_cache; static void set_delayacct(bool enabled) { if (enabled) { static_branch_enable(&delayacct_key); delayacct_on = 1; } else { delayacct_on = 0; static_branch_disable(&delayacct_key); } } static int __init delayacct_setup_enable(char *str) { delayacct_on = 1; return 1; } __setup("delayacct", delayacct_setup_enable); void delayacct_init(void) { delayacct_cache = KMEM_CACHE(task_delay_info, SLAB_PANIC|SLAB_ACCOUNT); delayacct_tsk_init(&init_task); set_delayacct(delayacct_on); } #ifdef CONFIG_PROC_SYSCTL static int sysctl_delayacct(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int state = delayacct_on; struct ctl_table t; int err; if (write && !capable(CAP_SYS_ADMIN)) return -EPERM; t = *table; t.data = &state; err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); if (err < 0) return err; if (write) set_delayacct(state); return err; } static struct ctl_table kern_delayacct_table[] = { { .procname = "task_delayacct", .data = NULL, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = sysctl_delayacct, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { } }; static __init int kernel_delayacct_sysctls_init(void) { register_sysctl_init("kernel", kern_delayacct_table); return 0; } late_initcall(kernel_delayacct_sysctls_init); #endif void __delayacct_tsk_init(struct task_struct *tsk) { tsk->delays = kmem_cache_zalloc(delayacct_cache, GFP_KERNEL); if (tsk->delays) raw_spin_lock_init(&tsk->delays->lock); } /* * Finish delay accounting for a statistic using its timestamps (@start), * accumalator (@total) and @count */ static void delayacct_end(raw_spinlock_t *lock, u64 *start, u64 *total, u32 *count) { s64 ns = local_clock() - *start; unsigned long flags; if (ns > 0) { raw_spin_lock_irqsave(lock, flags); *total += ns; (*count)++; raw_spin_unlock_irqrestore(lock, flags); } } void __delayacct_blkio_start(void) { current->delays->blkio_start = local_clock(); } /* * We cannot rely on the `current` macro, as we haven't yet switched back to * the process being woken. */ void __delayacct_blkio_end(struct task_struct *p) { delayacct_end(&p->delays->lock, &p->delays->blkio_start, &p->delays->blkio_delay, &p->delays->blkio_count); } int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) { u64 utime, stime, stimescaled, utimescaled; unsigned long long t2, t3; unsigned long flags, t1; s64 tmp; task_cputime(tsk, &utime, &stime); tmp = (s64)d->cpu_run_real_total; tmp += utime + stime; d->cpu_run_real_total = (tmp < (s64)d->cpu_run_real_total) ? 0 : tmp; task_cputime_scaled(tsk, &utimescaled, &stimescaled); tmp = (s64)d->cpu_scaled_run_real_total; tmp += utimescaled + stimescaled; d->cpu_scaled_run_real_total = (tmp < (s64)d->cpu_scaled_run_real_total) ? 0 : tmp; /* * No locking available for sched_info (and too expensive to add one) * Mitigate by taking snapshot of values */ t1 = tsk->sched_info.pcount; t2 = tsk->sched_info.run_delay; t3 = tsk->se.sum_exec_runtime; d->cpu_count += t1; tmp = (s64)d->cpu_delay_total + t2; d->cpu_delay_total = (tmp < (s64)d->cpu_delay_total) ? 0 : tmp; tmp = (s64)d->cpu_run_virtual_total + t3; d->cpu_run_virtual_total = (tmp < (s64)d->cpu_run_virtual_total) ? 0 : tmp; if (!tsk->delays) return 0; /* zero XXX_total, non-zero XXX_count implies XXX stat overflowed */ raw_spin_lock_irqsave(&tsk->delays->lock, flags); tmp = d->blkio_delay_total + tsk->delays->blkio_delay; d->blkio_delay_total = (tmp < d->blkio_delay_total) ? 0 : tmp; tmp = d->swapin_delay_total + tsk->delays->swapin_delay; d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp; tmp = d->freepages_delay_total + tsk->delays->freepages_delay; d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp; tmp = d->thrashing_delay_total + tsk->delays->thrashing_delay; d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp; tmp = d->compact_delay_total + tsk->delays->compact_delay; d->compact_delay_total = (tmp < d->compact_delay_total) ? 0 : tmp; tmp = d->wpcopy_delay_total + tsk->delays->wpcopy_delay; d->wpcopy_delay_total = (tmp < d->wpcopy_delay_total) ? 0 : tmp; d->blkio_count += tsk->delays->blkio_count; d->swapin_count += tsk->delays->swapin_count; d->freepages_count += tsk->delays->freepages_count; d->thrashing_count += tsk->delays->thrashing_count; d->compact_count += tsk->delays->compact_count; d->wpcopy_count += tsk->delays->wpcopy_count; raw_spin_unlock_irqrestore(&tsk->delays->lock, flags); return 0; } __u64 __delayacct_blkio_ticks(struct task_struct *tsk) { __u64 ret; unsigned long flags; raw_spin_lock_irqsave(&tsk->delays->lock, flags); ret = nsec_to_clock_t(tsk->delays->blkio_delay); raw_spin_unlock_irqrestore(&tsk->delays->lock, flags); return ret; } void __delayacct_freepages_start(void) { current->delays->freepages_start = local_clock(); } void __delayacct_freepages_end(void) { delayacct_end(¤t->delays->lock, ¤t->delays->freepages_start, ¤t->delays->freepages_delay, ¤t->delays->freepages_count); } void __delayacct_thrashing_start(bool *in_thrashing) { *in_thrashing = !!current->in_thrashing; if (*in_thrashing) return; current->in_thrashing = 1; current->delays->thrashing_start = local_clock(); } void __delayacct_thrashing_end(bool *in_thrashing) { if (*in_thrashing) return; current->in_thrashing = 0; delayacct_end(¤t->delays->lock, ¤t->delays->thrashing_start, ¤t->delays->thrashing_delay, ¤t->delays->thrashing_count); } void __delayacct_swapin_start(void) { current->delays->swapin_start = local_clock(); } void __delayacct_swapin_end(void) { delayacct_end(¤t->delays->lock, ¤t->delays->swapin_start, ¤t->delays->swapin_delay, ¤t->delays->swapin_count); } void __delayacct_compact_start(void) { current->delays->compact_start = local_clock(); } void __delayacct_compact_end(void) { delayacct_end(¤t->delays->lock, ¤t->delays->compact_start, ¤t->delays->compact_delay, ¤t->delays->compact_count); } void __delayacct_wpcopy_start(void) { current->delays->wpcopy_start = local_clock(); } void __delayacct_wpcopy_end(void) { delayacct_end(¤t->delays->lock, ¤t->delays->wpcopy_start, ¤t->delays->wpcopy_delay, ¤t->delays->wpcopy_count); } #else #include <trace/hooks/delayacct.h> int delayacct_enabled __read_mostly; /* Delay accounting turned on/off */ bool get_delayacct_enabled(void) { return delayacct_enabled; } void set_delayacct_enabled(bool enabled) { delayacct_enabled = enabled; } EXPORT_SYMBOL_GPL(set_delayacct_enabled); void _trace_android_rvh_delayacct_init(void) { trace_android_rvh_delayacct_init(NULL); } void _trace_android_rvh_delayacct_tsk_init(struct task_struct *tsk) { trace_android_rvh_delayacct_tsk_init(tsk); } void _trace_android_rvh_delayacct_tsk_free(struct task_struct *tsk) { trace_android_rvh_delayacct_tsk_free(tsk); } void _trace_android_vh_delayacct_blkio_start(void) { trace_android_vh_delayacct_blkio_start(NULL); } void _trace_android_vh_delayacct_blkio_end(struct task_struct *p) { trace_android_vh_delayacct_blkio_end(p); } void _trace_android_vh_delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk, int *ret) { trace_android_vh_delayacct_add_tsk(d, tsk, ret); } void _trace_android_vh_delayacct_blkio_ticks(struct task_struct *tsk, __u64 *ret) { trace_android_vh_delayacct_blkio_ticks(tsk, ret); } void _trace_android_vh_delayacct_freepages_start(void) { trace_android_vh_delayacct_freepages_start(NULL); } void _trace_android_vh_delayacct_freepages_end(void) { trace_android_vh_delayacct_freepages_end(NULL); } void _trace_android_vh_delayacct_thrashing_start(bool *in_thrashing) { trace_android_vh_delayacct_thrashing_start(in_thrashing); } void _trace_android_vh_delayacct_thrashing_end(bool *in_thrashing) { trace_android_vh_delayacct_thrashing_end(in_thrashing); } void _trace_android_vh_delayacct_swapin_start(void) { trace_android_vh_delayacct_swapin_start(NULL); } void _trace_android_vh_delayacct_swapin_end(void) { trace_android_vh_delayacct_swapin_end(NULL); } void _trace_android_vh_delayacct_compact_start(void) { trace_android_vh_delayacct_compact_start(NULL); } void _trace_android_vh_delayacct_compact_end(void) { trace_android_vh_delayacct_compact_end(NULL); } void _trace_android_vh_delayacct_wpcopy_start(void) { trace_android_vh_delayacct_wpcopy_start(NULL); } void _trace_android_vh_delayacct_wpcopy_end(void) { trace_android_vh_delayacct_wpcopy_end(NULL); } #endif |
| 7145 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 | /* SPDX-License-Identifier: GPL-2.0 */ /* thread_info.h: common low-level thread information accessors * * Copyright (C) 2002 David Howells (dhowells@redhat.com) * - Incorporating suggestions made by Linus Torvalds */ #ifndef _LINUX_THREAD_INFO_H #define _LINUX_THREAD_INFO_H #include <linux/types.h> #include <linux/limits.h> #include <linux/bug.h> #include <linux/restart_block.h> #include <linux/errno.h> #ifdef CONFIG_THREAD_INFO_IN_TASK /* * For CONFIG_THREAD_INFO_IN_TASK kernels we need <asm/current.h> for the * definition of current, but for !CONFIG_THREAD_INFO_IN_TASK kernels, * including <asm/current.h> can cause a circular dependency on some platforms. */ #include <asm/current.h> #define current_thread_info() ((struct thread_info *)current) #endif #include <linux/bitops.h> /* * For per-arch arch_within_stack_frames() implementations, defined in * asm/thread_info.h. */ enum { BAD_STACK = -1, NOT_STACK = 0, GOOD_FRAME, GOOD_STACK, }; #ifdef CONFIG_GENERIC_ENTRY enum syscall_work_bit { SYSCALL_WORK_BIT_SECCOMP, SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT, SYSCALL_WORK_BIT_SYSCALL_TRACE, SYSCALL_WORK_BIT_SYSCALL_EMU, SYSCALL_WORK_BIT_SYSCALL_AUDIT, SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH, SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP, }; #define SYSCALL_WORK_SECCOMP BIT(SYSCALL_WORK_BIT_SECCOMP) #define SYSCALL_WORK_SYSCALL_TRACEPOINT BIT(SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT) #define SYSCALL_WORK_SYSCALL_TRACE BIT(SYSCALL_WORK_BIT_SYSCALL_TRACE) #define SYSCALL_WORK_SYSCALL_EMU BIT(SYSCALL_WORK_BIT_SYSCALL_EMU) #define SYSCALL_WORK_SYSCALL_AUDIT BIT(SYSCALL_WORK_BIT_SYSCALL_AUDIT) #define SYSCALL_WORK_SYSCALL_USER_DISPATCH BIT(SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH) #define SYSCALL_WORK_SYSCALL_EXIT_TRAP BIT(SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP) #endif #include <asm/thread_info.h> #ifdef __KERNEL__ #ifndef arch_set_restart_data #define arch_set_restart_data(restart) do { } while (0) #endif static inline long set_restart_fn(struct restart_block *restart, long (*fn)(struct restart_block *)) { restart->fn = fn; arch_set_restart_data(restart); return -ERESTART_RESTARTBLOCK; } #ifndef THREAD_ALIGN #define THREAD_ALIGN THREAD_SIZE #endif #define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_ZERO) /* * flag set/clear/test wrappers * - pass TIF_xxxx constants to these functions */ static inline void set_ti_thread_flag(struct thread_info *ti, int flag) { set_bit(flag, (unsigned long *)&ti->flags); } static inline void clear_ti_thread_flag(struct thread_info *ti, int flag) { clear_bit(flag, (unsigned long *)&ti->flags); } static inline void update_ti_thread_flag(struct thread_info *ti, int flag, bool value) { if (value) set_ti_thread_flag(ti, flag); else clear_ti_thread_flag(ti, flag); } static inline int test_and_set_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_set_bit(flag, (unsigned long *)&ti->flags); } static inline int test_and_clear_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_clear_bit(flag, (unsigned long *)&ti->flags); } static inline int test_ti_thread_flag(struct thread_info *ti, int flag) { return test_bit(flag, (unsigned long *)&ti->flags); } /* * This may be used in noinstr code, and needs to be __always_inline to prevent * inadvertent instrumentation. */ static __always_inline unsigned long read_ti_thread_flags(struct thread_info *ti) { return READ_ONCE(ti->flags); } #define set_thread_flag(flag) \ set_ti_thread_flag(current_thread_info(), flag) #define clear_thread_flag(flag) \ clear_ti_thread_flag(current_thread_info(), flag) #define update_thread_flag(flag, value) \ update_ti_thread_flag(current_thread_info(), flag, value) #define test_and_set_thread_flag(flag) \ test_and_set_ti_thread_flag(current_thread_info(), flag) #define test_and_clear_thread_flag(flag) \ test_and_clear_ti_thread_flag(current_thread_info(), flag) #define test_thread_flag(flag) \ test_ti_thread_flag(current_thread_info(), flag) #define read_thread_flags() \ read_ti_thread_flags(current_thread_info()) #define read_task_thread_flags(t) \ read_ti_thread_flags(task_thread_info(t)) #ifdef CONFIG_GENERIC_ENTRY #define set_syscall_work(fl) \ set_bit(SYSCALL_WORK_BIT_##fl, ¤t_thread_info()->syscall_work) #define test_syscall_work(fl) \ test_bit(SYSCALL_WORK_BIT_##fl, ¤t_thread_info()->syscall_work) #define clear_syscall_work(fl) \ clear_bit(SYSCALL_WORK_BIT_##fl, ¤t_thread_info()->syscall_work) #define set_task_syscall_work(t, fl) \ set_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work) #define test_task_syscall_work(t, fl) \ test_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work) #define clear_task_syscall_work(t, fl) \ clear_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work) #else /* CONFIG_GENERIC_ENTRY */ #define set_syscall_work(fl) \ set_ti_thread_flag(current_thread_info(), TIF_##fl) #define test_syscall_work(fl) \ test_ti_thread_flag(current_thread_info(), TIF_##fl) #define clear_syscall_work(fl) \ clear_ti_thread_flag(current_thread_info(), TIF_##fl) #define set_task_syscall_work(t, fl) \ set_ti_thread_flag(task_thread_info(t), TIF_##fl) #define test_task_syscall_work(t, fl) \ test_ti_thread_flag(task_thread_info(t), TIF_##fl) #define clear_task_syscall_work(t, fl) \ clear_ti_thread_flag(task_thread_info(t), TIF_##fl) #endif /* !CONFIG_GENERIC_ENTRY */ #define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES static inline int arch_within_stack_frames(const void * const stack, const void * const stackend, const void *obj, unsigned long len) { return 0; } #endif #ifdef CONFIG_HARDENED_USERCOPY extern void __check_object_size(const void *ptr, unsigned long n, bool to_user); static __always_inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { if (!__builtin_constant_p(n)) __check_object_size(ptr, n, to_user); } #else static inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { } #endif /* CONFIG_HARDENED_USERCOPY */ extern void __compiletime_error("copy source size is too small") __bad_copy_from(void); extern void __compiletime_error("copy destination size is too small") __bad_copy_to(void); void __copy_overflow(int size, unsigned long count); static inline void copy_overflow(int size, unsigned long count) { if (IS_ENABLED(CONFIG_BUG)) __copy_overflow(size, count); } static __always_inline __must_check bool check_copy_size(const void *addr, size_t bytes, bool is_source) { int sz = __builtin_object_size(addr, 0); if (unlikely(sz >= 0 && sz < bytes)) { if (!__builtin_constant_p(bytes)) copy_overflow(sz, bytes); else if (is_source) __bad_copy_from(); else __bad_copy_to(); return false; } if (WARN_ON_ONCE(bytes > INT_MAX)) return false; check_object_size(addr, bytes, is_source); return true; } #ifndef arch_setup_new_exec static inline void arch_setup_new_exec(void) { } #endif #endif /* __KERNEL__ */ #endif /* _LINUX_THREAD_INFO_H */ |
| 70 259 260 167 39 38 636 70 70 375 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * net/tipc/msg.h: Include file for TIPC message header routines * * Copyright (c) 2000-2007, 2014-2017 Ericsson AB * Copyright (c) 2005-2008, 2010-2011, Wind River Systems * 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_MSG_H #define _TIPC_MSG_H #include <linux/tipc.h> #include "core.h" /* * Constants and routines used to read and write TIPC payload message headers * * Note: Some items are also used with TIPC internal message headers */ #define TIPC_VERSION 2 struct plist; /* * Payload message users are defined in TIPC's public API: * - TIPC_LOW_IMPORTANCE * - TIPC_MEDIUM_IMPORTANCE * - TIPC_HIGH_IMPORTANCE * - TIPC_CRITICAL_IMPORTANCE */ #define TIPC_SYSTEM_IMPORTANCE 4 /* * Payload message types */ #define TIPC_CONN_MSG 0 #define TIPC_MCAST_MSG 1 #define TIPC_NAMED_MSG 2 #define TIPC_DIRECT_MSG 3 #define TIPC_GRP_MEMBER_EVT 4 #define TIPC_GRP_BCAST_MSG 5 #define TIPC_GRP_MCAST_MSG 6 #define TIPC_GRP_UCAST_MSG 7 /* * Internal message users */ #define BCAST_PROTOCOL 5 #define MSG_BUNDLER 6 #define LINK_PROTOCOL 7 #define CONN_MANAGER 8 #define GROUP_PROTOCOL 9 #define TUNNEL_PROTOCOL 10 #define NAME_DISTRIBUTOR 11 #define MSG_FRAGMENTER 12 #define LINK_CONFIG 13 #define MSG_CRYPTO 14 #define SOCK_WAKEUP 14 /* pseudo user */ #define TOP_SRV 15 /* pseudo user */ /* * Message header sizes */ #define SHORT_H_SIZE 24 /* In-cluster basic payload message */ #define BASIC_H_SIZE 32 /* Basic payload message */ #define NAMED_H_SIZE 40 /* Named payload message */ #define MCAST_H_SIZE 44 /* Multicast payload message */ #define GROUP_H_SIZE 44 /* Group payload message */ #define INT_H_SIZE 40 /* Internal messages */ #define MIN_H_SIZE 24 /* Smallest legal TIPC header size */ #define MAX_H_SIZE 60 /* Largest possible TIPC header size */ #define MAX_MSG_SIZE (MAX_H_SIZE + TIPC_MAX_USER_MSG_SIZE) #define TIPC_MEDIA_INFO_OFFSET 5 extern const int one_page_mtu; struct tipc_skb_cb { union { struct { struct sk_buff *tail; unsigned long nxt_retr; unsigned long retr_stamp; u32 bytes_read; u32 orig_member; u16 chain_imp; u16 ackers; u16 retr_cnt; } __packed; #ifdef CONFIG_TIPC_CRYPTO struct { struct tipc_crypto *rx; struct tipc_aead *last; u8 recurs; } tx_clone_ctx __packed; #endif } __packed; union { struct { u8 validated:1; #ifdef CONFIG_TIPC_CRYPTO u8 encrypted:1; u8 decrypted:1; #define SKB_PROBING 1 #define SKB_GRACING 2 u8 xmit_type:2; u8 tx_clone_deferred:1; #endif }; u8 flags; }; u8 reserved; #ifdef CONFIG_TIPC_CRYPTO void *crypto_ctx; #endif } __packed; #define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0])) struct tipc_msg { __be32 hdr[15]; }; /* struct tipc_gap_ack - TIPC Gap ACK block * @ack: seqno of the last consecutive packet in link deferdq * @gap: number of gap packets since the last ack * * E.g: * link deferdq: 1 2 3 4 10 11 13 14 15 20 * --> Gap ACK blocks: <4, 5>, <11, 1>, <15, 4>, <20, 0> */ struct tipc_gap_ack { __be16 ack; __be16 gap; }; /* struct tipc_gap_ack_blks * @len: actual length of the record * @ugack_cnt: number of Gap ACK blocks for unicast (following the broadcast * ones) * @start_index: starting index for "valid" broadcast Gap ACK blocks * @bgack_cnt: number of Gap ACK blocks for broadcast in the record * @gacks: array of Gap ACK blocks * * 31 16 15 0 * +-------------+-------------+-------------+-------------+ * | bgack_cnt | ugack_cnt | len | * +-------------+-------------+-------------+-------------+ - * | gap | ack | | * +-------------+-------------+-------------+-------------+ > bc gacks * : : : | * +-------------+-------------+-------------+-------------+ - * | gap | ack | | * +-------------+-------------+-------------+-------------+ > uc gacks * : : : | * +-------------+-------------+-------------+-------------+ - */ struct tipc_gap_ack_blks { __be16 len; union { u8 ugack_cnt; u8 start_index; }; u8 bgack_cnt; struct tipc_gap_ack gacks[]; }; #define MAX_GAP_ACK_BLKS 128 #define MAX_GAP_ACK_BLKS_SZ (sizeof(struct tipc_gap_ack_blks) + \ sizeof(struct tipc_gap_ack) * MAX_GAP_ACK_BLKS) static inline struct tipc_msg *buf_msg(struct sk_buff *skb) { return (struct tipc_msg *)skb->data; } static inline u32 msg_word(struct tipc_msg *m, u32 pos) { return ntohl(m->hdr[pos]); } static inline void msg_set_word(struct tipc_msg *m, u32 w, u32 val) { m->hdr[w] = htonl(val); } static inline u32 msg_bits(struct tipc_msg *m, u32 w, u32 pos, u32 mask) { return (msg_word(m, w) >> pos) & mask; } static inline void msg_set_bits(struct tipc_msg *m, u32 w, u32 pos, u32 mask, u32 val) { val = (val & mask) << pos; mask = mask << pos; m->hdr[w] &= ~htonl(mask); m->hdr[w] |= htonl(val); } /* * Word 0 */ static inline u32 msg_version(struct tipc_msg *m) { return msg_bits(m, 0, 29, 7); } static inline void msg_set_version(struct tipc_msg *m) { msg_set_bits(m, 0, 29, 7, TIPC_VERSION); } static inline u32 msg_user(struct tipc_msg *m) { return msg_bits(m, 0, 25, 0xf); } static inline u32 msg_isdata(struct tipc_msg *m) { return msg_user(m) <= TIPC_CRITICAL_IMPORTANCE; } static inline void msg_set_user(struct tipc_msg *m, u32 n) { msg_set_bits(m, 0, 25, 0xf, n); } static inline u32 msg_hdr_sz(struct tipc_msg *m) { return msg_bits(m, 0, 21, 0xf) << 2; } static inline void msg_set_hdr_sz(struct tipc_msg *m, u32 n) { msg_set_bits(m, 0, 21, 0xf, n>>2); } static inline u32 msg_size(struct tipc_msg *m) { return msg_bits(m, 0, 0, 0x1ffff); } static inline u32 msg_blocks(struct tipc_msg *m) { return (msg_size(m) / 1024) + 1; } static inline u32 msg_data_sz(struct tipc_msg *m) { return msg_size(m) - msg_hdr_sz(m); } static inline int msg_non_seq(struct tipc_msg *m) { return msg_bits(m, 0, 20, 1); } static inline void msg_set_non_seq(struct tipc_msg *m, u32 n) { msg_set_bits(m, 0, 20, 1, n); } static inline int msg_is_syn(struct tipc_msg *m) { return msg_bits(m, 0, 17, 1); } static inline void msg_set_syn(struct tipc_msg *m, u32 d) { msg_set_bits(m, 0, 17, 1, d); } static inline int msg_dest_droppable(struct tipc_msg *m) { return msg_bits(m, 0, 19, 1); } static inline void msg_set_dest_droppable(struct tipc_msg *m, u32 d) { msg_set_bits(m, 0, 19, 1, d); } static inline int msg_is_keepalive(struct tipc_msg *m) { return msg_bits(m, 0, 19, 1); } static inline void msg_set_is_keepalive(struct tipc_msg *m, u32 d) { msg_set_bits(m, 0, 19, 1, d); } static inline int msg_src_droppable(struct tipc_msg *m) { return msg_bits(m, 0, 18, 1); } static inline void msg_set_src_droppable(struct tipc_msg *m, u32 d) { msg_set_bits(m, 0, 18, 1, d); } static inline int msg_ack_required(struct tipc_msg *m) { return msg_bits(m, 0, 18, 1); } static inline void msg_set_ack_required(struct tipc_msg *m) { msg_set_bits(m, 0, 18, 1, 1); } static inline int msg_nagle_ack(struct tipc_msg *m) { return msg_bits(m, 0, 18, 1); } static inline void msg_set_nagle_ack(struct tipc_msg *m) { msg_set_bits(m, 0, 18, 1, 1); } static inline bool msg_is_rcast(struct tipc_msg *m) { return msg_bits(m, 0, 18, 0x1); } static inline void msg_set_is_rcast(struct tipc_msg *m, bool d) { msg_set_bits(m, 0, 18, 0x1, d); } static inline void msg_set_size(struct tipc_msg *m, u32 sz) { m->hdr[0] = htonl((msg_word(m, 0) & ~0x1ffff) | sz); } static inline unchar *msg_data(struct tipc_msg *m) { return ((unchar *)m) + msg_hdr_sz(m); } static inline struct tipc_msg *msg_inner_hdr(struct tipc_msg *m) { return (struct tipc_msg *)msg_data(m); } /* * Word 1 */ static inline u32 msg_type(struct tipc_msg *m) { return msg_bits(m, 1, 29, 0x7); } static inline void msg_set_type(struct tipc_msg *m, u32 n) { msg_set_bits(m, 1, 29, 0x7, n); } static inline int msg_in_group(struct tipc_msg *m) { int mtyp = msg_type(m); return mtyp >= TIPC_GRP_MEMBER_EVT && mtyp <= TIPC_GRP_UCAST_MSG; } static inline bool msg_is_grp_evt(struct tipc_msg *m) { return msg_type(m) == TIPC_GRP_MEMBER_EVT; } static inline u32 msg_named(struct tipc_msg *m) { return msg_type(m) == TIPC_NAMED_MSG; } static inline u32 msg_mcast(struct tipc_msg *m) { int mtyp = msg_type(m); return ((mtyp == TIPC_MCAST_MSG) || (mtyp == TIPC_GRP_BCAST_MSG) || (mtyp == TIPC_GRP_MCAST_MSG)); } static inline u32 msg_connected(struct tipc_msg *m) { return msg_type(m) == TIPC_CONN_MSG; } static inline u32 msg_direct(struct tipc_msg *m) { return msg_type(m) == TIPC_DIRECT_MSG; } static inline u32 msg_errcode(struct tipc_msg *m) { return msg_bits(m, 1, 25, 0xf); } static inline void msg_set_errcode(struct tipc_msg *m, u32 err) { msg_set_bits(m, 1, 25, 0xf, err); } static inline void msg_set_bulk(struct tipc_msg *m) { msg_set_bits(m, 1, 28, 0x1, 1); } static inline u32 msg_is_bulk(struct tipc_msg *m) { return msg_bits(m, 1, 28, 0x1); } static inline void msg_set_last_bulk(struct tipc_msg *m) { msg_set_bits(m, 1, 27, 0x1, 1); } static inline u32 msg_is_last_bulk(struct tipc_msg *m) { return msg_bits(m, 1, 27, 0x1); } static inline void msg_set_non_legacy(struct tipc_msg *m) { msg_set_bits(m, 1, 26, 0x1, 1); } static inline u32 msg_is_legacy(struct tipc_msg *m) { return !msg_bits(m, 1, 26, 0x1); } static inline u32 msg_reroute_cnt(struct tipc_msg *m) { return msg_bits(m, 1, 21, 0xf); } static inline void msg_incr_reroute_cnt(struct tipc_msg *m) { msg_set_bits(m, 1, 21, 0xf, msg_reroute_cnt(m) + 1); } static inline u32 msg_lookup_scope(struct tipc_msg *m) { return msg_bits(m, 1, 19, 0x3); } static inline void msg_set_lookup_scope(struct tipc_msg *m, u32 n) { msg_set_bits(m, 1, 19, 0x3, n); } static inline u16 msg_bcast_ack(struct tipc_msg *m) { return msg_bits(m, 1, 0, 0xffff); } static inline void msg_set_bcast_ack(struct tipc_msg *m, u16 n) { msg_set_bits(m, 1, 0, 0xffff, n); } /* Note: reusing bits in word 1 for ACTIVATE_MSG only, to re-synch * link peer session number */ static inline bool msg_dest_session_valid(struct tipc_msg *m) { return msg_bits(m, 1, 16, 0x1); } static inline void msg_set_dest_session_valid(struct tipc_msg *m, bool valid) { msg_set_bits(m, 1, 16, 0x1, valid); } static inline u16 msg_dest_session(struct tipc_msg *m) { return msg_bits(m, 1, 0, 0xffff); } static inline void msg_set_dest_session(struct tipc_msg *m, u16 n) { msg_set_bits(m, 1, 0, 0xffff, n); } /* * Word 2 */ static inline u16 msg_ack(struct tipc_msg *m) { return msg_bits(m, 2, 16, 0xffff); } static inline void msg_set_ack(struct tipc_msg *m, u16 n) { msg_set_bits(m, 2, 16, 0xffff, n); } static inline u16 msg_seqno(struct tipc_msg *m) { return msg_bits(m, 2, 0, 0xffff); } static inline void msg_set_seqno(struct tipc_msg *m, u16 n) { msg_set_bits(m, 2, 0, 0xffff, n); } /* * Words 3-10 */ static inline u32 msg_importance(struct tipc_msg *m) { int usr = msg_user(m); if (likely((usr <= TIPC_CRITICAL_IMPORTANCE) && !msg_errcode(m))) return usr; if ((usr == MSG_FRAGMENTER) || (usr == MSG_BUNDLER)) return msg_bits(m, 9, 0, 0x7); return TIPC_SYSTEM_IMPORTANCE; } static inline void msg_set_importance(struct tipc_msg *m, u32 i) { int usr = msg_user(m); if (likely((usr == MSG_FRAGMENTER) || (usr == MSG_BUNDLER))) msg_set_bits(m, 9, 0, 0x7, i); else if (i < TIPC_SYSTEM_IMPORTANCE) msg_set_user(m, i); else pr_warn("Trying to set illegal importance in message\n"); } static inline u32 msg_prevnode(struct tipc_msg *m) { return msg_word(m, 3); } static inline void msg_set_prevnode(struct tipc_msg *m, u32 a) { msg_set_word(m, 3, a); } static inline u32 msg_origport(struct tipc_msg *m) { if (msg_user(m) == MSG_FRAGMENTER) m = msg_inner_hdr(m); return msg_word(m, 4); } static inline void msg_set_origport(struct tipc_msg *m, u32 p) { msg_set_word(m, 4, p); } static inline u16 msg_named_seqno(struct tipc_msg *m) { return msg_bits(m, 4, 0, 0xffff); } static inline void msg_set_named_seqno(struct tipc_msg *m, u16 n) { msg_set_bits(m, 4, 0, 0xffff, n); } static inline u32 msg_destport(struct tipc_msg *m) { return msg_word(m, 5); } static inline void msg_set_destport(struct tipc_msg *m, u32 p) { msg_set_word(m, 5, p); } static inline u32 msg_mc_netid(struct tipc_msg *m) { return msg_word(m, 5); } static inline void msg_set_mc_netid(struct tipc_msg *m, u32 p) { msg_set_word(m, 5, p); } static inline int msg_short(struct tipc_msg *m) { return msg_hdr_sz(m) == SHORT_H_SIZE; } static inline u32 msg_orignode(struct tipc_msg *m) { if (likely(msg_short(m))) return msg_prevnode(m); return msg_word(m, 6); } static inline void msg_set_orignode(struct tipc_msg *m, u32 a) { msg_set_word(m, 6, a); } static inline u32 msg_destnode(struct tipc_msg *m) { return msg_word(m, 7); } static inline void msg_set_destnode(struct tipc_msg *m, u32 a) { msg_set_word(m, 7, a); } static inline u32 msg_nametype(struct tipc_msg *m) { return msg_word(m, 8); } static inline void msg_set_nametype(struct tipc_msg *m, u32 n) { msg_set_word(m, 8, n); } static inline u32 msg_nameinst(struct tipc_msg *m) { return msg_word(m, 9); } static inline u32 msg_namelower(struct tipc_msg *m) { return msg_nameinst(m); } static inline void msg_set_namelower(struct tipc_msg *m, u32 n) { msg_set_word(m, 9, n); } static inline void msg_set_nameinst(struct tipc_msg *m, u32 n) { msg_set_namelower(m, n); } static inline u32 msg_nameupper(struct tipc_msg *m) { return msg_word(m, 10); } static inline void msg_set_nameupper(struct tipc_msg *m, u32 n) { msg_set_word(m, 10, n); } /* * Constants and routines used to read and write TIPC internal message headers */ /* * Connection management protocol message types */ #define CONN_PROBE 0 #define CONN_PROBE_REPLY 1 #define CONN_ACK 2 /* * Name distributor message types */ #define PUBLICATION 0 #define WITHDRAWAL 1 /* * Segmentation message types */ #define FIRST_FRAGMENT 0 #define FRAGMENT 1 #define LAST_FRAGMENT 2 /* * Link management protocol message types */ #define STATE_MSG 0 #define RESET_MSG 1 #define ACTIVATE_MSG 2 /* * Changeover tunnel message types */ #define SYNCH_MSG 0 #define FAILOVER_MSG 1 /* * Config protocol message types */ #define DSC_REQ_MSG 0 #define DSC_RESP_MSG 1 #define DSC_TRIAL_MSG 2 #define DSC_TRIAL_FAIL_MSG 3 /* * Group protocol message types */ #define GRP_JOIN_MSG 0 #define GRP_LEAVE_MSG 1 #define GRP_ADV_MSG 2 #define GRP_ACK_MSG 3 #define GRP_RECLAIM_MSG 4 #define GRP_REMIT_MSG 5 /* Crypto message types */ #define KEY_DISTR_MSG 0 /* * Word 1 */ static inline u32 msg_seq_gap(struct tipc_msg *m) { return msg_bits(m, 1, 16, 0x1fff); } static inline void msg_set_seq_gap(struct tipc_msg *m, u32 n) { msg_set_bits(m, 1, 16, 0x1fff, n); } static inline u32 msg_node_sig(struct tipc_msg *m) { return msg_bits(m, 1, 0, 0xffff); } static inline void msg_set_node_sig(struct tipc_msg *m, u32 n) { msg_set_bits(m, 1, 0, 0xffff, n); } static inline u32 msg_node_capabilities(struct tipc_msg *m) { return msg_bits(m, 1, 15, 0x1fff); } static inline void msg_set_node_capabilities(struct tipc_msg *m, u32 n) { msg_set_bits(m, 1, 15, 0x1fff, n); } /* * Word 2 */ static inline u32 msg_dest_domain(struct tipc_msg *m) { return msg_word(m, 2); } static inline void msg_set_dest_domain(struct tipc_msg *m, u32 n) { msg_set_word(m, 2, n); } static inline void msg_set_bcgap_after(struct tipc_msg *m, u32 n) { msg_set_bits(m, 2, 16, 0xffff, n); } static inline u32 msg_bcgap_to(struct tipc_msg *m) { return msg_bits(m, 2, 0, 0xffff); } static inline void msg_set_bcgap_to(struct tipc_msg *m, u32 n) { msg_set_bits(m, 2, 0, 0xffff, n); } /* * Word 4 */ static inline u32 msg_last_bcast(struct tipc_msg *m) { return msg_bits(m, 4, 16, 0xffff); } static inline u32 msg_bc_snd_nxt(struct tipc_msg *m) { return msg_last_bcast(m) + 1; } static inline void msg_set_last_bcast(struct tipc_msg *m, u32 n) { msg_set_bits(m, 4, 16, 0xffff, n); } static inline u32 msg_nof_fragms(struct tipc_msg *m) { return msg_bits(m, 4, 0, 0xffff); } static inline void msg_set_nof_fragms(struct tipc_msg *m, u32 n) { msg_set_bits(m, 4, 0, 0xffff, n); } static inline u32 msg_fragm_no(struct tipc_msg *m) { return msg_bits(m, 4, 16, 0xffff); } static inline void msg_set_fragm_no(struct tipc_msg *m, u32 n) { msg_set_bits(m, 4, 16, 0xffff, n); } static inline u16 msg_next_sent(struct tipc_msg *m) { return msg_bits(m, 4, 0, 0xffff); } static inline void msg_set_next_sent(struct tipc_msg *m, u16 n) { msg_set_bits(m, 4, 0, 0xffff, n); } static inline u32 msg_bc_netid(struct tipc_msg *m) { return msg_word(m, 4); } static inline void msg_set_bc_netid(struct tipc_msg *m, u32 id) { msg_set_word(m, 4, id); } static inline u32 msg_link_selector(struct tipc_msg *m) { if (msg_user(m) == MSG_FRAGMENTER) m = (void *)msg_data(m); return msg_bits(m, 4, 0, 1); } /* * Word 5 */ static inline u16 msg_session(struct tipc_msg *m) { return msg_bits(m, 5, 16, 0xffff); } static inline void msg_set_session(struct tipc_msg *m, u16 n) { msg_set_bits(m, 5, 16, 0xffff, n); } static inline u32 msg_probe(struct tipc_msg *m) { return msg_bits(m, 5, 0, 1); } static inline void msg_set_probe(struct tipc_msg *m, u32 val) { msg_set_bits(m, 5, 0, 1, val); } static inline char msg_net_plane(struct tipc_msg *m) { return msg_bits(m, 5, 1, 7) + 'A'; } static inline void msg_set_net_plane(struct tipc_msg *m, char n) { msg_set_bits(m, 5, 1, 7, (n - 'A')); } static inline u32 msg_linkprio(struct tipc_msg *m) { return msg_bits(m, 5, 4, 0x1f); } static inline void msg_set_linkprio(struct tipc_msg *m, u32 n) { msg_set_bits(m, 5, 4, 0x1f, n); } static inline u32 msg_bearer_id(struct tipc_msg *m) { return msg_bits(m, 5, 9, 0x7); } static inline void msg_set_bearer_id(struct tipc_msg *m, u32 n) { msg_set_bits(m, 5, 9, 0x7, n); } static inline u32 msg_redundant_link(struct tipc_msg *m) { return msg_bits(m, 5, 12, 0x1); } static inline void msg_set_redundant_link(struct tipc_msg *m, u32 r) { msg_set_bits(m, 5, 12, 0x1, r); } static inline u32 msg_peer_stopping(struct tipc_msg *m) { return msg_bits(m, 5, 13, 0x1); } static inline void msg_set_peer_stopping(struct tipc_msg *m, u32 s) { msg_set_bits(m, 5, 13, 0x1, s); } static inline bool msg_bc_ack_invalid(struct tipc_msg *m) { switch (msg_user(m)) { case BCAST_PROTOCOL: case NAME_DISTRIBUTOR: case LINK_PROTOCOL: return msg_bits(m, 5, 14, 0x1); default: return false; } } static inline void msg_set_bc_ack_invalid(struct tipc_msg *m, bool invalid) { msg_set_bits(m, 5, 14, 0x1, invalid); } static inline char *msg_media_addr(struct tipc_msg *m) { return (char *)&m->hdr[TIPC_MEDIA_INFO_OFFSET]; } static inline u32 msg_bc_gap(struct tipc_msg *m) { return msg_bits(m, 8, 0, 0x3ff); } static inline void msg_set_bc_gap(struct tipc_msg *m, u32 n) { msg_set_bits(m, 8, 0, 0x3ff, n); } /* * Word 9 */ static inline u16 msg_msgcnt(struct tipc_msg *m) { return msg_bits(m, 9, 16, 0xffff); } static inline void msg_set_msgcnt(struct tipc_msg *m, u16 n) { msg_set_bits(m, 9, 16, 0xffff, n); } static inline u16 msg_syncpt(struct tipc_msg *m) { return msg_bits(m, 9, 16, 0xffff); } static inline void msg_set_syncpt(struct tipc_msg *m, u16 n) { msg_set_bits(m, 9, 16, 0xffff, n); } static inline u32 msg_conn_ack(struct tipc_msg *m) { return msg_bits(m, 9, 16, 0xffff); } static inline void msg_set_conn_ack(struct tipc_msg *m, u32 n) { msg_set_bits(m, 9, 16, 0xffff, n); } static inline u16 msg_adv_win(struct tipc_msg *m) { return msg_bits(m, 9, 0, 0xffff); } static inline void msg_set_adv_win(struct tipc_msg *m, u16 n) { msg_set_bits(m, 9, 0, 0xffff, n); } static inline u32 msg_max_pkt(struct tipc_msg *m) { return msg_bits(m, 9, 16, 0xffff) * 4; } static inline void msg_set_max_pkt(struct tipc_msg *m, u32 n) { msg_set_bits(m, 9, 16, 0xffff, (n / 4)); } static inline u32 msg_link_tolerance(struct tipc_msg *m) { return msg_bits(m, 9, 0, 0xffff); } static inline void msg_set_link_tolerance(struct tipc_msg *m, u32 n) { msg_set_bits(m, 9, 0, 0xffff, n); } static inline u16 msg_grp_bc_syncpt(struct tipc_msg *m) { return msg_bits(m, 9, 16, 0xffff); } static inline void msg_set_grp_bc_syncpt(struct tipc_msg *m, u16 n) { msg_set_bits(m, 9, 16, 0xffff, n); } static inline u16 msg_grp_bc_acked(struct tipc_msg *m) { return msg_bits(m, 9, 16, 0xffff); } static inline void msg_set_grp_bc_acked(struct tipc_msg *m, u16 n) { msg_set_bits(m, 9, 16, 0xffff, n); } static inline u16 msg_grp_remitted(struct tipc_msg *m) { return msg_bits(m, 9, 16, 0xffff); } static inline void msg_set_grp_remitted(struct tipc_msg *m, u16 n) { msg_set_bits(m, 9, 16, 0xffff, n); } /* Word 10 */ static inline u16 msg_grp_evt(struct tipc_msg *m) { return msg_bits(m, 10, 0, 0x3); } static inline void msg_set_grp_evt(struct tipc_msg *m, int n) { msg_set_bits(m, 10, 0, 0x3, n); } static inline u16 msg_grp_bc_ack_req(struct tipc_msg *m) { return msg_bits(m, 10, 0, 0x1); } static inline void msg_set_grp_bc_ack_req(struct tipc_msg *m, bool n) { msg_set_bits(m, 10, 0, 0x1, n); } static inline u16 msg_grp_bc_seqno(struct tipc_msg *m) { return msg_bits(m, 10, 16, 0xffff); } static inline void msg_set_grp_bc_seqno(struct tipc_msg *m, u32 n) { msg_set_bits(m, 10, 16, 0xffff, n); } static inline bool msg_peer_link_is_up(struct tipc_msg *m) { if (likely(msg_user(m) != LINK_PROTOCOL)) return true; if (msg_type(m) == STATE_MSG) return true; return false; } static inline bool msg_peer_node_is_up(struct tipc_msg *m) { if (msg_peer_link_is_up(m)) return true; return msg_redundant_link(m); } static inline bool msg_is_reset(struct tipc_msg *hdr) { return (msg_user(hdr) == LINK_PROTOCOL) && (msg_type(hdr) == RESET_MSG); } /* Word 13 */ static inline void msg_set_peer_net_hash(struct tipc_msg *m, u32 n) { msg_set_word(m, 13, n); } static inline u32 msg_peer_net_hash(struct tipc_msg *m) { return msg_word(m, 13); } /* Word 14 */ static inline u32 msg_sugg_node_addr(struct tipc_msg *m) { return msg_word(m, 14); } static inline void msg_set_sugg_node_addr(struct tipc_msg *m, u32 n) { msg_set_word(m, 14, n); } static inline void msg_set_node_id(struct tipc_msg *hdr, u8 *id) { memcpy(msg_data(hdr), id, 16); } static inline u8 *msg_node_id(struct tipc_msg *hdr) { return (u8 *)msg_data(hdr); } struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp); bool tipc_msg_validate(struct sk_buff **_skb); bool tipc_msg_reverse(u32 own_addr, struct sk_buff **skb, int err); void tipc_skb_reject(struct net *net, int err, struct sk_buff *skb, struct sk_buff_head *xmitq); void tipc_msg_init(u32 own_addr, struct tipc_msg *m, u32 user, u32 type, u32 hsize, u32 destnode); struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz, uint data_sz, u32 dnode, u32 onode, u32 dport, u32 oport, int errcode); int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf); bool tipc_msg_try_bundle(struct sk_buff *tskb, struct sk_buff **skb, u32 mss, u32 dnode, bool *new_bundle); bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos); int tipc_msg_fragment(struct sk_buff *skb, const struct tipc_msg *hdr, int pktmax, struct sk_buff_head *frags); int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, int dsz, int mtu, struct sk_buff_head *list); int tipc_msg_append(struct tipc_msg *hdr, struct msghdr *m, int dlen, int mss, struct sk_buff_head *txq); bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err); bool tipc_msg_assemble(struct sk_buff_head *list); bool tipc_msg_reassemble(struct sk_buff_head *list, struct sk_buff_head *rcvq); bool tipc_msg_pskb_copy(u32 dst, struct sk_buff_head *msg, struct sk_buff_head *cpy); bool __tipc_skb_queue_sorted(struct sk_buff_head *list, u16 seqno, struct sk_buff *skb); bool tipc_msg_skb_clone(struct sk_buff_head *msg, struct sk_buff_head *cpy); static inline u16 buf_seqno(struct sk_buff *skb) { return msg_seqno(buf_msg(skb)); } static inline int buf_roundup_len(struct sk_buff *skb) { return (skb->len / 1024 + 1) * 1024; } /* tipc_skb_peek(): peek and reserve first buffer in list * @list: list to be peeked in * Returns pointer to first buffer in list, if any */ static inline struct sk_buff *tipc_skb_peek(struct sk_buff_head *list, spinlock_t *lock) { struct sk_buff *skb; spin_lock_bh(lock); skb = skb_peek(list); if (skb) skb_get(skb); spin_unlock_bh(lock); return skb; } /* tipc_skb_peek_port(): find a destination port, ignoring all destinations * up to and including 'filter'. * Note: ignoring previously tried destinations minimizes the risk of * contention on the socket lock * @list: list to be peeked in * @filter: last destination to be ignored from search * Returns a destination port number, of applicable. */ static inline u32 tipc_skb_peek_port(struct sk_buff_head *list, u32 filter) { struct sk_buff *skb; u32 dport = 0; bool ignore = true; spin_lock_bh(&list->lock); skb_queue_walk(list, skb) { dport = msg_destport(buf_msg(skb)); if (!filter || skb_queue_is_last(list, skb)) break; if (dport == filter) ignore = false; else if (!ignore) break; } spin_unlock_bh(&list->lock); return dport; } /* tipc_skb_dequeue(): unlink first buffer with dest 'dport' from list * @list: list to be unlinked from * @dport: selection criteria for buffer to unlink */ static inline struct sk_buff *tipc_skb_dequeue(struct sk_buff_head *list, u32 dport) { struct sk_buff *_skb, *tmp, *skb = NULL; spin_lock_bh(&list->lock); skb_queue_walk_safe(list, _skb, tmp) { if (msg_destport(buf_msg(_skb)) == dport) { __skb_unlink(_skb, list); skb = _skb; break; } } spin_unlock_bh(&list->lock); return skb; } /* tipc_skb_queue_splice_tail - append an skb list to lock protected list * @list: the new list to append. Not lock protected * @head: target list. Lock protected. */ static inline void tipc_skb_queue_splice_tail(struct sk_buff_head *list, struct sk_buff_head *head) { spin_lock_bh(&head->lock); skb_queue_splice_tail(list, head); spin_unlock_bh(&head->lock); } /* tipc_skb_queue_splice_tail_init - merge two lock protected skb lists * @list: the new list to add. Lock protected. Will be reinitialized * @head: target list. Lock protected. */ static inline void tipc_skb_queue_splice_tail_init(struct sk_buff_head *list, struct sk_buff_head *head) { struct sk_buff_head tmp; __skb_queue_head_init(&tmp); spin_lock_bh(&list->lock); skb_queue_splice_tail_init(list, &tmp); spin_unlock_bh(&list->lock); tipc_skb_queue_splice_tail(&tmp, head); } /* __tipc_skb_dequeue() - dequeue the head skb according to expected seqno * @list: list to be dequeued from * @seqno: seqno of the expected msg * * returns skb dequeued from the list if its seqno is less than or equal to * the expected one, otherwise the skb is still hold * * Note: must be used with appropriate locks held only */ static inline struct sk_buff *__tipc_skb_dequeue(struct sk_buff_head *list, u16 seqno) { struct sk_buff *skb = skb_peek(list); if (skb && less_eq(buf_seqno(skb), seqno)) { __skb_unlink(skb, list); return skb; } return NULL; } #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM user #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH trace/hooks #if !defined(_TRACE_HOOK_USER_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_HOOK_USER_H #include <trace/hooks/vendor_hooks.h> struct user_struct; DECLARE_HOOK(android_vh_alloc_uid, TP_PROTO(struct user_struct *user), TP_ARGS(user)); DECLARE_HOOK(android_vh_free_user, TP_PROTO(struct user_struct *up), TP_ARGS(up)); #endif /* _TRACE_HOOK_USER_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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PIPE_FS_I_H #define _LINUX_PIPE_FS_I_H #define PIPE_DEF_BUFFERS 16 #define PIPE_BUF_FLAG_LRU 0x01 /* page is on the LRU */ #define PIPE_BUF_FLAG_ATOMIC 0x02 /* was atomically mapped */ #define PIPE_BUF_FLAG_GIFT 0x04 /* page is a gift */ #define PIPE_BUF_FLAG_PACKET 0x08 /* read() as a packet */ #define PIPE_BUF_FLAG_CAN_MERGE 0x10 /* can merge buffers */ #define PIPE_BUF_FLAG_WHOLE 0x20 /* read() must return entire buffer or error */ #ifdef CONFIG_WATCH_QUEUE #define PIPE_BUF_FLAG_LOSS 0x40 /* Message loss happened after this buffer */ #endif /** * struct pipe_buffer - a linux kernel pipe buffer * @page: the page containing the data for the pipe buffer * @offset: offset of data inside the @page * @len: length of data inside the @page * @ops: operations associated with this buffer. See @pipe_buf_operations. * @flags: pipe buffer flags. See above. * @private: private data owned by the ops. **/ struct pipe_buffer { struct page *page; unsigned int offset, len; const struct pipe_buf_operations *ops; unsigned int flags; unsigned long private; }; /** * struct pipe_inode_info - a linux kernel pipe * @mutex: mutex protecting the whole thing * @rd_wait: reader wait point in case of empty pipe * @wr_wait: writer wait point in case of full pipe * @head: The point of buffer production * @tail: The point of buffer consumption * @note_loss: The next read() should insert a data-lost message * @max_usage: The maximum number of slots that may be used in the ring * @ring_size: total number of buffers (should be a power of 2) * @nr_accounted: The amount this pipe accounts for in user->pipe_bufs * @tmp_page: cached released page * @readers: number of current readers of this pipe * @writers: number of current writers of this pipe * @files: number of struct file referring this pipe (protected by ->i_lock) * @r_counter: reader counter * @w_counter: writer counter * @poll_usage: is this pipe used for epoll, which has crazy wakeups? * @fasync_readers: reader side fasync * @fasync_writers: writer side fasync * @bufs: the circular array of pipe buffers * @user: the user who created this pipe * @watch_queue: If this pipe is a watch_queue, this is the stuff for that **/ struct pipe_inode_info { struct mutex mutex; wait_queue_head_t rd_wait, wr_wait; unsigned int head; unsigned int tail; unsigned int max_usage; unsigned int ring_size; #ifdef CONFIG_WATCH_QUEUE bool note_loss; #endif unsigned int nr_accounted; unsigned int readers; unsigned int writers; unsigned int files; unsigned int r_counter; unsigned int w_counter; bool poll_usage; struct page *tmp_page; struct fasync_struct *fasync_readers; struct fasync_struct *fasync_writers; struct pipe_buffer *bufs; struct user_struct *user; #ifdef CONFIG_WATCH_QUEUE struct watch_queue *watch_queue; #endif }; /* * Note on the nesting of these functions: * * ->confirm() * ->try_steal() * * That is, ->try_steal() must be called on a confirmed buffer. See below for * the meaning of each operation. Also see the kerneldoc in fs/pipe.c for the * pipe and generic variants of these hooks. */ struct pipe_buf_operations { /* * ->confirm() verifies that the data in the pipe buffer is there * and that the contents are good. If the pages in the pipe belong * to a file system, we may need to wait for IO completion in this * hook. Returns 0 for good, or a negative error value in case of * error. If not present all pages are considered good. */ int (*confirm)(struct pipe_inode_info *, struct pipe_buffer *); /* * When the contents of this pipe buffer has been completely * consumed by a reader, ->release() is called. */ void (*release)(struct pipe_inode_info *, struct pipe_buffer *); /* * Attempt to take ownership of the pipe buffer and its contents. * ->try_steal() returns %true for success, in which case the contents * of the pipe (the buf->page) is locked and now completely owned by the * caller. The page may then be transferred to a different mapping, the * most often used case is insertion into different file address space * cache. */ bool (*try_steal)(struct pipe_inode_info *, struct pipe_buffer *); /* * Get a reference to the pipe buffer. */ bool (*get)(struct pipe_inode_info *, struct pipe_buffer *); }; /** * pipe_has_watch_queue - Check whether the pipe is a watch_queue, * i.e. it was created with O_NOTIFICATION_PIPE * @pipe: The pipe to check * * Return: true if pipe is a watch queue, false otherwise. */ static inline bool pipe_has_watch_queue(const struct pipe_inode_info *pipe) { #ifdef CONFIG_WATCH_QUEUE return pipe->watch_queue != NULL; #else return false; #endif } /** * pipe_empty - Return true if the pipe is empty * @head: The pipe ring head pointer * @tail: The pipe ring tail pointer */ static inline bool pipe_empty(unsigned int head, unsigned int tail) { return head == tail; } /** * pipe_occupancy - Return number of slots used in the pipe * @head: The pipe ring head pointer * @tail: The pipe ring tail pointer */ static inline unsigned int pipe_occupancy(unsigned int head, unsigned int tail) { return head - tail; } /** * pipe_full - Return true if the pipe is full * @head: The pipe ring head pointer * @tail: The pipe ring tail pointer * @limit: The maximum amount of slots available. */ static inline bool pipe_full(unsigned int head, unsigned int tail, unsigned int limit) { return pipe_occupancy(head, tail) >= limit; } /** * pipe_buf_get - get a reference to a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to get a reference to * * Return: %true if the reference was successfully obtained. */ static inline __must_check bool pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { return buf->ops->get(pipe, buf); } /** * pipe_buf_release - put a reference to a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to put a reference to */ static inline void pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { const struct pipe_buf_operations *ops = buf->ops; buf->ops = NULL; ops->release(pipe, buf); } /** * pipe_buf_confirm - verify contents of the pipe buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to confirm */ static inline int pipe_buf_confirm(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { if (!buf->ops->confirm) return 0; return buf->ops->confirm(pipe, buf); } /** * pipe_buf_try_steal - attempt to take ownership of a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to attempt to steal */ static inline bool pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { if (!buf->ops->try_steal) return false; return buf->ops->try_steal(pipe, buf); } static inline void pipe_discard_from(struct pipe_inode_info *pipe, unsigned int old_head) { unsigned int mask = pipe->ring_size - 1; while (pipe->head > old_head) pipe_buf_release(pipe, &pipe->bufs[--pipe->head & mask]); } /* Differs from PIPE_BUF in that PIPE_SIZE is the length of the actual memory allocation, whereas PIPE_BUF makes atomicity guarantees. */ #define PIPE_SIZE PAGE_SIZE /* Pipe lock and unlock operations */ void pipe_lock(struct pipe_inode_info *); void pipe_unlock(struct pipe_inode_info *); void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *); /* Wait for a pipe to be readable/writable while dropping the pipe lock */ void pipe_wait_readable(struct pipe_inode_info *); void pipe_wait_writable(struct pipe_inode_info *); struct pipe_inode_info *alloc_pipe_info(void); void free_pipe_info(struct pipe_inode_info *); /* Generic pipe buffer ops functions */ bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); bool generic_pipe_buf_try_steal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); extern const struct pipe_buf_operations nosteal_pipe_buf_ops; unsigned long account_pipe_buffers(struct user_struct *user, unsigned long old, unsigned long new); bool too_many_pipe_buffers_soft(unsigned long user_bufs); bool too_many_pipe_buffers_hard(unsigned long user_bufs); bool pipe_is_unprivileged_user(void); /* for F_SETPIPE_SZ and F_GETPIPE_SZ */ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots); long pipe_fcntl(struct file *, unsigned int, unsigned long arg); struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice); int create_pipe_files(struct file **, int); unsigned int round_pipe_size(unsigned long size); #endif |
| 1625 1624 1624 1625 1625 1625 515 515 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 | // SPDX-License-Identifier: GPL-2.0-only /* * Link physical devices with ACPI devices support * * Copyright (c) 2005 David Shaohua Li <shaohua.li@intel.com> * Copyright (c) 2005 Intel Corp. */ #define pr_fmt(fmt) "ACPI: " fmt #include <linux/acpi_iort.h> #include <linux/export.h> #include <linux/init.h> #include <linux/list.h> #include <linux/device.h> #include <linux/slab.h> #include <linux/rwsem.h> #include <linux/acpi.h> #include <linux/dma-mapping.h> #include <linux/pci.h> #include <linux/pci-acpi.h> #include <linux/platform_device.h> #include "internal.h" static LIST_HEAD(bus_type_list); static DECLARE_RWSEM(bus_type_sem); #define PHYSICAL_NODE_STRING "physical_node" #define PHYSICAL_NODE_NAME_SIZE (sizeof(PHYSICAL_NODE_STRING) + 10) int register_acpi_bus_type(struct acpi_bus_type *type) { if (acpi_disabled) return -ENODEV; if (type && type->match && type->find_companion) { down_write(&bus_type_sem); list_add_tail(&type->list, &bus_type_list); up_write(&bus_type_sem); pr_info("bus type %s registered\n", type->name); return 0; } return -ENODEV; } EXPORT_SYMBOL_GPL(register_acpi_bus_type); int unregister_acpi_bus_type(struct acpi_bus_type *type) { if (acpi_disabled) return 0; if (type) { down_write(&bus_type_sem); list_del_init(&type->list); up_write(&bus_type_sem); pr_info("bus type %s unregistered\n", type->name); return 0; } return -ENODEV; } EXPORT_SYMBOL_GPL(unregister_acpi_bus_type); static struct acpi_bus_type *acpi_get_bus_type(struct device *dev) { struct acpi_bus_type *tmp, *ret = NULL; down_read(&bus_type_sem); list_for_each_entry(tmp, &bus_type_list, list) { if (tmp->match(dev)) { ret = tmp; break; } } up_read(&bus_type_sem); return ret; } #define FIND_CHILD_MIN_SCORE 1 #define FIND_CHILD_MID_SCORE 2 #define FIND_CHILD_MAX_SCORE 3 static int match_any(struct acpi_device *adev, void *not_used) { return 1; } static bool acpi_dev_has_children(struct acpi_device *adev) { return acpi_dev_for_each_child(adev, match_any, NULL) > 0; } static int find_child_checks(struct acpi_device *adev, bool check_children) { unsigned long long sta; acpi_status status; if (check_children && !acpi_dev_has_children(adev)) return -ENODEV; status = acpi_evaluate_integer(adev->handle, "_STA", NULL, &sta); if (status == AE_NOT_FOUND) { /* * Special case: backlight device objects without _STA are * preferred to other objects with the same _ADR value, because * it is more likely that they are actually useful. */ if (adev->pnp.type.backlight) return FIND_CHILD_MID_SCORE; return FIND_CHILD_MIN_SCORE; } if (ACPI_FAILURE(status) || !(sta & ACPI_STA_DEVICE_ENABLED)) return -ENODEV; /* * If the device has a _HID returning a valid ACPI/PNP device ID, it is * better to make it look less attractive here, so that the other device * with the same _ADR value (that may not have a valid device ID) can be * matched going forward. [This means a second spec violation in a row, * so whatever we do here is best effort anyway.] */ if (adev->pnp.type.platform_id) return FIND_CHILD_MIN_SCORE; return FIND_CHILD_MAX_SCORE; } struct find_child_walk_data { struct acpi_device *adev; u64 address; int score; bool check_sta; bool check_children; }; static int check_one_child(struct acpi_device *adev, void *data) { struct find_child_walk_data *wd = data; int score; if (!adev->pnp.type.bus_address || acpi_device_adr(adev) != wd->address) return 0; if (!wd->adev) { /* * This is the first matching object, so save it. If it is not * necessary to look for any other matching objects, stop the * search. */ wd->adev = adev; return !(wd->check_sta || wd->check_children); } /* * There is more than one matching device object with the same _ADR * value. That really is unexpected, so we are kind of beyond the scope * of the spec here. We have to choose which one to return, though. * * First, get the score for the previously found object and terminate * the walk if it is maximum. */ if (!wd->score) { score = find_child_checks(wd->adev, wd->check_children); if (score == FIND_CHILD_MAX_SCORE) return 1; wd->score = score; } /* * Second, if the object that has just been found has a better score, * replace the previously found one with it and terminate the walk if * the new score is maximum. */ score = find_child_checks(adev, wd->check_children); if (score > wd->score) { wd->adev = adev; if (score == FIND_CHILD_MAX_SCORE) return 1; wd->score = score; } /* Continue, because there may be better matches. */ return 0; } static struct acpi_device *acpi_find_child(struct acpi_device *parent, u64 address, bool check_children, bool check_sta) { struct find_child_walk_data wd = { .address = address, .check_children = check_children, .check_sta = check_sta, .adev = NULL, .score = 0, }; if (parent) acpi_dev_for_each_child(parent, check_one_child, &wd); return wd.adev; } struct acpi_device *acpi_find_child_device(struct acpi_device *parent, u64 address, bool check_children) { return acpi_find_child(parent, address, check_children, true); } EXPORT_SYMBOL_GPL(acpi_find_child_device); struct acpi_device *acpi_find_child_by_adr(struct acpi_device *adev, acpi_bus_address adr) { return acpi_find_child(adev, adr, false, false); } EXPORT_SYMBOL_GPL(acpi_find_child_by_adr); static void acpi_physnode_link_name(char *buf, unsigned int node_id) { if (node_id > 0) snprintf(buf, PHYSICAL_NODE_NAME_SIZE, PHYSICAL_NODE_STRING "%u", node_id); else strcpy(buf, PHYSICAL_NODE_STRING); } int acpi_bind_one(struct device *dev, struct acpi_device *acpi_dev) { struct acpi_device_physical_node *physical_node, *pn; char physical_node_name[PHYSICAL_NODE_NAME_SIZE]; struct list_head *physnode_list; unsigned int node_id; int retval = -EINVAL; if (has_acpi_companion(dev)) { if (acpi_dev) { dev_warn(dev, "ACPI companion already set\n"); return -EINVAL; } else { acpi_dev = ACPI_COMPANION(dev); } } if (!acpi_dev) return -EINVAL; acpi_dev_get(acpi_dev); get_device(dev); physical_node = kzalloc(sizeof(*physical_node), GFP_KERNEL); if (!physical_node) { retval = -ENOMEM; goto err; } mutex_lock(&acpi_dev->physical_node_lock); /* * Keep the list sorted by node_id so that the IDs of removed nodes can * be recycled easily. */ physnode_list = &acpi_dev->physical_node_list; node_id = 0; list_for_each_entry(pn, &acpi_dev->physical_node_list, node) { /* Sanity check. */ if (pn->dev == dev) { mutex_unlock(&acpi_dev->physical_node_lock); dev_warn(dev, "Already associated with ACPI node\n"); kfree(physical_node); if (ACPI_COMPANION(dev) != acpi_dev) goto err; put_device(dev); acpi_dev_put(acpi_dev); return 0; } if (pn->node_id == node_id) { physnode_list = &pn->node; node_id++; } } physical_node->node_id = node_id; physical_node->dev = dev; list_add(&physical_node->node, physnode_list); acpi_dev->physical_node_count++; if (!has_acpi_companion(dev)) ACPI_COMPANION_SET(dev, acpi_dev); acpi_physnode_link_name(physical_node_name, node_id); retval = sysfs_create_link(&acpi_dev->dev.kobj, &dev->kobj, physical_node_name); if (retval) dev_err(&acpi_dev->dev, "Failed to create link %s (%d)\n", physical_node_name, retval); retval = sysfs_create_link(&dev->kobj, &acpi_dev->dev.kobj, "firmware_node"); if (retval) dev_err(dev, "Failed to create link firmware_node (%d)\n", retval); mutex_unlock(&acpi_dev->physical_node_lock); if (acpi_dev->wakeup.flags.valid) device_set_wakeup_capable(dev, true); return 0; err: ACPI_COMPANION_SET(dev, NULL); put_device(dev); acpi_dev_put(acpi_dev); return retval; } EXPORT_SYMBOL_GPL(acpi_bind_one); int acpi_unbind_one(struct device *dev) { struct acpi_device *acpi_dev = ACPI_COMPANION(dev); struct acpi_device_physical_node *entry; if (!acpi_dev) return 0; mutex_lock(&acpi_dev->physical_node_lock); list_for_each_entry(entry, &acpi_dev->physical_node_list, node) if (entry->dev == dev) { char physnode_name[PHYSICAL_NODE_NAME_SIZE]; list_del(&entry->node); acpi_dev->physical_node_count--; acpi_physnode_link_name(physnode_name, entry->node_id); sysfs_remove_link(&acpi_dev->dev.kobj, physnode_name); sysfs_remove_link(&dev->kobj, "firmware_node"); ACPI_COMPANION_SET(dev, NULL); /* Drop references taken by acpi_bind_one(). */ put_device(dev); acpi_dev_put(acpi_dev); kfree(entry); break; } mutex_unlock(&acpi_dev->physical_node_lock); return 0; } EXPORT_SYMBOL_GPL(acpi_unbind_one); void acpi_device_notify(struct device *dev) { struct acpi_device *adev; int ret; ret = acpi_bind_one(dev, NULL); if (ret) { struct acpi_bus_type *type = acpi_get_bus_type(dev); if (!type) goto err; adev = type->find_companion(dev); if (!adev) { dev_dbg(dev, "ACPI companion not found\n"); goto err; } ret = acpi_bind_one(dev, adev); if (ret) goto err; if (type->setup) { type->setup(dev); goto done; } } else { adev = ACPI_COMPANION(dev); if (dev_is_pci(dev)) { pci_acpi_setup(dev, adev); goto done; } else if (dev_is_platform(dev)) { acpi_configure_pmsi_domain(dev); } } if (adev->handler && adev->handler->bind) adev->handler->bind(dev); done: acpi_handle_debug(ACPI_HANDLE(dev), "Bound to device %s\n", dev_name(dev)); return; err: dev_dbg(dev, "No ACPI support\n"); } void acpi_device_notify_remove(struct device *dev) { struct acpi_device *adev = ACPI_COMPANION(dev); if (!adev) return; if (dev_is_pci(dev)) pci_acpi_cleanup(dev, adev); else if (adev->handler && adev->handler->unbind) adev->handler->unbind(dev); acpi_unbind_one(dev); } |
| 4 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPV4 GSO/GRO offload support * Linux INET implementation * * UDPv4 GSO support */ #include <linux/skbuff.h> #include <net/gro.h> #include <net/udp.h> #include <net/protocol.h> #include <net/inet_common.h> static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, netdev_features_t features, struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb, netdev_features_t features), __be16 new_protocol, bool is_ipv6) { int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); bool remcsum, need_csum, offload_csum, gso_partial; struct sk_buff *segs = ERR_PTR(-EINVAL); struct udphdr *uh = udp_hdr(skb); u16 mac_offset = skb->mac_header; __be16 protocol = skb->protocol; u16 mac_len = skb->mac_len; int udp_offset, outer_hlen; __wsum partial; bool need_ipsec; if (unlikely(!pskb_may_pull(skb, tnl_hlen))) goto out; /* Adjust partial header checksum to negate old length. * We cannot rely on the value contained in uh->len as it is * possible that the actual value exceeds the boundaries of the * 16 bit length field due to the header being added outside of an * IP or IPv6 frame that was already limited to 64K - 1. */ if (skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) partial = (__force __wsum)uh->len; else partial = (__force __wsum)htonl(skb->len); partial = csum_sub(csum_unfold(uh->check), partial); /* setup inner skb. */ skb->encapsulation = 0; SKB_GSO_CB(skb)->encap_level = 0; __skb_pull(skb, tnl_hlen); skb_reset_mac_header(skb); skb_set_network_header(skb, skb_inner_network_offset(skb)); skb_set_transport_header(skb, skb_inner_transport_offset(skb)); skb->mac_len = skb_inner_network_offset(skb); skb->protocol = new_protocol; need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM); skb->encap_hdr_csum = need_csum; remcsum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TUNNEL_REMCSUM); skb->remcsum_offload = remcsum; need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb)); /* Try to offload checksum if possible */ offload_csum = !!(need_csum && !need_ipsec && (skb->dev->features & (is_ipv6 ? (NETIF_F_HW_CSUM | NETIF_F_IPV6_CSUM) : (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM)))); features &= skb->dev->hw_enc_features; if (need_csum) features &= ~NETIF_F_SCTP_CRC; /* The only checksum offload we care about from here on out is the * outer one so strip the existing checksum feature flags and * instead set the flag based on our outer checksum offload value. */ if (remcsum) { features &= ~NETIF_F_CSUM_MASK; if (!need_csum || offload_csum) features |= NETIF_F_HW_CSUM; } /* segment inner packet. */ segs = gso_inner_segment(skb, features); if (IS_ERR_OR_NULL(segs)) { skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset, mac_len); goto out; } gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); outer_hlen = skb_tnl_header_len(skb); udp_offset = outer_hlen - tnl_hlen; skb = segs; do { unsigned int len; if (remcsum) skb->ip_summed = CHECKSUM_NONE; /* Set up inner headers if we are offloading inner checksum */ if (skb->ip_summed == CHECKSUM_PARTIAL) { skb_reset_inner_headers(skb); skb->encapsulation = 1; } skb->mac_len = mac_len; skb->protocol = protocol; __skb_push(skb, outer_hlen); skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); skb_set_transport_header(skb, udp_offset); len = skb->len - udp_offset; uh = udp_hdr(skb); /* If we are only performing partial GSO the inner header * will be using a length value equal to only one MSS sized * segment instead of the entire frame. */ if (gso_partial && skb_is_gso(skb)) { uh->len = htons(skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)uh); } else { uh->len = htons(len); } if (!need_csum) continue; uh->check = ~csum_fold(csum_add(partial, (__force __wsum)htonl(len))); if (skb->encapsulation || !offload_csum) { uh->check = gso_make_checksum(skb, ~uh->check); if (uh->check == 0) uh->check = CSUM_MANGLED_0; } else { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); } } while ((skb = skb->next)); out: return segs; } struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, netdev_features_t features, bool is_ipv6) { const struct net_offload __rcu **offloads; __be16 protocol = skb->protocol; const struct net_offload *ops; struct sk_buff *segs = ERR_PTR(-EINVAL); struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb, netdev_features_t features); rcu_read_lock(); switch (skb->inner_protocol_type) { case ENCAP_TYPE_ETHER: protocol = skb->inner_protocol; gso_inner_segment = skb_mac_gso_segment; break; case ENCAP_TYPE_IPPROTO: offloads = is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[skb->inner_ipproto]); if (!ops || !ops->callbacks.gso_segment) goto out_unlock; gso_inner_segment = ops->callbacks.gso_segment; break; default: goto out_unlock; } segs = __skb_udp_tunnel_segment(skb, features, gso_inner_segment, protocol, is_ipv6); out_unlock: rcu_read_unlock(); return segs; } EXPORT_SYMBOL(skb_udp_tunnel_segment); static void __udpv4_gso_segment_csum(struct sk_buff *seg, __be32 *oldip, __be32 *newip, __be16 *oldport, __be16 *newport) { struct udphdr *uh; struct iphdr *iph; if (*oldip == *newip && *oldport == *newport) return; uh = udp_hdr(seg); iph = ip_hdr(seg); if (uh->check) { inet_proto_csum_replace4(&uh->check, seg, *oldip, *newip, true); inet_proto_csum_replace2(&uh->check, seg, *oldport, *newport, false); if (!uh->check) uh->check = CSUM_MANGLED_0; } *oldport = *newport; csum_replace4(&iph->check, *oldip, *newip); *oldip = *newip; } static struct sk_buff *__udpv4_gso_segment_list_csum(struct sk_buff *segs) { struct sk_buff *seg; struct udphdr *uh, *uh2; struct iphdr *iph, *iph2; seg = segs; uh = udp_hdr(seg); iph = ip_hdr(seg); if ((udp_hdr(seg)->dest == udp_hdr(seg->next)->dest) && (udp_hdr(seg)->source == udp_hdr(seg->next)->source) && (ip_hdr(seg)->daddr == ip_hdr(seg->next)->daddr) && (ip_hdr(seg)->saddr == ip_hdr(seg->next)->saddr)) return segs; while ((seg = seg->next)) { uh2 = udp_hdr(seg); iph2 = ip_hdr(seg); __udpv4_gso_segment_csum(seg, &iph2->saddr, &iph->saddr, &uh2->source, &uh->source); __udpv4_gso_segment_csum(seg, &iph2->daddr, &iph->daddr, &uh2->dest, &uh->dest); } return segs; } static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb, netdev_features_t features, bool is_ipv6) { unsigned int mss = skb_shinfo(skb)->gso_size; skb = skb_segment_list(skb, features, skb_mac_header_len(skb)); if (IS_ERR(skb)) return skb; udp_hdr(skb)->len = htons(sizeof(struct udphdr) + mss); return is_ipv6 ? skb : __udpv4_gso_segment_list_csum(skb); } struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, netdev_features_t features, bool is_ipv6) { struct sock *sk = gso_skb->sk; unsigned int sum_truesize = 0; struct sk_buff *segs, *seg; struct udphdr *uh; unsigned int mss; bool copy_dtor; __sum16 check; __be16 newlen; mss = skb_shinfo(gso_skb)->gso_size; if (gso_skb->len <= sizeof(*uh) + mss) return ERR_PTR(-EINVAL); if (unlikely(skb_checksum_start(gso_skb) != skb_transport_header(gso_skb) && !(skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST))) return ERR_PTR(-EINVAL); if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { /* Packet is from an untrusted source, reset gso_segs. */ skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh), mss); return NULL; } if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) { /* Detect modified geometry and pass those to skb_segment. */ if (skb_pagelen(gso_skb) - sizeof(*uh) == skb_shinfo(gso_skb)->gso_size) return __udp_gso_segment_list(gso_skb, features, is_ipv6); /* Setup csum, as fraglist skips this in udp4_gro_receive. */ gso_skb->csum_start = skb_transport_header(gso_skb) - gso_skb->head; gso_skb->csum_offset = offsetof(struct udphdr, check); gso_skb->ip_summed = CHECKSUM_PARTIAL; uh = udp_hdr(gso_skb); if (is_ipv6) uh->check = ~udp_v6_check(gso_skb->len, &ipv6_hdr(gso_skb)->saddr, &ipv6_hdr(gso_skb)->daddr, 0); else uh->check = ~udp_v4_check(gso_skb->len, ip_hdr(gso_skb)->saddr, ip_hdr(gso_skb)->daddr, 0); } skb_pull(gso_skb, sizeof(*uh)); /* clear destructor to avoid skb_segment assigning it to tail */ copy_dtor = gso_skb->destructor == sock_wfree; if (copy_dtor) gso_skb->destructor = NULL; segs = skb_segment(gso_skb, features); if (IS_ERR_OR_NULL(segs)) { if (copy_dtor) gso_skb->destructor = sock_wfree; return segs; } /* GSO partial and frag_list segmentation only requires splitting * the frame into an MSS multiple and possibly a remainder, both * cases return a GSO skb. So update the mss now. */ if (skb_is_gso(segs)) mss *= skb_shinfo(segs)->gso_segs; seg = segs; uh = udp_hdr(seg); /* preserve TX timestamp flags and TS key for first segment */ skb_shinfo(seg)->tskey = skb_shinfo(gso_skb)->tskey; skb_shinfo(seg)->tx_flags |= (skb_shinfo(gso_skb)->tx_flags & SKBTX_ANY_TSTAMP); /* compute checksum adjustment based on old length versus new */ newlen = htons(sizeof(*uh) + mss); check = csum16_add(csum16_sub(uh->check, uh->len), newlen); for (;;) { if (copy_dtor) { seg->destructor = sock_wfree; seg->sk = sk; sum_truesize += seg->truesize; } if (!seg->next) break; uh->len = newlen; uh->check = check; if (seg->ip_summed == CHECKSUM_PARTIAL) gso_reset_checksum(seg, ~check); else uh->check = gso_make_checksum(seg, ~check) ? : CSUM_MANGLED_0; seg = seg->next; uh = udp_hdr(seg); } /* last packet can be partial gso_size, account for that in checksum */ newlen = htons(skb_tail_pointer(seg) - skb_transport_header(seg) + seg->data_len); check = csum16_add(csum16_sub(uh->check, uh->len), newlen); uh->len = newlen; uh->check = check; if (seg->ip_summed == CHECKSUM_PARTIAL) gso_reset_checksum(seg, ~check); else uh->check = gso_make_checksum(seg, ~check) ? : CSUM_MANGLED_0; /* update refcount for the packet */ if (copy_dtor) { int delta = sum_truesize - gso_skb->truesize; /* In some pathological cases, delta can be negative. * We need to either use refcount_add() or refcount_sub_and_test() */ if (likely(delta >= 0)) refcount_add(delta, &sk->sk_wmem_alloc); else WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc)); } return segs; } EXPORT_SYMBOL_GPL(__udp_gso_segment); static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int mss; __wsum csum; struct udphdr *uh; struct iphdr *iph; if (skb->encapsulation && (skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))) { segs = skb_udp_tunnel_segment(skb, features, false); goto out; } if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4))) goto out; if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) return __udp_gso_segment(skb, features, false); mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) goto out; /* Do software UFO. Complete and fill in the UDP checksum as * HW cannot do checksum of UDP packets sent as multiple * IP fragments. */ uh = udp_hdr(skb); iph = ip_hdr(skb); uh->check = 0; csum = skb_checksum(skb, 0, skb->len, 0); uh->check = udp_v4_check(skb->len, iph->saddr, iph->daddr, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; skb->ip_summed = CHECKSUM_UNNECESSARY; /* If there is no outer header we can fake a checksum offload * due to the fact that we have already done the checksum in * software prior to segmenting the frame. */ if (!skb->encap_hdr_csum) features |= NETIF_F_HW_CSUM; /* Fragment the skb. IP headers of the fragments are updated in * inet_gso_segment() */ segs = skb_segment(skb, features); out: return segs; } static int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) { if (unlikely(p->len + skb->len >= 65536)) return -E2BIG; if (NAPI_GRO_CB(p)->last == p) skb_shinfo(p)->frag_list = skb; else NAPI_GRO_CB(p)->last->next = skb; skb_pull(skb, skb_gro_offset(skb)); NAPI_GRO_CB(p)->last = skb; NAPI_GRO_CB(p)->count++; p->data_len += skb->len; /* sk ownership - if any - completely transferred to the aggregated packet */ skb->destructor = NULL; skb->sk = NULL; p->truesize += skb->truesize; p->len += skb->len; NAPI_GRO_CB(skb)->same_flow = 1; return 0; } #define UDP_GRO_CNT_MAX 64 static struct sk_buff *udp_gro_receive_segment(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); struct sk_buff *pp = NULL; struct udphdr *uh2; struct sk_buff *p; unsigned int ulen; int ret = 0; int flush; /* requires non zero csum, for symmetry with GSO */ if (!uh->check) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } /* Do not deal with padded or malicious packets, sorry ! */ ulen = ntohs(uh->len); if (ulen <= sizeof(*uh) || ulen != skb_gro_len(skb)) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } /* pull encapsulating udp header */ skb_gro_pull(skb, sizeof(struct udphdr)); list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; uh2 = udp_hdr(p); /* Match ports only, as csum is always non zero */ if ((*(u32 *)&uh->source != *(u32 *)&uh2->source)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } if (NAPI_GRO_CB(skb)->is_flist != NAPI_GRO_CB(p)->is_flist) { NAPI_GRO_CB(skb)->flush = 1; return p; } flush = NAPI_GRO_CB(p)->flush; if (NAPI_GRO_CB(p)->flush_id != 1 || NAPI_GRO_CB(p)->count != 1 || !NAPI_GRO_CB(p)->is_atomic) flush |= NAPI_GRO_CB(p)->flush_id; else NAPI_GRO_CB(p)->is_atomic = false; /* Terminate the flow on len mismatch or if it grow "too much". * Under small packet flood GRO count could elsewhere grow a lot * leading to excessive truesize values. * On len mismatch merge the first packet shorter than gso_size, * otherwise complete the GRO packet. */ if (ulen > ntohs(uh2->len) || flush) { pp = p; } else { if (NAPI_GRO_CB(skb)->is_flist) { if (!pskb_may_pull(skb, skb_gro_offset(skb))) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } if ((skb->ip_summed != p->ip_summed) || (skb->csum_level != p->csum_level)) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } ret = skb_gro_receive_list(p, skb); } else { skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); ret = skb_gro_receive(p, skb); } } if (ret || ulen != ntohs(uh2->len) || NAPI_GRO_CB(p)->count >= UDP_GRO_CNT_MAX) pp = p; return pp; } /* mismatch, but we never need to flush */ return NULL; } struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, struct udphdr *uh, struct sock *sk) { struct sk_buff *pp = NULL; struct sk_buff *p; struct udphdr *uh2; unsigned int off = skb_gro_offset(skb); int flush = 1; /* We can do L4 aggregation only if the packet can't land in a tunnel * otherwise we could corrupt the inner stream. Detecting such packets * cannot be foolproof and the aggregation might still happen in some * cases. Such packets should be caught in udp_unexpected_gso later. */ NAPI_GRO_CB(skb)->is_flist = 0; if (!sk || !udp_sk(sk)->gro_receive) { /* If the packet was locally encapsulated in a UDP tunnel that * wasn't detected above, do not GRO. */ if (skb->encapsulation) goto out; if (skb->dev->features & NETIF_F_GRO_FRAGLIST) NAPI_GRO_CB(skb)->is_flist = sk ? !udp_sk(sk)->gro_enabled : 1; if ((!sk && (skb->dev->features & NETIF_F_GRO_UDP_FWD)) || (sk && udp_sk(sk)->gro_enabled) || NAPI_GRO_CB(skb)->is_flist) return call_gro_receive(udp_gro_receive_segment, head, skb); /* no GRO, be sure flush the current packet */ goto out; } if (NAPI_GRO_CB(skb)->encap_mark || (uh->check && skb->ip_summed != CHECKSUM_PARTIAL && NAPI_GRO_CB(skb)->csum_cnt == 0 && !NAPI_GRO_CB(skb)->csum_valid)) goto out; /* mark that this skb passed once through the tunnel gro layer */ NAPI_GRO_CB(skb)->encap_mark = 1; flush = 0; list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; uh2 = (struct udphdr *)(p->data + off); /* Match ports and either checksums are either both zero * or nonzero. */ if ((*(u32 *)&uh->source != *(u32 *)&uh2->source) || (!uh->check ^ !uh2->check)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */ skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); pp = call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb); out: skb_gro_flush_final(skb, pp, flush); return pp; } EXPORT_SYMBOL(udp_gro_receive); static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport) { const struct iphdr *iph = skb_gro_network_header(skb); return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport, iph->daddr, dport, inet_iif(skb), inet_sdif(skb), &udp_table, NULL); } INDIRECT_CALLABLE_SCOPE struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); struct sock *sk = NULL; struct sk_buff *pp; if (unlikely(!uh)) goto flush; /* Don't bother verifying checksum if we're going to flush anyway. */ if (NAPI_GRO_CB(skb)->flush) goto skip; if (skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check, inet_gro_compute_pseudo)) goto flush; else if (uh->check) skb_gro_checksum_try_convert(skb, IPPROTO_UDP, inet_gro_compute_pseudo); skip: NAPI_GRO_CB(skb)->is_ipv6 = 0; if (static_branch_unlikely(&udp_encap_needed_key)) sk = udp4_gro_lookup_skb(skb, uh->source, uh->dest); pp = udp_gro_receive(head, skb, uh, sk); return pp; flush: NAPI_GRO_CB(skb)->flush = 1; return NULL; } static int udp_gro_complete_segment(struct sk_buff *skb) { struct udphdr *uh = udp_hdr(skb); skb->csum_start = (unsigned char *)uh - skb->head; skb->csum_offset = offsetof(struct udphdr, check); skb->ip_summed = CHECKSUM_PARTIAL; skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_L4; if (skb->encapsulation) skb->inner_transport_header = skb->transport_header; return 0; } int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup) { __be16 newlen = htons(skb->len - nhoff); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); struct sock *sk; int err; uh->len = newlen; sk = INDIRECT_CALL_INET(lookup, udp6_lib_lookup_skb, udp4_lib_lookup_skb, skb, uh->source, uh->dest); if (sk && udp_sk(sk)->gro_complete) { skb_shinfo(skb)->gso_type = uh->check ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; /* clear the encap mark, so that inner frag_list gro_complete * can take place */ NAPI_GRO_CB(skb)->encap_mark = 0; /* Set encapsulation before calling into inner gro_complete() * functions to make them set up the inner offsets. */ skb->encapsulation = 1; err = udp_sk(sk)->gro_complete(sk, skb, nhoff + sizeof(struct udphdr)); } else { err = udp_gro_complete_segment(skb); } if (skb->remcsum_offload) skb_shinfo(skb)->gso_type |= SKB_GSO_TUNNEL_REMCSUM; return err; } EXPORT_SYMBOL(udp_gro_complete); INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) { const struct iphdr *iph = ip_hdr(skb); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); /* do fraglist only if there is no outer UDP encap (or we already processed it) */ if (NAPI_GRO_CB(skb)->is_flist && !NAPI_GRO_CB(skb)->encap_mark) { uh->len = htons(skb->len - nhoff); skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; __skb_incr_checksum_unnecessary(skb); return 0; } if (uh->check) uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr, iph->daddr, 0); return udp_gro_complete(skb, nhoff, udp4_lib_lookup_skb); } static const struct net_offload udpv4_offload = { .callbacks = { .gso_segment = udp4_ufo_fragment, .gro_receive = udp4_gro_receive, .gro_complete = udp4_gro_complete, }, }; int __init udpv4_offload_init(void) { return inet_add_offload(&udpv4_offload, IPPROTO_UDP); } |
| 536 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 | /* SPDX-License-Identifier: GPL-2.0 */ /* File: linux/posix_acl.h (C) 2002 Andreas Gruenbacher, <a.gruenbacher@computer.org> */ #ifndef __LINUX_POSIX_ACL_H #define __LINUX_POSIX_ACL_H #include <linux/bug.h> #include <linux/slab.h> #include <linux/rcupdate.h> #include <linux/refcount.h> #include <uapi/linux/posix_acl.h> struct user_namespace; struct posix_acl_entry { short e_tag; unsigned short e_perm; union { kuid_t e_uid; kgid_t e_gid; }; }; struct posix_acl { refcount_t a_refcount; struct rcu_head a_rcu; unsigned int a_count; struct posix_acl_entry a_entries[]; }; #define FOREACH_ACL_ENTRY(pa, acl, pe) \ for(pa=(acl)->a_entries, pe=pa+(acl)->a_count; pa<pe; pa++) /* * Duplicate an ACL handle. */ static inline struct posix_acl * posix_acl_dup(struct posix_acl *acl) { if (acl) refcount_inc(&acl->a_refcount); return acl; } /* * Free an ACL handle. */ static inline void posix_acl_release(struct posix_acl *acl) { if (acl && refcount_dec_and_test(&acl->a_refcount)) kfree_rcu(acl, a_rcu); } /* posix_acl.c */ extern void posix_acl_init(struct posix_acl *, int); extern struct posix_acl *posix_acl_alloc(int, gfp_t); extern struct posix_acl *posix_acl_from_mode(umode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, umode_t *); extern int __posix_acl_create(struct posix_acl **, gfp_t, umode_t *); extern int __posix_acl_chmod(struct posix_acl **, gfp_t, umode_t); extern struct posix_acl *get_posix_acl(struct inode *, int); extern int set_posix_acl(struct user_namespace *, struct inode *, int, struct posix_acl *); struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type); struct posix_acl *posix_acl_clone(const struct posix_acl *acl, gfp_t flags); #ifdef CONFIG_FS_POSIX_ACL int posix_acl_chmod(struct user_namespace *, struct inode *, umode_t); extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **, struct posix_acl **); int posix_acl_update_mode(struct user_namespace *, struct inode *, umode_t *, struct posix_acl **); extern int simple_set_acl(struct user_namespace *, struct inode *, struct posix_acl *, int); extern int simple_acl_create(struct inode *, struct inode *); struct posix_acl *get_cached_acl(struct inode *inode, int type); void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl); void forget_cached_acl(struct inode *inode, int type); void forget_all_cached_acls(struct inode *inode); int posix_acl_valid(struct user_namespace *, const struct posix_acl *); int posix_acl_permission(struct user_namespace *, struct inode *, const struct posix_acl *, int); static inline void cache_no_acl(struct inode *inode) { inode->i_acl = NULL; inode->i_default_acl = NULL; } #else static inline int posix_acl_chmod(struct user_namespace *mnt_userns, struct inode *inode, umode_t mode) { return 0; } #define simple_set_acl NULL static inline int simple_acl_create(struct inode *dir, struct inode *inode) { return 0; } static inline void cache_no_acl(struct inode *inode) { } static inline int posix_acl_create(struct inode *inode, umode_t *mode, struct posix_acl **default_acl, struct posix_acl **acl) { *default_acl = *acl = NULL; return 0; } static inline void forget_all_cached_acls(struct inode *inode) { } #endif /* CONFIG_FS_POSIX_ACL */ struct posix_acl *get_acl(struct inode *inode, int type); #endif /* __LINUX_POSIX_ACL_H */ |
| 83 83 83 804 804 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PTRACE_H #define _LINUX_PTRACE_H #include <linux/compiler.h> /* For unlikely. */ #include <linux/sched.h> /* For struct task_struct. */ #include <linux/sched/signal.h> /* For send_sig(), same_thread_group(), etc. */ #include <linux/err.h> /* for IS_ERR_VALUE */ #include <linux/bug.h> /* For BUG_ON. */ #include <linux/pid_namespace.h> /* For task_active_pid_ns. */ #include <uapi/linux/ptrace.h> #include <linux/seccomp.h> /* Add sp to seccomp_data, as seccomp is user API, we don't want to modify it */ struct syscall_info { __u64 sp; struct seccomp_data data; }; extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags); /* * Ptrace flags * * The owner ship rules for task->ptrace which holds the ptrace * flags is simple. When a task is running it owns it's task->ptrace * flags. When the a task is stopped the ptracer owns task->ptrace. */ #define PT_SEIZED 0x00010000 /* SEIZE used, enable new behavior */ #define PT_PTRACED 0x00000001 #define PT_OPT_FLAG_SHIFT 3 /* PT_TRACE_* event enable flags */ #define PT_EVENT_FLAG(event) (1 << (PT_OPT_FLAG_SHIFT + (event))) #define PT_TRACESYSGOOD PT_EVENT_FLAG(0) #define PT_TRACE_FORK PT_EVENT_FLAG(PTRACE_EVENT_FORK) #define PT_TRACE_VFORK PT_EVENT_FLAG(PTRACE_EVENT_VFORK) #define PT_TRACE_CLONE PT_EVENT_FLAG(PTRACE_EVENT_CLONE) #define PT_TRACE_EXEC PT_EVENT_FLAG(PTRACE_EVENT_EXEC) #define PT_TRACE_VFORK_DONE PT_EVENT_FLAG(PTRACE_EVENT_VFORK_DONE) #define PT_TRACE_EXIT PT_EVENT_FLAG(PTRACE_EVENT_EXIT) #define PT_TRACE_SECCOMP PT_EVENT_FLAG(PTRACE_EVENT_SECCOMP) #define PT_EXITKILL (PTRACE_O_EXITKILL << PT_OPT_FLAG_SHIFT) #define PT_SUSPEND_SECCOMP (PTRACE_O_SUSPEND_SECCOMP << PT_OPT_FLAG_SHIFT) extern long arch_ptrace(struct task_struct *child, long request, unsigned long addr, unsigned long data); extern int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len); extern int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len); extern void ptrace_disable(struct task_struct *); extern int ptrace_request(struct task_struct *child, long request, unsigned long addr, unsigned long data); extern int ptrace_notify(int exit_code, unsigned long message); extern void __ptrace_link(struct task_struct *child, struct task_struct *new_parent, const struct cred *ptracer_cred); extern void __ptrace_unlink(struct task_struct *child); extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); #define PTRACE_MODE_READ 0x01 #define PTRACE_MODE_ATTACH 0x02 #define PTRACE_MODE_NOAUDIT 0x04 #define PTRACE_MODE_FSCREDS 0x08 #define PTRACE_MODE_REALCREDS 0x10 /* shorthands for READ/ATTACH and FSCREDS/REALCREDS combinations */ #define PTRACE_MODE_READ_FSCREDS (PTRACE_MODE_READ | PTRACE_MODE_FSCREDS) #define PTRACE_MODE_READ_REALCREDS (PTRACE_MODE_READ | PTRACE_MODE_REALCREDS) #define PTRACE_MODE_ATTACH_FSCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_FSCREDS) #define PTRACE_MODE_ATTACH_REALCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_REALCREDS) /** * ptrace_may_access - check whether the caller is permitted to access * a target task. * @task: target task * @mode: selects type of access and caller credentials * * Returns true on success, false on denial. * * One of the flags PTRACE_MODE_FSCREDS and PTRACE_MODE_REALCREDS must * be set in @mode to specify whether the access was requested through * a filesystem syscall (should use effective capabilities and fsuid * of the caller) or through an explicit syscall such as * process_vm_writev or ptrace (and should use the real credentials). */ extern bool ptrace_may_access(struct task_struct *task, unsigned int mode); static inline int ptrace_reparented(struct task_struct *child) { return !same_thread_group(child->real_parent, child->parent); } static inline void ptrace_unlink(struct task_struct *child) { if (unlikely(child->ptrace)) __ptrace_unlink(child); } int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr, unsigned long data); int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr, unsigned long data); /** * ptrace_parent - return the task that is tracing the given task * @task: task to consider * * Returns %NULL if no one is tracing @task, or the &struct task_struct * pointer to its tracer. * * Must called under rcu_read_lock(). The pointer returned might be kept * live only by RCU. During exec, this may be called with task_lock() held * on @task, still held from when check_unsafe_exec() was called. */ static inline struct task_struct *ptrace_parent(struct task_struct *task) { if (unlikely(task->ptrace)) return rcu_dereference(task->parent); return NULL; } /** * ptrace_event_enabled - test whether a ptrace event is enabled * @task: ptracee of interest * @event: %PTRACE_EVENT_* to test * * Test whether @event is enabled for ptracee @task. * * Returns %true if @event is enabled, %false otherwise. */ static inline bool ptrace_event_enabled(struct task_struct *task, int event) { return task->ptrace & PT_EVENT_FLAG(event); } /** * ptrace_event - possibly stop for a ptrace event notification * @event: %PTRACE_EVENT_* value to report * @message: value for %PTRACE_GETEVENTMSG to return * * Check whether @event is enabled and, if so, report @event and @message * to the ptrace parent. * * Called without locks. */ static inline void ptrace_event(int event, unsigned long message) { if (unlikely(ptrace_event_enabled(current, event))) { ptrace_notify((event << 8) | SIGTRAP, message); } else if (event == PTRACE_EVENT_EXEC) { /* legacy EXEC report via SIGTRAP */ if ((current->ptrace & (PT_PTRACED|PT_SEIZED)) == PT_PTRACED) send_sig(SIGTRAP, current, 0); } } /** * ptrace_event_pid - possibly stop for a ptrace event notification * @event: %PTRACE_EVENT_* value to report * @pid: process identifier for %PTRACE_GETEVENTMSG to return * * Check whether @event is enabled and, if so, report @event and @pid * to the ptrace parent. @pid is reported as the pid_t seen from the * ptrace parent's pid namespace. * * Called without locks. */ static inline void ptrace_event_pid(int event, struct pid *pid) { /* * FIXME: There's a potential race if a ptracer in a different pid * namespace than parent attaches between computing message below and * when we acquire tasklist_lock in ptrace_stop(). If this happens, * the ptracer will get a bogus pid from PTRACE_GETEVENTMSG. */ unsigned long message = 0; struct pid_namespace *ns; rcu_read_lock(); ns = task_active_pid_ns(rcu_dereference(current->parent)); if (ns) message = pid_nr_ns(pid, ns); rcu_read_unlock(); ptrace_event(event, message); } /** * ptrace_init_task - initialize ptrace state for a new child * @child: new child task * @ptrace: true if child should be ptrace'd by parent's tracer * * This is called immediately after adding @child to its parent's children * list. @ptrace is false in the normal case, and true to ptrace @child. * * Called with current's siglock and write_lock_irq(&tasklist_lock) held. */ static inline void ptrace_init_task(struct task_struct *child, bool ptrace) { INIT_LIST_HEAD(&child->ptrace_entry); INIT_LIST_HEAD(&child->ptraced); child->jobctl = 0; child->ptrace = 0; child->parent = child->real_parent; if (unlikely(ptrace) && current->ptrace) { child->ptrace = current->ptrace; __ptrace_link(child, current->parent, current->ptracer_cred); if (child->ptrace & PT_SEIZED) task_set_jobctl_pending(child, JOBCTL_TRAP_STOP); else sigaddset(&child->pending.signal, SIGSTOP); } else child->ptracer_cred = NULL; } /** * ptrace_release_task - final ptrace-related cleanup of a zombie being reaped * @task: task in %EXIT_DEAD state * * Called with write_lock(&tasklist_lock) held. */ static inline void ptrace_release_task(struct task_struct *task) { BUG_ON(!list_empty(&task->ptraced)); ptrace_unlink(task); BUG_ON(!list_empty(&task->ptrace_entry)); } #ifndef force_successful_syscall_return /* * System call handlers that, upon successful completion, need to return a * negative value should call force_successful_syscall_return() right before * returning. On architectures where the syscall convention provides for a * separate error flag (e.g., alpha, ia64, ppc{,64}, sparc{,64}, possibly * others), this macro can be used to ensure that the error flag will not get * set. On architectures which do not support a separate error flag, the macro * is a no-op and the spurious error condition needs to be filtered out by some * other means (e.g., in user-level, by passing an extra argument to the * syscall handler, or something along those lines). */ #define force_successful_syscall_return() do { } while (0) #endif #ifndef is_syscall_success /* * On most systems we can tell if a syscall is a success based on if the retval * is an error value. On some systems like ia64 and powerpc they have different * indicators of success/failure and must define their own. */ #define is_syscall_success(regs) (!IS_ERR_VALUE((unsigned long)(regs_return_value(regs)))) #endif /* * <asm/ptrace.h> should define the following things inside #ifdef __KERNEL__. * * These do-nothing inlines are used when the arch does not * implement single-step. The kerneldoc comments are here * to document the interface for all arch definitions. */ #ifndef arch_has_single_step /** * arch_has_single_step - does this CPU support user-mode single-step? * * If this is defined, then there must be function declarations or * inlines for user_enable_single_step() and user_disable_single_step(). * arch_has_single_step() should evaluate to nonzero iff the machine * supports instruction single-step for user mode. * It can be a constant or it can test a CPU feature bit. */ #define arch_has_single_step() (0) /** * user_enable_single_step - single-step in user-mode task * @task: either current or a task stopped in %TASK_TRACED * * This can only be called when arch_has_single_step() has returned nonzero. * Set @task so that when it returns to user mode, it will trap after the * next single instruction executes. If arch_has_block_step() is defined, * this must clear the effects of user_enable_block_step() too. */ static inline void user_enable_single_step(struct task_struct *task) { BUG(); /* This can never be called. */ } /** * user_disable_single_step - cancel user-mode single-step * @task: either current or a task stopped in %TASK_TRACED * * Clear @task of the effects of user_enable_single_step() and * user_enable_block_step(). This can be called whether or not either * of those was ever called on @task, and even if arch_has_single_step() * returned zero. */ static inline void user_disable_single_step(struct task_struct *task) { } #else extern void user_enable_single_step(struct task_struct *); extern void user_disable_single_step(struct task_struct *); #endif /* arch_has_single_step */ #ifndef arch_has_block_step /** * arch_has_block_step - does this CPU support user-mode block-step? * * If this is defined, then there must be a function declaration or inline * for user_enable_block_step(), and arch_has_single_step() must be defined * too. arch_has_block_step() should evaluate to nonzero iff the machine * supports step-until-branch for user mode. It can be a constant or it * can test a CPU feature bit. */ #define arch_has_block_step() (0) /** * user_enable_block_step - step until branch in user-mode task * @task: either current or a task stopped in %TASK_TRACED * * This can only be called when arch_has_block_step() has returned nonzero, * and will never be called when single-instruction stepping is being used. * Set @task so that when it returns to user mode, it will trap after the * next branch or trap taken. */ static inline void user_enable_block_step(struct task_struct *task) { BUG(); /* This can never be called. */ } #else extern void user_enable_block_step(struct task_struct *); #endif /* arch_has_block_step */ #ifdef ARCH_HAS_USER_SINGLE_STEP_REPORT extern void user_single_step_report(struct pt_regs *regs); #else static inline void user_single_step_report(struct pt_regs *regs) { kernel_siginfo_t info; clear_siginfo(&info); info.si_signo = SIGTRAP; info.si_errno = 0; info.si_code = SI_USER; info.si_pid = 0; info.si_uid = 0; force_sig_info(&info); } #endif #ifndef arch_ptrace_stop_needed /** * arch_ptrace_stop_needed - Decide whether arch_ptrace_stop() should be called * * This is called with the siglock held, to decide whether or not it's * necessary to release the siglock and call arch_ptrace_stop(). It can be * defined to a constant if arch_ptrace_stop() is never required, or always * is. On machines where this makes sense, it should be defined to a quick * test to optimize out calling arch_ptrace_stop() when it would be * superfluous. For example, if the thread has not been back to user mode * since the last stop, the thread state might indicate that nothing needs * to be done. * * This is guaranteed to be invoked once before a task stops for ptrace and * may include arch-specific operations necessary prior to a ptrace stop. */ #define arch_ptrace_stop_needed() (0) #endif #ifndef arch_ptrace_stop /** * arch_ptrace_stop - Do machine-specific work before stopping for ptrace * * This is called with no locks held when arch_ptrace_stop_needed() has * just returned nonzero. It is allowed to block, e.g. for user memory * access. The arch can have machine-specific work to be done before * ptrace stops. On ia64, register backing store gets written back to user * memory here. Since this can be costly (requires dropping the siglock), * we only do it when the arch requires it for this particular stop, as * indicated by arch_ptrace_stop_needed(). */ #define arch_ptrace_stop() do { } while (0) #endif #ifndef current_pt_regs #define current_pt_regs() task_pt_regs(current) #endif /* * unlike current_pt_regs(), this one is equal to task_pt_regs(current) * on *all* architectures; the only reason to have a per-arch definition * is optimisation. */ #ifndef signal_pt_regs #define signal_pt_regs() task_pt_regs(current) #endif #ifndef current_user_stack_pointer #define current_user_stack_pointer() user_stack_pointer(current_pt_regs()) #endif extern int task_current_syscall(struct task_struct *target, struct syscall_info *info); extern void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact); /* * ptrace report for syscall entry and exit looks identical. */ static inline int ptrace_report_syscall(unsigned long message) { int ptrace = current->ptrace; int signr; if (!(ptrace & PT_PTRACED)) return 0; signr = ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0), message); /* * this isn't the same as continuing with a signal, but it will do * for normal use. strace only continues with a signal if the * stopping signal is not SIGTRAP. -brl */ if (signr) send_sig(signr, current, 1); return fatal_signal_pending(current); } /** * ptrace_report_syscall_entry - task is about to attempt a system call * @regs: user register state of current task * * This will be called if %SYSCALL_WORK_SYSCALL_TRACE or * %SYSCALL_WORK_SYSCALL_EMU have been set, when the current task has just * entered the kernel for a system call. Full user register state is * available here. Changing the values in @regs can affect the system * call number and arguments to be tried. It is safe to block here, * preventing the system call from beginning. * * Returns zero normally, or nonzero if the calling arch code should abort * the system call. That must prevent normal entry so no system call is * made. If @task ever returns to user mode after this, its register state * is unspecified, but should be something harmless like an %ENOSYS error * return. It should preserve enough information so that syscall_rollback() * can work (see asm-generic/syscall.h). * * Called without locks, just after entering kernel mode. */ static inline __must_check int ptrace_report_syscall_entry( struct pt_regs *regs) { return ptrace_report_syscall(PTRACE_EVENTMSG_SYSCALL_ENTRY); } /** * ptrace_report_syscall_exit - task has just finished a system call * @regs: user register state of current task * @step: nonzero if simulating single-step or block-step * * This will be called if %SYSCALL_WORK_SYSCALL_TRACE has been set, when * the current task has just finished an attempted system call. Full * user register state is available here. It is safe to block here, * preventing signals from being processed. * * If @step is nonzero, this report is also in lieu of the normal * trap that would follow the system call instruction because * user_enable_block_step() or user_enable_single_step() was used. * In this case, %SYSCALL_WORK_SYSCALL_TRACE might not be set. * * Called without locks, just before checking for pending signals. */ static inline void ptrace_report_syscall_exit(struct pt_regs *regs, int step) { if (step) user_single_step_report(regs); else ptrace_report_syscall(PTRACE_EVENTMSG_SYSCALL_EXIT); } #endif |
| 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 | // SPDX-License-Identifier: GPL-2.0-only #include "netlink.h" #include "common.h" struct linkinfo_req_info { struct ethnl_req_info base; }; struct linkinfo_reply_data { struct ethnl_reply_data base; struct ethtool_link_ksettings ksettings; struct ethtool_link_settings *lsettings; }; #define LINKINFO_REPDATA(__reply_base) \ container_of(__reply_base, struct linkinfo_reply_data, base) const struct nla_policy ethnl_linkinfo_get_policy[] = { [ETHTOOL_A_LINKINFO_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; static int linkinfo_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, struct genl_info *info) { struct linkinfo_reply_data *data = LINKINFO_REPDATA(reply_base); struct net_device *dev = reply_base->dev; int ret; data->lsettings = &data->ksettings.base; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; ret = __ethtool_get_link_ksettings(dev, &data->ksettings); if (ret < 0 && info) GENL_SET_ERR_MSG(info, "failed to retrieve link settings"); ethnl_ops_complete(dev); return ret; } static int linkinfo_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { return nla_total_size(sizeof(u8)) /* LINKINFO_PORT */ + nla_total_size(sizeof(u8)) /* LINKINFO_PHYADDR */ + nla_total_size(sizeof(u8)) /* LINKINFO_TP_MDIX */ + nla_total_size(sizeof(u8)) /* LINKINFO_TP_MDIX_CTRL */ + nla_total_size(sizeof(u8)) /* LINKINFO_TRANSCEIVER */ + 0; } static int linkinfo_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct linkinfo_reply_data *data = LINKINFO_REPDATA(reply_base); if (nla_put_u8(skb, ETHTOOL_A_LINKINFO_PORT, data->lsettings->port) || nla_put_u8(skb, ETHTOOL_A_LINKINFO_PHYADDR, data->lsettings->phy_address) || nla_put_u8(skb, ETHTOOL_A_LINKINFO_TP_MDIX, data->lsettings->eth_tp_mdix) || nla_put_u8(skb, ETHTOOL_A_LINKINFO_TP_MDIX_CTRL, data->lsettings->eth_tp_mdix_ctrl) || nla_put_u8(skb, ETHTOOL_A_LINKINFO_TRANSCEIVER, data->lsettings->transceiver)) return -EMSGSIZE; return 0; } const struct ethnl_request_ops ethnl_linkinfo_request_ops = { .request_cmd = ETHTOOL_MSG_LINKINFO_GET, .reply_cmd = ETHTOOL_MSG_LINKINFO_GET_REPLY, .hdr_attr = ETHTOOL_A_LINKINFO_HEADER, .req_info_size = sizeof(struct linkinfo_req_info), .reply_data_size = sizeof(struct linkinfo_reply_data), .prepare_data = linkinfo_prepare_data, .reply_size = linkinfo_reply_size, .fill_reply = linkinfo_fill_reply, }; /* LINKINFO_SET */ const struct nla_policy ethnl_linkinfo_set_policy[] = { [ETHTOOL_A_LINKINFO_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_LINKINFO_PORT] = { .type = NLA_U8 }, [ETHTOOL_A_LINKINFO_PHYADDR] = { .type = NLA_U8 }, [ETHTOOL_A_LINKINFO_TP_MDIX_CTRL] = { .type = NLA_U8 }, }; int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info) { struct ethtool_link_ksettings ksettings = {}; struct ethtool_link_settings *lsettings; struct ethnl_req_info req_info = {}; struct nlattr **tb = info->attrs; struct net_device *dev; bool mod = false; int ret; ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_LINKINFO_HEADER], genl_info_net(info), info->extack, true); if (ret < 0) return ret; dev = req_info.dev; ret = -EOPNOTSUPP; if (!dev->ethtool_ops->get_link_ksettings || !dev->ethtool_ops->set_link_ksettings) goto out_dev; rtnl_lock(); ret = ethnl_ops_begin(dev); if (ret < 0) goto out_rtnl; ret = __ethtool_get_link_ksettings(dev, &ksettings); if (ret < 0) { GENL_SET_ERR_MSG(info, "failed to retrieve link settings"); goto out_ops; } lsettings = &ksettings.base; ethnl_update_u8(&lsettings->port, tb[ETHTOOL_A_LINKINFO_PORT], &mod); ethnl_update_u8(&lsettings->phy_address, tb[ETHTOOL_A_LINKINFO_PHYADDR], &mod); ethnl_update_u8(&lsettings->eth_tp_mdix_ctrl, tb[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL], &mod); ret = 0; if (!mod) goto out_ops; ret = dev->ethtool_ops->set_link_ksettings(dev, &ksettings); if (ret < 0) GENL_SET_ERR_MSG(info, "link settings update failed"); else ethtool_notify(dev, ETHTOOL_MSG_LINKINFO_NTF, NULL); out_ops: ethnl_ops_complete(dev); out_rtnl: rtnl_unlock(); out_dev: ethnl_parse_header_dev_put(&req_info); return ret; } |
| 131 131 122 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 | #include <linux/dcache.h> #include "internal.h" unsigned name_to_int(const struct qstr *qstr) { const char *name = qstr->name; int len = qstr->len; unsigned n = 0; if (len > 1 && *name == '0') goto out; do { unsigned c = *name++ - '0'; if (c > 9) goto out; if (n >= (~0U-9)/10) goto out; n *= 10; n += c; } while (--len > 0); return n; out: return ~0U; } |
| 315 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Authors: Thiébaud Weksteen <tweek@google.com> * Peter Enderborg <Peter.Enderborg@sony.com> */ #undef TRACE_SYSTEM #define TRACE_SYSTEM avc #if !defined(_TRACE_SELINUX_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SELINUX_H #include <linux/tracepoint.h> TRACE_EVENT(selinux_audited, TP_PROTO(struct selinux_audit_data *sad, char *scontext, char *tcontext, const char *tclass ), TP_ARGS(sad, scontext, tcontext, tclass), TP_STRUCT__entry( __field(u32, requested) __field(u32, denied) __field(u32, audited) __field(int, result) __string(scontext, scontext) __string(tcontext, tcontext) __string(tclass, tclass) ), TP_fast_assign( __entry->requested = sad->requested; __entry->denied = sad->denied; __entry->audited = sad->audited; __entry->result = sad->result; __assign_str(tcontext, tcontext); __assign_str(scontext, scontext); __assign_str(tclass, tclass); ), TP_printk("requested=0x%x denied=0x%x audited=0x%x result=%d scontext=%s tcontext=%s tclass=%s", __entry->requested, __entry->denied, __entry->audited, __entry->result, __get_str(scontext), __get_str(tcontext), __get_str(tclass) ) ); #endif /* This part must be outside protection */ #include <trace/define_trace.h> |
| 253 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 | /* SPDX-License-Identifier: GPL-2.0 */ /* linux/net/inet/arp.h */ #ifndef _ARP_H #define _ARP_H #include <linux/if_arp.h> #include <linux/hash.h> #include <net/neighbour.h> extern struct neigh_table arp_tbl; static inline u32 arp_hashfn(const void *pkey, const struct net_device *dev, u32 *hash_rnd) { u32 key = *(const u32 *)pkey; u32 val = key ^ hash32_ptr(dev); return val * hash_rnd[0]; } #ifdef CONFIG_INET static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key) { if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) key = INADDR_ANY; return ___neigh_lookup_noref(&arp_tbl, neigh_key_eq32, arp_hashfn, &key, dev); } #else static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key) { return NULL; } #endif static inline struct neighbour *__ipv4_neigh_lookup(struct net_device *dev, u32 key) { struct neighbour *n; rcu_read_lock(); n = __ipv4_neigh_lookup_noref(dev, key); if (n && !refcount_inc_not_zero(&n->refcnt)) n = NULL; rcu_read_unlock(); return n; } static inline void __ipv4_confirm_neigh(struct net_device *dev, u32 key) { struct neighbour *n; rcu_read_lock(); n = __ipv4_neigh_lookup_noref(dev, key); neigh_confirm(n); rcu_read_unlock(); } void arp_init(void); int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg); void arp_send(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, const unsigned char *th); int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir); void arp_ifdown(struct net_device *dev); int arp_invalidate(struct net_device *dev, __be32 ip, bool force); struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, const unsigned char *target_hw); void arp_xmit(struct sk_buff *skb); #endif /* _ARP_H */ |
| 5347 933 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NF_CONNTRACK_COMMON_H #define _NF_CONNTRACK_COMMON_H #include <linux/refcount.h> #include <uapi/linux/netfilter/nf_conntrack_common.h> struct ip_conntrack_stat { unsigned int found; unsigned int invalid; unsigned int insert; unsigned int insert_failed; unsigned int clash_resolve; unsigned int drop; unsigned int early_drop; unsigned int error; unsigned int expect_new; unsigned int expect_create; unsigned int expect_delete; unsigned int search_restart; unsigned int chaintoolong; }; #define NFCT_INFOMASK 7UL #define NFCT_PTRMASK ~(NFCT_INFOMASK) struct nf_conntrack { refcount_t use; }; void nf_conntrack_destroy(struct nf_conntrack *nfct); /* like nf_ct_put, but without module dependency on nf_conntrack */ static inline void nf_conntrack_put(struct nf_conntrack *nfct) { if (nfct && refcount_dec_and_test(&nfct->use)) nf_conntrack_destroy(nfct); } static inline void nf_conntrack_get(struct nf_conntrack *nfct) { if (nfct) refcount_inc(&nfct->use); } #endif /* _NF_CONNTRACK_COMMON_H */ |
| 1131 107 1272 1271 1272 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ #include <linux/dcache.h> #include <linux/fs.h> #include <linux/gfp.h> #include <linux/init.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/srcu.h> #include <linux/fsnotify_backend.h> #include "fsnotify.h" /* * Clear all of the marks on an inode when it is being evicted from core */ void __fsnotify_inode_delete(struct inode *inode) { fsnotify_clear_marks_by_inode(inode); } EXPORT_SYMBOL_GPL(__fsnotify_inode_delete); void __fsnotify_vfsmount_delete(struct vfsmount *mnt) { fsnotify_clear_marks_by_mount(mnt); } /** * fsnotify_unmount_inodes - an sb is unmounting. handle any watched inodes. * @sb: superblock being unmounted. * * Called during unmount with no locks held, so needs to be safe against * concurrent modifiers. We temporarily drop sb->s_inode_list_lock and CAN block. */ static void fsnotify_unmount_inodes(struct super_block *sb) { struct inode *inode, *iput_inode = NULL; spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { /* * We cannot __iget() an inode in state I_FREEING, * I_WILL_FREE, or I_NEW which is fine because by that point * the inode cannot have any associated watches. */ spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) { spin_unlock(&inode->i_lock); continue; } /* * If i_count is zero, the inode cannot have any watches and * doing an __iget/iput with SB_ACTIVE clear would actually * evict all inodes with zero i_count from icache which is * unnecessarily violent and may in fact be illegal to do. * However, we should have been called /after/ evict_inodes * removed all zero refcount inodes, in any case. Test to * be sure. */ if (!atomic_read(&inode->i_count)) { spin_unlock(&inode->i_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inode_list_lock); iput(iput_inode); /* for each watch, send FS_UNMOUNT and then remove it */ fsnotify_inode(inode, FS_UNMOUNT); fsnotify_inode_delete(inode); iput_inode = inode; cond_resched(); spin_lock(&sb->s_inode_list_lock); } spin_unlock(&sb->s_inode_list_lock); iput(iput_inode); } void fsnotify_sb_delete(struct super_block *sb) { fsnotify_unmount_inodes(sb); fsnotify_clear_marks_by_sb(sb); /* Wait for outstanding object references from connectors */ wait_var_event(&sb->s_fsnotify_connectors, !atomic_long_read(&sb->s_fsnotify_connectors)); } /* * Given an inode, first check if we care what happens to our children. Inotify * and dnotify both tell their parents about events. If we care about any event * on a child we run all of our children and set a dentry flag saying that the * parent cares. Thus when an event happens on a child it can quickly tell * if there is a need to find a parent and send the event to the parent. */ void fsnotify_set_children_dentry_flags(struct inode *inode) { struct dentry *alias; if (!S_ISDIR(inode->i_mode)) return; spin_lock(&inode->i_lock); /* run all of the dentries associated with this inode. Since this is a * directory, there damn well better only be one item on this list */ hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { struct dentry *child; /* run all of the children of the original inode and fix their * d_flags to indicate parental interest (their parent is the * original inode) */ spin_lock(&alias->d_lock); list_for_each_entry(child, &alias->d_subdirs, d_child) { if (!child->d_inode) continue; spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED); child->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED; spin_unlock(&child->d_lock); } spin_unlock(&alias->d_lock); } spin_unlock(&inode->i_lock); } /* * Lazily clear false positive PARENT_WATCHED flag for child whose parent had * stopped watching children. */ static void fsnotify_clear_child_dentry_flag(struct inode *pinode, struct dentry *dentry) { spin_lock(&dentry->d_lock); /* * d_lock is a sufficient barrier to prevent observing a non-watched * parent state from before the fsnotify_set_children_dentry_flags() * or fsnotify_update_flags() call that had set PARENT_WATCHED. */ if (!fsnotify_inode_watches_children(pinode)) dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED; spin_unlock(&dentry->d_lock); } /* Are inode/sb/mount interested in parent and name info with this event? */ static bool fsnotify_event_needs_parent(struct inode *inode, struct mount *mnt, __u32 mask) { __u32 marks_mask = 0; /* We only send parent/name to inode/sb/mount for events on non-dir */ if (mask & FS_ISDIR) return false; /* * All events that are possible on child can also may be reported with * parent/name info to inode/sb/mount. Otherwise, a watching parent * could result in events reported with unexpected name info to sb/mount. */ BUILD_BUG_ON(FS_EVENTS_POSS_ON_CHILD & ~FS_EVENTS_POSS_TO_PARENT); /* Did either inode/sb/mount subscribe for events with parent/name? */ marks_mask |= fsnotify_parent_needed_mask(inode->i_fsnotify_mask); marks_mask |= fsnotify_parent_needed_mask(inode->i_sb->s_fsnotify_mask); if (mnt) marks_mask |= fsnotify_parent_needed_mask(mnt->mnt_fsnotify_mask); /* Did they subscribe for this event with parent/name info? */ return mask & marks_mask; } /* * Notify this dentry's parent about a child's events with child name info * if parent is watching or if inode/sb/mount are interested in events with * parent and name info. * * Notify only the child without name info if parent is not watching and * inode/sb/mount are not interested in events with parent and name info. */ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { const struct path *path = fsnotify_data_path(data, data_type); struct mount *mnt = path ? real_mount(path->mnt) : NULL; struct inode *inode = d_inode(dentry); struct dentry *parent; bool parent_watched = dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED; bool parent_needed, parent_interested; __u32 p_mask; struct inode *p_inode = NULL; struct name_snapshot name; struct qstr *file_name = NULL; int ret = 0; /* * Do inode/sb/mount care about parent and name info on non-dir? * Do they care about any event at all? */ if (!inode->i_fsnotify_marks && !inode->i_sb->s_fsnotify_marks && (!mnt || !mnt->mnt_fsnotify_marks) && !parent_watched) return 0; parent = NULL; parent_needed = fsnotify_event_needs_parent(inode, mnt, mask); if (!parent_watched && !parent_needed) goto notify; /* Does parent inode care about events on children? */ parent = dget_parent(dentry); p_inode = parent->d_inode; p_mask = fsnotify_inode_watches_children(p_inode); if (unlikely(parent_watched && !p_mask)) fsnotify_clear_child_dentry_flag(p_inode, dentry); /* * Include parent/name in notification either if some notification * groups require parent info or the parent is interested in this event. */ parent_interested = mask & p_mask & ALL_FSNOTIFY_EVENTS; if (parent_needed || parent_interested) { /* When notifying parent, child should be passed as data */ WARN_ON_ONCE(inode != fsnotify_data_inode(data, data_type)); /* Notify both parent and child with child name info */ take_dentry_name_snapshot(&name, dentry); file_name = &name.name; if (parent_interested) mask |= FS_EVENT_ON_CHILD; } notify: ret = fsnotify(mask, data, data_type, p_inode, file_name, inode, 0); if (file_name) release_dentry_name_snapshot(&name); dput(parent); return ret; } EXPORT_SYMBOL_GPL(__fsnotify_parent); static int fsnotify_handle_inode_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, u32 cookie) { const struct path *path = fsnotify_data_path(data, data_type); struct inode *inode = fsnotify_data_inode(data, data_type); const struct fsnotify_ops *ops = group->ops; if (WARN_ON_ONCE(!ops->handle_inode_event)) return 0; if (WARN_ON_ONCE(!inode && !dir)) return 0; if ((inode_mark->flags & FSNOTIFY_MARK_FLAG_EXCL_UNLINK) && path && d_unlinked(path->dentry)) return 0; /* Check interest of this mark in case event was sent with two marks */ if (!(mask & inode_mark->mask & ALL_FSNOTIFY_EVENTS)) return 0; return ops->handle_inode_event(inode_mark, mask, inode, dir, name, cookie); } static int fsnotify_handle_event(struct fsnotify_group *group, __u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, u32 cookie, struct fsnotify_iter_info *iter_info) { struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info); struct fsnotify_mark *parent_mark = fsnotify_iter_parent_mark(iter_info); int ret; if (WARN_ON_ONCE(fsnotify_iter_sb_mark(iter_info)) || WARN_ON_ONCE(fsnotify_iter_vfsmount_mark(iter_info))) return 0; /* * For FS_RENAME, 'dir' is old dir and 'data' is new dentry. * The only ->handle_inode_event() backend that supports FS_RENAME is * dnotify, where it means file was renamed within same parent. */ if (mask & FS_RENAME) { struct dentry *moved = fsnotify_data_dentry(data, data_type); if (dir != moved->d_parent->d_inode) return 0; } if (parent_mark) { ret = fsnotify_handle_inode_event(group, parent_mark, mask, data, data_type, dir, name, 0); if (ret) return ret; } if (!inode_mark) return 0; /* * Some events can be sent on both parent dir and child marks (e.g. * FS_ATTRIB). If both parent dir and child are watching, report the * event once to parent dir with name (if interested) and once to child * without name (if interested). * * In any case regardless whether the parent is watching or not, the * child watcher is expecting an event without the FS_EVENT_ON_CHILD * flag. The file name is expected if and only if this is a directory * event. */ mask &= ~FS_EVENT_ON_CHILD; if (!(mask & ALL_FSNOTIFY_DIRENT_EVENTS)) { dir = NULL; name = NULL; } return fsnotify_handle_inode_event(group, inode_mark, mask, data, data_type, dir, name, cookie); } static int send_to_group(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, u32 cookie, struct fsnotify_iter_info *iter_info) { struct fsnotify_group *group = NULL; __u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS); __u32 marks_mask = 0; __u32 marks_ignore_mask = 0; bool is_dir = mask & FS_ISDIR; struct fsnotify_mark *mark; int type; if (!iter_info->report_mask) return 0; /* clear ignored on inode modification */ if (mask & FS_MODIFY) { fsnotify_foreach_iter_mark_type(iter_info, mark, type) { if (!(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) mark->ignore_mask = 0; } } /* Are any of the group marks interested in this event? */ fsnotify_foreach_iter_mark_type(iter_info, mark, type) { group = mark->group; marks_mask |= mark->mask; marks_ignore_mask |= fsnotify_effective_ignore_mask(mark, is_dir, type); } pr_debug("%s: group=%p mask=%x marks_mask=%x marks_ignore_mask=%x data=%p data_type=%d dir=%p cookie=%d\n", __func__, group, mask, marks_mask, marks_ignore_mask, data, data_type, dir, cookie); if (!(test_mask & marks_mask & ~marks_ignore_mask)) return 0; if (group->ops->handle_event) { return group->ops->handle_event(group, mask, data, data_type, dir, file_name, cookie, iter_info); } return fsnotify_handle_event(group, mask, data, data_type, dir, file_name, cookie, iter_info); } static struct fsnotify_mark *fsnotify_first_mark(struct fsnotify_mark_connector **connp) { struct fsnotify_mark_connector *conn; struct hlist_node *node = NULL; conn = srcu_dereference(*connp, &fsnotify_mark_srcu); if (conn) node = srcu_dereference(conn->list.first, &fsnotify_mark_srcu); return hlist_entry_safe(node, struct fsnotify_mark, obj_list); } static struct fsnotify_mark *fsnotify_next_mark(struct fsnotify_mark *mark) { struct hlist_node *node = NULL; if (mark) node = srcu_dereference(mark->obj_list.next, &fsnotify_mark_srcu); return hlist_entry_safe(node, struct fsnotify_mark, obj_list); } /* * iter_info is a multi head priority queue of marks. * Pick a subset of marks from queue heads, all with the same group * and set the report_mask to a subset of the selected marks. * Returns false if there are no more groups to iterate. */ static bool fsnotify_iter_select_report_types( struct fsnotify_iter_info *iter_info) { struct fsnotify_group *max_prio_group = NULL; struct fsnotify_mark *mark; int type; /* Choose max prio group among groups of all queue heads */ fsnotify_foreach_iter_type(type) { mark = iter_info->marks[type]; if (mark && fsnotify_compare_groups(max_prio_group, mark->group) > 0) max_prio_group = mark->group; } if (!max_prio_group) return false; /* Set the report mask for marks from same group as max prio group */ iter_info->current_group = max_prio_group; iter_info->report_mask = 0; fsnotify_foreach_iter_type(type) { mark = iter_info->marks[type]; if (mark && mark->group == iter_info->current_group) { /* * FSNOTIFY_ITER_TYPE_PARENT indicates that this inode * is watching children and interested in this event, * which is an event possible on child. * But is *this mark* watching children? */ if (type == FSNOTIFY_ITER_TYPE_PARENT && !(mark->mask & FS_EVENT_ON_CHILD) && !(fsnotify_ignore_mask(mark) & FS_EVENT_ON_CHILD)) continue; fsnotify_iter_set_report_type(iter_info, type); } } return true; } /* * Pop from iter_info multi head queue, the marks that belong to the group of * current iteration step. */ static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info) { struct fsnotify_mark *mark; int type; /* * We cannot use fsnotify_foreach_iter_mark_type() here because we * may need to advance a mark of type X that belongs to current_group * but was not selected for reporting. */ fsnotify_foreach_iter_type(type) { mark = iter_info->marks[type]; if (mark && mark->group == iter_info->current_group) iter_info->marks[type] = fsnotify_next_mark(iter_info->marks[type]); } } /* * fsnotify - This is the main call to fsnotify. * * The VFS calls into hook specific functions in linux/fsnotify.h. * Those functions then in turn call here. Here will call out to all of the * registered fsnotify_group. Those groups can then use the notification event * in whatever means they feel necessary. * * @mask: event type and flags * @data: object that event happened on * @data_type: type of object for fanotify_data_XXX() accessors * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to * @file_name: optional file name associated with event * @inode: optional inode associated with event - * If @dir and @inode are both non-NULL, event may be * reported to both. * @cookie: inotify rename cookie */ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, struct inode *inode, u32 cookie) { const struct path *path = fsnotify_data_path(data, data_type); struct super_block *sb = fsnotify_data_sb(data, data_type); struct fsnotify_iter_info iter_info = {}; struct mount *mnt = NULL; struct inode *inode2 = NULL; struct dentry *moved; int inode2_type; int ret = 0; __u32 test_mask, marks_mask; if (path) mnt = real_mount(path->mnt); if (!inode) { /* Dirent event - report on TYPE_INODE to dir */ inode = dir; /* For FS_RENAME, inode is old_dir and inode2 is new_dir */ if (mask & FS_RENAME) { moved = fsnotify_data_dentry(data, data_type); inode2 = moved->d_parent->d_inode; inode2_type = FSNOTIFY_ITER_TYPE_INODE2; } } else if (mask & FS_EVENT_ON_CHILD) { /* * Event on child - report on TYPE_PARENT to dir if it is * watching children and on TYPE_INODE to child. */ inode2 = dir; inode2_type = FSNOTIFY_ITER_TYPE_PARENT; } /* * Optimization: srcu_read_lock() has a memory barrier which can * be expensive. It protects walking the *_fsnotify_marks lists. * However, if we do not walk the lists, we do not have to do * SRCU because we have no references to any objects and do not * need SRCU to keep them "alive". */ if (!sb->s_fsnotify_marks && (!mnt || !mnt->mnt_fsnotify_marks) && (!inode || !inode->i_fsnotify_marks) && (!inode2 || !inode2->i_fsnotify_marks)) return 0; marks_mask = sb->s_fsnotify_mask; if (mnt) marks_mask |= mnt->mnt_fsnotify_mask; if (inode) marks_mask |= inode->i_fsnotify_mask; if (inode2) marks_mask |= inode2->i_fsnotify_mask; /* * If this is a modify event we may need to clear some ignore masks. * In that case, the object with ignore masks will have the FS_MODIFY * event in its mask. * Otherwise, return if none of the marks care about this type of event. */ test_mask = (mask & ALL_FSNOTIFY_EVENTS); if (!(test_mask & marks_mask)) return 0; iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu); iter_info.marks[FSNOTIFY_ITER_TYPE_SB] = fsnotify_first_mark(&sb->s_fsnotify_marks); if (mnt) { iter_info.marks[FSNOTIFY_ITER_TYPE_VFSMOUNT] = fsnotify_first_mark(&mnt->mnt_fsnotify_marks); } if (inode) { iter_info.marks[FSNOTIFY_ITER_TYPE_INODE] = fsnotify_first_mark(&inode->i_fsnotify_marks); } if (inode2) { iter_info.marks[inode2_type] = fsnotify_first_mark(&inode2->i_fsnotify_marks); } /* * We need to merge inode/vfsmount/sb mark lists so that e.g. inode mark * ignore masks are properly reflected for mount/sb mark notifications. * That's why this traversal is so complicated... */ while (fsnotify_iter_select_report_types(&iter_info)) { ret = send_to_group(mask, data, data_type, dir, file_name, cookie, &iter_info); if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS)) goto out; fsnotify_iter_next(&iter_info); } ret = 0; out: srcu_read_unlock(&fsnotify_mark_srcu, iter_info.srcu_idx); return ret; } EXPORT_SYMBOL_GPL(fsnotify); static __init int fsnotify_init(void) { int ret; BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 23); ret = init_srcu_struct(&fsnotify_mark_srcu); if (ret) panic("initializing fsnotify_mark_srcu"); fsnotify_mark_connector_cachep = KMEM_CACHE(fsnotify_mark_connector, SLAB_PANIC); return 0; } core_initcall(fsnotify_init); |
| 16132 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/fault-inject.h> #include <linux/fault-inject-usercopy.h> static struct { struct fault_attr attr; } fail_usercopy = { .attr = FAULT_ATTR_INITIALIZER, }; static int __init setup_fail_usercopy(char *str) { return setup_fault_attr(&fail_usercopy.attr, str); } __setup("fail_usercopy=", setup_fail_usercopy); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS static int __init fail_usercopy_debugfs(void) { struct dentry *dir; dir = fault_create_debugfs_attr("fail_usercopy", NULL, &fail_usercopy.attr); if (IS_ERR(dir)) return PTR_ERR(dir); return 0; } late_initcall(fail_usercopy_debugfs); #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ bool should_fail_usercopy(void) { return should_fail(&fail_usercopy.attr, 1); } EXPORT_SYMBOL_GPL(should_fail_usercopy); |
| 9 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 | /* * net/tipc/addr.c: TIPC address utility routines * * Copyright (c) 2000-2006, 2018, Ericsson AB * Copyright (c) 2004-2005, 2010-2011, Wind River Systems * Copyright (c) 2020-2021, Red Hat Inc * 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. */ #include "addr.h" #include "core.h" bool tipc_in_scope(bool legacy_format, u32 domain, u32 addr) { if (!domain || (domain == addr)) return true; if (!legacy_format) return false; if (domain == tipc_cluster_mask(addr)) /* domain <Z.C.0> */ return true; if (domain == (addr & TIPC_ZONE_CLUSTER_MASK)) /* domain <Z.C.0> */ return true; if (domain == (addr & TIPC_ZONE_MASK)) /* domain <Z.0.0> */ return true; return false; } void tipc_set_node_id(struct net *net, u8 *id) { struct tipc_net *tn = tipc_net(net); memcpy(tn->node_id, id, NODE_ID_LEN); tipc_nodeid2string(tn->node_id_string, id); tn->trial_addr = hash128to32(id); pr_info("Node identity %s, cluster identity %u\n", tipc_own_id_string(net), tn->net_id); } void tipc_set_node_addr(struct net *net, u32 addr) { struct tipc_net *tn = tipc_net(net); u8 node_id[NODE_ID_LEN] = {0,}; tn->node_addr = addr; if (!tipc_own_id(net)) { sprintf(node_id, "%x", addr); tipc_set_node_id(net, node_id); } tn->trial_addr = addr; tn->addr_trial_end = jiffies; pr_info("Node number set to %u\n", addr); } char *tipc_nodeid2string(char *str, u8 *id) { int i; u8 c; /* Already a string ? */ for (i = 0; i < NODE_ID_LEN; i++) { c = id[i]; if (c >= '0' && c <= '9') continue; if (c >= 'A' && c <= 'Z') continue; if (c >= 'a' && c <= 'z') continue; if (c == '.') continue; if (c == ':') continue; if (c == '_') continue; if (c == '-') continue; if (c == '@') continue; if (c != 0) break; } if (i == NODE_ID_LEN) { memcpy(str, id, NODE_ID_LEN); str[NODE_ID_LEN] = 0; return str; } /* Translate to hex string */ for (i = 0; i < NODE_ID_LEN; i++) sprintf(&str[2 * i], "%02x", id[i]); /* Strip off trailing zeroes */ for (i = NODE_ID_STR_LEN - 2; str[i] == '0'; i--) str[i] = 0; return str; } |
| 462 68 68 | 1 2 3 4 5 6 7 8 9 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 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM creds #define TRACE_INCLUDE_PATH trace/hooks #if !defined(_TRACE_HOOK_CREDS_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_HOOK_CREDS_H #include <trace/hooks/vendor_hooks.h> /* * Following tracepoints are not exported in tracefs and provide a * mechanism for vendor modules to hook and extend functionality */ struct cred; struct task_struct; DECLARE_RESTRICTED_HOOK(android_rvh_commit_creds, TP_PROTO(const struct task_struct *task, const struct cred *new), TP_ARGS(task, new), 1); DECLARE_RESTRICTED_HOOK(android_rvh_exit_creds, TP_PROTO(const struct task_struct *task, const struct cred *cred), TP_ARGS(task, cred), 1); DECLARE_RESTRICTED_HOOK(android_rvh_override_creds, TP_PROTO(const struct task_struct *task, const struct cred *new), TP_ARGS(task, new), 1); DECLARE_RESTRICTED_HOOK(android_rvh_revert_creds, TP_PROTO(const struct task_struct *task, const struct cred *old), TP_ARGS(task, old), 1); #endif /* _TRACE_HOOK_CREDS_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 677 675 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_COOKIE_H #define __LINUX_COOKIE_H #include <linux/atomic.h> #include <linux/percpu.h> #include <asm/local.h> struct pcpu_gen_cookie { local_t nesting; u64 last; } __aligned(16); struct gen_cookie { struct pcpu_gen_cookie __percpu *local; atomic64_t forward_last ____cacheline_aligned_in_smp; atomic64_t reverse_last; }; #define COOKIE_LOCAL_BATCH 4096 #define DEFINE_COOKIE(name) \ static DEFINE_PER_CPU(struct pcpu_gen_cookie, __##name); \ static struct gen_cookie name = { \ .local = &__##name, \ .forward_last = ATOMIC64_INIT(0), \ .reverse_last = ATOMIC64_INIT(0), \ } static __always_inline u64 gen_cookie_next(struct gen_cookie *gc) { struct pcpu_gen_cookie *local = this_cpu_ptr(gc->local); u64 val; if (likely(local_inc_return(&local->nesting) == 1)) { val = local->last; if (__is_defined(CONFIG_SMP) && unlikely((val & (COOKIE_LOCAL_BATCH - 1)) == 0)) { s64 next = atomic64_add_return(COOKIE_LOCAL_BATCH, &gc->forward_last); val = next - COOKIE_LOCAL_BATCH; } local->last = ++val; } else { val = atomic64_dec_return(&gc->reverse_last); } local_dec(&local->nesting); return val; } #endif /* __LINUX_COOKIE_H */ |
| 2142 2144 1449 1448 2079 2079 2144 2228 1451 2228 1380 1822 2144 2143 2144 156 2078 1590 1572 2144 2144 2144 2026 158 1451 1451 1450 1451 1450 1450 1450 2149 105 40 417 2058 2144 3349 3343 97 97 1451 1452 1451 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 | // SPDX-License-Identifier: GPL-2.0 /* * KFENCE guarded object allocator and fault handling. * * Copyright (C) 2020, Google LLC. */ #define pr_fmt(fmt) "kfence: " fmt #include <linux/atomic.h> #include <linux/bug.h> #include <linux/debugfs.h> #include <linux/hash.h> #include <linux/irq_work.h> #include <linux/jhash.h> #include <linux/kcsan-checks.h> #include <linux/kfence.h> #include <linux/kmemleak.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/log2.h> #include <linux/memblock.h> #include <linux/moduleparam.h> #include <linux/notifier.h> #include <linux/panic_notifier.h> #include <linux/random.h> #include <linux/rcupdate.h> #include <linux/sched/clock.h> #include <linux/sched/sysctl.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/string.h> #include <asm/kfence.h> #include "kfence.h" /* Disables KFENCE on the first warning assuming an irrecoverable error. */ #define KFENCE_WARN_ON(cond) \ ({ \ const bool __cond = WARN_ON(cond); \ if (unlikely(__cond)) { \ WRITE_ONCE(kfence_enabled, false); \ disabled_by_warn = true; \ } \ __cond; \ }) /* === Data ================================================================= */ static bool kfence_enabled __read_mostly; static bool disabled_by_warn __read_mostly; unsigned long kfence_sample_interval __read_mostly = CONFIG_KFENCE_SAMPLE_INTERVAL; EXPORT_SYMBOL_GPL(kfence_sample_interval); /* Export for test modules. */ #ifdef MODULE_PARAM_PREFIX #undef MODULE_PARAM_PREFIX #endif #define MODULE_PARAM_PREFIX "kfence." static int kfence_enable_late(void); static int param_set_sample_interval(const char *val, const struct kernel_param *kp) { unsigned long num; int ret = kstrtoul(val, 0, &num); if (ret < 0) return ret; /* Using 0 to indicate KFENCE is disabled. */ if (!num && READ_ONCE(kfence_enabled)) { pr_info("disabled\n"); WRITE_ONCE(kfence_enabled, false); } *((unsigned long *)kp->arg) = num; if (num && !READ_ONCE(kfence_enabled) && system_state != SYSTEM_BOOTING) return disabled_by_warn ? -EINVAL : kfence_enable_late(); return 0; } static int param_get_sample_interval(char *buffer, const struct kernel_param *kp) { if (!READ_ONCE(kfence_enabled)) return sprintf(buffer, "0\n"); return param_get_ulong(buffer, kp); } static const struct kernel_param_ops sample_interval_param_ops = { .set = param_set_sample_interval, .get = param_get_sample_interval, }; module_param_cb(sample_interval, &sample_interval_param_ops, &kfence_sample_interval, 0600); /* Pool usage% threshold when currently covered allocations are skipped. */ static unsigned long kfence_skip_covered_thresh __read_mostly = 75; module_param_named(skip_covered_thresh, kfence_skip_covered_thresh, ulong, 0644); /* If true, use a deferrable timer. */ static bool kfence_deferrable __read_mostly = IS_ENABLED(CONFIG_KFENCE_DEFERRABLE); module_param_named(deferrable, kfence_deferrable, bool, 0444); /* If true, check all canary bytes on panic. */ static bool kfence_check_on_panic __read_mostly; module_param_named(check_on_panic, kfence_check_on_panic, bool, 0444); /* The pool of pages used for guard pages and objects. */ char *__kfence_pool __read_mostly; EXPORT_SYMBOL(__kfence_pool); /* Export for test modules. */ /* * Per-object metadata, with one-to-one mapping of object metadata to * backing pages (in __kfence_pool). */ static_assert(CONFIG_KFENCE_NUM_OBJECTS > 0); struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS]; /* Freelist with available objects. */ static struct list_head kfence_freelist = LIST_HEAD_INIT(kfence_freelist); static DEFINE_RAW_SPINLOCK(kfence_freelist_lock); /* Lock protecting freelist. */ /* * The static key to set up a KFENCE allocation; or if static keys are not used * to gate allocations, to avoid a load and compare if KFENCE is disabled. */ DEFINE_STATIC_KEY_FALSE(kfence_allocation_key); /* Gates the allocation, ensuring only one succeeds in a given period. */ atomic_t kfence_allocation_gate = ATOMIC_INIT(1); /* * A Counting Bloom filter of allocation coverage: limits currently covered * allocations of the same source filling up the pool. * * Assuming a range of 15%-85% unique allocations in the pool at any point in * time, the below parameters provide a probablity of 0.02-0.33 for false * positive hits respectively: * * P(alloc_traces) = (1 - e^(-HNUM * (alloc_traces / SIZE)) ^ HNUM */ #define ALLOC_COVERED_HNUM 2 #define ALLOC_COVERED_ORDER (const_ilog2(CONFIG_KFENCE_NUM_OBJECTS) + 2) #define ALLOC_COVERED_SIZE (1 << ALLOC_COVERED_ORDER) #define ALLOC_COVERED_HNEXT(h) hash_32(h, ALLOC_COVERED_ORDER) #define ALLOC_COVERED_MASK (ALLOC_COVERED_SIZE - 1) static atomic_t alloc_covered[ALLOC_COVERED_SIZE]; /* Stack depth used to determine uniqueness of an allocation. */ #define UNIQUE_ALLOC_STACK_DEPTH ((size_t)8) /* * Randomness for stack hashes, making the same collisions across reboots and * different machines less likely. */ static u32 stack_hash_seed __ro_after_init; /* Statistics counters for debugfs. */ enum kfence_counter_id { KFENCE_COUNTER_ALLOCATED, KFENCE_COUNTER_ALLOCS, KFENCE_COUNTER_FREES, KFENCE_COUNTER_ZOMBIES, KFENCE_COUNTER_BUGS, KFENCE_COUNTER_SKIP_INCOMPAT, KFENCE_COUNTER_SKIP_CAPACITY, KFENCE_COUNTER_SKIP_COVERED, KFENCE_COUNTER_COUNT, }; static atomic_long_t counters[KFENCE_COUNTER_COUNT]; static const char *const counter_names[] = { [KFENCE_COUNTER_ALLOCATED] = "currently allocated", [KFENCE_COUNTER_ALLOCS] = "total allocations", [KFENCE_COUNTER_FREES] = "total frees", [KFENCE_COUNTER_ZOMBIES] = "zombie allocations", [KFENCE_COUNTER_BUGS] = "total bugs", [KFENCE_COUNTER_SKIP_INCOMPAT] = "skipped allocations (incompatible)", [KFENCE_COUNTER_SKIP_CAPACITY] = "skipped allocations (capacity)", [KFENCE_COUNTER_SKIP_COVERED] = "skipped allocations (covered)", }; static_assert(ARRAY_SIZE(counter_names) == KFENCE_COUNTER_COUNT); /* === Internals ============================================================ */ static inline bool should_skip_covered(void) { unsigned long thresh = (CONFIG_KFENCE_NUM_OBJECTS * kfence_skip_covered_thresh) / 100; return atomic_long_read(&counters[KFENCE_COUNTER_ALLOCATED]) > thresh; } static u32 get_alloc_stack_hash(unsigned long *stack_entries, size_t num_entries) { num_entries = min(num_entries, UNIQUE_ALLOC_STACK_DEPTH); num_entries = filter_irq_stacks(stack_entries, num_entries); return jhash(stack_entries, num_entries * sizeof(stack_entries[0]), stack_hash_seed); } /* * Adds (or subtracts) count @val for allocation stack trace hash * @alloc_stack_hash from Counting Bloom filter. */ static void alloc_covered_add(u32 alloc_stack_hash, int val) { int i; for (i = 0; i < ALLOC_COVERED_HNUM; i++) { atomic_add(val, &alloc_covered[alloc_stack_hash & ALLOC_COVERED_MASK]); alloc_stack_hash = ALLOC_COVERED_HNEXT(alloc_stack_hash); } } /* * Returns true if the allocation stack trace hash @alloc_stack_hash is * currently contained (non-zero count) in Counting Bloom filter. */ static bool alloc_covered_contains(u32 alloc_stack_hash) { int i; for (i = 0; i < ALLOC_COVERED_HNUM; i++) { if (!atomic_read(&alloc_covered[alloc_stack_hash & ALLOC_COVERED_MASK])) return false; alloc_stack_hash = ALLOC_COVERED_HNEXT(alloc_stack_hash); } return true; } static bool kfence_protect(unsigned long addr) { return !KFENCE_WARN_ON(!kfence_protect_page(ALIGN_DOWN(addr, PAGE_SIZE), true)); } static bool kfence_unprotect(unsigned long addr) { return !KFENCE_WARN_ON(!kfence_protect_page(ALIGN_DOWN(addr, PAGE_SIZE), false)); } static inline unsigned long metadata_to_pageaddr(const struct kfence_metadata *meta) { unsigned long offset = (meta - kfence_metadata + 1) * PAGE_SIZE * 2; unsigned long pageaddr = (unsigned long)&__kfence_pool[offset]; /* The checks do not affect performance; only called from slow-paths. */ /* Only call with a pointer into kfence_metadata. */ if (KFENCE_WARN_ON(meta < kfence_metadata || meta >= kfence_metadata + CONFIG_KFENCE_NUM_OBJECTS)) return 0; /* * This metadata object only ever maps to 1 page; verify that the stored * address is in the expected range. */ if (KFENCE_WARN_ON(ALIGN_DOWN(meta->addr, PAGE_SIZE) != pageaddr)) return 0; return pageaddr; } /* * Update the object's metadata state, including updating the alloc/free stacks * depending on the state transition. */ static noinline void metadata_update_state(struct kfence_metadata *meta, enum kfence_object_state next, unsigned long *stack_entries, size_t num_stack_entries) { struct kfence_track *track = next == KFENCE_OBJECT_FREED ? &meta->free_track : &meta->alloc_track; lockdep_assert_held(&meta->lock); if (stack_entries) { memcpy(track->stack_entries, stack_entries, num_stack_entries * sizeof(stack_entries[0])); } else { /* * Skip over 1 (this) functions; noinline ensures we do not * accidentally skip over the caller by never inlining. */ num_stack_entries = stack_trace_save(track->stack_entries, KFENCE_STACK_DEPTH, 1); } track->num_stack_entries = num_stack_entries; track->pid = task_pid_nr(current); track->cpu = raw_smp_processor_id(); track->ts_nsec = local_clock(); /* Same source as printk timestamps. */ /* * Pairs with READ_ONCE() in * kfence_shutdown_cache(), * kfence_handle_page_fault(). */ WRITE_ONCE(meta->state, next); } /* Write canary byte to @addr. */ static inline bool set_canary_byte(u8 *addr) { *addr = KFENCE_CANARY_PATTERN(addr); return true; } /* Check canary byte at @addr. */ static inline bool check_canary_byte(u8 *addr) { struct kfence_metadata *meta; unsigned long flags; if (likely(*addr == KFENCE_CANARY_PATTERN(addr))) return true; atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]); meta = addr_to_metadata((unsigned long)addr); raw_spin_lock_irqsave(&meta->lock, flags); kfence_report_error((unsigned long)addr, false, NULL, meta, KFENCE_ERROR_CORRUPTION); raw_spin_unlock_irqrestore(&meta->lock, flags); return false; } /* __always_inline this to ensure we won't do an indirect call to fn. */ static __always_inline void for_each_canary(const struct kfence_metadata *meta, bool (*fn)(u8 *)) { const unsigned long pageaddr = ALIGN_DOWN(meta->addr, PAGE_SIZE); unsigned long addr; /* * We'll iterate over each canary byte per-side until fn() returns * false. However, we'll still iterate over the canary bytes to the * right of the object even if there was an error in the canary bytes to * the left of the object. Specifically, if check_canary_byte() * generates an error, showing both sides might give more clues as to * what the error is about when displaying which bytes were corrupted. */ /* Apply to left of object. */ for (addr = pageaddr; addr < meta->addr; addr++) { if (!fn((u8 *)addr)) break; } /* Apply to right of object. */ for (addr = meta->addr + meta->size; addr < pageaddr + PAGE_SIZE; addr++) { if (!fn((u8 *)addr)) break; } } static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t gfp, unsigned long *stack_entries, size_t num_stack_entries, u32 alloc_stack_hash) { struct kfence_metadata *meta = NULL; unsigned long flags; struct slab *slab; void *addr; const bool random_right_allocate = prandom_u32_max(2); const bool random_fault = CONFIG_KFENCE_STRESS_TEST_FAULTS && !prandom_u32_max(CONFIG_KFENCE_STRESS_TEST_FAULTS); /* Try to obtain a free object. */ raw_spin_lock_irqsave(&kfence_freelist_lock, flags); if (!list_empty(&kfence_freelist)) { meta = list_entry(kfence_freelist.next, struct kfence_metadata, list); list_del_init(&meta->list); } raw_spin_unlock_irqrestore(&kfence_freelist_lock, flags); if (!meta) { atomic_long_inc(&counters[KFENCE_COUNTER_SKIP_CAPACITY]); return NULL; } if (unlikely(!raw_spin_trylock_irqsave(&meta->lock, flags))) { /* * This is extremely unlikely -- we are reporting on a * use-after-free, which locked meta->lock, and the reporting * code via printk calls kmalloc() which ends up in * kfence_alloc() and tries to grab the same object that we're * reporting on. While it has never been observed, lockdep does * report that there is a possibility of deadlock. Fix it by * using trylock and bailing out gracefully. */ raw_spin_lock_irqsave(&kfence_freelist_lock, flags); /* Put the object back on the freelist. */ list_add_tail(&meta->list, &kfence_freelist); raw_spin_unlock_irqrestore(&kfence_freelist_lock, flags); return NULL; } meta->addr = metadata_to_pageaddr(meta); /* Unprotect if we're reusing this page. */ if (meta->state == KFENCE_OBJECT_FREED) kfence_unprotect(meta->addr); /* * Note: for allocations made before RNG initialization, will always * return zero. We still benefit from enabling KFENCE as early as * possible, even when the RNG is not yet available, as this will allow * KFENCE to detect bugs due to earlier allocations. The only downside * is that the out-of-bounds accesses detected are deterministic for * such allocations. */ if (random_right_allocate) { /* Allocate on the "right" side, re-calculate address. */ meta->addr += PAGE_SIZE - size; meta->addr = ALIGN_DOWN(meta->addr, cache->align); } addr = (void *)meta->addr; /* Update remaining metadata. */ metadata_update_state(meta, KFENCE_OBJECT_ALLOCATED, stack_entries, num_stack_entries); /* Pairs with READ_ONCE() in kfence_shutdown_cache(). */ WRITE_ONCE(meta->cache, cache); meta->size = size; meta->alloc_stack_hash = alloc_stack_hash; raw_spin_unlock_irqrestore(&meta->lock, flags); alloc_covered_add(alloc_stack_hash, 1); /* Set required slab fields. */ slab = virt_to_slab((void *)meta->addr); slab->slab_cache = cache; #if defined(CONFIG_SLUB) slab->objects = 1; #elif defined(CONFIG_SLAB) slab->s_mem = addr; #endif /* Memory initialization. */ for_each_canary(meta, set_canary_byte); /* * We check slab_want_init_on_alloc() ourselves, rather than letting * SL*B do the initialization, as otherwise we might overwrite KFENCE's * redzone. */ if (unlikely(slab_want_init_on_alloc(gfp, cache))) memzero_explicit(addr, size); if (cache->ctor) cache->ctor(addr); if (random_fault) kfence_protect(meta->addr); /* Random "faults" by protecting the object. */ atomic_long_inc(&counters[KFENCE_COUNTER_ALLOCATED]); atomic_long_inc(&counters[KFENCE_COUNTER_ALLOCS]); return addr; } static void kfence_guarded_free(void *addr, struct kfence_metadata *meta, bool zombie) { struct kcsan_scoped_access assert_page_exclusive; unsigned long flags; bool init; raw_spin_lock_irqsave(&meta->lock, flags); if (meta->state != KFENCE_OBJECT_ALLOCATED || meta->addr != (unsigned long)addr) { /* Invalid or double-free, bail out. */ atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]); kfence_report_error((unsigned long)addr, false, NULL, meta, KFENCE_ERROR_INVALID_FREE); raw_spin_unlock_irqrestore(&meta->lock, flags); return; } /* Detect racy use-after-free, or incorrect reallocation of this page by KFENCE. */ kcsan_begin_scoped_access((void *)ALIGN_DOWN((unsigned long)addr, PAGE_SIZE), PAGE_SIZE, KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ASSERT, &assert_page_exclusive); if (CONFIG_KFENCE_STRESS_TEST_FAULTS) kfence_unprotect((unsigned long)addr); /* To check canary bytes. */ /* Restore page protection if there was an OOB access. */ if (meta->unprotected_page) { memzero_explicit((void *)ALIGN_DOWN(meta->unprotected_page, PAGE_SIZE), PAGE_SIZE); kfence_protect(meta->unprotected_page); meta->unprotected_page = 0; } /* Mark the object as freed. */ metadata_update_state(meta, KFENCE_OBJECT_FREED, NULL, 0); init = slab_want_init_on_free(meta->cache); raw_spin_unlock_irqrestore(&meta->lock, flags); alloc_covered_add(meta->alloc_stack_hash, -1); /* Check canary bytes for memory corruption. */ for_each_canary(meta, check_canary_byte); /* * Clear memory if init-on-free is set. While we protect the page, the * data is still there, and after a use-after-free is detected, we * unprotect the page, so the data is still accessible. */ if (!zombie && unlikely(init)) memzero_explicit(addr, meta->size); /* Protect to detect use-after-frees. */ kfence_protect((unsigned long)addr); kcsan_end_scoped_access(&assert_page_exclusive); if (!zombie) { /* Add it to the tail of the freelist for reuse. */ raw_spin_lock_irqsave(&kfence_freelist_lock, flags); KFENCE_WARN_ON(!list_empty(&meta->list)); list_add_tail(&meta->list, &kfence_freelist); raw_spin_unlock_irqrestore(&kfence_freelist_lock, flags); atomic_long_dec(&counters[KFENCE_COUNTER_ALLOCATED]); atomic_long_inc(&counters[KFENCE_COUNTER_FREES]); } else { /* See kfence_shutdown_cache(). */ atomic_long_inc(&counters[KFENCE_COUNTER_ZOMBIES]); } } static void rcu_guarded_free(struct rcu_head *h) { struct kfence_metadata *meta = container_of(h, struct kfence_metadata, rcu_head); kfence_guarded_free((void *)meta->addr, meta, false); } /* * Initialization of the KFENCE pool after its allocation. * Returns 0 on success; otherwise returns the address up to * which partial initialization succeeded. */ static unsigned long kfence_init_pool(void) { unsigned long addr = (unsigned long)__kfence_pool; struct page *pages; int i; if (!arch_kfence_init_pool()) return addr; pages = virt_to_page(__kfence_pool); /* * Set up object pages: they must have PG_slab set, to avoid freeing * these as real pages. * * We also want to avoid inserting kfence_free() in the kfree() * fast-path in SLUB, and therefore need to ensure kfree() correctly * enters __slab_free() slow-path. */ for (i = 0; i < KFENCE_POOL_SIZE / PAGE_SIZE; i++) { struct slab *slab = page_slab(nth_page(pages, i)); if (!i || (i % 2)) continue; __folio_set_slab(slab_folio(slab)); #ifdef CONFIG_MEMCG slab->memcg_data = (unsigned long)&kfence_metadata[i / 2 - 1].objcg | MEMCG_DATA_OBJCGS; #endif } /* * Protect the first 2 pages. The first page is mostly unnecessary, and * merely serves as an extended guard page. However, adding one * additional page in the beginning gives us an even number of pages, * which simplifies the mapping of address to metadata index. */ for (i = 0; i < 2; i++) { if (unlikely(!kfence_protect(addr))) return addr; addr += PAGE_SIZE; } for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { struct kfence_metadata *meta = &kfence_metadata[i]; /* Initialize metadata. */ INIT_LIST_HEAD(&meta->list); raw_spin_lock_init(&meta->lock); meta->state = KFENCE_OBJECT_UNUSED; meta->addr = addr; /* Initialize for validation in metadata_to_pageaddr(). */ list_add_tail(&meta->list, &kfence_freelist); /* Protect the right redzone. */ if (unlikely(!kfence_protect(addr + PAGE_SIZE))) goto reset_slab; addr += 2 * PAGE_SIZE; } return 0; reset_slab: for (i = 0; i < KFENCE_POOL_SIZE / PAGE_SIZE; i++) { struct slab *slab = page_slab(nth_page(pages, i)); if (!i || (i % 2)) continue; #ifdef CONFIG_MEMCG slab->memcg_data = 0; #endif __folio_clear_slab(slab_folio(slab)); } return addr; } static bool __init kfence_init_pool_early(void) { unsigned long addr; if (!__kfence_pool) return false; addr = kfence_init_pool(); if (!addr) { /* * The pool is live and will never be deallocated from this point on. * Ignore the pool object from the kmemleak phys object tree, as it would * otherwise overlap with allocations returned by kfence_alloc(), which * are registered with kmemleak through the slab post-alloc hook. */ kmemleak_ignore_phys(__pa(__kfence_pool)); return true; } /* * Only release unprotected pages, and do not try to go back and change * page attributes due to risk of failing to do so as well. If changing * page attributes for some pages fails, it is very likely that it also * fails for the first page, and therefore expect addr==__kfence_pool in * most failure cases. */ memblock_free_late(__pa(addr), KFENCE_POOL_SIZE - (addr - (unsigned long)__kfence_pool)); __kfence_pool = NULL; return false; } static bool kfence_init_pool_late(void) { unsigned long addr, free_size; addr = kfence_init_pool(); if (!addr) return true; /* Same as above. */ free_size = KFENCE_POOL_SIZE - (addr - (unsigned long)__kfence_pool); #ifdef CONFIG_CONTIG_ALLOC free_contig_range(page_to_pfn(virt_to_page((void *)addr)), free_size / PAGE_SIZE); #else free_pages_exact((void *)addr, free_size); #endif __kfence_pool = NULL; return false; } /* === DebugFS Interface ==================================================== */ static int stats_show(struct seq_file *seq, void *v) { int i; seq_printf(seq, "enabled: %i\n", READ_ONCE(kfence_enabled)); for (i = 0; i < KFENCE_COUNTER_COUNT; i++) seq_printf(seq, "%s: %ld\n", counter_names[i], atomic_long_read(&counters[i])); return 0; } DEFINE_SHOW_ATTRIBUTE(stats); /* * debugfs seq_file operations for /sys/kernel/debug/kfence/objects. * start_object() and next_object() return the object index + 1, because NULL is used * to stop iteration. */ static void *start_object(struct seq_file *seq, loff_t *pos) { if (*pos < CONFIG_KFENCE_NUM_OBJECTS) return (void *)((long)*pos + 1); return NULL; } static void stop_object(struct seq_file *seq, void *v) { } static void *next_object(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; if (*pos < CONFIG_KFENCE_NUM_OBJECTS) return (void *)((long)*pos + 1); return NULL; } static int show_object(struct seq_file *seq, void *v) { struct kfence_metadata *meta = &kfence_metadata[(long)v - 1]; unsigned long flags; raw_spin_lock_irqsave(&meta->lock, flags); kfence_print_object(seq, meta); raw_spin_unlock_irqrestore(&meta->lock, flags); seq_puts(seq, "---------------------------------\n"); return 0; } static const struct seq_operations objects_sops = { .start = start_object, .next = next_object, .stop = stop_object, .show = show_object, }; DEFINE_SEQ_ATTRIBUTE(objects); static int kfence_debugfs_init(void) { struct dentry *kfence_dir; if (!READ_ONCE(kfence_enabled)) return 0; kfence_dir = debugfs_create_dir("kfence", NULL); debugfs_create_file("stats", 0444, kfence_dir, NULL, &stats_fops); debugfs_create_file("objects", 0400, kfence_dir, NULL, &objects_fops); return 0; } late_initcall(kfence_debugfs_init); /* === Panic Notifier ====================================================== */ static void kfence_check_all_canary(void) { int i; for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { struct kfence_metadata *meta = &kfence_metadata[i]; if (meta->state == KFENCE_OBJECT_ALLOCATED) for_each_canary(meta, check_canary_byte); } } static int kfence_check_canary_callback(struct notifier_block *nb, unsigned long reason, void *arg) { kfence_check_all_canary(); return NOTIFY_OK; } static struct notifier_block kfence_check_canary_notifier = { .notifier_call = kfence_check_canary_callback, }; /* === Allocation Gate Timer ================================================ */ static struct delayed_work kfence_timer; #ifdef CONFIG_KFENCE_STATIC_KEYS /* Wait queue to wake up allocation-gate timer task. */ static DECLARE_WAIT_QUEUE_HEAD(allocation_wait); static void wake_up_kfence_timer(struct irq_work *work) { wake_up(&allocation_wait); } static DEFINE_IRQ_WORK(wake_up_kfence_timer_work, wake_up_kfence_timer); #endif /* * Set up delayed work, which will enable and disable the static key. We need to * use a work queue (rather than a simple timer), since enabling and disabling a * static key cannot be done from an interrupt. * * Note: Toggling a static branch currently causes IPIs, and here we'll end up * with a total of 2 IPIs to all CPUs. If this ends up a problem in future (with * more aggressive sampling intervals), we could get away with a variant that * avoids IPIs, at the cost of not immediately capturing allocations if the * instructions remain cached. */ static void toggle_allocation_gate(struct work_struct *work) { if (!READ_ONCE(kfence_enabled)) return; atomic_set(&kfence_allocation_gate, 0); #ifdef CONFIG_KFENCE_STATIC_KEYS /* Enable static key, and await allocation to happen. */ static_branch_enable(&kfence_allocation_key); if (sysctl_hung_task_timeout_secs) { /* * During low activity with no allocations we might wait a * while; let's avoid the hung task warning. */ wait_event_idle_timeout(allocation_wait, atomic_read(&kfence_allocation_gate), sysctl_hung_task_timeout_secs * HZ / 2); } else { wait_event_idle(allocation_wait, atomic_read(&kfence_allocation_gate)); } /* Disable static key and reset timer. */ static_branch_disable(&kfence_allocation_key); #endif queue_delayed_work(system_unbound_wq, &kfence_timer, msecs_to_jiffies(kfence_sample_interval)); } /* === Public interface ===================================================== */ void __init kfence_alloc_pool(void) { if (!kfence_sample_interval) return; /* if the pool has already been initialized by arch, skip the below. */ if (__kfence_pool) return; __kfence_pool = memblock_alloc(KFENCE_POOL_SIZE, PAGE_SIZE); if (!__kfence_pool) pr_err("failed to allocate pool\n"); } static void kfence_init_enable(void) { if (!IS_ENABLED(CONFIG_KFENCE_STATIC_KEYS)) static_branch_enable(&kfence_allocation_key); if (kfence_deferrable) INIT_DEFERRABLE_WORK(&kfence_timer, toggle_allocation_gate); else INIT_DELAYED_WORK(&kfence_timer, toggle_allocation_gate); if (kfence_check_on_panic) atomic_notifier_chain_register(&panic_notifier_list, &kfence_check_canary_notifier); WRITE_ONCE(kfence_enabled, true); queue_delayed_work(system_unbound_wq, &kfence_timer, 0); pr_info("initialized - using %lu bytes for %d objects at 0x%p-0x%p\n", KFENCE_POOL_SIZE, CONFIG_KFENCE_NUM_OBJECTS, (void *)__kfence_pool, (void *)(__kfence_pool + KFENCE_POOL_SIZE)); } void __init kfence_init(void) { stack_hash_seed = get_random_u32(); /* Setting kfence_sample_interval to 0 on boot disables KFENCE. */ if (!kfence_sample_interval) return; if (!kfence_init_pool_early()) { pr_err("%s failed\n", __func__); return; } kfence_init_enable(); } static int kfence_init_late(void) { const unsigned long nr_pages = KFENCE_POOL_SIZE / PAGE_SIZE; #ifdef CONFIG_CONTIG_ALLOC struct page *pages; pages = alloc_contig_pages(nr_pages, GFP_KERNEL, first_online_node, NULL); if (!pages) return -ENOMEM; __kfence_pool = page_to_virt(pages); #else if (nr_pages > MAX_ORDER_NR_PAGES) { pr_warn("KFENCE_NUM_OBJECTS too large for buddy allocator\n"); return -EINVAL; } __kfence_pool = alloc_pages_exact(KFENCE_POOL_SIZE, GFP_KERNEL); if (!__kfence_pool) return -ENOMEM; #endif if (!kfence_init_pool_late()) { pr_err("%s failed\n", __func__); return -EBUSY; } kfence_init_enable(); kfence_debugfs_init(); return 0; } static int kfence_enable_late(void) { if (!__kfence_pool) return kfence_init_late(); WRITE_ONCE(kfence_enabled, true); queue_delayed_work(system_unbound_wq, &kfence_timer, 0); pr_info("re-enabled\n"); return 0; } void kfence_shutdown_cache(struct kmem_cache *s) { unsigned long flags; struct kfence_metadata *meta; int i; for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { bool in_use; meta = &kfence_metadata[i]; /* * If we observe some inconsistent cache and state pair where we * should have returned false here, cache destruction is racing * with either kmem_cache_alloc() or kmem_cache_free(). Taking * the lock will not help, as different critical section * serialization will have the same outcome. */ if (READ_ONCE(meta->cache) != s || READ_ONCE(meta->state) != KFENCE_OBJECT_ALLOCATED) continue; raw_spin_lock_irqsave(&meta->lock, flags); in_use = meta->cache == s && meta->state == KFENCE_OBJECT_ALLOCATED; raw_spin_unlock_irqrestore(&meta->lock, flags); if (in_use) { /* * This cache still has allocations, and we should not * release them back into the freelist so they can still * safely be used and retain the kernel's default * behaviour of keeping the allocations alive (leak the * cache); however, they effectively become "zombie * allocations" as the KFENCE objects are the only ones * still in use and the owning cache is being destroyed. * * We mark them freed, so that any subsequent use shows * more useful error messages that will include stack * traces of the user of the object, the original * allocation, and caller to shutdown_cache(). */ kfence_guarded_free((void *)meta->addr, meta, /*zombie=*/true); } } for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { meta = &kfence_metadata[i]; /* See above. */ if (READ_ONCE(meta->cache) != s || READ_ONCE(meta->state) != KFENCE_OBJECT_FREED) continue; raw_spin_lock_irqsave(&meta->lock, flags); if (meta->cache == s && meta->state == KFENCE_OBJECT_FREED) meta->cache = NULL; raw_spin_unlock_irqrestore(&meta->lock, flags); } } void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) { unsigned long stack_entries[KFENCE_STACK_DEPTH]; size_t num_stack_entries; u32 alloc_stack_hash; /* * Perform size check before switching kfence_allocation_gate, so that * we don't disable KFENCE without making an allocation. */ if (size > PAGE_SIZE) { atomic_long_inc(&counters[KFENCE_COUNTER_SKIP_INCOMPAT]); return NULL; } /* * Skip allocations from non-default zones, including DMA. We cannot * guarantee that pages in the KFENCE pool will have the requested * properties (e.g. reside in DMAable memory). */ if ((flags & GFP_ZONEMASK) || (s->flags & (SLAB_CACHE_DMA | SLAB_CACHE_DMA32))) { atomic_long_inc(&counters[KFENCE_COUNTER_SKIP_INCOMPAT]); return NULL; } /* * Skip allocations for this slab, if KFENCE has been disabled for * this slab. */ if (s->flags & SLAB_SKIP_KFENCE) return NULL; if (atomic_inc_return(&kfence_allocation_gate) > 1) return NULL; #ifdef CONFIG_KFENCE_STATIC_KEYS /* * waitqueue_active() is fully ordered after the update of * kfence_allocation_gate per atomic_inc_return(). */ if (waitqueue_active(&allocation_wait)) { /* * Calling wake_up() here may deadlock when allocations happen * from within timer code. Use an irq_work to defer it. */ irq_work_queue(&wake_up_kfence_timer_work); } #endif if (!READ_ONCE(kfence_enabled)) return NULL; num_stack_entries = stack_trace_save(stack_entries, KFENCE_STACK_DEPTH, 0); /* * Do expensive check for coverage of allocation in slow-path after * allocation_gate has already become non-zero, even though it might * mean not making any allocation within a given sample interval. * * This ensures reasonable allocation coverage when the pool is almost * full, including avoiding long-lived allocations of the same source * filling up the pool (e.g. pagecache allocations). */ alloc_stack_hash = get_alloc_stack_hash(stack_entries, num_stack_entries); if (should_skip_covered() && alloc_covered_contains(alloc_stack_hash)) { atomic_long_inc(&counters[KFENCE_COUNTER_SKIP_COVERED]); return NULL; } return kfence_guarded_alloc(s, size, flags, stack_entries, num_stack_entries, alloc_stack_hash); } size_t kfence_ksize(const void *addr) { const struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr); /* * Read locklessly -- if there is a race with __kfence_alloc(), this is * either a use-after-free or invalid access. */ return meta ? meta->size : 0; } void *kfence_object_start(const void *addr) { const struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr); /* * Read locklessly -- if there is a race with __kfence_alloc(), this is * either a use-after-free or invalid access. */ return meta ? (void *)meta->addr : NULL; } void __kfence_free(void *addr) { struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr); #ifdef CONFIG_MEMCG KFENCE_WARN_ON(meta->objcg); #endif /* * If the objects of the cache are SLAB_TYPESAFE_BY_RCU, defer freeing * the object, as the object page may be recycled for other-typed * objects once it has been freed. meta->cache may be NULL if the cache * was destroyed. */ if (unlikely(meta->cache && (meta->cache->flags & SLAB_TYPESAFE_BY_RCU))) call_rcu(&meta->rcu_head, rcu_guarded_free); else kfence_guarded_free(addr, meta, false); } bool kfence_handle_page_fault(unsigned long addr, bool is_write, struct pt_regs *regs) { const int page_index = (addr - (unsigned long)__kfence_pool) / PAGE_SIZE; struct kfence_metadata *to_report = NULL; enum kfence_error_type error_type; unsigned long flags; if (!is_kfence_address((void *)addr)) return false; if (!READ_ONCE(kfence_enabled)) /* If disabled at runtime ... */ return kfence_unprotect(addr); /* ... unprotect and proceed. */ atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]); if (page_index % 2) { /* This is a redzone, report a buffer overflow. */ struct kfence_metadata *meta; int distance = 0; meta = addr_to_metadata(addr - PAGE_SIZE); if (meta && READ_ONCE(meta->state) == KFENCE_OBJECT_ALLOCATED) { to_report = meta; /* Data race ok; distance calculation approximate. */ distance = addr - data_race(meta->addr + meta->size); } meta = addr_to_metadata(addr + PAGE_SIZE); if (meta && READ_ONCE(meta->state) == KFENCE_OBJECT_ALLOCATED) { /* Data race ok; distance calculation approximate. */ if (!to_report || distance > data_race(meta->addr) - addr) to_report = meta; } if (!to_report) goto out; raw_spin_lock_irqsave(&to_report->lock, flags); to_report->unprotected_page = addr; error_type = KFENCE_ERROR_OOB; /* * If the object was freed before we took the look we can still * report this as an OOB -- the report will simply show the * stacktrace of the free as well. */ } else { to_report = addr_to_metadata(addr); if (!to_report) goto out; raw_spin_lock_irqsave(&to_report->lock, flags); error_type = KFENCE_ERROR_UAF; /* * We may race with __kfence_alloc(), and it is possible that a * freed object may be reallocated. We simply report this as a * use-after-free, with the stack trace showing the place where * the object was re-allocated. */ } out: if (to_report) { kfence_report_error(addr, is_write, regs, to_report, error_type); raw_spin_unlock_irqrestore(&to_report->lock, flags); } else { /* This may be a UAF or OOB access, but we can't be sure. */ kfence_report_error(addr, is_write, regs, NULL, KFENCE_ERROR_INVALID); } return kfence_unprotect(addr); /* Unprotect and let access proceed. */ } |
| 804 803 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/seccomp.c * * Copyright 2004-2005 Andrea Arcangeli <andrea@cpushare.com> * * Copyright (C) 2012 Google, Inc. * Will Drewry <wad@chromium.org> * * This defines a simple but solid secure-computing facility. * * Mode 1 uses a fixed list of allowed system calls. * Mode 2 allows user-defined system call filters in the form * of Berkeley Packet Filters/Linux Socket Filters. */ #define pr_fmt(fmt) "seccomp: " fmt #include <linux/refcount.h> #include <linux/audit.h> #include <linux/compat.h> #include <linux/coredump.h> #include <linux/kmemleak.h> #include <linux/nospec.h> #include <linux/prctl.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> #include <linux/seccomp.h> #include <linux/slab.h> #include <linux/syscalls.h> #include <linux/sysctl.h> /* Not exposed in headers: strictly internal use only. */ #define SECCOMP_MODE_DEAD (SECCOMP_MODE_FILTER + 1) #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER #include <asm/syscall.h> #endif #ifdef CONFIG_SECCOMP_FILTER #include <linux/file.h> #include <linux/filter.h> #include <linux/pid.h> #include <linux/ptrace.h> #include <linux/capability.h> #include <linux/uaccess.h> #include <linux/anon_inodes.h> #include <linux/lockdep.h> /* * When SECCOMP_IOCTL_NOTIF_ID_VALID was first introduced, it had the * wrong direction flag in the ioctl number. This is the broken one, * which the kernel needs to keep supporting until all userspaces stop * using the wrong command number. */ #define SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR SECCOMP_IOR(2, __u64) enum notify_state { SECCOMP_NOTIFY_INIT, SECCOMP_NOTIFY_SENT, SECCOMP_NOTIFY_REPLIED, }; struct seccomp_knotif { /* The struct pid of the task whose filter triggered the notification */ struct task_struct *task; /* The "cookie" for this request; this is unique for this filter. */ u64 id; /* * The seccomp data. This pointer is valid the entire time this * notification is active, since it comes from __seccomp_filter which * eclipses the entire lifecycle here. */ const struct seccomp_data *data; /* * Notification states. When SECCOMP_RET_USER_NOTIF is returned, a * struct seccomp_knotif is created and starts out in INIT. Once the * handler reads the notification off of an FD, it transitions to SENT. * If a signal is received the state transitions back to INIT and * another message is sent. When the userspace handler replies, state * transitions to REPLIED. */ enum notify_state state; /* The return values, only valid when in SECCOMP_NOTIFY_REPLIED */ int error; long val; u32 flags; /* * Signals when this has changed states, such as the listener * dying, a new seccomp addfd message, or changing to REPLIED */ struct completion ready; struct list_head list; /* outstanding addfd requests */ struct list_head addfd; }; /** * struct seccomp_kaddfd - container for seccomp_addfd ioctl messages * * @file: A reference to the file to install in the other task * @fd: The fd number to install it at. If the fd number is -1, it means the * installing process should allocate the fd as normal. * @flags: The flags for the new file descriptor. At the moment, only O_CLOEXEC * is allowed. * @ioctl_flags: The flags used for the seccomp_addfd ioctl. * @ret: The return value of the installing process. It is set to the fd num * upon success (>= 0). * @completion: Indicates that the installing process has completed fd * installation, or gone away (either due to successful * reply, or signal) * */ struct seccomp_kaddfd { struct file *file; int fd; unsigned int flags; __u32 ioctl_flags; union { bool setfd; /* To only be set on reply */ int ret; }; struct completion completion; struct list_head list; }; /** * struct notification - container for seccomp userspace notifications. Since * most seccomp filters will not have notification listeners attached and this * structure is fairly large, we store the notification-specific stuff in a * separate structure. * * @request: A semaphore that users of this notification can wait on for * changes. Actual reads and writes are still controlled with * filter->notify_lock. * @next_id: The id of the next request. * @notifications: A list of struct seccomp_knotif elements. */ struct notification { struct semaphore request; u64 next_id; struct list_head notifications; }; #ifdef SECCOMP_ARCH_NATIVE /** * struct action_cache - per-filter cache of seccomp actions per * arch/syscall pair * * @allow_native: A bitmap where each bit represents whether the * filter will always allow the syscall, for the * native architecture. * @allow_compat: A bitmap where each bit represents whether the * filter will always allow the syscall, for the * compat architecture. */ struct action_cache { DECLARE_BITMAP(allow_native, SECCOMP_ARCH_NATIVE_NR); #ifdef SECCOMP_ARCH_COMPAT DECLARE_BITMAP(allow_compat, SECCOMP_ARCH_COMPAT_NR); #endif }; #else struct action_cache { }; static inline bool seccomp_cache_check_allow(const struct seccomp_filter *sfilter, const struct seccomp_data *sd) { return false; } static inline void seccomp_cache_prepare(struct seccomp_filter *sfilter) { } #endif /* SECCOMP_ARCH_NATIVE */ /** * struct seccomp_filter - container for seccomp BPF programs * * @refs: Reference count to manage the object lifetime. * A filter's reference count is incremented for each directly * attached task, once for the dependent filter, and if * requested for the user notifier. When @refs reaches zero, * the filter can be freed. * @users: A filter's @users count is incremented for each directly * attached task (filter installation, fork(), thread_sync), * and once for the dependent filter (tracked in filter->prev). * When it reaches zero it indicates that no direct or indirect * users of that filter exist. No new tasks can get associated with * this filter after reaching 0. The @users count is always smaller * or equal to @refs. Hence, reaching 0 for @users does not mean * the filter can be freed. * @cache: cache of arch/syscall mappings to actions * @log: true if all actions except for SECCOMP_RET_ALLOW should be logged * @wait_killable_recv: Put notifying process in killable state once the * notification is received by the userspace listener. * @prev: points to a previously installed, or inherited, filter * @prog: the BPF program to evaluate * @notif: the struct that holds all notification related information * @notify_lock: A lock for all notification-related accesses. * @wqh: A wait queue for poll if a notifier is in use. * * seccomp_filter objects are organized in a tree linked via the @prev * pointer. For any task, it appears to be a singly-linked list starting * with current->seccomp.filter, the most recently attached or inherited filter. * However, multiple filters may share a @prev node, by way of fork(), which * results in a unidirectional tree existing in memory. This is similar to * how namespaces work. * * seccomp_filter objects should never be modified after being attached * to a task_struct (other than @refs). */ struct seccomp_filter { refcount_t refs; refcount_t users; bool log; bool wait_killable_recv; struct action_cache cache; struct seccomp_filter *prev; struct bpf_prog *prog; struct notification *notif; struct mutex notify_lock; wait_queue_head_t wqh; }; /* Limit any path through the tree to 256KB worth of instructions. */ #define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter)) /* * Endianness is explicitly ignored and left for BPF program authors to manage * as per the specific architecture. */ static void populate_seccomp_data(struct seccomp_data *sd) { /* * Instead of using current_pt_reg(), we're already doing the work * to safely fetch "current", so just use "task" everywhere below. */ struct task_struct *task = current; struct pt_regs *regs = task_pt_regs(task); unsigned long args[6]; sd->nr = syscall_get_nr(task, regs); sd->arch = syscall_get_arch(task); syscall_get_arguments(task, regs, args); sd->args[0] = args[0]; sd->args[1] = args[1]; sd->args[2] = args[2]; sd->args[3] = args[3]; sd->args[4] = args[4]; sd->args[5] = args[5]; sd->instruction_pointer = KSTK_EIP(task); } /** * seccomp_check_filter - verify seccomp filter code * @filter: filter to verify * @flen: length of filter * * Takes a previously checked filter (by bpf_check_classic) and * redirects all filter code that loads struct sk_buff data * and related data through seccomp_bpf_load. It also * enforces length and alignment checking of those loads. * * Returns 0 if the rule set is legal or -EINVAL if not. */ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) { int pc; for (pc = 0; pc < flen; pc++) { struct sock_filter *ftest = &filter[pc]; u16 code = ftest->code; u32 k = ftest->k; switch (code) { case BPF_LD | BPF_W | BPF_ABS: ftest->code = BPF_LDX | BPF_W | BPF_ABS; /* 32-bit aligned and not out of bounds. */ if (k >= sizeof(struct seccomp_data) || k & 3) return -EINVAL; continue; case BPF_LD | BPF_W | BPF_LEN: ftest->code = BPF_LD | BPF_IMM; ftest->k = sizeof(struct seccomp_data); continue; case BPF_LDX | BPF_W | BPF_LEN: ftest->code = BPF_LDX | BPF_IMM; ftest->k = sizeof(struct seccomp_data); continue; /* Explicitly include allowed calls. */ case BPF_RET | BPF_K: case BPF_RET | BPF_A: case BPF_ALU | BPF_ADD | BPF_K: case BPF_ALU | BPF_ADD | BPF_X: case BPF_ALU | BPF_SUB | BPF_K: case BPF_ALU | BPF_SUB | BPF_X: case BPF_ALU | BPF_MUL | BPF_K: case BPF_ALU | BPF_MUL | BPF_X: case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU | BPF_DIV | BPF_X: case BPF_ALU | BPF_AND | BPF_K: case BPF_ALU | BPF_AND | BPF_X: case BPF_ALU | BPF_OR | BPF_K: case BPF_ALU | BPF_OR | BPF_X: case BPF_ALU | BPF_XOR | BPF_K: case BPF_ALU | BPF_XOR | BPF_X: case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU | BPF_LSH | BPF_X: case BPF_ALU | BPF_RSH | BPF_K: case BPF_ALU | BPF_RSH | BPF_X: case BPF_ALU | BPF_NEG: case BPF_LD | BPF_IMM: case BPF_LDX | BPF_IMM: case BPF_MISC | BPF_TAX: case BPF_MISC | BPF_TXA: case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: case BPF_ST: case BPF_STX: case BPF_JMP | BPF_JA: case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: continue; default: return -EINVAL; } } return 0; } #ifdef SECCOMP_ARCH_NATIVE static inline bool seccomp_cache_check_allow_bitmap(const void *bitmap, size_t bitmap_size, int syscall_nr) { if (unlikely(syscall_nr < 0 || syscall_nr >= bitmap_size)) return false; syscall_nr = array_index_nospec(syscall_nr, bitmap_size); return test_bit(syscall_nr, bitmap); } /** * seccomp_cache_check_allow - lookup seccomp cache * @sfilter: The seccomp filter * @sd: The seccomp data to lookup the cache with * * Returns true if the seccomp_data is cached and allowed. */ static inline bool seccomp_cache_check_allow(const struct seccomp_filter *sfilter, const struct seccomp_data *sd) { int syscall_nr = sd->nr; const struct action_cache *cache = &sfilter->cache; #ifndef SECCOMP_ARCH_COMPAT /* A native-only architecture doesn't need to check sd->arch. */ return seccomp_cache_check_allow_bitmap(cache->allow_native, SECCOMP_ARCH_NATIVE_NR, syscall_nr); #else if (likely(sd->arch == SECCOMP_ARCH_NATIVE)) return seccomp_cache_check_allow_bitmap(cache->allow_native, SECCOMP_ARCH_NATIVE_NR, syscall_nr); if (likely(sd->arch == SECCOMP_ARCH_COMPAT)) return seccomp_cache_check_allow_bitmap(cache->allow_compat, SECCOMP_ARCH_COMPAT_NR, syscall_nr); #endif /* SECCOMP_ARCH_COMPAT */ WARN_ON_ONCE(true); return false; } #endif /* SECCOMP_ARCH_NATIVE */ /** * seccomp_run_filters - evaluates all seccomp filters against @sd * @sd: optional seccomp data to be passed to filters * @match: stores struct seccomp_filter that resulted in the return value, * unless filter returned SECCOMP_RET_ALLOW, in which case it will * be unchanged. * * Returns valid seccomp BPF response codes. */ #define ACTION_ONLY(ret) ((s32)((ret) & (SECCOMP_RET_ACTION_FULL))) static u32 seccomp_run_filters(const struct seccomp_data *sd, struct seccomp_filter **match) { u32 ret = SECCOMP_RET_ALLOW; /* Make sure cross-thread synced filter points somewhere sane. */ struct seccomp_filter *f = READ_ONCE(current->seccomp.filter); /* Ensure unexpected behavior doesn't result in failing open. */ if (WARN_ON(f == NULL)) return SECCOMP_RET_KILL_PROCESS; if (seccomp_cache_check_allow(f, sd)) return SECCOMP_RET_ALLOW; /* * All filters in the list are evaluated and the lowest BPF return * value always takes priority (ignoring the DATA). */ for (; f; f = f->prev) { u32 cur_ret = bpf_prog_run_pin_on_cpu(f->prog, sd); if (ACTION_ONLY(cur_ret) < ACTION_ONLY(ret)) { ret = cur_ret; *match = f; } } return ret; } #endif /* CONFIG_SECCOMP_FILTER */ static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode) { assert_spin_locked(¤t->sighand->siglock); if (current->seccomp.mode && current->seccomp.mode != seccomp_mode) return false; return true; } void __weak arch_seccomp_spec_mitigate(struct task_struct *task) { } static inline void seccomp_assign_mode(struct task_struct *task, unsigned long seccomp_mode, unsigned long flags) { assert_spin_locked(&task->sighand->siglock); task->seccomp.mode = seccomp_mode; /* * Make sure SYSCALL_WORK_SECCOMP cannot be set before the mode (and * filter) is set. */ smp_mb__before_atomic(); /* Assume default seccomp processes want spec flaw mitigation. */ if ((flags & SECCOMP_FILTER_FLAG_SPEC_ALLOW) == 0) arch_seccomp_spec_mitigate(task); set_task_syscall_work(task, SECCOMP); } #ifdef CONFIG_SECCOMP_FILTER /* Returns 1 if the parent is an ancestor of the child. */ static int is_ancestor(struct seccomp_filter *parent, struct seccomp_filter *child) { /* NULL is the root ancestor. */ if (parent == NULL) return 1; for (; child; child = child->prev) if (child == parent) return 1; return 0; } /** * seccomp_can_sync_threads: checks if all threads can be synchronized * * Expects sighand and cred_guard_mutex locks to be held. * * Returns 0 on success, -ve on error, or the pid of a thread which was * either not in the correct seccomp mode or did not have an ancestral * seccomp filter. */ static inline pid_t seccomp_can_sync_threads(void) { struct task_struct *thread, *caller; BUG_ON(!mutex_is_locked(¤t->signal->cred_guard_mutex)); assert_spin_locked(¤t->sighand->siglock); /* Validate all threads being eligible for synchronization. */ caller = current; for_each_thread(caller, thread) { pid_t failed; /* Skip current, since it is initiating the sync. */ if (thread == caller) continue; if (thread->seccomp.mode == SECCOMP_MODE_DISABLED || (thread->seccomp.mode == SECCOMP_MODE_FILTER && is_ancestor(thread->seccomp.filter, caller->seccomp.filter))) continue; /* Return the first thread that cannot be synchronized. */ failed = task_pid_vnr(thread); /* If the pid cannot be resolved, then return -ESRCH */ if (WARN_ON(failed == 0)) failed = -ESRCH; return failed; } return 0; } static inline void seccomp_filter_free(struct seccomp_filter *filter) { if (filter) { bpf_prog_destroy(filter->prog); kfree(filter); } } static void __seccomp_filter_orphan(struct seccomp_filter *orig) { while (orig && refcount_dec_and_test(&orig->users)) { if (waitqueue_active(&orig->wqh)) wake_up_poll(&orig->wqh, EPOLLHUP); orig = orig->prev; } } static void __put_seccomp_filter(struct seccomp_filter *orig) { /* Clean up single-reference branches iteratively. */ while (orig && refcount_dec_and_test(&orig->refs)) { struct seccomp_filter *freeme = orig; orig = orig->prev; seccomp_filter_free(freeme); } } static void __seccomp_filter_release(struct seccomp_filter *orig) { /* Notify about any unused filters in the task's former filter tree. */ __seccomp_filter_orphan(orig); /* Finally drop all references to the task's former tree. */ __put_seccomp_filter(orig); } /** * seccomp_filter_release - Detach the task from its filter tree, * drop its reference count, and notify * about unused filters * * This function should only be called when the task is exiting as * it detaches it from its filter tree. As such, READ_ONCE() and * barriers are not needed here, as would normally be needed. */ void seccomp_filter_release(struct task_struct *tsk) { struct seccomp_filter *orig = tsk->seccomp.filter; /* We are effectively holding the siglock by not having any sighand. */ WARN_ON(tsk->sighand != NULL); /* Detach task from its filter tree. */ tsk->seccomp.filter = NULL; __seccomp_filter_release(orig); } /** * seccomp_sync_threads: sets all threads to use current's filter * * Expects sighand and cred_guard_mutex locks to be held, and for * seccomp_can_sync_threads() to have returned success already * without dropping the locks. * */ static inline void seccomp_sync_threads(unsigned long flags) { struct task_struct *thread, *caller; BUG_ON(!mutex_is_locked(¤t->signal->cred_guard_mutex)); assert_spin_locked(¤t->sighand->siglock); /* Synchronize all threads. */ caller = current; for_each_thread(caller, thread) { /* Skip current, since it needs no changes. */ if (thread == caller) continue; /* Get a task reference for the new leaf node. */ get_seccomp_filter(caller); /* * Drop the task reference to the shared ancestor since * current's path will hold a reference. (This also * allows a put before the assignment.) */ __seccomp_filter_release(thread->seccomp.filter); /* Make our new filter tree visible. */ smp_store_release(&thread->seccomp.filter, caller->seccomp.filter); atomic_set(&thread->seccomp.filter_count, atomic_read(&caller->seccomp.filter_count)); /* * Don't let an unprivileged task work around * the no_new_privs restriction by creating * a thread that sets it up, enters seccomp, * then dies. */ if (task_no_new_privs(caller)) task_set_no_new_privs(thread); /* * Opt the other thread into seccomp if needed. * As threads are considered to be trust-realm * equivalent (see ptrace_may_access), it is safe to * allow one thread to transition the other. */ if (thread->seccomp.mode == SECCOMP_MODE_DISABLED) seccomp_assign_mode(thread, SECCOMP_MODE_FILTER, flags); } } /** * seccomp_prepare_filter: Prepares a seccomp filter for use. * @fprog: BPF program to install * * Returns filter on success or an ERR_PTR on failure. */ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog) { struct seccomp_filter *sfilter; int ret; const bool save_orig = #if defined(CONFIG_CHECKPOINT_RESTORE) || defined(SECCOMP_ARCH_NATIVE) true; #else false; #endif if (fprog->len == 0 || fprog->len > BPF_MAXINSNS) return ERR_PTR(-EINVAL); BUG_ON(INT_MAX / fprog->len < sizeof(struct sock_filter)); /* * Installing a seccomp filter requires that the task has * CAP_SYS_ADMIN in its namespace or be running with no_new_privs. * This avoids scenarios where unprivileged tasks can affect the * behavior of privileged children. */ if (!task_no_new_privs(current) && !ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN)) return ERR_PTR(-EACCES); /* Allocate a new seccomp_filter */ sfilter = kzalloc(sizeof(*sfilter), GFP_KERNEL | __GFP_NOWARN); if (!sfilter) return ERR_PTR(-ENOMEM); mutex_init(&sfilter->notify_lock); ret = bpf_prog_create_from_user(&sfilter->prog, fprog, seccomp_check_filter, save_orig); if (ret < 0) { kfree(sfilter); return ERR_PTR(ret); } refcount_set(&sfilter->refs, 1); refcount_set(&sfilter->users, 1); init_waitqueue_head(&sfilter->wqh); return sfilter; } /** * seccomp_prepare_user_filter - prepares a user-supplied sock_fprog * @user_filter: pointer to the user data containing a sock_fprog. * * Returns 0 on success and non-zero otherwise. */ static struct seccomp_filter * seccomp_prepare_user_filter(const char __user *user_filter) { struct sock_fprog fprog; struct seccomp_filter *filter = ERR_PTR(-EFAULT); #ifdef CONFIG_COMPAT if (in_compat_syscall()) { struct compat_sock_fprog fprog32; if (copy_from_user(&fprog32, user_filter, sizeof(fprog32))) goto out; fprog.len = fprog32.len; fprog.filter = compat_ptr(fprog32.filter); } else /* falls through to the if below. */ #endif if (copy_from_user(&fprog, user_filter, sizeof(fprog))) goto out; filter = seccomp_prepare_filter(&fprog); out: return filter; } #ifdef SECCOMP_ARCH_NATIVE /** * seccomp_is_const_allow - check if filter is constant allow with given data * @fprog: The BPF programs * @sd: The seccomp data to check against, only syscall number and arch * number are considered constant. */ static bool seccomp_is_const_allow(struct sock_fprog_kern *fprog, struct seccomp_data *sd) { unsigned int reg_value = 0; unsigned int pc; bool op_res; if (WARN_ON_ONCE(!fprog)) return false; for (pc = 0; pc < fprog->len; pc++) { struct sock_filter *insn = &fprog->filter[pc]; u16 code = insn->code; u32 k = insn->k; switch (code) { case BPF_LD | BPF_W | BPF_ABS: switch (k) { case offsetof(struct seccomp_data, nr): reg_value = sd->nr; break; case offsetof(struct seccomp_data, arch): reg_value = sd->arch; break; default: /* can't optimize (non-constant value load) */ return false; } break; case BPF_RET | BPF_K: /* reached return with constant values only, check allow */ return k == SECCOMP_RET_ALLOW; case BPF_JMP | BPF_JA: pc += insn->k; break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JSET | BPF_K: switch (BPF_OP(code)) { case BPF_JEQ: op_res = reg_value == k; break; case BPF_JGE: op_res = reg_value >= k; break; case BPF_JGT: op_res = reg_value > k; break; case BPF_JSET: op_res = !!(reg_value & k); break; default: /* can't optimize (unknown jump) */ return false; } pc += op_res ? insn->jt : insn->jf; break; case BPF_ALU | BPF_AND | BPF_K: reg_value &= k; break; default: /* can't optimize (unknown insn) */ return false; } } /* ran off the end of the filter?! */ WARN_ON(1); return false; } static void seccomp_cache_prepare_bitmap(struct seccomp_filter *sfilter, void *bitmap, const void *bitmap_prev, size_t bitmap_size, int arch) { struct sock_fprog_kern *fprog = sfilter->prog->orig_prog; struct seccomp_data sd; int nr; if (bitmap_prev) { /* The new filter must be as restrictive as the last. */ bitmap_copy(bitmap, bitmap_prev, bitmap_size); } else { /* Before any filters, all syscalls are always allowed. */ bitmap_fill(bitmap, bitmap_size); } for (nr = 0; nr < bitmap_size; nr++) { /* No bitmap change: not a cacheable action. */ if (!test_bit(nr, bitmap)) continue; sd.nr = nr; sd.arch = arch; /* No bitmap change: continue to always allow. */ if (seccomp_is_const_allow(fprog, &sd)) continue; /* * Not a cacheable action: always run filters. * atomic clear_bit() not needed, filter not visible yet. */ __clear_bit(nr, bitmap); } } /** * seccomp_cache_prepare - emulate the filter to find cacheable syscalls * @sfilter: The seccomp filter * * Returns 0 if successful or -errno if error occurred. */ static void seccomp_cache_prepare(struct seccomp_filter *sfilter) { struct action_cache *cache = &sfilter->cache; const struct action_cache *cache_prev = sfilter->prev ? &sfilter->prev->cache : NULL; seccomp_cache_prepare_bitmap(sfilter, cache->allow_native, cache_prev ? cache_prev->allow_native : NULL, SECCOMP_ARCH_NATIVE_NR, SECCOMP_ARCH_NATIVE); #ifdef SECCOMP_ARCH_COMPAT seccomp_cache_prepare_bitmap(sfilter, cache->allow_compat, cache_prev ? cache_prev->allow_compat : NULL, SECCOMP_ARCH_COMPAT_NR, SECCOMP_ARCH_COMPAT); #endif /* SECCOMP_ARCH_COMPAT */ } #endif /* SECCOMP_ARCH_NATIVE */ /** * seccomp_attach_filter: validate and attach filter * @flags: flags to change filter behavior * @filter: seccomp filter to add to the current process * * Caller must be holding current->sighand->siglock lock. * * Returns 0 on success, -ve on error, or * - in TSYNC mode: the pid of a thread which was either not in the correct * seccomp mode or did not have an ancestral seccomp filter * - in NEW_LISTENER mode: the fd of the new listener */ static long seccomp_attach_filter(unsigned int flags, struct seccomp_filter *filter) { unsigned long total_insns; struct seccomp_filter *walker; assert_spin_locked(¤t->sighand->siglock); /* Validate resulting filter length. */ total_insns = filter->prog->len; for (walker = current->seccomp.filter; walker; walker = walker->prev) total_insns += walker->prog->len + 4; /* 4 instr penalty */ if (total_insns > MAX_INSNS_PER_PATH) return -ENOMEM; /* If thread sync has been requested, check that it is possible. */ if (flags & SECCOMP_FILTER_FLAG_TSYNC) { int ret; ret = seccomp_can_sync_threads(); if (ret) { if (flags & SECCOMP_FILTER_FLAG_TSYNC_ESRCH) return -ESRCH; else return ret; } } /* Set log flag, if present. */ if (flags & SECCOMP_FILTER_FLAG_LOG) filter->log = true; /* Set wait killable flag, if present. */ if (flags & SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV) filter->wait_killable_recv = true; /* * If there is an existing filter, make it the prev and don't drop its * task reference. */ filter->prev = current->seccomp.filter; seccomp_cache_prepare(filter); current->seccomp.filter = filter; atomic_inc(¤t->seccomp.filter_count); /* Now that the new filter is in place, synchronize to all threads. */ if (flags & SECCOMP_FILTER_FLAG_TSYNC) seccomp_sync_threads(flags); return 0; } static void __get_seccomp_filter(struct seccomp_filter *filter) { refcount_inc(&filter->refs); } /* get_seccomp_filter - increments the reference count of the filter on @tsk */ void get_seccomp_filter(struct task_struct *tsk) { struct seccomp_filter *orig = tsk->seccomp.filter; if (!orig) return; __get_seccomp_filter(orig); refcount_inc(&orig->users); } #endif /* CONFIG_SECCOMP_FILTER */ /* For use with seccomp_actions_logged */ #define SECCOMP_LOG_KILL_PROCESS (1 << 0) #define SECCOMP_LOG_KILL_THREAD (1 << 1) #define SECCOMP_LOG_TRAP (1 << 2) #define SECCOMP_LOG_ERRNO (1 << 3) #define SECCOMP_LOG_TRACE (1 << 4) #define SECCOMP_LOG_LOG (1 << 5) #define SECCOMP_LOG_ALLOW (1 << 6) #define SECCOMP_LOG_USER_NOTIF (1 << 7) static u32 seccomp_actions_logged = SECCOMP_LOG_KILL_PROCESS | SECCOMP_LOG_KILL_THREAD | SECCOMP_LOG_TRAP | SECCOMP_LOG_ERRNO | SECCOMP_LOG_USER_NOTIF | SECCOMP_LOG_TRACE | SECCOMP_LOG_LOG; static inline void seccomp_log(unsigned long syscall, long signr, u32 action, bool requested) { bool log = false; switch (action) { case SECCOMP_RET_ALLOW: break; case SECCOMP_RET_TRAP: log = requested && seccomp_actions_logged & SECCOMP_LOG_TRAP; break; case SECCOMP_RET_ERRNO: log = requested && seccomp_actions_logged & SECCOMP_LOG_ERRNO; break; case SECCOMP_RET_TRACE: log = requested && seccomp_actions_logged & SECCOMP_LOG_TRACE; break; case SECCOMP_RET_USER_NOTIF: log = requested && seccomp_actions_logged & SECCOMP_LOG_USER_NOTIF; break; case SECCOMP_RET_LOG: log = seccomp_actions_logged & SECCOMP_LOG_LOG; break; case SECCOMP_RET_KILL_THREAD: log = seccomp_actions_logged & SECCOMP_LOG_KILL_THREAD; break; case SECCOMP_RET_KILL_PROCESS: default: log = seccomp_actions_logged & SECCOMP_LOG_KILL_PROCESS; } /* * Emit an audit message when the action is RET_KILL_*, RET_LOG, or the * FILTER_FLAG_LOG bit was set. The admin has the ability to silence * any action from being logged by removing the action name from the * seccomp_actions_logged sysctl. */ if (!log) return; audit_seccomp(syscall, signr, action); } /* * Secure computing mode 1 allows only read/write/exit/sigreturn. * To be fully secure this must be combined with rlimit * to limit the stack allocations too. */ static const int mode1_syscalls[] = { __NR_seccomp_read, __NR_seccomp_write, __NR_seccomp_exit, __NR_seccomp_sigreturn, -1, /* negative terminated */ }; static void __secure_computing_strict(int this_syscall) { const int *allowed_syscalls = mode1_syscalls; #ifdef CONFIG_COMPAT if (in_compat_syscall()) allowed_syscalls = get_compat_mode1_syscalls(); #endif do { if (*allowed_syscalls == this_syscall) return; } while (*++allowed_syscalls != -1); #ifdef SECCOMP_DEBUG dump_stack(); #endif current->seccomp.mode = SECCOMP_MODE_DEAD; seccomp_log(this_syscall, SIGKILL, SECCOMP_RET_KILL_THREAD, true); do_exit(SIGKILL); } #ifndef CONFIG_HAVE_ARCH_SECCOMP_FILTER void secure_computing_strict(int this_syscall) { int mode = current->seccomp.mode; if (IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) && unlikely(current->ptrace & PT_SUSPEND_SECCOMP)) return; if (mode == SECCOMP_MODE_DISABLED) return; else if (mode == SECCOMP_MODE_STRICT) __secure_computing_strict(this_syscall); else BUG(); } #else #ifdef CONFIG_SECCOMP_FILTER static u64 seccomp_next_notify_id(struct seccomp_filter *filter) { /* * Note: overflow is ok here, the id just needs to be unique per * filter. */ lockdep_assert_held(&filter->notify_lock); return filter->notif->next_id++; } static void seccomp_handle_addfd(struct seccomp_kaddfd *addfd, struct seccomp_knotif *n) { int fd; /* * Remove the notification, and reset the list pointers, indicating * that it has been handled. */ list_del_init(&addfd->list); if (!addfd->setfd) fd = receive_fd(addfd->file, addfd->flags); else fd = receive_fd_replace(addfd->fd, addfd->file, addfd->flags); addfd->ret = fd; if (addfd->ioctl_flags & SECCOMP_ADDFD_FLAG_SEND) { /* If we fail reset and return an error to the notifier */ if (fd < 0) { n->state = SECCOMP_NOTIFY_SENT; } else { /* Return the FD we just added */ n->flags = 0; n->error = 0; n->val = fd; } } /* * Mark the notification as completed. From this point, addfd mem * might be invalidated and we can't safely read it anymore. */ complete(&addfd->completion); } static bool should_sleep_killable(struct seccomp_filter *match, struct seccomp_knotif *n) { return match->wait_killable_recv && n->state == SECCOMP_NOTIFY_SENT; } static int seccomp_do_user_notification(int this_syscall, struct seccomp_filter *match, const struct seccomp_data *sd) { int err; u32 flags = 0; long ret = 0; struct seccomp_knotif n = {}; struct seccomp_kaddfd *addfd, *tmp; mutex_lock(&match->notify_lock); err = -ENOSYS; if (!match->notif) goto out; n.task = current; n.state = SECCOMP_NOTIFY_INIT; n.data = sd; n.id = seccomp_next_notify_id(match); init_completion(&n.ready); list_add_tail(&n.list, &match->notif->notifications); INIT_LIST_HEAD(&n.addfd); up(&match->notif->request); wake_up_poll(&match->wqh, EPOLLIN | EPOLLRDNORM); /* * This is where we wait for a reply from userspace. */ do { bool wait_killable = should_sleep_killable(match, &n); mutex_unlock(&match->notify_lock); if (wait_killable) err = wait_for_completion_killable(&n.ready); else err = wait_for_completion_interruptible(&n.ready); mutex_lock(&match->notify_lock); if (err != 0) { /* * Check to see if the notifcation got picked up and * whether we should switch to wait killable. */ if (!wait_killable && should_sleep_killable(match, &n)) continue; goto interrupted; } addfd = list_first_entry_or_null(&n.addfd, struct seccomp_kaddfd, list); /* Check if we were woken up by a addfd message */ if (addfd) seccomp_handle_addfd(addfd, &n); } while (n.state != SECCOMP_NOTIFY_REPLIED); ret = n.val; err = n.error; flags = n.flags; interrupted: /* If there were any pending addfd calls, clear them out */ list_for_each_entry_safe(addfd, tmp, &n.addfd, list) { /* The process went away before we got a chance to handle it */ addfd->ret = -ESRCH; list_del_init(&addfd->list); complete(&addfd->completion); } /* * Note that it's possible the listener died in between the time when * we were notified of a response (or a signal) and when we were able to * re-acquire the lock, so only delete from the list if the * notification actually exists. * * Also note that this test is only valid because there's no way to * *reattach* to a notifier right now. If one is added, we'll need to * keep track of the notif itself and make sure they match here. */ if (match->notif) list_del(&n.list); out: mutex_unlock(&match->notify_lock); /* Userspace requests to continue the syscall. */ if (flags & SECCOMP_USER_NOTIF_FLAG_CONTINUE) return 0; syscall_set_return_value(current, current_pt_regs(), err, ret); return -1; } static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, const bool recheck_after_trace) { u32 filter_ret, action; struct seccomp_filter *match = NULL; int data; struct seccomp_data sd_local; /* * Make sure that any changes to mode from another thread have * been seen after SYSCALL_WORK_SECCOMP was seen. */ smp_rmb(); if (!sd) { populate_seccomp_data(&sd_local); sd = &sd_local; } filter_ret = seccomp_run_filters(sd, &match); data = filter_ret & SECCOMP_RET_DATA; action = filter_ret & SECCOMP_RET_ACTION_FULL; switch (action) { case SECCOMP_RET_ERRNO: /* Set low-order bits as an errno, capped at MAX_ERRNO. */ if (data > MAX_ERRNO) data = MAX_ERRNO; syscall_set_return_value(current, current_pt_regs(), -data, 0); goto skip; case SECCOMP_RET_TRAP: /* Show the handler the original registers. */ syscall_rollback(current, current_pt_regs()); /* Let the filter pass back 16 bits of data. */ force_sig_seccomp(this_syscall, data, false); goto skip; case SECCOMP_RET_TRACE: /* We've been put in this state by the ptracer already. */ if (recheck_after_trace) return 0; /* ENOSYS these calls if there is no tracer attached. */ if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) { syscall_set_return_value(current, current_pt_regs(), -ENOSYS, 0); goto skip; } /* Allow the BPF to provide the event message */ ptrace_event(PTRACE_EVENT_SECCOMP, data); /* * The delivery of a fatal signal during event * notification may silently skip tracer notification, * which could leave us with a potentially unmodified * syscall that the tracer would have liked to have * changed. Since the process is about to die, we just * force the syscall to be skipped and let the signal * kill the process and correctly handle any tracer exit * notifications. */ if (fatal_signal_pending(current)) goto skip; /* Check if the tracer forced the syscall to be skipped. */ this_syscall = syscall_get_nr(current, current_pt_regs()); if (this_syscall < 0) goto skip; /* * Recheck the syscall, since it may have changed. This * intentionally uses a NULL struct seccomp_data to force * a reload of all registers. This does not goto skip since * a skip would have already been reported. */ if (__seccomp_filter(this_syscall, NULL, true)) return -1; return 0; case SECCOMP_RET_USER_NOTIF: if (seccomp_do_user_notification(this_syscall, match, sd)) goto skip; return 0; case SECCOMP_RET_LOG: seccomp_log(this_syscall, 0, action, true); return 0; case SECCOMP_RET_ALLOW: /* * Note that the "match" filter will always be NULL for * this action since SECCOMP_RET_ALLOW is the starting * state in seccomp_run_filters(). */ return 0; case SECCOMP_RET_KILL_THREAD: case SECCOMP_RET_KILL_PROCESS: default: current->seccomp.mode = SECCOMP_MODE_DEAD; seccomp_log(this_syscall, SIGSYS, action, true); /* Dump core only if this is the last remaining thread. */ if (action != SECCOMP_RET_KILL_THREAD || (atomic_read(¤t->signal->live) == 1)) { /* Show the original registers in the dump. */ syscall_rollback(current, current_pt_regs()); /* Trigger a coredump with SIGSYS */ force_sig_seccomp(this_syscall, data, true); } else { do_exit(SIGSYS); } return -1; /* skip the syscall go directly to signal handling */ } unreachable(); skip: seccomp_log(this_syscall, 0, action, match ? match->log : false); return -1; } #else static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, const bool recheck_after_trace) { BUG(); return -1; } #endif int __secure_computing(const struct seccomp_data *sd) { int mode = current->seccomp.mode; int this_syscall; if (IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) && unlikely(current->ptrace & PT_SUSPEND_SECCOMP)) return 0; this_syscall = sd ? sd->nr : syscall_get_nr(current, current_pt_regs()); switch (mode) { case SECCOMP_MODE_STRICT: __secure_computing_strict(this_syscall); /* may call do_exit */ return 0; case SECCOMP_MODE_FILTER: return __seccomp_filter(this_syscall, sd, false); /* Surviving SECCOMP_RET_KILL_* must be proactively impossible. */ case SECCOMP_MODE_DEAD: WARN_ON_ONCE(1); do_exit(SIGKILL); return -1; default: BUG(); } } #endif /* CONFIG_HAVE_ARCH_SECCOMP_FILTER */ long prctl_get_seccomp(void) { return current->seccomp.mode; } /** * seccomp_set_mode_strict: internal function for setting strict seccomp * * Once current->seccomp.mode is non-zero, it may not be changed. * * Returns 0 on success or -EINVAL on failure. */ static long seccomp_set_mode_strict(void) { const unsigned long seccomp_mode = SECCOMP_MODE_STRICT; long ret = -EINVAL; spin_lock_irq(¤t->sighand->siglock); if (!seccomp_may_assign_mode(seccomp_mode)) goto out; #ifdef TIF_NOTSC disable_TSC(); #endif seccomp_assign_mode(current, seccomp_mode, 0); ret = 0; out: spin_unlock_irq(¤t->sighand->siglock); return ret; } #ifdef CONFIG_SECCOMP_FILTER static void seccomp_notify_free(struct seccomp_filter *filter) { kfree(filter->notif); filter->notif = NULL; } static void seccomp_notify_detach(struct seccomp_filter *filter) { struct seccomp_knotif *knotif; if (!filter) return; mutex_lock(&filter->notify_lock); /* * If this file is being closed because e.g. the task who owned it * died, let's wake everyone up who was waiting on us. */ list_for_each_entry(knotif, &filter->notif->notifications, list) { if (knotif->state == SECCOMP_NOTIFY_REPLIED) continue; knotif->state = SECCOMP_NOTIFY_REPLIED; knotif->error = -ENOSYS; knotif->val = 0; /* * We do not need to wake up any pending addfd messages, as * the notifier will do that for us, as this just looks * like a standard reply. */ complete(&knotif->ready); } seccomp_notify_free(filter); mutex_unlock(&filter->notify_lock); } static int seccomp_notify_release(struct inode *inode, struct file *file) { struct seccomp_filter *filter = file->private_data; seccomp_notify_detach(filter); __put_seccomp_filter(filter); return 0; } /* must be called with notif_lock held */ static inline struct seccomp_knotif * find_notification(struct seccomp_filter *filter, u64 id) { struct seccomp_knotif *cur; lockdep_assert_held(&filter->notify_lock); list_for_each_entry(cur, &filter->notif->notifications, list) { if (cur->id == id) return cur; } return NULL; } static long seccomp_notify_recv(struct seccomp_filter *filter, void __user *buf) { struct seccomp_knotif *knotif = NULL, *cur; struct seccomp_notif unotif; ssize_t ret; /* Verify that we're not given garbage to keep struct extensible. */ ret = check_zeroed_user(buf, sizeof(unotif)); if (ret < 0) return ret; if (!ret) return -EINVAL; memset(&unotif, 0, sizeof(unotif)); ret = down_interruptible(&filter->notif->request); if (ret < 0) return ret; mutex_lock(&filter->notify_lock); list_for_each_entry(cur, &filter->notif->notifications, list) { if (cur->state == SECCOMP_NOTIFY_INIT) { knotif = cur; break; } } /* * If we didn't find a notification, it could be that the task was * interrupted by a fatal signal between the time we were woken and * when we were able to acquire the rw lock. */ if (!knotif) { ret = -ENOENT; goto out; } unotif.id = knotif->id; unotif.pid = task_pid_vnr(knotif->task); unotif.data = *(knotif->data); knotif->state = SECCOMP_NOTIFY_SENT; wake_up_poll(&filter->wqh, EPOLLOUT | EPOLLWRNORM); ret = 0; out: mutex_unlock(&filter->notify_lock); if (ret == 0 && copy_to_user(buf, &unotif, sizeof(unotif))) { ret = -EFAULT; /* * Userspace screwed up. To make sure that we keep this * notification alive, let's reset it back to INIT. It * may have died when we released the lock, so we need to make * sure it's still around. */ mutex_lock(&filter->notify_lock); knotif = find_notification(filter, unotif.id); if (knotif) { /* Reset the process to make sure it's not stuck */ if (should_sleep_killable(filter, knotif)) complete(&knotif->ready); knotif->state = SECCOMP_NOTIFY_INIT; up(&filter->notif->request); } mutex_unlock(&filter->notify_lock); } return ret; } static long seccomp_notify_send(struct seccomp_filter *filter, void __user *buf) { struct seccomp_notif_resp resp = {}; struct seccomp_knotif *knotif; long ret; if (copy_from_user(&resp, buf, sizeof(resp))) return -EFAULT; if (resp.flags & ~SECCOMP_USER_NOTIF_FLAG_CONTINUE) return -EINVAL; if ((resp.flags & SECCOMP_USER_NOTIF_FLAG_CONTINUE) && (resp.error || resp.val)) return -EINVAL; ret = mutex_lock_interruptible(&filter->notify_lock); if (ret < 0) return ret; knotif = find_notification(filter, resp.id); if (!knotif) { ret = -ENOENT; goto out; } /* Allow exactly one reply. */ if (knotif->state != SECCOMP_NOTIFY_SENT) { ret = -EINPROGRESS; goto out; } ret = 0; knotif->state = SECCOMP_NOTIFY_REPLIED; knotif->error = resp.error; knotif->val = resp.val; knotif->flags = resp.flags; complete(&knotif->ready); out: mutex_unlock(&filter->notify_lock); return ret; } static long seccomp_notify_id_valid(struct seccomp_filter *filter, void __user *buf) { struct seccomp_knotif *knotif; u64 id; long ret; if (copy_from_user(&id, buf, sizeof(id))) return -EFAULT; ret = mutex_lock_interruptible(&filter->notify_lock); if (ret < 0) return ret; knotif = find_notification(filter, id); if (knotif && knotif->state == SECCOMP_NOTIFY_SENT) ret = 0; else ret = -ENOENT; mutex_unlock(&filter->notify_lock); return ret; } static long seccomp_notify_addfd(struct seccomp_filter *filter, struct seccomp_notif_addfd __user *uaddfd, unsigned int size) { struct seccomp_notif_addfd addfd; struct seccomp_knotif *knotif; struct seccomp_kaddfd kaddfd; int ret; BUILD_BUG_ON(sizeof(addfd) < SECCOMP_NOTIFY_ADDFD_SIZE_VER0); BUILD_BUG_ON(sizeof(addfd) != SECCOMP_NOTIFY_ADDFD_SIZE_LATEST); if (size < SECCOMP_NOTIFY_ADDFD_SIZE_VER0 || size >= PAGE_SIZE) return -EINVAL; ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size); if (ret) return ret; if (addfd.newfd_flags & ~O_CLOEXEC) return -EINVAL; if (addfd.flags & ~(SECCOMP_ADDFD_FLAG_SETFD | SECCOMP_ADDFD_FLAG_SEND)) return -EINVAL; if (addfd.newfd && !(addfd.flags & SECCOMP_ADDFD_FLAG_SETFD)) return -EINVAL; kaddfd.file = fget(addfd.srcfd); if (!kaddfd.file) return -EBADF; kaddfd.ioctl_flags = addfd.flags; kaddfd.flags = addfd.newfd_flags; kaddfd.setfd = addfd.flags & SECCOMP_ADDFD_FLAG_SETFD; kaddfd.fd = addfd.newfd; init_completion(&kaddfd.completion); ret = mutex_lock_interruptible(&filter->notify_lock); if (ret < 0) goto out; knotif = find_notification(filter, addfd.id); if (!knotif) { ret = -ENOENT; goto out_unlock; } /* * We do not want to allow for FD injection to occur before the * notification has been picked up by a userspace handler, or after * the notification has been replied to. */ if (knotif->state != SECCOMP_NOTIFY_SENT) { ret = -EINPROGRESS; goto out_unlock; } if (addfd.flags & SECCOMP_ADDFD_FLAG_SEND) { /* * Disallow queuing an atomic addfd + send reply while there are * some addfd requests still to process. * * There is no clear reason to support it and allows us to keep * the loop on the other side straight-forward. */ if (!list_empty(&knotif->addfd)) { ret = -EBUSY; goto out_unlock; } /* Allow exactly only one reply */ knotif->state = SECCOMP_NOTIFY_REPLIED; } list_add(&kaddfd.list, &knotif->addfd); complete(&knotif->ready); mutex_unlock(&filter->notify_lock); /* Now we wait for it to be processed or be interrupted */ ret = wait_for_completion_interruptible(&kaddfd.completion); if (ret == 0) { /* * We had a successful completion. The other side has already * removed us from the addfd queue, and * wait_for_completion_interruptible has a memory barrier upon * success that lets us read this value directly without * locking. */ ret = kaddfd.ret; goto out; } mutex_lock(&filter->notify_lock); /* * Even though we were woken up by a signal and not a successful * completion, a completion may have happened in the mean time. * * We need to check again if the addfd request has been handled, * and if not, we will remove it from the queue. */ if (list_empty(&kaddfd.list)) ret = kaddfd.ret; else list_del(&kaddfd.list); out_unlock: mutex_unlock(&filter->notify_lock); out: fput(kaddfd.file); return ret; } static long seccomp_notify_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct seccomp_filter *filter = file->private_data; void __user *buf = (void __user *)arg; /* Fixed-size ioctls */ switch (cmd) { case SECCOMP_IOCTL_NOTIF_RECV: return seccomp_notify_recv(filter, buf); case SECCOMP_IOCTL_NOTIF_SEND: return seccomp_notify_send(filter, buf); case SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR: case SECCOMP_IOCTL_NOTIF_ID_VALID: return seccomp_notify_id_valid(filter, buf); } /* Extensible Argument ioctls */ #define EA_IOCTL(cmd) ((cmd) & ~(IOC_INOUT | IOCSIZE_MASK)) switch (EA_IOCTL(cmd)) { case EA_IOCTL(SECCOMP_IOCTL_NOTIF_ADDFD): return seccomp_notify_addfd(filter, buf, _IOC_SIZE(cmd)); default: return -EINVAL; } } static __poll_t seccomp_notify_poll(struct file *file, struct poll_table_struct *poll_tab) { struct seccomp_filter *filter = file->private_data; __poll_t ret = 0; struct seccomp_knotif *cur; poll_wait(file, &filter->wqh, poll_tab); if (mutex_lock_interruptible(&filter->notify_lock) < 0) return EPOLLERR; list_for_each_entry(cur, &filter->notif->notifications, list) { if (cur->state == SECCOMP_NOTIFY_INIT) ret |= EPOLLIN | EPOLLRDNORM; if (cur->state == SECCOMP_NOTIFY_SENT) ret |= EPOLLOUT | EPOLLWRNORM; if ((ret & EPOLLIN) && (ret & EPOLLOUT)) break; } mutex_unlock(&filter->notify_lock); if (refcount_read(&filter->users) == 0) ret |= EPOLLHUP; return ret; } static const struct file_operations seccomp_notify_ops = { .poll = seccomp_notify_poll, .release = seccomp_notify_release, .unlocked_ioctl = seccomp_notify_ioctl, .compat_ioctl = seccomp_notify_ioctl, }; static struct file *init_listener(struct seccomp_filter *filter) { struct file *ret; ret = ERR_PTR(-ENOMEM); filter->notif = kzalloc(sizeof(*(filter->notif)), GFP_KERNEL); if (!filter->notif) goto out; sema_init(&filter->notif->request, 0); filter->notif->next_id = get_random_u64(); INIT_LIST_HEAD(&filter->notif->notifications); ret = anon_inode_getfile("seccomp notify", &seccomp_notify_ops, filter, O_RDWR); if (IS_ERR(ret)) goto out_notif; /* The file has a reference to it now */ __get_seccomp_filter(filter); out_notif: if (IS_ERR(ret)) seccomp_notify_free(filter); out: return ret; } /* * Does @new_child have a listener while an ancestor also has a listener? * If so, we'll want to reject this filter. * This only has to be tested for the current process, even in the TSYNC case, * because TSYNC installs @child with the same parent on all threads. * Note that @new_child is not hooked up to its parent at this point yet, so * we use current->seccomp.filter. */ static bool has_duplicate_listener(struct seccomp_filter *new_child) { struct seccomp_filter *cur; /* must be protected against concurrent TSYNC */ lockdep_assert_held(¤t->sighand->siglock); if (!new_child->notif) return false; for (cur = current->seccomp.filter; cur; cur = cur->prev) { if (cur->notif) return true; } return false; } /** * seccomp_set_mode_filter: internal function for setting seccomp filter * @flags: flags to change filter behavior * @filter: struct sock_fprog containing filter * * This function may be called repeatedly to install additional filters. * Every filter successfully installed will be evaluated (in reverse order) * for each system call the task makes. * * Once current->seccomp.mode is non-zero, it may not be changed. * * Returns 0 on success or -EINVAL on failure. */ static long seccomp_set_mode_filter(unsigned int flags, const char __user *filter) { const unsigned long seccomp_mode = SECCOMP_MODE_FILTER; struct seccomp_filter *prepared = NULL; long ret = -EINVAL; int listener = -1; struct file *listener_f = NULL; /* Validate flags. */ if (flags & ~SECCOMP_FILTER_FLAG_MASK) return -EINVAL; /* * In the successful case, NEW_LISTENER returns the new listener fd. * But in the failure case, TSYNC returns the thread that died. If you * combine these two flags, there's no way to tell whether something * succeeded or failed. So, let's disallow this combination if the user * has not explicitly requested no errors from TSYNC. */ if ((flags & SECCOMP_FILTER_FLAG_TSYNC) && (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) && ((flags & SECCOMP_FILTER_FLAG_TSYNC_ESRCH) == 0)) return -EINVAL; /* * The SECCOMP_FILTER_FLAG_WAIT_KILLABLE_SENT flag doesn't make sense * without the SECCOMP_FILTER_FLAG_NEW_LISTENER flag. */ if ((flags & SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV) && ((flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) == 0)) return -EINVAL; /* Prepare the new filter before holding any locks. */ prepared = seccomp_prepare_user_filter(filter); if (IS_ERR(prepared)) return PTR_ERR(prepared); if (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) { listener = get_unused_fd_flags(O_CLOEXEC); if (listener < 0) { ret = listener; goto out_free; } listener_f = init_listener(prepared); if (IS_ERR(listener_f)) { put_unused_fd(listener); ret = PTR_ERR(listener_f); goto out_free; } } /* * Make sure we cannot change seccomp or nnp state via TSYNC * while another thread is in the middle of calling exec. */ if (flags & SECCOMP_FILTER_FLAG_TSYNC && mutex_lock_killable(¤t->signal->cred_guard_mutex)) goto out_put_fd; spin_lock_irq(¤t->sighand->siglock); if (!seccomp_may_assign_mode(seccomp_mode)) goto out; if (has_duplicate_listener(prepared)) { ret = -EBUSY; goto out; } ret = seccomp_attach_filter(flags, prepared); if (ret) goto out; /* Do not free the successfully attached filter. */ prepared = NULL; seccomp_assign_mode(current, seccomp_mode, flags); out: spin_unlock_irq(¤t->sighand->siglock); if (flags & SECCOMP_FILTER_FLAG_TSYNC) mutex_unlock(¤t->signal->cred_guard_mutex); out_put_fd: if (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) { if (ret) { listener_f->private_data = NULL; fput(listener_f); put_unused_fd(listener); seccomp_notify_detach(prepared); } else { fd_install(listener, listener_f); ret = listener; } } out_free: seccomp_filter_free(prepared); return ret; } #else static inline long seccomp_set_mode_filter(unsigned int flags, const char __user *filter) { return -EINVAL; } #endif static long seccomp_get_action_avail(const char __user *uaction) { u32 action; if (copy_from_user(&action, uaction, sizeof(action))) return -EFAULT; switch (action) { case SECCOMP_RET_KILL_PROCESS: case SECCOMP_RET_KILL_THREAD: case SECCOMP_RET_TRAP: case SECCOMP_RET_ERRNO: case SECCOMP_RET_USER_NOTIF: case SECCOMP_RET_TRACE: case SECCOMP_RET_LOG: case SECCOMP_RET_ALLOW: break; default: return -EOPNOTSUPP; } return 0; } static long seccomp_get_notif_sizes(void __user *usizes) { struct seccomp_notif_sizes sizes = { .seccomp_notif = sizeof(struct seccomp_notif), .seccomp_notif_resp = sizeof(struct seccomp_notif_resp), .seccomp_data = sizeof(struct seccomp_data), }; if (copy_to_user(usizes, &sizes, sizeof(sizes))) return -EFAULT; return 0; } /* Common entry point for both prctl and syscall. */ static long do_seccomp(unsigned int op, unsigned int flags, void __user *uargs) { switch (op) { case SECCOMP_SET_MODE_STRICT: if (flags != 0 || uargs != NULL) return -EINVAL; return seccomp_set_mode_strict(); case SECCOMP_SET_MODE_FILTER: return seccomp_set_mode_filter(flags, uargs); case SECCOMP_GET_ACTION_AVAIL: if (flags != 0) return -EINVAL; return seccomp_get_action_avail(uargs); case SECCOMP_GET_NOTIF_SIZES: if (flags != 0) return -EINVAL; return seccomp_get_notif_sizes(uargs); default: return -EINVAL; } } SYSCALL_DEFINE3(seccomp, unsigned int, op, unsigned int, flags, void __user *, uargs) { return do_seccomp(op, flags, uargs); } /** * prctl_set_seccomp: configures current->seccomp.mode * @seccomp_mode: requested mode to use * @filter: optional struct sock_fprog for use with SECCOMP_MODE_FILTER * * Returns 0 on success or -EINVAL on failure. */ long prctl_set_seccomp(unsigned long seccomp_mode, void __user *filter) { unsigned int op; void __user *uargs; switch (seccomp_mode) { case SECCOMP_MODE_STRICT: op = SECCOMP_SET_MODE_STRICT; /* * Setting strict mode through prctl always ignored filter, * so make sure it is always NULL here to pass the internal * check in do_seccomp(). */ uargs = NULL; break; case SECCOMP_MODE_FILTER: op = SECCOMP_SET_MODE_FILTER; uargs = filter; break; default: return -EINVAL; } /* prctl interface doesn't have flags, so they are always zero. */ return do_seccomp(op, 0, uargs); } #if defined(CONFIG_SECCOMP_FILTER) && defined(CONFIG_CHECKPOINT_RESTORE) static struct seccomp_filter *get_nth_filter(struct task_struct *task, unsigned long filter_off) { struct seccomp_filter *orig, *filter; unsigned long count; /* * Note: this is only correct because the caller should be the (ptrace) * tracer of the task, otherwise lock_task_sighand is needed. */ spin_lock_irq(&task->sighand->siglock); if (task->seccomp.mode != SECCOMP_MODE_FILTER) { spin_unlock_irq(&task->sighand->siglock); return ERR_PTR(-EINVAL); } orig = task->seccomp.filter; __get_seccomp_filter(orig); spin_unlock_irq(&task->sighand->siglock); count = 0; for (filter = orig; filter; filter = filter->prev) count++; if (filter_off >= count) { filter = ERR_PTR(-ENOENT); goto out; } count -= filter_off; for (filter = orig; filter && count > 1; filter = filter->prev) count--; if (WARN_ON(count != 1 || !filter)) { filter = ERR_PTR(-ENOENT); goto out; } __get_seccomp_filter(filter); out: __put_seccomp_filter(orig); return filter; } long seccomp_get_filter(struct task_struct *task, unsigned long filter_off, void __user *data) { struct seccomp_filter *filter; struct sock_fprog_kern *fprog; long ret; if (!capable(CAP_SYS_ADMIN) || current->seccomp.mode != SECCOMP_MODE_DISABLED) { return -EACCES; } filter = get_nth_filter(task, filter_off); if (IS_ERR(filter)) return PTR_ERR(filter); fprog = filter->prog->orig_prog; if (!fprog) { /* This must be a new non-cBPF filter, since we save * every cBPF filter's orig_prog above when * CONFIG_CHECKPOINT_RESTORE is enabled. */ ret = -EMEDIUMTYPE; goto out; } ret = fprog->len; if (!data) goto out; if (copy_to_user(data, fprog->filter, bpf_classic_proglen(fprog))) ret = -EFAULT; out: __put_seccomp_filter(filter); return ret; } long seccomp_get_metadata(struct task_struct *task, unsigned long size, void __user *data) { long ret; struct seccomp_filter *filter; struct seccomp_metadata kmd = {}; if (!capable(CAP_SYS_ADMIN) || current->seccomp.mode != SECCOMP_MODE_DISABLED) { return -EACCES; } size = min_t(unsigned long, size, sizeof(kmd)); if (size < sizeof(kmd.filter_off)) return -EINVAL; if (copy_from_user(&kmd.filter_off, data, sizeof(kmd.filter_off))) return -EFAULT; filter = get_nth_filter(task, kmd.filter_off); if (IS_ERR(filter)) return PTR_ERR(filter); if (filter->log) kmd.flags |= SECCOMP_FILTER_FLAG_LOG; ret = size; if (copy_to_user(data, &kmd, size)) ret = -EFAULT; __put_seccomp_filter(filter); return ret; } #endif #ifdef CONFIG_SYSCTL /* Human readable action names for friendly sysctl interaction */ #define SECCOMP_RET_KILL_PROCESS_NAME "kill_process" #define SECCOMP_RET_KILL_THREAD_NAME "kill_thread" #define SECCOMP_RET_TRAP_NAME "trap" #define SECCOMP_RET_ERRNO_NAME "errno" #define SECCOMP_RET_USER_NOTIF_NAME "user_notif" #define SECCOMP_RET_TRACE_NAME "trace" #define SECCOMP_RET_LOG_NAME "log" #define SECCOMP_RET_ALLOW_NAME "allow" static const char seccomp_actions_avail[] = SECCOMP_RET_KILL_PROCESS_NAME " " SECCOMP_RET_KILL_THREAD_NAME " " SECCOMP_RET_TRAP_NAME " " SECCOMP_RET_ERRNO_NAME " " SECCOMP_RET_USER_NOTIF_NAME " " SECCOMP_RET_TRACE_NAME " " SECCOMP_RET_LOG_NAME " " SECCOMP_RET_ALLOW_NAME; struct seccomp_log_name { u32 log; const char *name; }; static const struct seccomp_log_name seccomp_log_names[] = { { SECCOMP_LOG_KILL_PROCESS, SECCOMP_RET_KILL_PROCESS_NAME }, { SECCOMP_LOG_KILL_THREAD, SECCOMP_RET_KILL_THREAD_NAME }, { SECCOMP_LOG_TRAP, SECCOMP_RET_TRAP_NAME }, { SECCOMP_LOG_ERRNO, SECCOMP_RET_ERRNO_NAME }, { SECCOMP_LOG_USER_NOTIF, SECCOMP_RET_USER_NOTIF_NAME }, { SECCOMP_LOG_TRACE, SECCOMP_RET_TRACE_NAME }, { SECCOMP_LOG_LOG, SECCOMP_RET_LOG_NAME }, { SECCOMP_LOG_ALLOW, SECCOMP_RET_ALLOW_NAME }, { } }; static bool seccomp_names_from_actions_logged(char *names, size_t size, u32 actions_logged, const char *sep) { const struct seccomp_log_name *cur; bool append_sep = false; for (cur = seccomp_log_names; cur->name && size; cur++) { ssize_t ret; if (!(actions_logged & cur->log)) continue; if (append_sep) { ret = strscpy(names, sep, size); if (ret < 0) return false; names += ret; size -= ret; } else append_sep = true; ret = strscpy(names, cur->name, size); if (ret < 0) return false; names += ret; size -= ret; } return true; } static bool seccomp_action_logged_from_name(u32 *action_logged, const char *name) { const struct seccomp_log_name *cur; for (cur = seccomp_log_names; cur->name; cur++) { if (!strcmp(cur->name, name)) { *action_logged = cur->log; return true; } } return false; } static bool seccomp_actions_logged_from_names(u32 *actions_logged, char *names) { char *name; *actions_logged = 0; while ((name = strsep(&names, " ")) && *name) { u32 action_logged = 0; if (!seccomp_action_logged_from_name(&action_logged, name)) return false; *actions_logged |= action_logged; } return true; } static int read_actions_logged(struct ctl_table *ro_table, void *buffer, size_t *lenp, loff_t *ppos) { char names[sizeof(seccomp_actions_avail)]; struct ctl_table table; memset(names, 0, sizeof(names)); if (!seccomp_names_from_actions_logged(names, sizeof(names), seccomp_actions_logged, " ")) return -EINVAL; table = *ro_table; table.data = names; table.maxlen = sizeof(names); return proc_dostring(&table, 0, buffer, lenp, ppos); } static int write_actions_logged(struct ctl_table *ro_table, void *buffer, size_t *lenp, loff_t *ppos, u32 *actions_logged) { char names[sizeof(seccomp_actions_avail)]; struct ctl_table table; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; memset(names, 0, sizeof(names)); table = *ro_table; table.data = names; table.maxlen = sizeof(names); ret = proc_dostring(&table, 1, buffer, lenp, ppos); if (ret) return ret; if (!seccomp_actions_logged_from_names(actions_logged, table.data)) return -EINVAL; if (*actions_logged & SECCOMP_LOG_ALLOW) return -EINVAL; seccomp_actions_logged = *actions_logged; return 0; } static void audit_actions_logged(u32 actions_logged, u32 old_actions_logged, int ret) { char names[sizeof(seccomp_actions_avail)]; char old_names[sizeof(seccomp_actions_avail)]; const char *new = names; const char *old = old_names; if (!audit_enabled) return; memset(names, 0, sizeof(names)); memset(old_names, 0, sizeof(old_names)); if (ret) new = "?"; else if (!actions_logged) new = "(none)"; else if (!seccomp_names_from_actions_logged(names, sizeof(names), actions_logged, ",")) new = "?"; if (!old_actions_logged) old = "(none)"; else if (!seccomp_names_from_actions_logged(old_names, sizeof(old_names), old_actions_logged, ",")) old = "?"; return audit_seccomp_actions_logged(new, old, !ret); } static int seccomp_actions_logged_handler(struct ctl_table *ro_table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; if (write) { u32 actions_logged = 0; u32 old_actions_logged = seccomp_actions_logged; ret = write_actions_logged(ro_table, buffer, lenp, ppos, &actions_logged); audit_actions_logged(actions_logged, old_actions_logged, ret); } else ret = read_actions_logged(ro_table, buffer, lenp, ppos); return ret; } static struct ctl_path seccomp_sysctl_path[] = { { .procname = "kernel", }, { .procname = "seccomp", }, { } }; static struct ctl_table seccomp_sysctl_table[] = { { .procname = "actions_avail", .data = (void *) &seccomp_actions_avail, .maxlen = sizeof(seccomp_actions_avail), .mode = 0444, .proc_handler = proc_dostring, }, { .procname = "actions_logged", .mode = 0644, .proc_handler = seccomp_actions_logged_handler, }, { } }; static int __init seccomp_sysctl_init(void) { struct ctl_table_header *hdr; hdr = register_sysctl_paths(seccomp_sysctl_path, seccomp_sysctl_table); if (!hdr) pr_warn("sysctl registration failed\n"); else kmemleak_not_leak(hdr); return 0; } device_initcall(seccomp_sysctl_init) #endif /* CONFIG_SYSCTL */ #ifdef CONFIG_SECCOMP_CACHE_DEBUG /* Currently CONFIG_SECCOMP_CACHE_DEBUG implies SECCOMP_ARCH_NATIVE */ static void proc_pid_seccomp_cache_arch(struct seq_file *m, const char *name, const void *bitmap, size_t bitmap_size) { int nr; for (nr = 0; nr < bitmap_size; nr++) { bool cached = test_bit(nr, bitmap); char *status = cached ? "ALLOW" : "FILTER"; seq_printf(m, "%s %d %s\n", name, nr, status); } } int proc_pid_seccomp_cache(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { struct seccomp_filter *f; unsigned long flags; /* * We don't want some sandboxed process to know what their seccomp * filters consist of. */ if (!file_ns_capable(m->file, &init_user_ns, CAP_SYS_ADMIN)) return -EACCES; if (!lock_task_sighand(task, &flags)) return -ESRCH; f = READ_ONCE(task->seccomp.filter); if (!f) { unlock_task_sighand(task, &flags); return 0; } /* prevent filter from being freed while we are printing it */ __get_seccomp_filter(f); unlock_task_sighand(task, &flags); proc_pid_seccomp_cache_arch(m, SECCOMP_ARCH_NATIVE_NAME, f->cache.allow_native, SECCOMP_ARCH_NATIVE_NR); #ifdef SECCOMP_ARCH_COMPAT proc_pid_seccomp_cache_arch(m, SECCOMP_ARCH_COMPAT_NAME, f->cache.allow_compat, SECCOMP_ARCH_COMPAT_NR); #endif /* SECCOMP_ARCH_COMPAT */ __put_seccomp_filter(f); return 0; } #endif /* CONFIG_SECCOMP_CACHE_DEBUG */ |
| 236 105 105 85 20 202 185 202 20 185 185 185 185 185 185 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 | // SPDX-License-Identifier: GPL-2.0-only /* * net/sched/sch_mq.c Classful multiqueue dummy scheduler * * Copyright (c) 2009 Patrick McHardy <kaber@trash.net> */ #include <linux/types.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <net/netlink.h> #include <net/pkt_cls.h> #include <net/pkt_sched.h> #include <net/sch_generic.h> struct mq_sched { struct Qdisc **qdiscs; }; static int mq_offload(struct Qdisc *sch, enum tc_mq_command cmd) { struct net_device *dev = qdisc_dev(sch); struct tc_mq_qopt_offload opt = { .command = cmd, .handle = sch->handle, }; if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return -EOPNOTSUPP; return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQ, &opt); } static int mq_offload_stats(struct Qdisc *sch) { struct tc_mq_qopt_offload opt = { .command = TC_MQ_STATS, .handle = sch->handle, .stats = { .bstats = &sch->bstats, .qstats = &sch->qstats, }, }; return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_MQ, &opt); } static void mq_destroy(struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); struct mq_sched *priv = qdisc_priv(sch); unsigned int ntx; mq_offload(sch, TC_MQ_DESTROY); if (!priv->qdiscs) return; for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++) qdisc_put(priv->qdiscs[ntx]); kfree(priv->qdiscs); } static int mq_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct net_device *dev = qdisc_dev(sch); struct mq_sched *priv = qdisc_priv(sch); struct netdev_queue *dev_queue; struct Qdisc *qdisc; unsigned int ntx; if (sch->parent != TC_H_ROOT) return -EOPNOTSUPP; if (!netif_is_multiqueue(dev)) return -EOPNOTSUPP; /* pre-allocate qdiscs, attachment can't fail */ priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]), GFP_KERNEL); if (!priv->qdiscs) return -ENOMEM; for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { dev_queue = netdev_get_tx_queue(dev, ntx); qdisc = qdisc_create_dflt(dev_queue, get_default_qdisc_ops(dev, ntx), TC_H_MAKE(TC_H_MAJ(sch->handle), TC_H_MIN(ntx + 1)), extack); if (!qdisc) return -ENOMEM; priv->qdiscs[ntx] = qdisc; qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; } sch->flags |= TCQ_F_MQROOT; mq_offload(sch, TC_MQ_CREATE); return 0; } static void mq_attach(struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); struct mq_sched *priv = qdisc_priv(sch); struct Qdisc *qdisc, *old; unsigned int ntx; for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { qdisc = priv->qdiscs[ntx]; old = dev_graft_qdisc(qdisc->dev_queue, qdisc); if (old) qdisc_put(old); #ifdef CONFIG_NET_SCHED if (ntx < dev->real_num_tx_queues) qdisc_hash_add(qdisc, false); #endif } kfree(priv->qdiscs); priv->qdiscs = NULL; } static int mq_dump(struct Qdisc *sch, struct sk_buff *skb) { struct net_device *dev = qdisc_dev(sch); struct Qdisc *qdisc; unsigned int ntx; sch->q.qlen = 0; gnet_stats_basic_sync_init(&sch->bstats); memset(&sch->qstats, 0, sizeof(sch->qstats)); /* MQ supports lockless qdiscs. However, statistics accounting needs * to account for all, none, or a mix of locked and unlocked child * qdiscs. Percpu stats are added to counters in-band and locking * qdisc totals are added at end. */ for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { qdisc = rtnl_dereference(netdev_get_tx_queue(dev, ntx)->qdisc_sleeping); spin_lock_bh(qdisc_lock(qdisc)); gnet_stats_add_basic(&sch->bstats, qdisc->cpu_bstats, &qdisc->bstats, false); gnet_stats_add_queue(&sch->qstats, qdisc->cpu_qstats, &qdisc->qstats); sch->q.qlen += qdisc_qlen(qdisc); spin_unlock_bh(qdisc_lock(qdisc)); } return mq_offload_stats(sch); } static struct netdev_queue *mq_queue_get(struct Qdisc *sch, unsigned long cl) { struct net_device *dev = qdisc_dev(sch); unsigned long ntx = cl - 1; if (ntx >= dev->num_tx_queues) return NULL; return netdev_get_tx_queue(dev, ntx); } static struct netdev_queue *mq_select_queue(struct Qdisc *sch, struct tcmsg *tcm) { return mq_queue_get(sch, TC_H_MIN(tcm->tcm_parent)); } static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, struct Qdisc **old, struct netlink_ext_ack *extack) { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); struct tc_mq_qopt_offload graft_offload; struct net_device *dev = qdisc_dev(sch); if (dev->flags & IFF_UP) dev_deactivate(dev); *old = dev_graft_qdisc(dev_queue, new); if (new) new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; if (dev->flags & IFF_UP) dev_activate(dev); graft_offload.handle = sch->handle; graft_offload.graft_params.queue = cl - 1; graft_offload.graft_params.child_handle = new ? new->handle : 0; graft_offload.command = TC_MQ_GRAFT; qdisc_offload_graft_helper(qdisc_dev(sch), sch, new, *old, TC_SETUP_QDISC_MQ, &graft_offload, extack); return 0; } static struct Qdisc *mq_leaf(struct Qdisc *sch, unsigned long cl) { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); return rtnl_dereference(dev_queue->qdisc_sleeping); } static unsigned long mq_find(struct Qdisc *sch, u32 classid) { unsigned int ntx = TC_H_MIN(classid); if (!mq_queue_get(sch, ntx)) return 0; return ntx; } static int mq_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); tcm->tcm_parent = TC_H_ROOT; tcm->tcm_handle |= TC_H_MIN(cl); tcm->tcm_info = rtnl_dereference(dev_queue->qdisc_sleeping)->handle; return 0; } static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct gnet_dump *d) { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); sch = rtnl_dereference(dev_queue->qdisc_sleeping); if (gnet_stats_copy_basic(d, sch->cpu_bstats, &sch->bstats, true) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; return 0; } static void mq_walk(struct Qdisc *sch, struct qdisc_walker *arg) { struct net_device *dev = qdisc_dev(sch); unsigned int ntx; if (arg->stop) return; arg->count = arg->skip; for (ntx = arg->skip; ntx < dev->num_tx_queues; ntx++) { if (!tc_qdisc_stats_dump(sch, ntx + 1, arg)) break; } } static const struct Qdisc_class_ops mq_class_ops = { .select_queue = mq_select_queue, .graft = mq_graft, .leaf = mq_leaf, .find = mq_find, .walk = mq_walk, .dump = mq_dump_class, .dump_stats = mq_dump_class_stats, }; struct Qdisc_ops mq_qdisc_ops __read_mostly = { .cl_ops = &mq_class_ops, .id = "mq", .priv_size = sizeof(struct mq_sched), .init = mq_init, .destroy = mq_destroy, .attach = mq_attach, .change_real_num_tx = mq_change_real_num_tx, .dump = mq_dump, .owner = THIS_MODULE, }; |
| 783 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * fs/kernfs/kernfs-internal.h - kernfs internal header file * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007, 2013 Tejun Heo <teheo@suse.de> */ #ifndef __KERNFS_INTERNAL_H #define __KERNFS_INTERNAL_H #include <linux/lockdep.h> #include <linux/fs.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/xattr.h> #include <linux/kernfs.h> #include <linux/fs_context.h> struct kernfs_iattrs { kuid_t ia_uid; kgid_t ia_gid; struct timespec64 ia_atime; struct timespec64 ia_mtime; struct timespec64 ia_ctime; struct simple_xattrs xattrs; atomic_t nr_user_xattrs; atomic_t user_xattr_size; }; struct kernfs_root { /* published fields */ struct kernfs_node *kn; unsigned int flags; /* KERNFS_ROOT_* flags */ /* private fields, do not use outside kernfs proper */ struct idr ino_idr; u32 last_id_lowbits; u32 id_highbits; struct kernfs_syscall_ops *syscall_ops; /* list of kernfs_super_info of this root, protected by kernfs_rwsem */ struct list_head supers; wait_queue_head_t deactivate_waitq; struct rw_semaphore kernfs_rwsem; }; /* +1 to avoid triggering overflow warning when negating it */ #define KN_DEACTIVATED_BIAS (INT_MIN + 1) /* KERNFS_TYPE_MASK and types are defined in include/linux/kernfs.h */ /** * kernfs_root - find out the kernfs_root a kernfs_node belongs to * @kn: kernfs_node of interest * * Return: the kernfs_root @kn belongs to. */ static inline struct kernfs_root *kernfs_root(struct kernfs_node *kn) { /* if parent exists, it's always a dir; otherwise, @sd is a dir */ if (kn->parent) kn = kn->parent; return kn->dir.root; } /* * mount.c */ struct kernfs_super_info { struct super_block *sb; /* * The root associated with this super_block. Each super_block is * identified by the root and ns it's associated with. */ struct kernfs_root *root; /* * Each sb is associated with one namespace tag, currently the * network namespace of the task which mounted this kernfs * instance. If multiple tags become necessary, make the following * an array and compare kernfs_node tag against every entry. */ const void *ns; /* anchored at kernfs_root->supers, protected by kernfs_rwsem */ struct list_head node; }; #define kernfs_info(SB) ((struct kernfs_super_info *)(SB->s_fs_info)) static inline struct kernfs_node *kernfs_dentry_node(struct dentry *dentry) { if (d_really_is_negative(dentry)) return NULL; return d_inode(dentry)->i_private; } static inline void kernfs_set_rev(struct kernfs_node *parent, struct dentry *dentry) { dentry->d_time = parent->dir.rev; } static inline void kernfs_inc_rev(struct kernfs_node *parent) { parent->dir.rev++; } static inline bool kernfs_dir_changed(struct kernfs_node *parent, struct dentry *dentry) { if (parent->dir.rev != dentry->d_time) return true; return false; } extern const struct super_operations kernfs_sops; extern struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache; /* * inode.c */ extern const struct xattr_handler *kernfs_xattr_handlers[]; void kernfs_evict_inode(struct inode *inode); int kernfs_iop_permission(struct user_namespace *mnt_userns, struct inode *inode, int mask); int kernfs_iop_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, struct iattr *iattr); int kernfs_iop_getattr(struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags); ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size); int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr); /* * dir.c */ extern const struct dentry_operations kernfs_dops; extern const struct file_operations kernfs_dir_fops; extern const struct inode_operations kernfs_dir_iops; struct kernfs_node *kernfs_get_active(struct kernfs_node *kn); void kernfs_put_active(struct kernfs_node *kn); int kernfs_add_one(struct kernfs_node *kn); struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, unsigned flags); /* * file.c */ extern const struct file_operations kernfs_file_fops; bool kernfs_should_drain_open_files(struct kernfs_node *kn); void kernfs_drain_open_files(struct kernfs_node *kn); /* * symlink.c */ extern const struct inode_operations kernfs_symlink_iops; /* * kernfs locks */ extern struct kernfs_global_locks *kernfs_locks; #endif /* __KERNFS_INTERNAL_H */ |
| 7096 7096 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PGALLOC_TRACK_H #define _LINUX_PGALLOC_TRACK_H #if defined(CONFIG_MMU) static inline p4d_t *p4d_alloc_track(struct mm_struct *mm, pgd_t *pgd, unsigned long address, pgtbl_mod_mask *mod_mask) { if (unlikely(pgd_none(*pgd))) { if (__p4d_alloc(mm, pgd, address)) return NULL; *mod_mask |= PGTBL_PGD_MODIFIED; } return p4d_offset(pgd, address); } static inline pud_t *pud_alloc_track(struct mm_struct *mm, p4d_t *p4d, unsigned long address, pgtbl_mod_mask *mod_mask) { if (unlikely(p4d_none(*p4d))) { if (__pud_alloc(mm, p4d, address)) return NULL; *mod_mask |= PGTBL_P4D_MODIFIED; } return pud_offset(p4d, address); } static inline pmd_t *pmd_alloc_track(struct mm_struct *mm, pud_t *pud, unsigned long address, pgtbl_mod_mask *mod_mask) { if (unlikely(pud_none(*pud))) { if (__pmd_alloc(mm, pud, address)) return NULL; *mod_mask |= PGTBL_PUD_MODIFIED; } return pmd_offset(pud, address); } #endif /* CONFIG_MMU */ #define pte_alloc_kernel_track(pmd, address, mask) \ ((unlikely(pmd_none(*(pmd))) && \ (__pte_alloc_kernel(pmd) || ({*(mask)|=PGTBL_PMD_MODIFIED;0;})))?\ NULL: pte_offset_kernel(pmd, address)) #endif /* _LINUX_PGALLOC_TRACK_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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __IEEE802154_CORE_H #define __IEEE802154_CORE_H #include <net/cfg802154.h> struct cfg802154_registered_device { const struct cfg802154_ops *ops; struct list_head list; /* wpan_phy index, internal only */ int wpan_phy_idx; /* also protected by devlist_mtx */ int opencount; wait_queue_head_t dev_wait; /* protected by RTNL only */ int num_running_ifaces; /* associated wpan interfaces, protected by rtnl or RCU */ struct list_head wpan_dev_list; int devlist_generation, wpan_dev_id; /* must be last because of the way we do wpan_phy_priv(), * and it should at least be aligned to NETDEV_ALIGN */ struct wpan_phy wpan_phy __aligned(NETDEV_ALIGN); }; static inline struct cfg802154_registered_device * wpan_phy_to_rdev(struct wpan_phy *wpan_phy) { BUG_ON(!wpan_phy); return container_of(wpan_phy, struct cfg802154_registered_device, wpan_phy); } extern struct list_head cfg802154_rdev_list; extern int cfg802154_rdev_list_generation; int cfg802154_switch_netns(struct cfg802154_registered_device *rdev, struct net *net); /* free object */ void cfg802154_dev_free(struct cfg802154_registered_device *rdev); struct cfg802154_registered_device * cfg802154_rdev_by_wpan_phy_idx(int wpan_phy_idx); struct wpan_phy *wpan_phy_idx_to_wpan_phy(int wpan_phy_idx); #endif /* __IEEE802154_CORE_H */ |
| 25 25 34 34 1 2 9 22 2 26 1 24 10 10 9 10 9 10 10 2574 2574 706 681 1513 1513 1513 553 10 455 2573 2 1 1 9 5 4 9 1 2 1 1 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2016 Facebook */ #include <linux/bpf.h> #include <linux/jhash.h> #include <linux/filter.h> #include <linux/kernel.h> #include <linux/stacktrace.h> #include <linux/perf_event.h> #include <linux/btf_ids.h> #include <linux/buildid.h> #include "percpu_freelist.h" #include "mmap_unlock_work.h" #define STACK_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY | \ BPF_F_STACK_BUILD_ID) struct stack_map_bucket { struct pcpu_freelist_node fnode; u32 hash; u32 nr; u64 data[]; }; struct bpf_stack_map { struct bpf_map map; void *elems; struct pcpu_freelist freelist; u32 n_buckets; struct stack_map_bucket *buckets[]; }; static inline bool stack_map_use_build_id(struct bpf_map *map) { return (map->map_flags & BPF_F_STACK_BUILD_ID); } static inline int stack_map_data_size(struct bpf_map *map) { return stack_map_use_build_id(map) ? sizeof(struct bpf_stack_build_id) : sizeof(u64); } static int prealloc_elems_and_freelist(struct bpf_stack_map *smap) { u64 elem_size = sizeof(struct stack_map_bucket) + (u64)smap->map.value_size; int err; smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries, smap->map.numa_node); if (!smap->elems) return -ENOMEM; err = pcpu_freelist_init(&smap->freelist); if (err) goto free_elems; pcpu_freelist_populate(&smap->freelist, smap->elems, elem_size, smap->map.max_entries); return 0; free_elems: bpf_map_area_free(smap->elems); return err; } /* Called from syscall */ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) { u32 value_size = attr->value_size; struct bpf_stack_map *smap; u64 cost, n_buckets; int err; if (!bpf_capable()) return ERR_PTR(-EPERM); if (attr->map_flags & ~STACK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || value_size < 8 || value_size % 8) return ERR_PTR(-EINVAL); BUILD_BUG_ON(sizeof(struct bpf_stack_build_id) % sizeof(u64)); if (attr->map_flags & BPF_F_STACK_BUILD_ID) { if (value_size % sizeof(struct bpf_stack_build_id) || value_size / sizeof(struct bpf_stack_build_id) > sysctl_perf_event_max_stack) return ERR_PTR(-EINVAL); } else if (value_size / 8 > sysctl_perf_event_max_stack) return ERR_PTR(-EINVAL); /* hash table size must be power of 2; roundup_pow_of_two() can overflow * into UB on 32-bit arches, so check that first */ if (attr->max_entries > 1UL << 31) return ERR_PTR(-E2BIG); n_buckets = roundup_pow_of_two(attr->max_entries); cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap); smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr)); if (!smap) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&smap->map, attr); smap->n_buckets = n_buckets; err = get_callchain_buffers(sysctl_perf_event_max_stack); if (err) goto free_smap; err = prealloc_elems_and_freelist(smap); if (err) goto put_buffers; return &smap->map; put_buffers: put_callchain_buffers(); free_smap: bpf_map_area_free(smap); return ERR_PTR(err); } static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, u64 *ips, u32 trace_nr, bool user) { int i; struct mmap_unlock_irq_work *work = NULL; bool irq_work_busy = bpf_mmap_unlock_get_irq_work(&work); struct vm_area_struct *vma, *prev_vma = NULL; const char *prev_build_id; /* If the irq_work is in use, fall back to report ips. Same * fallback is used for kernel stack (!user) on a stackmap with * build_id. */ if (!user || !current || !current->mm || irq_work_busy || !mmap_read_trylock(current->mm)) { /* cannot access current->mm, fall back to ips */ for (i = 0; i < trace_nr; i++) { id_offs[i].status = BPF_STACK_BUILD_ID_IP; id_offs[i].ip = ips[i]; memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX); } return; } for (i = 0; i < trace_nr; i++) { if (range_in_vma(prev_vma, ips[i], ips[i])) { vma = prev_vma; memcpy(id_offs[i].build_id, prev_build_id, BUILD_ID_SIZE_MAX); goto build_id_valid; } vma = find_vma(current->mm, ips[i]); if (!vma || build_id_parse(vma, id_offs[i].build_id, NULL)) { /* per entry fall back to ips */ id_offs[i].status = BPF_STACK_BUILD_ID_IP; id_offs[i].ip = ips[i]; memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX); continue; } build_id_valid: id_offs[i].offset = (vma->vm_pgoff << PAGE_SHIFT) + ips[i] - vma->vm_start; id_offs[i].status = BPF_STACK_BUILD_ID_VALID; prev_vma = vma; prev_build_id = id_offs[i].build_id; } bpf_mmap_unlock_mm(work, current->mm); } static struct perf_callchain_entry * get_callchain_entry_for_task(struct task_struct *task, u32 max_depth) { #ifdef CONFIG_STACKTRACE struct perf_callchain_entry *entry; int rctx; entry = get_callchain_entry(&rctx); if (!entry) return NULL; entry->nr = stack_trace_save_tsk(task, (unsigned long *)entry->ip, max_depth, 0); /* stack_trace_save_tsk() works on unsigned long array, while * perf_callchain_entry uses u64 array. For 32-bit systems, it is * necessary to fix this mismatch. */ if (__BITS_PER_LONG != 64) { unsigned long *from = (unsigned long *) entry->ip; u64 *to = entry->ip; int i; /* copy data from the end to avoid using extra buffer */ for (i = entry->nr - 1; i >= 0; i--) to[i] = (u64)(from[i]); } put_callchain_entry(rctx); return entry; #else /* CONFIG_STACKTRACE */ return NULL; #endif } static long __bpf_get_stackid(struct bpf_map *map, struct perf_callchain_entry *trace, u64 flags) { struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); struct stack_map_bucket *bucket, *new_bucket, *old_bucket; u32 skip = flags & BPF_F_SKIP_FIELD_MASK; u32 hash, id, trace_nr, trace_len; bool user = flags & BPF_F_USER_STACK; u64 *ips; bool hash_matches; if (trace->nr <= skip) /* skipping more than usable stack trace */ return -EFAULT; trace_nr = trace->nr - skip; trace_len = trace_nr * sizeof(u64); ips = trace->ip + skip; hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0); id = hash & (smap->n_buckets - 1); bucket = READ_ONCE(smap->buckets[id]); hash_matches = bucket && bucket->hash == hash; /* fast cmp */ if (hash_matches && flags & BPF_F_FAST_STACK_CMP) return id; if (stack_map_use_build_id(map)) { /* for build_id+offset, pop a bucket before slow cmp */ new_bucket = (struct stack_map_bucket *) pcpu_freelist_pop(&smap->freelist); if (unlikely(!new_bucket)) return -ENOMEM; new_bucket->nr = trace_nr; stack_map_get_build_id_offset( (struct bpf_stack_build_id *)new_bucket->data, ips, trace_nr, user); trace_len = trace_nr * sizeof(struct bpf_stack_build_id); if (hash_matches && bucket->nr == trace_nr && memcmp(bucket->data, new_bucket->data, trace_len) == 0) { pcpu_freelist_push(&smap->freelist, &new_bucket->fnode); return id; } if (bucket && !(flags & BPF_F_REUSE_STACKID)) { pcpu_freelist_push(&smap->freelist, &new_bucket->fnode); return -EEXIST; } } else { if (hash_matches && bucket->nr == trace_nr && memcmp(bucket->data, ips, trace_len) == 0) return id; if (bucket && !(flags & BPF_F_REUSE_STACKID)) return -EEXIST; new_bucket = (struct stack_map_bucket *) pcpu_freelist_pop(&smap->freelist); if (unlikely(!new_bucket)) return -ENOMEM; memcpy(new_bucket->data, ips, trace_len); } new_bucket->hash = hash; new_bucket->nr = trace_nr; old_bucket = xchg(&smap->buckets[id], new_bucket); if (old_bucket) pcpu_freelist_push(&smap->freelist, &old_bucket->fnode); return id; } BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, u64, flags) { u32 max_depth = map->value_size / stack_map_data_size(map); u32 skip = flags & BPF_F_SKIP_FIELD_MASK; bool user = flags & BPF_F_USER_STACK; struct perf_callchain_entry *trace; bool kernel = !user; if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID))) return -EINVAL; max_depth += skip; if (max_depth > sysctl_perf_event_max_stack) max_depth = sysctl_perf_event_max_stack; trace = get_perf_callchain(regs, 0, kernel, user, max_depth, false, false); if (unlikely(!trace)) /* couldn't fetch the stack trace */ return -EFAULT; return __bpf_get_stackid(map, trace, flags); } const struct bpf_func_proto bpf_get_stackid_proto = { .func = bpf_get_stackid, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, }; static __u64 count_kernel_ip(struct perf_callchain_entry *trace) { __u64 nr_kernel = 0; while (nr_kernel < trace->nr) { if (trace->ip[nr_kernel] == PERF_CONTEXT_USER) break; nr_kernel++; } return nr_kernel; } BPF_CALL_3(bpf_get_stackid_pe, struct bpf_perf_event_data_kern *, ctx, struct bpf_map *, map, u64, flags) { struct perf_event *event = ctx->event; struct perf_callchain_entry *trace; bool kernel, user; __u64 nr_kernel; int ret; /* perf_sample_data doesn't have callchain, use bpf_get_stackid */ if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)) return bpf_get_stackid((unsigned long)(ctx->regs), (unsigned long) map, flags, 0, 0); if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID))) return -EINVAL; user = flags & BPF_F_USER_STACK; kernel = !user; trace = ctx->data->callchain; if (unlikely(!trace)) return -EFAULT; nr_kernel = count_kernel_ip(trace); if (kernel) { __u64 nr = trace->nr; trace->nr = nr_kernel; ret = __bpf_get_stackid(map, trace, flags); /* restore nr */ trace->nr = nr; } else { /* user */ u64 skip = flags & BPF_F_SKIP_FIELD_MASK; skip += nr_kernel; if (skip > BPF_F_SKIP_FIELD_MASK) return -EFAULT; flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip; ret = __bpf_get_stackid(map, trace, flags); } return ret; } const struct bpf_func_proto bpf_get_stackid_proto_pe = { .func = bpf_get_stackid_pe, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, }; static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, struct perf_callchain_entry *trace_in, void *buf, u32 size, u64 flags) { u32 trace_nr, copy_len, elem_size, num_elem, max_depth; bool user_build_id = flags & BPF_F_USER_BUILD_ID; bool crosstask = task && task != current; u32 skip = flags & BPF_F_SKIP_FIELD_MASK; bool user = flags & BPF_F_USER_STACK; struct perf_callchain_entry *trace; bool kernel = !user; int err = -EINVAL; u64 *ips; if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | BPF_F_USER_BUILD_ID))) goto clear; if (kernel && user_build_id) goto clear; elem_size = (user && user_build_id) ? sizeof(struct bpf_stack_build_id) : sizeof(u64); if (unlikely(size % elem_size)) goto clear; /* cannot get valid user stack for task without user_mode regs */ if (task && user && !user_mode(regs)) goto err_fault; /* get_perf_callchain does not support crosstask user stack walking * but returns an empty stack instead of NULL. */ if (crosstask && user) { err = -EOPNOTSUPP; goto clear; } num_elem = size / elem_size; max_depth = num_elem + skip; if (sysctl_perf_event_max_stack < max_depth) max_depth = sysctl_perf_event_max_stack; if (trace_in) trace = trace_in; else if (kernel && task) trace = get_callchain_entry_for_task(task, max_depth); else trace = get_perf_callchain(regs, 0, kernel, user, max_depth, crosstask, false); if (unlikely(!trace)) goto err_fault; if (trace->nr < skip) goto err_fault; trace_nr = trace->nr - skip; trace_nr = (trace_nr <= num_elem) ? trace_nr : num_elem; copy_len = trace_nr * elem_size; ips = trace->ip + skip; if (user && user_build_id) stack_map_get_build_id_offset(buf, ips, trace_nr, user); else memcpy(buf, ips, copy_len); if (size > copy_len) memset(buf + copy_len, 0, size - copy_len); return copy_len; err_fault: err = -EFAULT; clear: memset(buf, 0, size); return err; } BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size, u64, flags) { return __bpf_get_stack(regs, NULL, NULL, buf, size, flags); } const struct bpf_func_proto bpf_get_stack_proto = { .func = bpf_get_stack, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf, u32, size, u64, flags) { struct pt_regs *regs; long res = -EINVAL; if (!try_get_task_stack(task)) return -EFAULT; regs = task_pt_regs(task); if (regs) res = __bpf_get_stack(regs, task, NULL, buf, size, flags); put_task_stack(task); return res; } const struct bpf_func_proto bpf_get_task_stack_proto = { .func = bpf_get_task_stack, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx, void *, buf, u32, size, u64, flags) { struct pt_regs *regs = (struct pt_regs *)(ctx->regs); struct perf_event *event = ctx->event; struct perf_callchain_entry *trace; bool kernel, user; int err = -EINVAL; __u64 nr_kernel; if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)) return __bpf_get_stack(regs, NULL, NULL, buf, size, flags); if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | BPF_F_USER_BUILD_ID))) goto clear; user = flags & BPF_F_USER_STACK; kernel = !user; err = -EFAULT; trace = ctx->data->callchain; if (unlikely(!trace)) goto clear; nr_kernel = count_kernel_ip(trace); if (kernel) { __u64 nr = trace->nr; trace->nr = nr_kernel; err = __bpf_get_stack(regs, NULL, trace, buf, size, flags); /* restore nr */ trace->nr = nr; } else { /* user */ u64 skip = flags & BPF_F_SKIP_FIELD_MASK; skip += nr_kernel; if (skip > BPF_F_SKIP_FIELD_MASK) goto clear; flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip; err = __bpf_get_stack(regs, NULL, trace, buf, size, flags); } return err; clear: memset(buf, 0, size); return err; } const struct bpf_func_proto bpf_get_stack_proto_pe = { .func = bpf_get_stack_pe, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; /* Called from eBPF program */ static void *stack_map_lookup_elem(struct bpf_map *map, void *key) { return ERR_PTR(-EOPNOTSUPP); } /* Called from syscall */ int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) { struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); struct stack_map_bucket *bucket, *old_bucket; u32 id = *(u32 *)key, trace_len; if (unlikely(id >= smap->n_buckets)) return -ENOENT; bucket = xchg(&smap->buckets[id], NULL); if (!bucket) return -ENOENT; trace_len = bucket->nr * stack_map_data_size(map); memcpy(value, bucket->data, trace_len); memset(value + trace_len, 0, map->value_size - trace_len); old_bucket = xchg(&smap->buckets[id], bucket); if (old_bucket) pcpu_freelist_push(&smap->freelist, &old_bucket->fnode); return 0; } static int stack_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); u32 id; WARN_ON_ONCE(!rcu_read_lock_held()); if (!key) { id = 0; } else { id = *(u32 *)key; if (id >= smap->n_buckets || !smap->buckets[id]) id = 0; else id++; } while (id < smap->n_buckets && !smap->buckets[id]) id++; if (id >= smap->n_buckets) return -ENOENT; *(u32 *)next_key = id; return 0; } static int stack_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return -EINVAL; } /* Called from syscall or from eBPF program */ static int stack_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); struct stack_map_bucket *old_bucket; u32 id = *(u32 *)key; if (unlikely(id >= smap->n_buckets)) return -E2BIG; old_bucket = xchg(&smap->buckets[id], NULL); if (old_bucket) { pcpu_freelist_push(&smap->freelist, &old_bucket->fnode); return 0; } else { return -ENOENT; } } /* Called when map->refcnt goes to zero, either from workqueue or from syscall */ static void stack_map_free(struct bpf_map *map) { struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); bpf_map_area_free(smap->elems); pcpu_freelist_destroy(&smap->freelist); bpf_map_area_free(smap); put_callchain_buffers(); } BTF_ID_LIST_SINGLE(stack_trace_map_btf_ids, struct, bpf_stack_map) const struct bpf_map_ops stack_trace_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = stack_map_alloc, .map_free = stack_map_free, .map_get_next_key = stack_map_get_next_key, .map_lookup_elem = stack_map_lookup_elem, .map_update_elem = stack_map_update_elem, .map_delete_elem = stack_map_delete_elem, .map_check_btf = map_check_no_btf, .map_btf_id = &stack_trace_map_btf_ids[0], }; |
| 1242 13908 13956 1591 1592 1594 3211 3213 3217 1132 1130 1131 536 536 529 529 44 44 169 169 885 885 2146 2147 181 182 480 481 1833 1833 1562 1560 7808 7807 7813 1809 1808 1807 3605 3624 3 3 4 4 103 103 1466 1468 1244 1242 1244 460 462 1267 1268 1268 470 470 72 72 253 252 7528 7526 2362 3 3 3 3 105 105 2558 2559 2365 2366 1851 1853 842 843 654 660 416 422 310 310 588 590 4118 4125 2025 2024 102 102 620 620 330 330 621 621 6 6 657 657 76 76 11292 11320 1193 1193 3646 3649 1185 1189 5512 5518 2067 2068 249 249 1964 1964 1702 1704 230 229 304 308 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Security plug functions * * Copyright (C) 2001 WireX Communications, Inc <chris@wirex.com> * Copyright (C) 2001-2002 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.com> * Copyright (C) 2016 Mellanox Technologies */ #define pr_fmt(fmt) "LSM: " fmt #include <linux/bpf.h> #include <linux/capability.h> #include <linux/dcache.h> #include <linux/export.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kernel_read_file.h> #include <linux/lsm_hooks.h> #include <linux/integrity.h> #include <linux/ima.h> #include <linux/evm.h> #include <linux/fsnotify.h> #include <linux/mman.h> #include <linux/mount.h> #include <linux/personality.h> #include <linux/backing-dev.h> #include <linux/string.h> #include <linux/msg.h> #include <net/flow.h> #define MAX_LSM_EVM_XATTR 2 /* How many LSMs were built into the kernel? */ #define LSM_COUNT (__end_lsm_info - __start_lsm_info) /* * These are descriptions of the reasons that can be passed to the * security_locked_down() LSM hook. Placing this array here allows * all security modules to use the same descriptions for auditing * purposes. */ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1] = { [LOCKDOWN_NONE] = "none", [LOCKDOWN_MODULE_SIGNATURE] = "unsigned module loading", [LOCKDOWN_DEV_MEM] = "/dev/mem,kmem,port", [LOCKDOWN_EFI_TEST] = "/dev/efi_test access", [LOCKDOWN_KEXEC] = "kexec of unsigned images", [LOCKDOWN_HIBERNATION] = "hibernation", [LOCKDOWN_PCI_ACCESS] = "direct PCI access", [LOCKDOWN_IOPORT] = "raw io port access", [LOCKDOWN_MSR] = "raw MSR access", [LOCKDOWN_ACPI_TABLES] = "modifying ACPI tables", [LOCKDOWN_DEVICE_TREE] = "modifying device tree contents", [LOCKDOWN_PCMCIA_CIS] = "direct PCMCIA CIS storage", [LOCKDOWN_TIOCSSERIAL] = "reconfiguration of serial port IO", [LOCKDOWN_MODULE_PARAMETERS] = "unsafe module parameters", [LOCKDOWN_MMIOTRACE] = "unsafe mmio", [LOCKDOWN_DEBUGFS] = "debugfs access", [LOCKDOWN_XMON_WR] = "xmon write access", [LOCKDOWN_BPF_WRITE_USER] = "use of bpf to write user RAM", [LOCKDOWN_DBG_WRITE_KERNEL] = "use of kgdb/kdb to write kernel RAM", [LOCKDOWN_RTAS_ERROR_INJECTION] = "RTAS error injection", [LOCKDOWN_INTEGRITY_MAX] = "integrity", [LOCKDOWN_KCORE] = "/proc/kcore access", [LOCKDOWN_KPROBES] = "use of kprobes", [LOCKDOWN_BPF_READ_KERNEL] = "use of bpf to read kernel RAM", [LOCKDOWN_DBG_READ_KERNEL] = "use of kgdb/kdb to read kernel RAM", [LOCKDOWN_PERF] = "unsafe use of perf", [LOCKDOWN_TRACEFS] = "use of tracefs", [LOCKDOWN_XMON_RW] = "xmon read and write access", [LOCKDOWN_XFRM_SECRET] = "xfrm SA secret", [LOCKDOWN_CONFIDENTIALITY_MAX] = "confidentiality", }; struct security_hook_heads security_hook_heads __lsm_ro_after_init; static BLOCKING_NOTIFIER_HEAD(blocking_lsm_notifier_chain); static struct kmem_cache *lsm_file_cache; static struct kmem_cache *lsm_inode_cache; char *lsm_names; static struct lsm_blob_sizes blob_sizes __lsm_ro_after_init; /* Boot-time LSM user choice */ static __initdata const char *chosen_lsm_order; static __initdata const char *chosen_major_lsm; static __initconst const char * const builtin_lsm_order = CONFIG_LSM; /* Ordered list of LSMs to initialize. */ static __initdata struct lsm_info **ordered_lsms; static __initdata struct lsm_info *exclusive; static __initdata bool debug; #define init_debug(...) \ do { \ if (debug) \ pr_info(__VA_ARGS__); \ } while (0) static bool __init is_enabled(struct lsm_info *lsm) { if (!lsm->enabled) return false; return *lsm->enabled; } /* Mark an LSM's enabled flag. */ static int lsm_enabled_true __initdata = 1; static int lsm_enabled_false __initdata = 0; static void __init set_enabled(struct lsm_info *lsm, bool enabled) { /* * When an LSM hasn't configured an enable variable, we can use * a hard-coded location for storing the default enabled state. */ if (!lsm->enabled) { if (enabled) lsm->enabled = &lsm_enabled_true; else lsm->enabled = &lsm_enabled_false; } else if (lsm->enabled == &lsm_enabled_true) { if (!enabled) lsm->enabled = &lsm_enabled_false; } else if (lsm->enabled == &lsm_enabled_false) { if (enabled) lsm->enabled = &lsm_enabled_true; } else { *lsm->enabled = enabled; } } /* Is an LSM already listed in the ordered LSMs list? */ static bool __init exists_ordered_lsm(struct lsm_info *lsm) { struct lsm_info **check; for (check = ordered_lsms; *check; check++) if (*check == lsm) return true; return false; } /* Append an LSM to the list of ordered LSMs to initialize. */ static int last_lsm __initdata; static void __init append_ordered_lsm(struct lsm_info *lsm, const char *from) { /* Ignore duplicate selections. */ if (exists_ordered_lsm(lsm)) return; if (WARN(last_lsm == LSM_COUNT, "%s: out of LSM slots!?\n", from)) return; /* Enable this LSM, if it is not already set. */ if (!lsm->enabled) lsm->enabled = &lsm_enabled_true; ordered_lsms[last_lsm++] = lsm; init_debug("%s ordering: %s (%sabled)\n", from, lsm->name, is_enabled(lsm) ? "en" : "dis"); } /* Is an LSM allowed to be initialized? */ static bool __init lsm_allowed(struct lsm_info *lsm) { /* Skip if the LSM is disabled. */ if (!is_enabled(lsm)) return false; /* Not allowed if another exclusive LSM already initialized. */ if ((lsm->flags & LSM_FLAG_EXCLUSIVE) && exclusive) { init_debug("exclusive disabled: %s\n", lsm->name); return false; } return true; } static void __init lsm_set_blob_size(int *need, int *lbs) { int offset; if (*need > 0) { offset = *lbs; *lbs += *need; *need = offset; } } static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed) { if (!needed) return; lsm_set_blob_size(&needed->lbs_cred, &blob_sizes.lbs_cred); lsm_set_blob_size(&needed->lbs_file, &blob_sizes.lbs_file); /* * The inode blob gets an rcu_head in addition to * what the modules might need. */ if (needed->lbs_inode && blob_sizes.lbs_inode == 0) blob_sizes.lbs_inode = sizeof(struct rcu_head); lsm_set_blob_size(&needed->lbs_inode, &blob_sizes.lbs_inode); lsm_set_blob_size(&needed->lbs_ipc, &blob_sizes.lbs_ipc); lsm_set_blob_size(&needed->lbs_msg_msg, &blob_sizes.lbs_msg_msg); lsm_set_blob_size(&needed->lbs_superblock, &blob_sizes.lbs_superblock); lsm_set_blob_size(&needed->lbs_task, &blob_sizes.lbs_task); } /* Prepare LSM for initialization. */ static void __init prepare_lsm(struct lsm_info *lsm) { int enabled = lsm_allowed(lsm); /* Record enablement (to handle any following exclusive LSMs). */ set_enabled(lsm, enabled); /* If enabled, do pre-initialization work. */ if (enabled) { if ((lsm->flags & LSM_FLAG_EXCLUSIVE) && !exclusive) { exclusive = lsm; init_debug("exclusive chosen: %s\n", lsm->name); } lsm_set_blob_sizes(lsm->blobs); } } /* Initialize a given LSM, if it is enabled. */ static void __init initialize_lsm(struct lsm_info *lsm) { if (is_enabled(lsm)) { int ret; init_debug("initializing %s\n", lsm->name); ret = lsm->init(); WARN(ret, "%s failed to initialize: %d\n", lsm->name, ret); } } /* Populate ordered LSMs list from comma-separated LSM name list. */ static void __init ordered_lsm_parse(const char *order, const char *origin) { struct lsm_info *lsm; char *sep, *name, *next; /* LSM_ORDER_FIRST is always first. */ for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if (lsm->order == LSM_ORDER_FIRST) append_ordered_lsm(lsm, "first"); } /* Process "security=", if given. */ if (chosen_major_lsm) { struct lsm_info *major; /* * To match the original "security=" behavior, this * explicitly does NOT fallback to another Legacy Major * if the selected one was separately disabled: disable * all non-matching Legacy Major LSMs. */ for (major = __start_lsm_info; major < __end_lsm_info; major++) { if ((major->flags & LSM_FLAG_LEGACY_MAJOR) && strcmp(major->name, chosen_major_lsm) != 0) { set_enabled(major, false); init_debug("security=%s disabled: %s\n", chosen_major_lsm, major->name); } } } sep = kstrdup(order, GFP_KERNEL); next = sep; /* Walk the list, looking for matching LSMs. */ while ((name = strsep(&next, ",")) != NULL) { bool found = false; for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if (lsm->order == LSM_ORDER_MUTABLE && strcmp(lsm->name, name) == 0) { append_ordered_lsm(lsm, origin); found = true; } } if (!found) init_debug("%s ignored: %s\n", origin, name); } /* Process "security=", if given. */ if (chosen_major_lsm) { for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if (exists_ordered_lsm(lsm)) continue; if (strcmp(lsm->name, chosen_major_lsm) == 0) append_ordered_lsm(lsm, "security="); } } /* Disable all LSMs not in the ordered list. */ for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if (exists_ordered_lsm(lsm)) continue; set_enabled(lsm, false); init_debug("%s disabled: %s\n", origin, lsm->name); } kfree(sep); } static void __init lsm_early_cred(struct cred *cred); static void __init lsm_early_task(struct task_struct *task); static int lsm_append(const char *new, char **result); static void __init ordered_lsm_init(void) { struct lsm_info **lsm; ordered_lsms = kcalloc(LSM_COUNT + 1, sizeof(*ordered_lsms), GFP_KERNEL); if (chosen_lsm_order) { if (chosen_major_lsm) { pr_info("security= is ignored because it is superseded by lsm=\n"); chosen_major_lsm = NULL; } ordered_lsm_parse(chosen_lsm_order, "cmdline"); } else ordered_lsm_parse(builtin_lsm_order, "builtin"); for (lsm = ordered_lsms; *lsm; lsm++) prepare_lsm(*lsm); init_debug("cred blob size = %d\n", blob_sizes.lbs_cred); init_debug("file blob size = %d\n", blob_sizes.lbs_file); init_debug("inode blob size = %d\n", blob_sizes.lbs_inode); init_debug("ipc blob size = %d\n", blob_sizes.lbs_ipc); init_debug("msg_msg blob size = %d\n", blob_sizes.lbs_msg_msg); init_debug("superblock blob size = %d\n", blob_sizes.lbs_superblock); init_debug("task blob size = %d\n", blob_sizes.lbs_task); /* * Create any kmem_caches needed for blobs */ if (blob_sizes.lbs_file) lsm_file_cache = kmem_cache_create("lsm_file_cache", blob_sizes.lbs_file, 0, SLAB_PANIC, NULL); if (blob_sizes.lbs_inode) lsm_inode_cache = kmem_cache_create("lsm_inode_cache", blob_sizes.lbs_inode, 0, SLAB_PANIC, NULL); lsm_early_cred((struct cred *) current->cred); lsm_early_task(current); for (lsm = ordered_lsms; *lsm; lsm++) initialize_lsm(*lsm); kfree(ordered_lsms); } int __init early_security_init(void) { struct lsm_info *lsm; #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ INIT_HLIST_HEAD(&security_hook_heads.NAME); #include "linux/lsm_hook_defs.h" #undef LSM_HOOK for (lsm = __start_early_lsm_info; lsm < __end_early_lsm_info; lsm++) { if (!lsm->enabled) lsm->enabled = &lsm_enabled_true; prepare_lsm(lsm); initialize_lsm(lsm); } return 0; } /** * security_init - initializes the security framework * * This should be called early in the kernel initialization sequence. */ int __init security_init(void) { struct lsm_info *lsm; pr_info("Security Framework initializing\n"); /* * Append the names of the early LSM modules now that kmalloc() is * available */ for (lsm = __start_early_lsm_info; lsm < __end_early_lsm_info; lsm++) { if (lsm->enabled) lsm_append(lsm->name, &lsm_names); } /* Load LSMs in specified order. */ ordered_lsm_init(); return 0; } /* Save user chosen LSM */ static int __init choose_major_lsm(char *str) { chosen_major_lsm = str; return 1; } __setup("security=", choose_major_lsm); /* Explicitly choose LSM initialization order. */ static int __init choose_lsm_order(char *str) { chosen_lsm_order = str; return 1; } __setup("lsm=", choose_lsm_order); /* Enable LSM order debugging. */ static int __init enable_debug(char *str) { debug = true; return 1; } __setup("lsm.debug", enable_debug); static bool match_last_lsm(const char *list, const char *lsm) { const char *last; if (WARN_ON(!list || !lsm)) return false; last = strrchr(list, ','); if (last) /* Pass the comma, strcmp() will check for '\0' */ last++; else last = list; return !strcmp(last, lsm); } static int lsm_append(const char *new, char **result) { char *cp; if (*result == NULL) { *result = kstrdup(new, GFP_KERNEL); if (*result == NULL) return -ENOMEM; } else { /* Check if it is the last registered name */ if (match_last_lsm(*result, new)) return 0; cp = kasprintf(GFP_KERNEL, "%s,%s", *result, new); if (cp == NULL) return -ENOMEM; kfree(*result); *result = cp; } return 0; } /** * security_add_hooks - Add a modules hooks to the hook lists. * @hooks: the hooks to add * @count: the number of hooks to add * @lsm: the name of the security module * * Each LSM has to register its hooks with the infrastructure. */ void __init security_add_hooks(struct security_hook_list *hooks, int count, const char *lsm) { int i; for (i = 0; i < count; i++) { hooks[i].lsm = lsm; hlist_add_tail_rcu(&hooks[i].list, hooks[i].head); } /* * Don't try to append during early_security_init(), we'll come back * and fix this up afterwards. */ if (slab_is_available()) { if (lsm_append(lsm, &lsm_names) < 0) panic("%s - Cannot get early memory.\n", __func__); } } int call_blocking_lsm_notifier(enum lsm_event event, void *data) { return blocking_notifier_call_chain(&blocking_lsm_notifier_chain, event, data); } EXPORT_SYMBOL(call_blocking_lsm_notifier); int register_blocking_lsm_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&blocking_lsm_notifier_chain, nb); } EXPORT_SYMBOL(register_blocking_lsm_notifier); int unregister_blocking_lsm_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&blocking_lsm_notifier_chain, nb); } EXPORT_SYMBOL(unregister_blocking_lsm_notifier); /** * lsm_cred_alloc - allocate a composite cred blob * @cred: the cred that needs a blob * @gfp: allocation type * * Allocate the cred blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_cred_alloc(struct cred *cred, gfp_t gfp) { if (blob_sizes.lbs_cred == 0) { cred->security = NULL; return 0; } cred->security = kzalloc(blob_sizes.lbs_cred, gfp); if (cred->security == NULL) return -ENOMEM; return 0; } /** * lsm_early_cred - during initialization allocate a composite cred blob * @cred: the cred that needs a blob * * Allocate the cred blob for all the modules */ static void __init lsm_early_cred(struct cred *cred) { int rc = lsm_cred_alloc(cred, GFP_KERNEL); if (rc) panic("%s: Early cred alloc failed.\n", __func__); } /** * lsm_file_alloc - allocate a composite file blob * @file: the file that needs a blob * * Allocate the file blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_file_alloc(struct file *file) { if (!lsm_file_cache) { file->f_security = NULL; return 0; } file->f_security = kmem_cache_zalloc(lsm_file_cache, GFP_KERNEL); if (file->f_security == NULL) return -ENOMEM; return 0; } /** * lsm_inode_alloc - allocate a composite inode blob * @inode: the inode that needs a blob * * Allocate the inode blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ int lsm_inode_alloc(struct inode *inode) { if (!lsm_inode_cache) { inode->i_security = NULL; return 0; } inode->i_security = kmem_cache_zalloc(lsm_inode_cache, GFP_NOFS); if (inode->i_security == NULL) return -ENOMEM; return 0; } /** * lsm_task_alloc - allocate a composite task blob * @task: the task that needs a blob * * Allocate the task blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_task_alloc(struct task_struct *task) { if (blob_sizes.lbs_task == 0) { task->security = NULL; return 0; } task->security = kzalloc(blob_sizes.lbs_task, GFP_KERNEL); if (task->security == NULL) return -ENOMEM; return 0; } /** * lsm_ipc_alloc - allocate a composite ipc blob * @kip: the ipc that needs a blob * * Allocate the ipc blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_ipc_alloc(struct kern_ipc_perm *kip) { if (blob_sizes.lbs_ipc == 0) { kip->security = NULL; return 0; } kip->security = kzalloc(blob_sizes.lbs_ipc, GFP_KERNEL); if (kip->security == NULL) return -ENOMEM; return 0; } /** * lsm_msg_msg_alloc - allocate a composite msg_msg blob * @mp: the msg_msg that needs a blob * * Allocate the ipc blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_msg_msg_alloc(struct msg_msg *mp) { if (blob_sizes.lbs_msg_msg == 0) { mp->security = NULL; return 0; } mp->security = kzalloc(blob_sizes.lbs_msg_msg, GFP_KERNEL); if (mp->security == NULL) return -ENOMEM; return 0; } /** * lsm_early_task - during initialization allocate a composite task blob * @task: the task that needs a blob * * Allocate the task blob for all the modules */ static void __init lsm_early_task(struct task_struct *task) { int rc = lsm_task_alloc(task); if (rc) panic("%s: Early task alloc failed.\n", __func__); } /** * lsm_superblock_alloc - allocate a composite superblock blob * @sb: the superblock that needs a blob * * Allocate the superblock blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_superblock_alloc(struct super_block *sb) { if (blob_sizes.lbs_superblock == 0) { sb->s_security = NULL; return 0; } sb->s_security = kzalloc(blob_sizes.lbs_superblock, GFP_KERNEL); if (sb->s_security == NULL) return -ENOMEM; return 0; } /* * The default value of the LSM hook is defined in linux/lsm_hook_defs.h and * can be accessed with: * * LSM_RET_DEFAULT(<hook_name>) * * The macros below define static constants for the default value of each * LSM hook. */ #define LSM_RET_DEFAULT(NAME) (NAME##_default) #define DECLARE_LSM_RET_DEFAULT_void(DEFAULT, NAME) #define DECLARE_LSM_RET_DEFAULT_int(DEFAULT, NAME) \ static const int __maybe_unused LSM_RET_DEFAULT(NAME) = (DEFAULT); #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ DECLARE_LSM_RET_DEFAULT_##RET(DEFAULT, NAME) #include <linux/lsm_hook_defs.h> #undef LSM_HOOK /* * Hook list operation macros. * * call_void_hook: * This is a hook that does not return a value. * * call_int_hook: * This is a hook that returns a value. */ #define call_void_hook(FUNC, ...) \ do { \ struct security_hook_list *P; \ \ hlist_for_each_entry(P, &security_hook_heads.FUNC, list) \ P->hook.FUNC(__VA_ARGS__); \ } while (0) #define call_int_hook(FUNC, IRC, ...) ({ \ int RC = IRC; \ do { \ struct security_hook_list *P; \ \ hlist_for_each_entry(P, &security_hook_heads.FUNC, list) { \ RC = P->hook.FUNC(__VA_ARGS__); \ if (RC != 0) \ break; \ } \ } while (0); \ RC; \ }) /* Security operations */ int security_binder_set_context_mgr(const struct cred *mgr) { return call_int_hook(binder_set_context_mgr, 0, mgr); } int security_binder_transaction(const struct cred *from, const struct cred *to) { return call_int_hook(binder_transaction, 0, from, to); } int security_binder_transfer_binder(const struct cred *from, const struct cred *to) { return call_int_hook(binder_transfer_binder, 0, from, to); } int security_binder_transfer_file(const struct cred *from, const struct cred *to, struct file *file) { return call_int_hook(binder_transfer_file, 0, from, to, file); } int security_ptrace_access_check(struct task_struct *child, unsigned int mode) { return call_int_hook(ptrace_access_check, 0, child, mode); } int security_ptrace_traceme(struct task_struct *parent) { return call_int_hook(ptrace_traceme, 0, parent); } int security_capget(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { return call_int_hook(capget, 0, target, effective, inheritable, permitted); } int security_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { return call_int_hook(capset, 0, new, old, effective, inheritable, permitted); } int security_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) { return call_int_hook(capable, 0, cred, ns, cap, opts); } int security_quotactl(int cmds, int type, int id, struct super_block *sb) { return call_int_hook(quotactl, 0, cmds, type, id, sb); } int security_quota_on(struct dentry *dentry) { return call_int_hook(quota_on, 0, dentry); } int security_syslog(int type) { return call_int_hook(syslog, 0, type); } int security_settime64(const struct timespec64 *ts, const struct timezone *tz) { return call_int_hook(settime, 0, ts, tz); } int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) { struct security_hook_list *hp; int cap_sys_admin = 1; int rc; /* * The module will respond with a positive value if * it thinks the __vm_enough_memory() call should be * made with the cap_sys_admin set. If all of the modules * agree that it should be set it will. If any module * thinks it should not be set it won't. */ hlist_for_each_entry(hp, &security_hook_heads.vm_enough_memory, list) { rc = hp->hook.vm_enough_memory(mm, pages); if (rc <= 0) { cap_sys_admin = 0; break; } } return __vm_enough_memory(mm, pages, cap_sys_admin); } int security_bprm_creds_for_exec(struct linux_binprm *bprm) { return call_int_hook(bprm_creds_for_exec, 0, bprm); } int security_bprm_creds_from_file(struct linux_binprm *bprm, struct file *file) { return call_int_hook(bprm_creds_from_file, 0, bprm, file); } int security_bprm_check(struct linux_binprm *bprm) { int ret; ret = call_int_hook(bprm_check_security, 0, bprm); if (ret) return ret; return ima_bprm_check(bprm); } void security_bprm_committing_creds(struct linux_binprm *bprm) { call_void_hook(bprm_committing_creds, bprm); } void security_bprm_committed_creds(struct linux_binprm *bprm) { call_void_hook(bprm_committed_creds, bprm); } /** * security_fs_context_submount() - Initialise fc->security * @fc: new filesystem context * @reference: dentry reference for submount/remount * * Fill out the ->security field for a new fs_context. * * Return: Returns 0 on success or negative error code on failure. */ int security_fs_context_submount(struct fs_context *fc, struct super_block *reference) { return call_int_hook(fs_context_submount, 0, fc, reference); } int security_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { return call_int_hook(fs_context_dup, 0, fc, src_fc); } int security_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct security_hook_list *hp; int trc; int rc = -ENOPARAM; hlist_for_each_entry(hp, &security_hook_heads.fs_context_parse_param, list) { trc = hp->hook.fs_context_parse_param(fc, param); if (trc == 0) rc = 0; else if (trc != -ENOPARAM) return trc; } return rc; } int security_sb_alloc(struct super_block *sb) { int rc = lsm_superblock_alloc(sb); if (unlikely(rc)) return rc; rc = call_int_hook(sb_alloc_security, 0, sb); if (unlikely(rc)) security_sb_free(sb); return rc; } void security_sb_delete(struct super_block *sb) { call_void_hook(sb_delete, sb); } void security_sb_free(struct super_block *sb) { call_void_hook(sb_free_security, sb); kfree(sb->s_security); sb->s_security = NULL; } void security_free_mnt_opts(void **mnt_opts) { if (!*mnt_opts) return; call_void_hook(sb_free_mnt_opts, *mnt_opts); *mnt_opts = NULL; } EXPORT_SYMBOL(security_free_mnt_opts); int security_sb_eat_lsm_opts(char *options, void **mnt_opts) { return call_int_hook(sb_eat_lsm_opts, 0, options, mnt_opts); } EXPORT_SYMBOL(security_sb_eat_lsm_opts); int security_sb_mnt_opts_compat(struct super_block *sb, void *mnt_opts) { return call_int_hook(sb_mnt_opts_compat, 0, sb, mnt_opts); } EXPORT_SYMBOL(security_sb_mnt_opts_compat); int security_sb_remount(struct super_block *sb, void *mnt_opts) { return call_int_hook(sb_remount, 0, sb, mnt_opts); } EXPORT_SYMBOL(security_sb_remount); int security_sb_kern_mount(struct super_block *sb) { return call_int_hook(sb_kern_mount, 0, sb); } int security_sb_show_options(struct seq_file *m, struct super_block *sb) { return call_int_hook(sb_show_options, 0, m, sb); } int security_sb_statfs(struct dentry *dentry) { return call_int_hook(sb_statfs, 0, dentry); } int security_sb_mount(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data) { return call_int_hook(sb_mount, 0, dev_name, path, type, flags, data); } int security_sb_umount(struct vfsmount *mnt, int flags) { return call_int_hook(sb_umount, 0, mnt, flags); } int security_sb_pivotroot(const struct path *old_path, const struct path *new_path) { return call_int_hook(sb_pivotroot, 0, old_path, new_path); } int security_sb_set_mnt_opts(struct super_block *sb, void *mnt_opts, unsigned long kern_flags, unsigned long *set_kern_flags) { return call_int_hook(sb_set_mnt_opts, mnt_opts ? -EOPNOTSUPP : 0, sb, mnt_opts, kern_flags, set_kern_flags); } EXPORT_SYMBOL(security_sb_set_mnt_opts); int security_sb_clone_mnt_opts(const struct super_block *oldsb, struct super_block *newsb, unsigned long kern_flags, unsigned long *set_kern_flags) { return call_int_hook(sb_clone_mnt_opts, 0, oldsb, newsb, kern_flags, set_kern_flags); } EXPORT_SYMBOL(security_sb_clone_mnt_opts); int security_move_mount(const struct path *from_path, const struct path *to_path) { return call_int_hook(move_mount, 0, from_path, to_path); } int security_path_notify(const struct path *path, u64 mask, unsigned int obj_type) { return call_int_hook(path_notify, 0, path, mask, obj_type); } int security_inode_alloc(struct inode *inode) { int rc = lsm_inode_alloc(inode); if (unlikely(rc)) return rc; rc = call_int_hook(inode_alloc_security, 0, inode); if (unlikely(rc)) security_inode_free(inode); return rc; } static void inode_free_by_rcu(struct rcu_head *head) { /* * The rcu head is at the start of the inode blob */ kmem_cache_free(lsm_inode_cache, head); } void security_inode_free(struct inode *inode) { integrity_inode_free(inode); call_void_hook(inode_free_security, inode); /* * The inode may still be referenced in a path walk and * a call to security_inode_permission() can be made * after inode_free_security() is called. Ideally, the VFS * wouldn't do this, but fixing that is a much harder * job. For now, simply free the i_security via RCU, and * leave the current inode->i_security pointer intact. * The inode will be freed after the RCU grace period too. */ if (inode->i_security) call_rcu((struct rcu_head *)inode->i_security, inode_free_by_rcu); } int security_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, const char **xattr_name, void **ctx, u32 *ctxlen) { struct security_hook_list *hp; int rc; /* * Only one module will provide a security context. */ hlist_for_each_entry(hp, &security_hook_heads.dentry_init_security, list) { rc = hp->hook.dentry_init_security(dentry, mode, name, xattr_name, ctx, ctxlen); if (rc != LSM_RET_DEFAULT(dentry_init_security)) return rc; } return LSM_RET_DEFAULT(dentry_init_security); } EXPORT_SYMBOL(security_dentry_init_security); int security_dentry_create_files_as(struct dentry *dentry, int mode, struct qstr *name, const struct cred *old, struct cred *new) { return call_int_hook(dentry_create_files_as, 0, dentry, mode, name, old, new); } EXPORT_SYMBOL(security_dentry_create_files_as); int security_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, const initxattrs initxattrs, void *fs_data) { struct xattr new_xattrs[MAX_LSM_EVM_XATTR + 1]; struct xattr *lsm_xattr, *evm_xattr, *xattr; int ret; if (unlikely(IS_PRIVATE(inode))) return 0; if (!initxattrs) return call_int_hook(inode_init_security, -EOPNOTSUPP, inode, dir, qstr, NULL, NULL, NULL); memset(new_xattrs, 0, sizeof(new_xattrs)); lsm_xattr = new_xattrs; ret = call_int_hook(inode_init_security, -EOPNOTSUPP, inode, dir, qstr, &lsm_xattr->name, &lsm_xattr->value, &lsm_xattr->value_len); if (ret) goto out; evm_xattr = lsm_xattr + 1; ret = evm_inode_init_security(inode, lsm_xattr, evm_xattr); if (ret) goto out; ret = initxattrs(inode, new_xattrs, fs_data); out: for (xattr = new_xattrs; xattr->value != NULL; xattr++) kfree(xattr->value); return (ret == -EOPNOTSUPP) ? 0 : ret; } EXPORT_SYMBOL(security_inode_init_security); int security_inode_init_security_anon(struct inode *inode, const struct qstr *name, const struct inode *context_inode) { return call_int_hook(inode_init_security_anon, 0, inode, name, context_inode); } int security_old_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, const char **name, void **value, size_t *len) { if (unlikely(IS_PRIVATE(inode))) return -EOPNOTSUPP; return call_int_hook(inode_init_security, -EOPNOTSUPP, inode, dir, qstr, name, value, len); } EXPORT_SYMBOL(security_old_inode_init_security); #ifdef CONFIG_SECURITY_PATH int security_path_mknod(const struct path *dir, struct dentry *dentry, umode_t mode, unsigned int dev) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_mknod, 0, dir, dentry, mode, dev); } EXPORT_SYMBOL(security_path_mknod); int security_path_mkdir(const struct path *dir, struct dentry *dentry, umode_t mode) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_mkdir, 0, dir, dentry, mode); } EXPORT_SYMBOL(security_path_mkdir); int security_path_rmdir(const struct path *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_rmdir, 0, dir, dentry); } int security_path_unlink(const struct path *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_unlink, 0, dir, dentry); } EXPORT_SYMBOL(security_path_unlink); int security_path_symlink(const struct path *dir, struct dentry *dentry, const char *old_name) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_symlink, 0, dir, dentry, old_name); } int security_path_link(struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)))) return 0; return call_int_hook(path_link, 0, old_dentry, new_dir, new_dentry); } int security_path_rename(const struct path *old_dir, struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry, unsigned int flags) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)) || (d_is_positive(new_dentry) && IS_PRIVATE(d_backing_inode(new_dentry))))) return 0; return call_int_hook(path_rename, 0, old_dir, old_dentry, new_dir, new_dentry, flags); } EXPORT_SYMBOL(security_path_rename); int security_path_truncate(const struct path *path) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(path_truncate, 0, path); } int security_path_chmod(const struct path *path, umode_t mode) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(path_chmod, 0, path, mode); } int security_path_chown(const struct path *path, kuid_t uid, kgid_t gid) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(path_chown, 0, path, uid, gid); } int security_path_chroot(const struct path *path) { return call_int_hook(path_chroot, 0, path); } #endif int security_inode_create(struct inode *dir, struct dentry *dentry, umode_t mode) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_create, 0, dir, dentry, mode); } EXPORT_SYMBOL_GPL(security_inode_create); int security_inode_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)))) return 0; return call_int_hook(inode_link, 0, old_dentry, dir, new_dentry); } int security_inode_unlink(struct inode *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_unlink, 0, dir, dentry); } int security_inode_symlink(struct inode *dir, struct dentry *dentry, const char *old_name) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_symlink, 0, dir, dentry, old_name); } int security_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_mkdir, 0, dir, dentry, mode); } EXPORT_SYMBOL_GPL(security_inode_mkdir); int security_inode_rmdir(struct inode *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_rmdir, 0, dir, dentry); } int security_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_mknod, 0, dir, dentry, mode, dev); } int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)) || (d_is_positive(new_dentry) && IS_PRIVATE(d_backing_inode(new_dentry))))) return 0; if (flags & RENAME_EXCHANGE) { int err = call_int_hook(inode_rename, 0, new_dir, new_dentry, old_dir, old_dentry); if (err) return err; } return call_int_hook(inode_rename, 0, old_dir, old_dentry, new_dir, new_dentry); } int security_inode_readlink(struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_readlink, 0, dentry); } int security_inode_follow_link(struct dentry *dentry, struct inode *inode, bool rcu) { if (unlikely(IS_PRIVATE(inode))) return 0; return call_int_hook(inode_follow_link, 0, dentry, inode, rcu); } int security_inode_permission(struct inode *inode, int mask) { if (unlikely(IS_PRIVATE(inode))) return 0; return call_int_hook(inode_permission, 0, inode, mask); } int security_inode_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, struct iattr *attr) { int ret; if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; ret = call_int_hook(inode_setattr, 0, dentry, attr); if (ret) return ret; return evm_inode_setattr(mnt_userns, dentry, attr); } EXPORT_SYMBOL_GPL(security_inode_setattr); int security_inode_getattr(const struct path *path) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(inode_getattr, 0, path); } int security_inode_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { int ret; if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; /* * SELinux and Smack integrate the cap call, * so assume that all LSMs supplying this call do so. */ ret = call_int_hook(inode_setxattr, 1, mnt_userns, dentry, name, value, size, flags); if (ret == 1) ret = cap_inode_setxattr(dentry, name, value, size, flags); if (ret) return ret; ret = ima_inode_setxattr(dentry, name, value, size); if (ret) return ret; return evm_inode_setxattr(mnt_userns, dentry, name, value, size); } void security_inode_post_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(inode_post_setxattr, dentry, name, value, size, flags); evm_inode_post_setxattr(dentry, name, value, size); } int security_inode_getxattr(struct dentry *dentry, const char *name) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_getxattr, 0, dentry, name); } int security_inode_listxattr(struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_listxattr, 0, dentry); } int security_inode_removexattr(struct user_namespace *mnt_userns, struct dentry *dentry, const char *name) { int ret; if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; /* * SELinux and Smack integrate the cap call, * so assume that all LSMs supplying this call do so. */ ret = call_int_hook(inode_removexattr, 1, mnt_userns, dentry, name); if (ret == 1) ret = cap_inode_removexattr(mnt_userns, dentry, name); if (ret) return ret; ret = ima_inode_removexattr(dentry, name); if (ret) return ret; return evm_inode_removexattr(mnt_userns, dentry, name); } int security_inode_need_killpriv(struct dentry *dentry) { return call_int_hook(inode_need_killpriv, 0, dentry); } int security_inode_killpriv(struct user_namespace *mnt_userns, struct dentry *dentry) { return call_int_hook(inode_killpriv, 0, mnt_userns, dentry); } int security_inode_getsecurity(struct user_namespace *mnt_userns, struct inode *inode, const char *name, void **buffer, bool alloc) { struct security_hook_list *hp; int rc; if (unlikely(IS_PRIVATE(inode))) return LSM_RET_DEFAULT(inode_getsecurity); /* * Only one module will provide an attribute with a given name. */ hlist_for_each_entry(hp, &security_hook_heads.inode_getsecurity, list) { rc = hp->hook.inode_getsecurity(mnt_userns, inode, name, buffer, alloc); if (rc != LSM_RET_DEFAULT(inode_getsecurity)) return rc; } return LSM_RET_DEFAULT(inode_getsecurity); } int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) { struct security_hook_list *hp; int rc; if (unlikely(IS_PRIVATE(inode))) return LSM_RET_DEFAULT(inode_setsecurity); /* * Only one module will provide an attribute with a given name. */ hlist_for_each_entry(hp, &security_hook_heads.inode_setsecurity, list) { rc = hp->hook.inode_setsecurity(inode, name, value, size, flags); if (rc != LSM_RET_DEFAULT(inode_setsecurity)) return rc; } return LSM_RET_DEFAULT(inode_setsecurity); } int security_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size) { if (unlikely(IS_PRIVATE(inode))) return 0; return call_int_hook(inode_listsecurity, 0, inode, buffer, buffer_size); } EXPORT_SYMBOL(security_inode_listsecurity); void security_inode_getsecid(struct inode *inode, u32 *secid) { call_void_hook(inode_getsecid, inode, secid); } int security_inode_copy_up(struct dentry *src, struct cred **new) { return call_int_hook(inode_copy_up, 0, src, new); } EXPORT_SYMBOL(security_inode_copy_up); int security_inode_copy_up_xattr(const char *name) { struct security_hook_list *hp; int rc; /* * The implementation can return 0 (accept the xattr), 1 (discard the * xattr), -EOPNOTSUPP if it does not know anything about the xattr or * any other error code incase of an error. */ hlist_for_each_entry(hp, &security_hook_heads.inode_copy_up_xattr, list) { rc = hp->hook.inode_copy_up_xattr(name); if (rc != LSM_RET_DEFAULT(inode_copy_up_xattr)) return rc; } return LSM_RET_DEFAULT(inode_copy_up_xattr); } EXPORT_SYMBOL(security_inode_copy_up_xattr); int security_kernfs_init_security(struct kernfs_node *kn_dir, struct kernfs_node *kn) { return call_int_hook(kernfs_init_security, 0, kn_dir, kn); } int security_file_permission(struct file *file, int mask) { int ret; ret = call_int_hook(file_permission, 0, file, mask); if (ret) return ret; return fsnotify_perm(file, mask); } int security_file_alloc(struct file *file) { int rc = lsm_file_alloc(file); if (rc) return rc; rc = call_int_hook(file_alloc_security, 0, file); if (unlikely(rc)) security_file_free(file); return rc; } void security_file_free(struct file *file) { void *blob; call_void_hook(file_free_security, file); blob = file->f_security; if (blob) { file->f_security = NULL; kmem_cache_free(lsm_file_cache, blob); } } int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return call_int_hook(file_ioctl, 0, file, cmd, arg); } EXPORT_SYMBOL_GPL(security_file_ioctl); /** * security_file_ioctl_compat() - Check if an ioctl is allowed in compat mode * @file: associated file * @cmd: ioctl cmd * @arg: ioctl arguments * * Compat version of security_file_ioctl() that correctly handles 32-bit * processes running on 64-bit kernels. * * Return: Returns 0 if permission is granted. */ int security_file_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) { return call_int_hook(file_ioctl_compat, 0, file, cmd, arg); } EXPORT_SYMBOL_GPL(security_file_ioctl_compat); static inline unsigned long mmap_prot(struct file *file, unsigned long prot) { /* * Does we have PROT_READ and does the application expect * it to imply PROT_EXEC? If not, nothing to talk about... */ if ((prot & (PROT_READ | PROT_EXEC)) != PROT_READ) return prot; if (!(current->personality & READ_IMPLIES_EXEC)) return prot; /* * if that's an anonymous mapping, let it. */ if (!file) return prot | PROT_EXEC; /* * ditto if it's not on noexec mount, except that on !MMU we need * NOMMU_MAP_EXEC (== VM_MAYEXEC) in this case */ if (!path_noexec(&file->f_path)) { #ifndef CONFIG_MMU if (file->f_op->mmap_capabilities) { unsigned caps = file->f_op->mmap_capabilities(file); if (!(caps & NOMMU_MAP_EXEC)) return prot; } #endif return prot | PROT_EXEC; } /* anything on noexec mount won't get PROT_EXEC */ return prot; } int security_mmap_file(struct file *file, unsigned long prot, unsigned long flags) { unsigned long prot_adj = mmap_prot(file, prot); int ret; ret = call_int_hook(mmap_file, 0, file, prot, prot_adj, flags); if (ret) return ret; return ima_file_mmap(file, prot, prot_adj, flags); } int security_mmap_addr(unsigned long addr) { return call_int_hook(mmap_addr, 0, addr); } int security_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) { int ret; ret = call_int_hook(file_mprotect, 0, vma, reqprot, prot); if (ret) return ret; return ima_file_mprotect(vma, prot); } int security_file_lock(struct file *file, unsigned int cmd) { return call_int_hook(file_lock, 0, file, cmd); } int security_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg) { return call_int_hook(file_fcntl, 0, file, cmd, arg); } void security_file_set_fowner(struct file *file) { call_void_hook(file_set_fowner, file); } int security_file_send_sigiotask(struct task_struct *tsk, struct fown_struct *fown, int sig) { return call_int_hook(file_send_sigiotask, 0, tsk, fown, sig); } int security_file_receive(struct file *file) { return call_int_hook(file_receive, 0, file); } int security_file_open(struct file *file) { int ret; ret = call_int_hook(file_open, 0, file); if (ret) return ret; return fsnotify_perm(file, MAY_OPEN); } int security_task_alloc(struct task_struct *task, unsigned long clone_flags) { int rc = lsm_task_alloc(task); if (rc) return rc; rc = call_int_hook(task_alloc, 0, task, clone_flags); if (unlikely(rc)) security_task_free(task); return rc; } void security_task_free(struct task_struct *task) { call_void_hook(task_free, task); kfree(task->security); task->security = NULL; } int security_cred_alloc_blank(struct cred *cred, gfp_t gfp) { int rc = lsm_cred_alloc(cred, gfp); if (rc) return rc; rc = call_int_hook(cred_alloc_blank, 0, cred, gfp); if (unlikely(rc)) security_cred_free(cred); return rc; } void security_cred_free(struct cred *cred) { /* * There is a failure case in prepare_creds() that * may result in a call here with ->security being NULL. */ if (unlikely(cred->security == NULL)) return; call_void_hook(cred_free, cred); kfree(cred->security); cred->security = NULL; } int security_prepare_creds(struct cred *new, const struct cred *old, gfp_t gfp) { int rc = lsm_cred_alloc(new, gfp); if (rc) return rc; rc = call_int_hook(cred_prepare, 0, new, old, gfp); if (unlikely(rc)) security_cred_free(new); return rc; } void security_transfer_creds(struct cred *new, const struct cred *old) { call_void_hook(cred_transfer, new, old); } void security_cred_getsecid(const struct cred *c, u32 *secid) { *secid = 0; call_void_hook(cred_getsecid, c, secid); } EXPORT_SYMBOL(security_cred_getsecid); int security_kernel_act_as(struct cred *new, u32 secid) { return call_int_hook(kernel_act_as, 0, new, secid); } int security_kernel_create_files_as(struct cred *new, struct inode *inode) { return call_int_hook(kernel_create_files_as, 0, new, inode); } int security_kernel_module_request(char *kmod_name) { int ret; ret = call_int_hook(kernel_module_request, 0, kmod_name); if (ret) return ret; return integrity_kernel_module_request(kmod_name); } int security_kernel_read_file(struct file *file, enum kernel_read_file_id id, bool contents) { int ret; ret = call_int_hook(kernel_read_file, 0, file, id, contents); if (ret) return ret; return ima_read_file(file, id, contents); } EXPORT_SYMBOL_GPL(security_kernel_read_file); int security_kernel_post_read_file(struct file *file, char *buf, loff_t size, enum kernel_read_file_id id) { int ret; ret = call_int_hook(kernel_post_read_file, 0, file, buf, size, id); if (ret) return ret; return ima_post_read_file(file, buf, size, id); } EXPORT_SYMBOL_GPL(security_kernel_post_read_file); int security_kernel_load_data(enum kernel_load_data_id id, bool contents) { int ret; ret = call_int_hook(kernel_load_data, 0, id, contents); if (ret) return ret; return ima_load_data(id, contents); } EXPORT_SYMBOL_GPL(security_kernel_load_data); int security_kernel_post_load_data(char *buf, loff_t size, enum kernel_load_data_id id, char *description) { int ret; ret = call_int_hook(kernel_post_load_data, 0, buf, size, id, description); if (ret) return ret; return ima_post_load_data(buf, size, id, description); } EXPORT_SYMBOL_GPL(security_kernel_post_load_data); int security_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { return call_int_hook(task_fix_setuid, 0, new, old, flags); } int security_task_fix_setgid(struct cred *new, const struct cred *old, int flags) { return call_int_hook(task_fix_setgid, 0, new, old, flags); } int security_task_fix_setgroups(struct cred *new, const struct cred *old) { return call_int_hook(task_fix_setgroups, 0, new, old); } int security_task_setpgid(struct task_struct *p, pid_t pgid) { return call_int_hook(task_setpgid, 0, p, pgid); } int security_task_getpgid(struct task_struct *p) { return call_int_hook(task_getpgid, 0, p); } int security_task_getsid(struct task_struct *p) { return call_int_hook(task_getsid, 0, p); } void security_current_getsecid_subj(u32 *secid) { *secid = 0; call_void_hook(current_getsecid_subj, secid); } EXPORT_SYMBOL(security_current_getsecid_subj); void security_task_getsecid_obj(struct task_struct *p, u32 *secid) { *secid = 0; call_void_hook(task_getsecid_obj, p, secid); } EXPORT_SYMBOL(security_task_getsecid_obj); int security_task_setnice(struct task_struct *p, int nice) { return call_int_hook(task_setnice, 0, p, nice); } int security_task_setioprio(struct task_struct *p, int ioprio) { return call_int_hook(task_setioprio, 0, p, ioprio); } int security_task_getioprio(struct task_struct *p) { return call_int_hook(task_getioprio, 0, p); } int security_task_prlimit(const struct cred *cred, const struct cred *tcred, unsigned int flags) { return call_int_hook(task_prlimit, 0, cred, tcred, flags); } int security_task_setrlimit(struct task_struct *p, unsigned int resource, struct rlimit *new_rlim) { return call_int_hook(task_setrlimit, 0, p, resource, new_rlim); } int security_task_setscheduler(struct task_struct *p) { return call_int_hook(task_setscheduler, 0, p); } int security_task_getscheduler(struct task_struct *p) { return call_int_hook(task_getscheduler, 0, p); } int security_task_movememory(struct task_struct *p) { return call_int_hook(task_movememory, 0, p); } int security_task_kill(struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred) { return call_int_hook(task_kill, 0, p, info, sig, cred); } int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { int thisrc; int rc = LSM_RET_DEFAULT(task_prctl); struct security_hook_list *hp; hlist_for_each_entry(hp, &security_hook_heads.task_prctl, list) { thisrc = hp->hook.task_prctl(option, arg2, arg3, arg4, arg5); if (thisrc != LSM_RET_DEFAULT(task_prctl)) { rc = thisrc; if (thisrc != 0) break; } } return rc; } void security_task_to_inode(struct task_struct *p, struct inode *inode) { call_void_hook(task_to_inode, p, inode); } int security_create_user_ns(const struct cred *cred) { return call_int_hook(userns_create, 0, cred); } int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag) { return call_int_hook(ipc_permission, 0, ipcp, flag); } void security_ipc_getsecid(struct kern_ipc_perm *ipcp, u32 *secid) { *secid = 0; call_void_hook(ipc_getsecid, ipcp, secid); } int security_msg_msg_alloc(struct msg_msg *msg) { int rc = lsm_msg_msg_alloc(msg); if (unlikely(rc)) return rc; rc = call_int_hook(msg_msg_alloc_security, 0, msg); if (unlikely(rc)) security_msg_msg_free(msg); return rc; } void security_msg_msg_free(struct msg_msg *msg) { call_void_hook(msg_msg_free_security, msg); kfree(msg->security); msg->security = NULL; } int security_msg_queue_alloc(struct kern_ipc_perm *msq) { int rc = lsm_ipc_alloc(msq); if (unlikely(rc)) return rc; rc = call_int_hook(msg_queue_alloc_security, 0, msq); if (unlikely(rc)) security_msg_queue_free(msq); return rc; } void security_msg_queue_free(struct kern_ipc_perm *msq) { call_void_hook(msg_queue_free_security, msq); kfree(msq->security); msq->security = NULL; } int security_msg_queue_associate(struct kern_ipc_perm *msq, int msqflg) { return call_int_hook(msg_queue_associate, 0, msq, msqflg); } int security_msg_queue_msgctl(struct kern_ipc_perm *msq, int cmd) { return call_int_hook(msg_queue_msgctl, 0, msq, cmd); } int security_msg_queue_msgsnd(struct kern_ipc_perm *msq, struct msg_msg *msg, int msqflg) { return call_int_hook(msg_queue_msgsnd, 0, msq, msg, msqflg); } int security_msg_queue_msgrcv(struct kern_ipc_perm *msq, struct msg_msg *msg, struct task_struct *target, long type, int mode) { return call_int_hook(msg_queue_msgrcv, 0, msq, msg, target, type, mode); } int security_shm_alloc(struct kern_ipc_perm *shp) { int rc = lsm_ipc_alloc(shp); if (unlikely(rc)) return rc; rc = call_int_hook(shm_alloc_security, 0, shp); if (unlikely(rc)) security_shm_free(shp); return rc; } void security_shm_free(struct kern_ipc_perm *shp) { call_void_hook(shm_free_security, shp); kfree(shp->security); shp->security = NULL; } int security_shm_associate(struct kern_ipc_perm *shp, int shmflg) { return call_int_hook(shm_associate, 0, shp, shmflg); } int security_shm_shmctl(struct kern_ipc_perm *shp, int cmd) { return call_int_hook(shm_shmctl, 0, shp, cmd); } int security_shm_shmat(struct kern_ipc_perm *shp, char __user *shmaddr, int shmflg) { return call_int_hook(shm_shmat, 0, shp, shmaddr, shmflg); } int security_sem_alloc(struct kern_ipc_perm *sma) { int rc = lsm_ipc_alloc(sma); if (unlikely(rc)) return rc; rc = call_int_hook(sem_alloc_security, 0, sma); if (unlikely(rc)) security_sem_free(sma); return rc; } void security_sem_free(struct kern_ipc_perm *sma) { call_void_hook(sem_free_security, sma); kfree(sma->security); sma->security = NULL; } int security_sem_associate(struct kern_ipc_perm *sma, int semflg) { return call_int_hook(sem_associate, 0, sma, semflg); } int security_sem_semctl(struct kern_ipc_perm *sma, int cmd) { return call_int_hook(sem_semctl, 0, sma, cmd); } int security_sem_semop(struct kern_ipc_perm *sma, struct sembuf *sops, unsigned nsops, int alter) { return call_int_hook(sem_semop, 0, sma, sops, nsops, alter); } void security_d_instantiate(struct dentry *dentry, struct inode *inode) { if (unlikely(inode && IS_PRIVATE(inode))) return; call_void_hook(d_instantiate, dentry, inode); } EXPORT_SYMBOL(security_d_instantiate); int security_getprocattr(struct task_struct *p, const char *lsm, const char *name, char **value) { struct security_hook_list *hp; hlist_for_each_entry(hp, &security_hook_heads.getprocattr, list) { if (lsm != NULL && strcmp(lsm, hp->lsm)) continue; return hp->hook.getprocattr(p, name, value); } return LSM_RET_DEFAULT(getprocattr); } int security_setprocattr(const char *lsm, const char *name, void *value, size_t size) { struct security_hook_list *hp; hlist_for_each_entry(hp, &security_hook_heads.setprocattr, list) { if (lsm != NULL && strcmp(lsm, hp->lsm)) continue; return hp->hook.setprocattr(name, value, size); } return LSM_RET_DEFAULT(setprocattr); } int security_netlink_send(struct sock *sk, struct sk_buff *skb) { return call_int_hook(netlink_send, 0, sk, skb); } int security_ismaclabel(const char *name) { return call_int_hook(ismaclabel, 0, name); } EXPORT_SYMBOL(security_ismaclabel); int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) { struct security_hook_list *hp; int rc; /* * Currently, only one LSM can implement secid_to_secctx (i.e this * LSM hook is not "stackable"). */ hlist_for_each_entry(hp, &security_hook_heads.secid_to_secctx, list) { rc = hp->hook.secid_to_secctx(secid, secdata, seclen); if (rc != LSM_RET_DEFAULT(secid_to_secctx)) return rc; } return LSM_RET_DEFAULT(secid_to_secctx); } EXPORT_SYMBOL(security_secid_to_secctx); int security_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) { *secid = 0; return call_int_hook(secctx_to_secid, 0, secdata, seclen, secid); } EXPORT_SYMBOL(security_secctx_to_secid); void security_release_secctx(char *secdata, u32 seclen) { call_void_hook(release_secctx, secdata, seclen); } EXPORT_SYMBOL(security_release_secctx); void security_inode_invalidate_secctx(struct inode *inode) { call_void_hook(inode_invalidate_secctx, inode); } EXPORT_SYMBOL(security_inode_invalidate_secctx); int security_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen) { return call_int_hook(inode_notifysecctx, 0, inode, ctx, ctxlen); } EXPORT_SYMBOL(security_inode_notifysecctx); int security_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen) { return call_int_hook(inode_setsecctx, 0, dentry, ctx, ctxlen); } EXPORT_SYMBOL(security_inode_setsecctx); int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) { struct security_hook_list *hp; int rc; /* * Only one module will provide a security context. */ hlist_for_each_entry(hp, &security_hook_heads.inode_getsecctx, list) { rc = hp->hook.inode_getsecctx(inode, ctx, ctxlen); if (rc != LSM_RET_DEFAULT(inode_getsecctx)) return rc; } return LSM_RET_DEFAULT(inode_getsecctx); } EXPORT_SYMBOL(security_inode_getsecctx); #ifdef CONFIG_WATCH_QUEUE int security_post_notification(const struct cred *w_cred, const struct cred *cred, struct watch_notification *n) { return call_int_hook(post_notification, 0, w_cred, cred, n); } #endif /* CONFIG_WATCH_QUEUE */ #ifdef CONFIG_KEY_NOTIFICATIONS int security_watch_key(struct key *key) { return call_int_hook(watch_key, 0, key); } #endif #ifdef CONFIG_SECURITY_NETWORK int security_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk) { return call_int_hook(unix_stream_connect, 0, sock, other, newsk); } EXPORT_SYMBOL(security_unix_stream_connect); int security_unix_may_send(struct socket *sock, struct socket *other) { return call_int_hook(unix_may_send, 0, sock, other); } EXPORT_SYMBOL(security_unix_may_send); int security_socket_create(int family, int type, int protocol, int kern) { return call_int_hook(socket_create, 0, family, type, protocol, kern); } int security_socket_post_create(struct socket *sock, int family, int type, int protocol, int kern) { return call_int_hook(socket_post_create, 0, sock, family, type, protocol, kern); } int security_socket_socketpair(struct socket *socka, struct socket *sockb) { return call_int_hook(socket_socketpair, 0, socka, sockb); } EXPORT_SYMBOL(security_socket_socketpair); int security_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen) { return call_int_hook(socket_bind, 0, sock, address, addrlen); } int security_socket_connect(struct socket *sock, struct sockaddr *address, int addrlen) { return call_int_hook(socket_connect, 0, sock, address, addrlen); } int security_socket_listen(struct socket *sock, int backlog) { return call_int_hook(socket_listen, 0, sock, backlog); } int security_socket_accept(struct socket *sock, struct socket *newsock) { return call_int_hook(socket_accept, 0, sock, newsock); } int security_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size) { return call_int_hook(socket_sendmsg, 0, sock, msg, size); } int security_socket_recvmsg(struct socket *sock, struct msghdr *msg, int size, int flags) { return call_int_hook(socket_recvmsg, 0, sock, msg, size, flags); } int security_socket_getsockname(struct socket *sock) { return call_int_hook(socket_getsockname, 0, sock); } int security_socket_getpeername(struct socket *sock) { return call_int_hook(socket_getpeername, 0, sock); } int security_socket_getsockopt(struct socket *sock, int level, int optname) { return call_int_hook(socket_getsockopt, 0, sock, level, optname); } int security_socket_setsockopt(struct socket *sock, int level, int optname) { return call_int_hook(socket_setsockopt, 0, sock, level, optname); } int security_socket_shutdown(struct socket *sock, int how) { return call_int_hook(socket_shutdown, 0, sock, how); } int security_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) { return call_int_hook(socket_sock_rcv_skb, 0, sk, skb); } EXPORT_SYMBOL(security_sock_rcv_skb); int security_socket_getpeersec_stream(struct socket *sock, char __user *optval, int __user *optlen, unsigned len) { return call_int_hook(socket_getpeersec_stream, -ENOPROTOOPT, sock, optval, optlen, len); } int security_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid) { return call_int_hook(socket_getpeersec_dgram, -ENOPROTOOPT, sock, skb, secid); } EXPORT_SYMBOL(security_socket_getpeersec_dgram); int security_sk_alloc(struct sock *sk, int family, gfp_t priority) { return call_int_hook(sk_alloc_security, 0, sk, family, priority); } void security_sk_free(struct sock *sk) { call_void_hook(sk_free_security, sk); } void security_sk_clone(const struct sock *sk, struct sock *newsk) { call_void_hook(sk_clone_security, sk, newsk); } EXPORT_SYMBOL(security_sk_clone); void security_sk_classify_flow(struct sock *sk, struct flowi_common *flic) { call_void_hook(sk_getsecid, sk, &flic->flowic_secid); } EXPORT_SYMBOL(security_sk_classify_flow); void security_req_classify_flow(const struct request_sock *req, struct flowi_common *flic) { call_void_hook(req_classify_flow, req, flic); } EXPORT_SYMBOL(security_req_classify_flow); void security_sock_graft(struct sock *sk, struct socket *parent) { call_void_hook(sock_graft, sk, parent); } EXPORT_SYMBOL(security_sock_graft); int security_inet_conn_request(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { return call_int_hook(inet_conn_request, 0, sk, skb, req); } EXPORT_SYMBOL(security_inet_conn_request); void security_inet_csk_clone(struct sock *newsk, const struct request_sock *req) { call_void_hook(inet_csk_clone, newsk, req); } void security_inet_conn_established(struct sock *sk, struct sk_buff *skb) { call_void_hook(inet_conn_established, sk, skb); } EXPORT_SYMBOL(security_inet_conn_established); int security_secmark_relabel_packet(u32 secid) { return call_int_hook(secmark_relabel_packet, 0, secid); } EXPORT_SYMBOL(security_secmark_relabel_packet); void security_secmark_refcount_inc(void) { call_void_hook(secmark_refcount_inc); } EXPORT_SYMBOL(security_secmark_refcount_inc); void security_secmark_refcount_dec(void) { call_void_hook(secmark_refcount_dec); } EXPORT_SYMBOL(security_secmark_refcount_dec); int security_tun_dev_alloc_security(void **security) { return call_int_hook(tun_dev_alloc_security, 0, security); } EXPORT_SYMBOL(security_tun_dev_alloc_security); void security_tun_dev_free_security(void *security) { call_void_hook(tun_dev_free_security, security); } EXPORT_SYMBOL(security_tun_dev_free_security); int security_tun_dev_create(void) { return call_int_hook(tun_dev_create, 0); } EXPORT_SYMBOL(security_tun_dev_create); int security_tun_dev_attach_queue(void *security) { return call_int_hook(tun_dev_attach_queue, 0, security); } EXPORT_SYMBOL(security_tun_dev_attach_queue); int security_tun_dev_attach(struct sock *sk, void *security) { return call_int_hook(tun_dev_attach, 0, sk, security); } EXPORT_SYMBOL(security_tun_dev_attach); int security_tun_dev_open(void *security) { return call_int_hook(tun_dev_open, 0, security); } EXPORT_SYMBOL(security_tun_dev_open); int security_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb) { return call_int_hook(sctp_assoc_request, 0, asoc, skb); } EXPORT_SYMBOL(security_sctp_assoc_request); int security_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen) { return call_int_hook(sctp_bind_connect, 0, sk, optname, address, addrlen); } EXPORT_SYMBOL(security_sctp_bind_connect); void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk) { call_void_hook(sctp_sk_clone, asoc, sk, newsk); } EXPORT_SYMBOL(security_sctp_sk_clone); int security_sctp_assoc_established(struct sctp_association *asoc, struct sk_buff *skb) { return call_int_hook(sctp_assoc_established, 0, asoc, skb); } EXPORT_SYMBOL(security_sctp_assoc_established); #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND int security_ib_pkey_access(void *sec, u64 subnet_prefix, u16 pkey) { return call_int_hook(ib_pkey_access, 0, sec, subnet_prefix, pkey); } EXPORT_SYMBOL(security_ib_pkey_access); int security_ib_endport_manage_subnet(void *sec, const char *dev_name, u8 port_num) { return call_int_hook(ib_endport_manage_subnet, 0, sec, dev_name, port_num); } EXPORT_SYMBOL(security_ib_endport_manage_subnet); int security_ib_alloc_security(void **sec) { return call_int_hook(ib_alloc_security, 0, sec); } EXPORT_SYMBOL(security_ib_alloc_security); void security_ib_free_security(void *sec) { call_void_hook(ib_free_security, sec); } EXPORT_SYMBOL(security_ib_free_security); #endif /* CONFIG_SECURITY_INFINIBAND */ #ifdef CONFIG_SECURITY_NETWORK_XFRM int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *sec_ctx, gfp_t gfp) { return call_int_hook(xfrm_policy_alloc_security, 0, ctxp, sec_ctx, gfp); } EXPORT_SYMBOL(security_xfrm_policy_alloc); int security_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx, struct xfrm_sec_ctx **new_ctxp) { return call_int_hook(xfrm_policy_clone_security, 0, old_ctx, new_ctxp); } void security_xfrm_policy_free(struct xfrm_sec_ctx *ctx) { call_void_hook(xfrm_policy_free_security, ctx); } EXPORT_SYMBOL(security_xfrm_policy_free); int security_xfrm_policy_delete(struct xfrm_sec_ctx *ctx) { return call_int_hook(xfrm_policy_delete_security, 0, ctx); } int security_xfrm_state_alloc(struct xfrm_state *x, struct xfrm_user_sec_ctx *sec_ctx) { return call_int_hook(xfrm_state_alloc, 0, x, sec_ctx); } EXPORT_SYMBOL(security_xfrm_state_alloc); int security_xfrm_state_alloc_acquire(struct xfrm_state *x, struct xfrm_sec_ctx *polsec, u32 secid) { return call_int_hook(xfrm_state_alloc_acquire, 0, x, polsec, secid); } int security_xfrm_state_delete(struct xfrm_state *x) { return call_int_hook(xfrm_state_delete_security, 0, x); } EXPORT_SYMBOL(security_xfrm_state_delete); void security_xfrm_state_free(struct xfrm_state *x) { call_void_hook(xfrm_state_free_security, x); } int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid) { return call_int_hook(xfrm_policy_lookup, 0, ctx, fl_secid); } int security_xfrm_state_pol_flow_match(struct xfrm_state *x, struct xfrm_policy *xp, const struct flowi_common *flic) { struct security_hook_list *hp; int rc = LSM_RET_DEFAULT(xfrm_state_pol_flow_match); /* * Since this function is expected to return 0 or 1, the judgment * becomes difficult if multiple LSMs supply this call. Fortunately, * we can use the first LSM's judgment because currently only SELinux * supplies this call. * * For speed optimization, we explicitly break the loop rather than * using the macro */ hlist_for_each_entry(hp, &security_hook_heads.xfrm_state_pol_flow_match, list) { rc = hp->hook.xfrm_state_pol_flow_match(x, xp, flic); break; } return rc; } int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid) { return call_int_hook(xfrm_decode_session, 0, skb, secid, 1); } void security_skb_classify_flow(struct sk_buff *skb, struct flowi_common *flic) { int rc = call_int_hook(xfrm_decode_session, 0, skb, &flic->flowic_secid, 0); BUG_ON(rc); } EXPORT_SYMBOL(security_skb_classify_flow); #endif /* CONFIG_SECURITY_NETWORK_XFRM */ #ifdef CONFIG_KEYS int security_key_alloc(struct key *key, const struct cred *cred, unsigned long flags) { return call_int_hook(key_alloc, 0, key, cred, flags); } void security_key_free(struct key *key) { call_void_hook(key_free, key); } int security_key_permission(key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) { return call_int_hook(key_permission, 0, key_ref, cred, need_perm); } int security_key_getsecurity(struct key *key, char **_buffer) { *_buffer = NULL; return call_int_hook(key_getsecurity, 0, key, _buffer); } #endif /* CONFIG_KEYS */ #ifdef CONFIG_AUDIT int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule, gfp_t gfp) { return call_int_hook(audit_rule_init, 0, field, op, rulestr, lsmrule, gfp); } int security_audit_rule_known(struct audit_krule *krule) { return call_int_hook(audit_rule_known, 0, krule); } void security_audit_rule_free(void *lsmrule) { call_void_hook(audit_rule_free, lsmrule); } int security_audit_rule_match(u32 secid, u32 field, u32 op, void *lsmrule) { return call_int_hook(audit_rule_match, 0, secid, field, op, lsmrule); } #endif /* CONFIG_AUDIT */ #ifdef CONFIG_BPF_SYSCALL int security_bpf(int cmd, union bpf_attr *attr, unsigned int size) { return call_int_hook(bpf, 0, cmd, attr, size); } int security_bpf_map(struct bpf_map *map, fmode_t fmode) { return call_int_hook(bpf_map, 0, map, fmode); } int security_bpf_prog(struct bpf_prog *prog) { return call_int_hook(bpf_prog, 0, prog); } int security_bpf_map_alloc(struct bpf_map *map) { return call_int_hook(bpf_map_alloc_security, 0, map); } int security_bpf_prog_alloc(struct bpf_prog_aux *aux) { return call_int_hook(bpf_prog_alloc_security, 0, aux); } void security_bpf_map_free(struct bpf_map *map) { call_void_hook(bpf_map_free_security, map); } void security_bpf_prog_free(struct bpf_prog_aux *aux) { call_void_hook(bpf_prog_free_security, aux); } #endif /* CONFIG_BPF_SYSCALL */ int security_locked_down(enum lockdown_reason what) { return call_int_hook(locked_down, 0, what); } EXPORT_SYMBOL(security_locked_down); #ifdef CONFIG_PERF_EVENTS int security_perf_event_open(struct perf_event_attr *attr, int type) { return call_int_hook(perf_event_open, 0, attr, type); } int security_perf_event_alloc(struct perf_event *event) { return call_int_hook(perf_event_alloc, 0, event); } void security_perf_event_free(struct perf_event *event) { call_void_hook(perf_event_free, event); } int security_perf_event_read(struct perf_event *event) { return call_int_hook(perf_event_read, 0, event); } int security_perf_event_write(struct perf_event *event) { return call_int_hook(perf_event_write, 0, event); } #endif /* CONFIG_PERF_EVENTS */ #ifdef CONFIG_IO_URING int security_uring_override_creds(const struct cred *new) { return call_int_hook(uring_override_creds, 0, new); } int security_uring_sqpoll(void) { return call_int_hook(uring_sqpoll, 0); } int security_uring_cmd(struct io_uring_cmd *ioucmd) { return call_int_hook(uring_cmd, 0, ioucmd); } #endif /* CONFIG_IO_URING */ |
| 3688 690 8 3 5280 5288 1104 1100 698 5 8 8 43 32 11 147 726 3096 3096 2847 354 2821 3093 3095 3093 232 3095 3095 3096 929 842 836 25 841 839 13 839 844 3 842 842 726 656 726 112 724 653 726 2 2608 2604 145 723 2 2 2 3 3 2 1 2 2 2 739 810 724 724 184 725 726 726 223 726 611 112 726 726 725 16 725 19 726 5 279 14 724 34 725 279 11 280 30 279 22 205 155 204 160 280 33 280 33 280 31 279 30 723 145 47 145 145 66 99 55 1 98 114 722 5 726 723 222 723 724 726 2135 2138 1976 163 2605 753 163 163 163 163 147 1 147 147 5013 5010 126 5018 5013 1900 4876 1976 1976 1977 1978 1 1 1977 1975 1054 1977 1978 3900 629 4877 180 1050 96 954 1054 1201 1039 668 3144 2155 2156 1 146 8 16 20 306 826 225 632 3190 3189 3183 3190 522 589 272 213 447 649 334 768 4789 4789 5071 5072 8 8 1 5070 5074 5073 5079 385 1 197 5426 5421 3 5426 5 5421 3 4 3 1 20 2 7 11 1 29 9 11 9 9 3 8 8 3666 1 5425 5422 388 30 395 5071 398 5411 1 3629 68 5343 4141 5211 25 1955 5402 5231 268 5232 371 4912 4912 1710 733 1276 1499 3159 4070 3377 16 1599 1593 1645 2412 4 594 3670 2058 48 12 3611 808 750 4864 887 5060 5062 6 5063 4975 72 2909 1179 4882 14 5000 4660 3770 3798 764 2596 186 186 1 348 2469 138 2552 1682 8 2389 569 281 286 393 1012 210 118 420 385 60 261 1 232 232 679 570 417 386 274 274 59 224 225 224 225 201 19 209 1716 1716 1716 1548 1715 1027 120 761 2661 2662 2663 2662 432 2598 2596 2661 132 2662 2470 138 2599 2599 2509 2598 1054 2597 223 752 752 749 275 751 751 4 34 7 132 640 112 313 751 1304 2512 42 4 18 3 224 4286 1510 299 1348 1441 1510 1508 299 2605 2603 2604 2134 2603 2604 1154 2058 1022 47 1060 8 1660 235 493 1854 3 175 1631 351 703 1195 1439 466 1408 1721 1720 8 8 5 3 3 8 8 8 8 8 8 8 75 75 61 14 61 61 14 75 560 169 72 240 89 150 51 42 10 200 240 241 6 244 88 76 12 88 18 75 4448 2 2 1 1 559 560 559 560 2 2605 2604 2605 2605 8 35 3 127 127 18 6 6 5 92 91 92 92 12 80 3283 3 1 3280 84 84 84 7 76 77 77 34 33 36 36 1 1 6 1470 511 1 983 352 980 2 29 29 29 1500 4288 594 737 148 148 150 150 149 149 30 6 1 1865 2568 3 3782 116 36 3784 2605 2602 2146 2602 3691 13 3691 3691 213 213 212 2 3674 3673 198 3677 3675 3691 3692 2 11 2 8 9 2 1 1 274 729 916 201 815 474 599 2 2 2 1 1 31 1 2 16 28 6 25 17 8 16 1 2 10 2 3 2606 561 2605 2608 2606 2607 1 8 2608 2601 11 3 3781 3783 1061 4 9 1 10 4 6 2 2 1 6 5 1 1468 2 513 94 730 17 243 1 9 2605 559 2604 35 1 14 15 28 30 9 2 6 1 1 7 22 10 6 31 16 11 2 1 1 3339 914 156 1 156 2 1 102 2 49 151 151 1 1 3 84 49 15 64 85 60 1713 1714 1712 2 6 1704 2 1336 442 1335 1 1321 1310 17 890 61 459 1 480 1 1 1321 1334 1725 1726 17 25 25 24 2 1712 15 928 1 828 131 3 10 911 2 2 2 1 1 1 1 1 1 156 1 1 59 2515 2512 100 2430 96 37 2431 2431 2428 1717 1 1865 3262 3035 3 30 1706 2528 19 2516 215 2516 2508 6 2516 2432 2425 1 1 135 135 2428 137 848 1276 644 210 1 1 1 930 424 544 3 158 2 37 2 1 1 19 19 1 16 2 3094 2221 809 61 13 293 1 4 5 15 101 18 9 3 8 13 1 145 60 1011 60 13 296 1 5 34 14 35 178 92 3260 3264 3264 3263 3263 3260 15 3265 3265 3265 284 284 284 60 60 20 135 135 135 301 301 302 302 302 301 300 302 302 116 185 302 302 302 280 281 1 280 279 279 114 166 280 279 3095 732 2582 3107 848 109 951 10 3101 3103 3060 4 5 55 1 4035 4035 4032 3970 11 45 1 44 5 5 1 4 3365 3360 1 101 3266 26 3262 4 3260 3265 3157 3265 1728 3107 4 3101 3102 3099 1 2 2 3098 135 135 135 3023 60 16 45 2 6 45 2585 194 460 2 1 158 60 2748 605 3066 163 32 3059 65 65 5 2872 284 7 7 1 6 6 2457 2 13 1 2455 1 2748 766 2453 2454 2454 5076 2452 2453 2466 2469 2462 121 1 9 2456 2 3 3 3 2452 2 100 2409 100 54 45 1 1 28 69 28 7 21 14 2453 117 586 319 473 148 558 388 403 151 230 201 154 24 274 201 171 203 84 2 9 159 37 5 83 14 79 5 13 49 1 7 48 10 8 8 10 101 80 13 13 81 18 116 52 112 112 116 116 116 23 23 23 8 8 8 64 64 17 17 921 633 101 610 32 92 40 614 766 643 643 281 281 224 224 92 92 54 54 17 17 3 13 115 6 23 8 11 64 17 126 911 637 2857 2854 2466 926 1 6 8 120 287 2 899 2459 287 922 3500 27 1 1 18 17 2 41 2 2845 3142 3 2631 384 61 213 2860 303 2 400 2843 5 2863 19 1 169 228 3 60 28 21 48 85 56 114 16 122 126 24 223 51 106 19 43 46 79 14 13 6 27 4 14 10 13 160 33 1 45 4 176 44 318 36 12 9 32 138 90 35 4 165 229 43 1492 717 7 20 756 836 69 35 33 40 30 2 14 11 667 616 86 117 114 23 9 3 6 29 447 447 523 523 89 81 8 148 148 147 148 148 148 148 147 148 148 1076 969 273 42 25 9 33 12 7 2 13 151 5 8 6 13 17 6 18 14 10 4 11 10 20 5 24 78 3 5 4 2 3 3 4 355 355 355 1582 4 3 1 799 1417 2 1419 725 230 486 348 413 60 69 1111 40 1001 888 371 1014 1111 642 528 115 712 649 64 1200 497 82 184 155 123 156 111 579 654 727 354 945 776 148 1073 60 1034 166 3739 1 2 3 1 1875 1875 258 43 44 44 1 4 1 2 1 1 5 34 3963 3962 3959 9 3955 3954 2258 95 79 16 109 4 1628 67 4 87 8 43 547 3 3899 5079 5085 1959 1954 5082 725 1503 3547 3542 3455 371 3753 3 5006 5046 3538 2 3547 186 43 186 1732 1730 5078 5085 5087 5023 4 5083 4 5212 373 1 37 1 1 2 11 9 1 2 7 7 7 3644 3 3 6 1 2 20 1 32 31 4 6 25 1 1 10 11 1 2 1 1 57 5185 5 1 52 7 43 16 379 218 335 25 70 12 70 18 220 65 65 31 605 605 548 605 248 368 488 604 605 3897 3897 684 40 84 603 605 606 604 192 520 3 109 95 273 356 199 5 19 43 34 24 60 59 52 595 357 247 235 234 1 230 4 177 36 193 1 416 595 1 604 606 593 607 579 71 579 578 579 333 510 578 395 579 578 578 579 409 358 67 426 579 361 30 87 78 54 132 599 597 5025 3896 2146 3897 3899 3898 86 599 596 599 2 565 596 431 579 579 643 661 677 231 397 701 724 725 3798 1716 1714 1715 1715 109 1715 1716 1714 1714 1 567 5074 4991 5076 506 31 65 189 5075 106 4425 725 725 5073 5073 5074 4791 3501 2857 4 3 425 1235 303 157 21 117 1 3 2 142 2229 270 1 2 1 592 3452 1 2 3450 302 7 3363 3451 1 1 206 42 2 10 3962 3900 3901 1584 43 44 3744 3734 7 1 3 2 2 1896 1895 1896 1895 1896 1848 49 5158 5149 5161 3 3 1 3815 7 3 1954 1816 2 4 1940 10 99 1761 264 1885 195 94 102 1887 1887 1887 5093 15 1627 1627 1627 808 340 610 610 610 610 807 2 807 342 608 808 610 807 188 244 243 57 244 1 1 244 244 244 242 244 243 244 242 3635 3676 3679 3679 139 1062 141 3677 3677 3677 141 3679 3677 242 3670 3670 3627 44 43 5 929 3 12 2798 1071 8 3678 3679 2300 2208 753 8 244 526 338 438 524 52 188 1 25 701 3491 196 196 196 195 196 7 7 196 196 196 196 196 196 196 196 127 196 196 195 196 196 127 196 3668 1 3667 3671 18 18 3669 2990 33 3668 127 195 1 2822 12 2806 163 2827 60 5 55 5 2776 787 36 42 304 186 101 34 75 50 89 13 2122 2123 3666 3667 3677 200 3679 3678 3678 3676 4864 4877 4875 5071 5073 5072 5074 4871 4877 1550 3557 4879 5072 5069 3 1399 4714 591 590 591 179 1 4 130 3 128 1 1 1 124 1 113 1 1 1 6 17 98 98 98 1 96 1 5190 160 2 1 5040 5 34 97 1 96 96 161 5447 5437 5444 5434 5439 5430 5434 5440 1004 5426 5423 5425 5425 5427 5417 5424 5430 5414 5234 29 43 149 5083 8 1399 3692 3679 3674 1924 3679 3678 3679 3679 3671 3670 3662 3668 5239 4415 922 1875 2209 1627 3647 3648 1627 3646 1627 3944 5236 5237 4 5251 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 9772 9773 9774 9775 9776 9777 9778 9779 9780 9781 9782 9783 9784 9785 9786 9787 9788 9789 9790 9791 9792 9793 9794 9795 9796 9797 9798 9799 9800 9801 9802 9803 9804 9805 9806 9807 9808 9809 9810 9811 9812 9813 9814 9815 9816 9817 9818 9819 9820 9821 9822 9823 9824 9825 9826 9827 9828 9829 9830 9831 9832 9833 9834 9835 9836 9837 9838 9839 9840 9841 9842 9843 9844 9845 9846 9847 9848 9849 9850 9851 9852 9853 9854 9855 9856 9857 9858 9859 9860 9861 9862 9863 9864 9865 9866 9867 9868 9869 9870 9871 9872 9873 9874 9875 9876 9877 9878 9879 9880 9881 9882 9883 9884 9885 9886 9887 9888 9889 9890 9891 9892 9893 9894 9895 9896 9897 9898 9899 9900 9901 9902 9903 9904 9905 9906 9907 9908 9909 9910 9911 9912 9913 9914 9915 9916 9917 9918 9919 9920 9921 9922 9923 9924 9925 9926 9927 9928 9929 9930 9931 9932 9933 9934 9935 9936 9937 9938 9939 9940 9941 9942 9943 9944 9945 9946 9947 9948 9949 9950 9951 9952 9953 9954 9955 9956 9957 9958 9959 9960 9961 9962 9963 9964 9965 9966 9967 9968 9969 9970 9971 9972 9973 9974 9975 9976 9977 9978 9979 9980 9981 9982 9983 9984 9985 9986 9987 9988 9989 9990 9991 9992 9993 9994 9995 9996 9997 9998 9999 10000 10001 10002 10003 10004 10005 10006 10007 10008 10009 10010 10011 10012 10013 10014 10015 10016 10017 10018 10019 10020 10021 10022 10023 10024 10025 10026 10027 10028 10029 10030 10031 10032 10033 10034 10035 10036 10037 10038 10039 10040 10041 10042 10043 10044 10045 10046 10047 10048 10049 10050 10051 10052 10053 10054 10055 10056 10057 10058 10059 10060 10061 10062 10063 10064 10065 10066 10067 10068 10069 10070 10071 10072 10073 10074 10075 10076 10077 10078 10079 10080 10081 10082 10083 10084 10085 10086 10087 10088 10089 10090 10091 10092 10093 10094 10095 10096 10097 10098 10099 10100 10101 10102 10103 10104 10105 10106 10107 10108 10109 10110 10111 10112 10113 10114 10115 10116 10117 10118 10119 10120 10121 10122 10123 10124 10125 10126 10127 10128 10129 10130 10131 10132 10133 10134 10135 10136 10137 10138 10139 10140 10141 10142 10143 10144 10145 10146 10147 10148 10149 10150 10151 10152 10153 10154 10155 10156 10157 10158 10159 10160 10161 10162 10163 10164 10165 10166 10167 10168 10169 10170 10171 10172 10173 10174 10175 10176 10177 10178 10179 10180 10181 10182 10183 10184 10185 10186 10187 10188 10189 10190 10191 10192 10193 10194 10195 10196 10197 10198 10199 10200 10201 10202 10203 10204 10205 10206 10207 10208 10209 10210 10211 10212 10213 10214 10215 10216 10217 10218 10219 10220 10221 10222 10223 10224 10225 10226 10227 10228 10229 10230 10231 10232 10233 10234 10235 10236 10237 10238 10239 10240 10241 10242 10243 10244 10245 10246 10247 10248 10249 10250 10251 10252 10253 10254 10255 10256 10257 10258 10259 10260 10261 10262 10263 10264 10265 10266 10267 10268 10269 10270 10271 10272 10273 10274 10275 10276 10277 10278 10279 10280 10281 10282 10283 10284 10285 10286 10287 10288 10289 10290 10291 10292 10293 10294 10295 10296 10297 10298 10299 10300 10301 10302 10303 10304 10305 10306 10307 10308 10309 10310 10311 10312 10313 10314 10315 10316 10317 10318 10319 10320 10321 10322 10323 10324 10325 10326 10327 10328 10329 10330 10331 10332 10333 10334 10335 10336 10337 10338 10339 10340 10341 10342 10343 10344 10345 10346 10347 10348 10349 10350 10351 10352 10353 10354 10355 10356 10357 10358 10359 10360 10361 10362 10363 10364 10365 10366 10367 10368 10369 10370 10371 10372 10373 10374 10375 10376 10377 10378 10379 10380 10381 10382 10383 10384 10385 10386 10387 10388 10389 10390 10391 10392 10393 10394 10395 10396 10397 10398 10399 10400 10401 10402 10403 10404 10405 10406 10407 10408 10409 10410 10411 10412 10413 10414 10415 10416 10417 10418 10419 10420 10421 10422 10423 10424 10425 10426 10427 10428 10429 10430 10431 10432 10433 10434 10435 10436 10437 10438 10439 10440 10441 10442 10443 10444 10445 10446 10447 10448 10449 10450 10451 10452 10453 10454 10455 10456 10457 10458 10459 10460 10461 10462 10463 10464 10465 10466 10467 10468 10469 10470 10471 10472 10473 10474 10475 10476 10477 10478 10479 10480 10481 10482 10483 10484 10485 10486 10487 10488 10489 10490 10491 10492 10493 10494 10495 10496 10497 10498 10499 10500 10501 10502 10503 10504 10505 10506 10507 10508 10509 10510 10511 10512 10513 10514 10515 10516 10517 10518 10519 10520 10521 10522 10523 10524 10525 10526 10527 10528 10529 10530 10531 10532 10533 10534 10535 10536 10537 10538 10539 10540 10541 10542 10543 10544 10545 10546 10547 10548 10549 10550 10551 10552 10553 10554 10555 10556 10557 10558 10559 10560 10561 10562 10563 10564 10565 10566 10567 10568 10569 10570 10571 10572 10573 10574 10575 10576 10577 10578 10579 10580 10581 10582 10583 10584 10585 10586 10587 10588 10589 10590 10591 10592 10593 10594 10595 10596 10597 10598 10599 10600 10601 10602 10603 10604 10605 10606 10607 10608 10609 10610 10611 10612 10613 10614 10615 10616 10617 10618 10619 10620 10621 10622 10623 10624 10625 10626 10627 10628 10629 10630 10631 10632 10633 10634 10635 10636 10637 10638 10639 10640 10641 10642 10643 10644 10645 10646 10647 10648 10649 10650 10651 10652 10653 10654 10655 10656 10657 10658 10659 10660 10661 10662 10663 10664 10665 10666 10667 10668 10669 10670 10671 10672 10673 10674 10675 10676 10677 10678 10679 10680 10681 10682 10683 10684 10685 10686 10687 10688 10689 10690 10691 10692 10693 10694 10695 10696 10697 10698 10699 10700 10701 10702 10703 10704 10705 10706 10707 10708 10709 10710 10711 10712 10713 10714 10715 10716 10717 10718 10719 10720 10721 10722 10723 10724 10725 10726 10727 10728 10729 10730 10731 10732 10733 10734 10735 10736 10737 10738 10739 10740 10741 10742 10743 10744 10745 10746 10747 10748 10749 10750 10751 10752 10753 10754 10755 10756 10757 10758 10759 10760 10761 10762 10763 10764 10765 10766 10767 10768 10769 10770 10771 10772 10773 10774 10775 10776 10777 10778 10779 10780 10781 10782 10783 10784 10785 10786 10787 10788 10789 10790 10791 10792 10793 10794 10795 10796 10797 10798 10799 10800 10801 10802 10803 10804 10805 10806 10807 10808 10809 10810 10811 10812 10813 10814 10815 10816 10817 10818 10819 10820 10821 10822 10823 10824 10825 10826 10827 10828 10829 10830 10831 10832 10833 10834 10835 10836 10837 10838 10839 10840 10841 10842 10843 10844 10845 10846 10847 10848 10849 10850 10851 10852 10853 10854 10855 10856 10857 10858 10859 10860 10861 10862 10863 10864 10865 10866 10867 10868 10869 10870 10871 10872 10873 10874 10875 10876 10877 10878 10879 10880 10881 10882 10883 10884 10885 10886 10887 10888 10889 10890 10891 10892 10893 10894 10895 10896 10897 10898 10899 10900 10901 10902 10903 10904 10905 10906 10907 10908 10909 10910 10911 10912 10913 10914 10915 10916 10917 10918 10919 10920 10921 10922 10923 10924 10925 10926 10927 10928 10929 10930 10931 10932 10933 10934 10935 10936 10937 10938 10939 10940 10941 10942 10943 10944 10945 10946 10947 10948 10949 10950 10951 10952 10953 10954 10955 10956 10957 10958 10959 10960 10961 10962 10963 10964 10965 10966 10967 10968 10969 10970 10971 10972 10973 10974 10975 10976 10977 10978 10979 10980 10981 10982 10983 10984 10985 10986 10987 10988 10989 10990 10991 10992 10993 10994 10995 10996 10997 10998 10999 11000 11001 11002 11003 11004 11005 11006 11007 11008 11009 11010 11011 11012 11013 11014 11015 11016 11017 11018 11019 11020 11021 11022 11023 11024 11025 11026 11027 11028 11029 11030 11031 11032 11033 11034 11035 11036 11037 11038 11039 11040 11041 11042 11043 11044 11045 11046 11047 11048 11049 11050 11051 11052 11053 11054 11055 11056 11057 11058 11059 11060 11061 11062 11063 11064 11065 11066 11067 11068 11069 11070 11071 11072 11073 11074 11075 11076 11077 11078 11079 11080 11081 11082 11083 11084 11085 11086 11087 11088 11089 11090 11091 11092 11093 11094 11095 11096 11097 11098 11099 11100 11101 11102 11103 11104 11105 11106 11107 11108 11109 11110 11111 11112 11113 11114 11115 11116 11117 11118 11119 11120 11121 11122 11123 11124 11125 11126 11127 11128 11129 11130 11131 11132 11133 11134 11135 11136 11137 11138 11139 11140 11141 11142 11143 11144 11145 11146 11147 11148 11149 11150 11151 11152 11153 11154 11155 11156 11157 11158 11159 11160 11161 11162 11163 11164 11165 11166 11167 11168 11169 11170 11171 11172 11173 11174 11175 11176 11177 11178 11179 11180 11181 11182 11183 11184 11185 11186 11187 11188 11189 11190 11191 11192 11193 11194 11195 11196 11197 11198 11199 11200 11201 11202 11203 11204 11205 11206 11207 11208 11209 11210 11211 11212 11213 11214 11215 11216 11217 11218 11219 11220 11221 11222 11223 11224 11225 11226 11227 11228 11229 11230 11231 11232 11233 11234 11235 11236 11237 11238 11239 11240 11241 11242 11243 11244 11245 11246 11247 11248 11249 11250 11251 11252 11253 11254 11255 11256 11257 11258 11259 11260 11261 11262 11263 11264 11265 11266 11267 11268 11269 11270 11271 11272 11273 11274 11275 11276 11277 11278 11279 11280 11281 11282 11283 11284 11285 11286 11287 11288 11289 11290 11291 11292 11293 11294 11295 11296 11297 11298 11299 11300 11301 11302 11303 11304 11305 11306 11307 11308 11309 11310 11311 11312 11313 11314 11315 11316 11317 11318 11319 11320 11321 11322 11323 11324 11325 11326 11327 11328 11329 11330 11331 11332 11333 11334 11335 11336 11337 11338 11339 11340 11341 11342 11343 11344 11345 11346 11347 11348 11349 11350 11351 11352 11353 11354 11355 11356 11357 11358 11359 11360 11361 11362 11363 11364 11365 11366 11367 11368 11369 11370 11371 11372 11373 11374 11375 11376 11377 11378 11379 11380 11381 11382 11383 11384 11385 11386 11387 11388 11389 11390 11391 11392 11393 11394 11395 11396 11397 11398 11399 11400 11401 11402 11403 11404 11405 11406 11407 11408 11409 11410 11411 11412 11413 11414 11415 11416 11417 11418 11419 11420 11421 11422 11423 11424 11425 11426 11427 11428 11429 11430 11431 11432 11433 11434 11435 11436 11437 11438 11439 11440 11441 11442 11443 11444 11445 11446 11447 11448 11449 11450 11451 11452 11453 11454 11455 11456 11457 11458 11459 11460 11461 11462 11463 11464 11465 11466 11467 11468 11469 11470 11471 11472 11473 11474 11475 11476 11477 11478 11479 11480 11481 11482 11483 11484 11485 11486 11487 11488 11489 11490 11491 11492 11493 11494 11495 11496 11497 11498 11499 11500 11501 11502 11503 11504 11505 11506 11507 11508 11509 11510 11511 11512 11513 11514 11515 11516 11517 11518 11519 11520 11521 11522 11523 11524 11525 11526 11527 11528 11529 11530 11531 11532 11533 11534 11535 11536 11537 11538 11539 11540 11541 11542 11543 11544 11545 11546 11547 11548 11549 11550 11551 11552 11553 11554 11555 11556 11557 11558 11559 11560 11561 11562 11563 11564 11565 11566 11567 11568 11569 11570 11571 11572 11573 11574 11575 11576 11577 11578 11579 11580 11581 11582 11583 11584 11585 11586 11587 11588 11589 11590 11591 11592 11593 11594 11595 11596 11597 11598 11599 11600 11601 11602 11603 11604 11605 11606 11607 11608 11609 11610 11611 11612 11613 11614 11615 11616 11617 11618 11619 11620 11621 11622 11623 11624 11625 11626 11627 11628 11629 11630 11631 11632 11633 11634 11635 11636 11637 11638 11639 11640 11641 11642 11643 11644 11645 11646 11647 11648 11649 11650 11651 11652 11653 11654 11655 11656 11657 11658 11659 11660 11661 11662 11663 11664 11665 11666 11667 11668 11669 11670 11671 11672 11673 11674 11675 11676 11677 11678 11679 11680 11681 11682 11683 11684 11685 11686 11687 11688 11689 11690 11691 11692 11693 11694 11695 11696 11697 11698 11699 11700 11701 11702 11703 11704 11705 11706 11707 11708 11709 11710 11711 11712 11713 11714 11715 11716 11717 11718 11719 11720 11721 11722 11723 11724 11725 11726 11727 11728 11729 11730 11731 11732 11733 11734 11735 11736 11737 11738 11739 11740 11741 11742 11743 11744 11745 11746 11747 11748 11749 11750 11751 11752 11753 11754 11755 11756 11757 11758 11759 11760 11761 11762 11763 11764 11765 11766 11767 11768 11769 11770 11771 11772 11773 11774 11775 11776 11777 11778 11779 11780 11781 11782 11783 11784 11785 11786 11787 11788 11789 11790 11791 11792 11793 11794 11795 11796 11797 11798 11799 11800 11801 11802 11803 11804 11805 11806 11807 11808 11809 11810 11811 11812 11813 11814 11815 11816 11817 11818 11819 11820 11821 11822 11823 11824 11825 11826 11827 11828 11829 11830 11831 11832 11833 11834 11835 11836 11837 11838 11839 11840 11841 11842 11843 11844 11845 11846 11847 11848 11849 11850 11851 11852 11853 11854 11855 11856 11857 11858 11859 11860 11861 11862 11863 11864 11865 11866 11867 11868 11869 11870 11871 11872 11873 11874 11875 11876 11877 11878 11879 11880 11881 11882 11883 11884 11885 11886 11887 11888 11889 11890 11891 11892 11893 11894 11895 11896 11897 11898 11899 11900 11901 11902 11903 11904 11905 11906 11907 11908 11909 11910 11911 11912 11913 11914 11915 11916 11917 11918 11919 11920 11921 11922 11923 11924 11925 11926 11927 11928 11929 11930 11931 11932 11933 11934 11935 11936 11937 11938 11939 11940 11941 11942 11943 11944 11945 11946 11947 11948 11949 11950 11951 11952 11953 11954 11955 11956 11957 11958 11959 11960 11961 11962 11963 11964 11965 11966 11967 11968 11969 11970 11971 11972 11973 11974 11975 11976 11977 11978 11979 11980 11981 11982 11983 11984 11985 11986 11987 11988 11989 11990 11991 11992 11993 11994 11995 11996 11997 11998 11999 12000 12001 12002 12003 12004 12005 12006 12007 12008 12009 12010 12011 12012 12013 12014 12015 12016 12017 12018 12019 12020 12021 12022 12023 12024 12025 12026 12027 12028 12029 12030 12031 12032 12033 12034 12035 12036 12037 12038 12039 12040 12041 12042 12043 12044 12045 12046 12047 12048 12049 12050 12051 12052 12053 12054 12055 12056 12057 12058 12059 12060 12061 12062 12063 12064 12065 12066 12067 12068 12069 12070 12071 12072 12073 12074 12075 12076 12077 12078 12079 12080 12081 12082 12083 12084 12085 12086 12087 12088 12089 12090 12091 12092 12093 12094 12095 12096 12097 12098 12099 12100 12101 12102 12103 12104 12105 12106 12107 12108 12109 12110 12111 12112 12113 12114 12115 12116 12117 12118 12119 12120 12121 12122 12123 12124 12125 12126 12127 12128 12129 12130 12131 12132 12133 12134 12135 12136 12137 12138 12139 12140 12141 12142 12143 12144 12145 12146 12147 12148 12149 12150 12151 12152 12153 12154 12155 12156 12157 12158 12159 12160 12161 12162 12163 12164 12165 12166 12167 12168 12169 12170 12171 12172 12173 12174 12175 12176 12177 12178 12179 12180 12181 12182 12183 12184 12185 12186 12187 12188 12189 12190 12191 12192 12193 12194 12195 12196 12197 12198 12199 12200 12201 12202 12203 12204 12205 12206 12207 12208 12209 12210 12211 12212 12213 12214 12215 12216 12217 12218 12219 12220 12221 12222 12223 12224 12225 12226 12227 12228 12229 12230 12231 12232 12233 12234 12235 12236 12237 12238 12239 12240 12241 12242 12243 12244 12245 12246 12247 12248 12249 12250 12251 12252 12253 12254 12255 12256 12257 12258 12259 12260 12261 12262 12263 12264 12265 12266 12267 12268 12269 12270 12271 12272 12273 12274 12275 12276 12277 12278 12279 12280 12281 12282 12283 12284 12285 12286 12287 12288 12289 12290 12291 12292 12293 12294 12295 12296 12297 12298 12299 12300 12301 12302 12303 12304 12305 12306 12307 12308 12309 12310 12311 12312 12313 12314 12315 12316 12317 12318 12319 12320 12321 12322 12323 12324 12325 12326 12327 12328 12329 12330 12331 12332 12333 12334 12335 12336 12337 12338 12339 12340 12341 12342 12343 12344 12345 12346 12347 12348 12349 12350 12351 12352 12353 12354 12355 12356 12357 12358 12359 12360 12361 12362 12363 12364 12365 12366 12367 12368 12369 12370 12371 12372 12373 12374 12375 12376 12377 12378 12379 12380 12381 12382 12383 12384 12385 12386 12387 12388 12389 12390 12391 12392 12393 12394 12395 12396 12397 12398 12399 12400 12401 12402 12403 12404 12405 12406 12407 12408 12409 12410 12411 12412 12413 12414 12415 12416 12417 12418 12419 12420 12421 12422 12423 12424 12425 12426 12427 12428 12429 12430 12431 12432 12433 12434 12435 12436 12437 12438 12439 12440 12441 12442 12443 12444 12445 12446 12447 12448 12449 12450 12451 12452 12453 12454 12455 12456 12457 12458 12459 12460 12461 12462 12463 12464 12465 12466 12467 12468 12469 12470 12471 12472 12473 12474 12475 12476 12477 12478 12479 12480 12481 12482 12483 12484 12485 12486 12487 12488 12489 12490 12491 12492 12493 12494 12495 12496 12497 12498 12499 12500 12501 12502 12503 12504 12505 12506 12507 12508 12509 12510 12511 12512 12513 12514 12515 12516 12517 12518 12519 12520 12521 12522 12523 12524 12525 12526 12527 12528 12529 12530 12531 12532 12533 12534 12535 12536 12537 12538 12539 12540 12541 12542 12543 12544 12545 12546 12547 12548 12549 12550 12551 12552 12553 12554 12555 12556 12557 12558 12559 12560 12561 12562 12563 12564 12565 12566 12567 12568 12569 12570 12571 12572 12573 12574 12575 12576 12577 12578 12579 12580 12581 12582 12583 12584 12585 12586 12587 12588 12589 12590 12591 12592 12593 12594 12595 12596 12597 12598 12599 12600 12601 12602 12603 12604 12605 12606 12607 12608 12609 12610 12611 12612 12613 12614 12615 12616 12617 12618 12619 12620 12621 12622 12623 12624 12625 12626 12627 12628 12629 12630 12631 12632 12633 12634 12635 12636 12637 12638 12639 12640 12641 12642 12643 12644 12645 12646 12647 12648 12649 12650 12651 12652 12653 12654 12655 12656 12657 12658 12659 12660 12661 12662 12663 12664 12665 12666 12667 12668 12669 12670 12671 12672 12673 12674 12675 12676 12677 12678 12679 12680 12681 12682 12683 12684 12685 12686 12687 12688 12689 12690 12691 12692 12693 12694 12695 12696 12697 12698 12699 12700 12701 12702 12703 12704 12705 12706 12707 12708 12709 12710 12711 12712 12713 12714 12715 12716 12717 12718 12719 12720 12721 12722 12723 12724 12725 12726 12727 12728 12729 12730 12731 12732 12733 12734 12735 12736 12737 12738 12739 12740 12741 12742 12743 12744 12745 12746 12747 12748 12749 12750 12751 12752 12753 12754 12755 12756 12757 12758 12759 12760 12761 12762 12763 12764 12765 12766 12767 12768 12769 12770 12771 12772 12773 12774 12775 12776 12777 12778 12779 12780 12781 12782 12783 12784 12785 12786 12787 12788 12789 12790 12791 12792 12793 12794 12795 12796 12797 12798 12799 12800 12801 12802 12803 12804 12805 12806 12807 12808 12809 12810 12811 12812 12813 12814 12815 12816 12817 12818 12819 12820 12821 12822 12823 12824 12825 12826 12827 12828 12829 12830 12831 12832 12833 12834 12835 12836 12837 12838 12839 12840 12841 12842 12843 12844 12845 12846 12847 12848 12849 12850 12851 12852 12853 12854 12855 12856 12857 12858 12859 12860 12861 12862 12863 12864 12865 12866 12867 12868 12869 12870 12871 12872 12873 12874 12875 12876 12877 12878 12879 12880 12881 12882 12883 12884 12885 12886 12887 12888 12889 12890 12891 12892 12893 12894 12895 12896 12897 12898 12899 12900 12901 12902 12903 12904 12905 12906 12907 12908 12909 12910 12911 12912 12913 12914 12915 12916 12917 12918 12919 12920 12921 12922 12923 12924 12925 12926 12927 12928 12929 12930 12931 12932 12933 12934 12935 12936 12937 12938 12939 12940 12941 12942 12943 12944 12945 12946 12947 12948 12949 12950 12951 12952 12953 12954 12955 12956 12957 12958 12959 12960 12961 12962 12963 12964 12965 12966 12967 12968 12969 12970 12971 12972 12973 12974 12975 12976 12977 12978 12979 12980 12981 12982 12983 12984 12985 12986 12987 12988 12989 12990 12991 12992 12993 12994 12995 12996 12997 12998 12999 13000 13001 13002 13003 13004 13005 13006 13007 13008 13009 13010 13011 13012 13013 13014 13015 13016 13017 13018 13019 13020 13021 13022 13023 13024 13025 13026 13027 13028 13029 13030 13031 13032 13033 13034 13035 13036 13037 13038 13039 13040 13041 13042 13043 13044 13045 13046 13047 13048 13049 13050 13051 13052 13053 13054 13055 13056 13057 13058 13059 13060 13061 13062 13063 13064 13065 13066 13067 13068 13069 13070 13071 13072 13073 13074 13075 13076 13077 13078 13079 13080 13081 13082 13083 13084 13085 13086 13087 13088 13089 13090 13091 13092 13093 13094 13095 13096 13097 13098 13099 13100 13101 13102 13103 13104 13105 13106 13107 13108 13109 13110 13111 13112 13113 13114 13115 13116 13117 13118 13119 13120 13121 13122 13123 13124 13125 13126 13127 13128 13129 13130 13131 13132 13133 13134 13135 13136 13137 13138 13139 13140 13141 13142 13143 13144 13145 13146 13147 13148 13149 13150 13151 13152 13153 13154 13155 13156 13157 13158 13159 13160 13161 13162 13163 13164 13165 13166 13167 13168 13169 13170 13171 13172 13173 13174 13175 13176 13177 13178 13179 13180 13181 13182 13183 13184 13185 13186 13187 13188 13189 13190 13191 13192 13193 13194 13195 13196 13197 13198 13199 13200 13201 13202 13203 13204 13205 13206 13207 13208 13209 13210 13211 13212 13213 13214 13215 13216 13217 13218 13219 13220 13221 13222 13223 13224 13225 13226 13227 13228 13229 13230 13231 13232 13233 13234 13235 13236 13237 13238 13239 13240 13241 13242 13243 13244 13245 13246 13247 13248 13249 13250 13251 13252 13253 13254 13255 13256 13257 13258 13259 13260 13261 13262 13263 13264 13265 13266 13267 13268 13269 13270 13271 13272 13273 13274 13275 13276 13277 13278 13279 13280 13281 13282 13283 13284 13285 13286 13287 13288 13289 13290 13291 13292 13293 13294 13295 13296 13297 13298 13299 13300 13301 13302 13303 13304 13305 13306 13307 13308 13309 13310 13311 13312 13313 13314 13315 13316 13317 13318 13319 13320 13321 13322 13323 13324 13325 13326 13327 13328 13329 13330 13331 13332 13333 13334 13335 13336 13337 13338 13339 13340 13341 13342 13343 13344 13345 13346 13347 13348 13349 13350 13351 13352 13353 13354 13355 13356 13357 13358 13359 13360 13361 13362 13363 13364 13365 13366 13367 13368 13369 13370 13371 13372 13373 13374 13375 13376 13377 13378 13379 13380 13381 13382 13383 13384 13385 13386 13387 13388 13389 13390 13391 13392 13393 13394 13395 13396 13397 13398 13399 13400 13401 13402 13403 13404 13405 13406 13407 13408 13409 13410 13411 13412 13413 13414 13415 13416 13417 13418 13419 13420 13421 13422 13423 13424 13425 13426 13427 13428 13429 13430 13431 13432 13433 13434 13435 13436 13437 13438 13439 13440 13441 13442 13443 13444 13445 13446 13447 13448 13449 13450 13451 13452 13453 13454 13455 13456 13457 13458 13459 13460 13461 13462 13463 13464 13465 13466 13467 13468 13469 13470 13471 13472 13473 13474 13475 13476 13477 13478 13479 13480 13481 13482 13483 13484 13485 13486 13487 13488 13489 13490 13491 13492 13493 13494 13495 13496 13497 13498 13499 13500 13501 13502 13503 13504 13505 13506 13507 13508 13509 13510 13511 13512 13513 13514 13515 13516 13517 13518 13519 13520 13521 13522 13523 13524 13525 13526 13527 13528 13529 13530 13531 13532 13533 13534 13535 13536 13537 13538 13539 13540 13541 13542 13543 13544 13545 13546 13547 13548 13549 13550 13551 13552 13553 13554 13555 13556 13557 13558 13559 13560 13561 13562 13563 13564 13565 13566 13567 13568 13569 13570 13571 13572 13573 13574 13575 13576 13577 13578 13579 13580 13581 13582 13583 13584 13585 13586 13587 13588 13589 13590 13591 13592 13593 13594 13595 13596 13597 13598 13599 13600 13601 13602 13603 13604 13605 13606 13607 13608 13609 13610 13611 13612 13613 13614 13615 13616 13617 13618 13619 13620 13621 13622 13623 13624 13625 13626 13627 13628 13629 13630 13631 13632 13633 13634 13635 13636 13637 13638 13639 13640 13641 13642 13643 13644 13645 13646 13647 13648 13649 13650 13651 13652 13653 13654 13655 13656 13657 13658 13659 13660 13661 13662 13663 13664 13665 13666 13667 13668 13669 13670 13671 13672 13673 13674 13675 13676 13677 13678 13679 13680 13681 13682 13683 13684 13685 13686 13687 13688 13689 13690 13691 13692 13693 13694 13695 13696 13697 13698 13699 13700 13701 13702 13703 13704 13705 13706 13707 13708 13709 13710 13711 13712 13713 13714 13715 13716 13717 13718 13719 13720 13721 13722 13723 13724 13725 13726 13727 13728 13729 13730 13731 13732 13733 13734 13735 13736 13737 13738 13739 13740 13741 13742 13743 13744 13745 13746 13747 13748 13749 13750 13751 13752 13753 13754 13755 13756 13757 13758 13759 13760 13761 13762 13763 13764 13765 13766 13767 13768 13769 13770 13771 13772 13773 13774 13775 13776 13777 13778 13779 13780 13781 13782 13783 13784 13785 13786 13787 13788 13789 13790 13791 13792 13793 13794 13795 13796 13797 13798 13799 13800 13801 13802 13803 13804 13805 13806 13807 13808 13809 13810 13811 13812 13813 13814 13815 13816 13817 13818 13819 13820 13821 13822 13823 13824 13825 13826 13827 13828 13829 13830 13831 13832 13833 13834 13835 13836 13837 13838 13839 13840 13841 13842 13843 13844 13845 13846 13847 13848 13849 13850 13851 13852 13853 13854 13855 13856 13857 13858 13859 13860 13861 13862 13863 13864 13865 13866 13867 13868 13869 13870 13871 13872 13873 13874 13875 13876 13877 13878 13879 13880 13881 13882 13883 13884 13885 13886 13887 13888 13889 13890 13891 13892 13893 13894 13895 13896 13897 13898 13899 13900 13901 13902 13903 13904 13905 13906 13907 13908 13909 13910 13911 13912 13913 13914 13915 13916 13917 13918 13919 13920 13921 13922 13923 13924 13925 13926 13927 13928 13929 13930 13931 13932 13933 13934 13935 13936 13937 13938 13939 13940 13941 13942 13943 13944 13945 13946 13947 13948 13949 13950 13951 13952 13953 13954 13955 13956 13957 13958 13959 13960 13961 13962 13963 13964 13965 13966 13967 13968 13969 13970 13971 13972 13973 13974 13975 13976 13977 13978 13979 13980 13981 13982 13983 13984 13985 13986 13987 13988 13989 13990 13991 13992 13993 13994 13995 13996 13997 13998 13999 14000 14001 14002 14003 14004 14005 14006 14007 14008 14009 14010 14011 14012 14013 14014 14015 14016 14017 14018 14019 14020 14021 14022 14023 14024 14025 14026 14027 14028 14029 14030 14031 14032 14033 14034 14035 14036 14037 14038 14039 14040 14041 14042 14043 14044 14045 14046 14047 14048 14049 14050 14051 14052 14053 14054 14055 14056 14057 14058 14059 14060 14061 14062 14063 14064 14065 14066 14067 14068 14069 14070 14071 14072 14073 14074 14075 14076 14077 14078 14079 14080 14081 14082 14083 14084 14085 14086 14087 14088 14089 14090 14091 14092 14093 14094 14095 14096 14097 14098 14099 14100 14101 14102 14103 14104 14105 14106 14107 14108 14109 14110 14111 14112 14113 14114 14115 14116 14117 14118 14119 14120 14121 14122 14123 14124 14125 14126 14127 14128 14129 14130 14131 14132 14133 14134 14135 14136 14137 14138 14139 14140 14141 14142 14143 14144 14145 14146 14147 14148 14149 14150 14151 14152 14153 14154 14155 14156 14157 14158 14159 14160 14161 14162 14163 14164 14165 14166 14167 14168 14169 14170 14171 14172 14173 14174 14175 14176 14177 14178 14179 14180 14181 14182 14183 14184 14185 14186 14187 14188 14189 14190 14191 14192 14193 14194 14195 14196 14197 14198 14199 14200 14201 14202 14203 14204 14205 14206 14207 14208 14209 14210 14211 14212 14213 14214 14215 14216 14217 14218 14219 14220 14221 14222 14223 14224 14225 14226 14227 14228 14229 14230 14231 14232 14233 14234 14235 14236 14237 14238 14239 14240 14241 14242 14243 14244 14245 14246 14247 14248 14249 14250 14251 14252 14253 14254 14255 14256 14257 14258 14259 14260 14261 14262 14263 14264 14265 14266 14267 14268 14269 14270 14271 14272 14273 14274 14275 14276 14277 14278 14279 14280 14281 14282 14283 14284 14285 14286 14287 14288 14289 14290 14291 14292 14293 14294 14295 14296 14297 14298 14299 14300 14301 14302 14303 14304 14305 14306 14307 14308 14309 14310 14311 14312 14313 14314 14315 14316 14317 14318 14319 14320 14321 14322 14323 14324 14325 14326 14327 14328 14329 14330 14331 14332 14333 14334 14335 14336 14337 14338 14339 14340 14341 14342 14343 14344 14345 14346 14347 14348 14349 14350 14351 14352 14353 14354 14355 14356 14357 14358 14359 14360 14361 14362 14363 14364 14365 14366 14367 14368 14369 14370 14371 14372 14373 14374 14375 14376 14377 14378 14379 14380 14381 14382 14383 14384 14385 14386 14387 14388 14389 14390 14391 14392 14393 14394 14395 14396 14397 14398 14399 14400 14401 14402 14403 14404 14405 14406 14407 14408 14409 14410 14411 14412 14413 14414 14415 14416 14417 14418 14419 14420 14421 14422 14423 14424 14425 14426 14427 14428 14429 14430 14431 14432 14433 14434 14435 14436 14437 14438 14439 14440 14441 14442 14443 14444 14445 14446 14447 14448 14449 14450 14451 14452 14453 14454 14455 14456 14457 14458 14459 14460 14461 14462 14463 14464 14465 14466 14467 14468 14469 14470 14471 14472 14473 14474 14475 14476 14477 14478 14479 14480 14481 14482 14483 14484 14485 14486 14487 14488 14489 14490 14491 14492 14493 14494 14495 14496 14497 14498 14499 14500 14501 14502 14503 14504 14505 14506 14507 14508 14509 14510 14511 14512 14513 14514 14515 14516 14517 14518 14519 14520 14521 14522 14523 14524 14525 14526 14527 14528 14529 14530 14531 14532 14533 14534 14535 14536 14537 14538 14539 14540 14541 14542 14543 14544 14545 14546 14547 14548 14549 14550 14551 14552 14553 14554 14555 14556 14557 14558 14559 14560 14561 14562 14563 14564 14565 14566 14567 14568 14569 14570 14571 14572 14573 14574 14575 14576 14577 14578 14579 14580 14581 14582 14583 14584 14585 14586 14587 14588 14589 14590 14591 14592 14593 14594 14595 14596 14597 14598 14599 14600 14601 14602 14603 14604 14605 14606 14607 14608 14609 14610 14611 14612 14613 14614 14615 14616 14617 14618 14619 14620 14621 14622 14623 14624 14625 14626 14627 14628 14629 14630 14631 14632 14633 14634 14635 14636 14637 14638 14639 14640 14641 14642 14643 14644 14645 14646 14647 14648 14649 14650 14651 14652 14653 14654 14655 14656 14657 14658 14659 14660 14661 14662 14663 14664 14665 14666 14667 14668 14669 14670 14671 14672 14673 14674 14675 14676 14677 14678 14679 14680 14681 14682 14683 14684 14685 14686 14687 14688 14689 14690 14691 14692 14693 14694 14695 14696 14697 14698 14699 14700 14701 14702 14703 14704 14705 14706 14707 14708 14709 14710 14711 14712 14713 14714 14715 14716 14717 14718 14719 14720 14721 14722 14723 14724 14725 14726 14727 14728 14729 14730 14731 14732 14733 14734 14735 14736 14737 14738 14739 14740 14741 14742 14743 14744 14745 14746 14747 14748 14749 14750 14751 14752 14753 14754 14755 14756 14757 14758 14759 14760 14761 14762 14763 14764 14765 14766 14767 14768 14769 14770 14771 14772 14773 14774 14775 14776 14777 14778 14779 14780 14781 14782 14783 14784 14785 14786 14787 14788 14789 14790 14791 14792 14793 14794 14795 14796 14797 14798 14799 14800 14801 14802 14803 14804 14805 14806 14807 14808 14809 14810 14811 14812 14813 14814 14815 14816 14817 14818 14819 14820 14821 14822 14823 14824 14825 14826 14827 14828 14829 14830 14831 14832 14833 14834 14835 14836 14837 14838 14839 14840 14841 14842 14843 14844 14845 14846 14847 14848 14849 14850 14851 14852 14853 14854 14855 14856 14857 14858 14859 14860 14861 14862 14863 14864 14865 14866 14867 14868 14869 14870 14871 14872 14873 14874 14875 14876 14877 14878 14879 14880 14881 14882 14883 14884 14885 14886 14887 14888 14889 14890 14891 14892 14893 14894 14895 14896 14897 14898 14899 14900 14901 14902 14903 14904 14905 14906 14907 14908 14909 14910 14911 14912 14913 14914 14915 14916 14917 14918 14919 14920 14921 14922 14923 14924 14925 14926 14927 14928 14929 14930 14931 14932 14933 14934 14935 14936 14937 14938 14939 14940 14941 14942 14943 14944 14945 14946 14947 14948 14949 14950 14951 14952 14953 14954 14955 14956 14957 14958 14959 14960 14961 14962 14963 14964 14965 14966 14967 14968 14969 14970 14971 14972 14973 14974 14975 14976 14977 14978 14979 14980 14981 14982 14983 14984 14985 14986 14987 14988 14989 14990 14991 14992 14993 14994 14995 14996 14997 14998 14999 15000 15001 15002 15003 15004 15005 15006 15007 15008 15009 15010 15011 15012 15013 15014 15015 15016 15017 15018 15019 15020 15021 15022 15023 15024 15025 15026 15027 15028 15029 15030 15031 15032 15033 15034 15035 15036 15037 15038 15039 15040 15041 15042 15043 15044 15045 15046 15047 15048 15049 15050 15051 15052 15053 15054 15055 15056 15057 15058 15059 15060 15061 15062 15063 15064 15065 15066 15067 15068 15069 15070 15071 15072 15073 15074 15075 15076 15077 15078 15079 15080 15081 15082 15083 15084 15085 15086 15087 15088 15089 15090 15091 15092 15093 15094 15095 15096 15097 15098 15099 15100 15101 15102 15103 15104 15105 15106 15107 15108 15109 15110 15111 15112 15113 15114 15115 15116 15117 15118 15119 15120 15121 15122 15123 15124 15125 15126 15127 15128 15129 15130 15131 15132 15133 15134 15135 15136 15137 15138 15139 15140 15141 15142 15143 15144 15145 15146 15147 15148 15149 15150 15151 15152 15153 15154 15155 15156 15157 15158 15159 15160 15161 15162 15163 15164 15165 15166 15167 15168 15169 15170 15171 15172 15173 15174 15175 15176 15177 15178 15179 15180 15181 15182 15183 15184 15185 15186 15187 15188 15189 15190 15191 15192 15193 15194 15195 15196 15197 15198 15199 15200 15201 15202 15203 15204 15205 15206 15207 15208 15209 15210 15211 15212 15213 15214 15215 15216 15217 15218 15219 15220 15221 15222 15223 15224 15225 15226 15227 15228 15229 15230 15231 15232 15233 15234 15235 15236 15237 15238 15239 15240 15241 15242 15243 15244 15245 15246 15247 15248 15249 15250 15251 15252 15253 15254 15255 15256 15257 15258 15259 15260 15261 15262 15263 15264 15265 15266 15267 15268 15269 15270 15271 15272 15273 15274 15275 15276 15277 15278 15279 15280 15281 15282 15283 15284 15285 15286 15287 15288 15289 15290 15291 15292 15293 15294 15295 15296 15297 15298 15299 15300 15301 15302 15303 15304 15305 15306 15307 15308 15309 15310 15311 15312 15313 15314 15315 15316 15317 15318 15319 15320 15321 15322 15323 15324 15325 15326 15327 15328 15329 15330 15331 15332 15333 15334 15335 15336 15337 15338 15339 15340 15341 15342 15343 15344 15345 15346 15347 15348 15349 15350 15351 15352 15353 15354 15355 15356 15357 15358 15359 15360 15361 15362 15363 15364 15365 15366 15367 15368 15369 15370 15371 15372 15373 15374 15375 15376 15377 15378 15379 15380 15381 15382 15383 15384 15385 15386 15387 15388 15389 15390 15391 15392 15393 15394 15395 15396 15397 15398 15399 15400 15401 15402 15403 15404 15405 15406 15407 15408 15409 15410 15411 15412 15413 15414 15415 15416 15417 15418 15419 15420 15421 15422 15423 15424 15425 15426 15427 15428 15429 15430 15431 15432 15433 15434 15435 15436 15437 15438 15439 15440 15441 15442 15443 15444 15445 15446 15447 15448 15449 15450 15451 15452 15453 15454 15455 15456 15457 15458 15459 15460 15461 15462 15463 15464 15465 15466 15467 15468 15469 15470 15471 15472 15473 15474 15475 15476 15477 15478 15479 15480 15481 15482 15483 15484 15485 15486 15487 15488 15489 15490 15491 15492 15493 15494 15495 15496 15497 15498 15499 15500 15501 15502 15503 15504 15505 15506 15507 15508 15509 15510 15511 15512 15513 15514 15515 15516 15517 15518 15519 15520 15521 15522 15523 15524 15525 15526 15527 15528 15529 15530 15531 15532 15533 15534 15535 15536 15537 15538 15539 15540 15541 15542 15543 15544 15545 15546 15547 15548 15549 15550 15551 15552 15553 15554 15555 15556 15557 15558 15559 15560 15561 15562 15563 15564 15565 15566 15567 15568 15569 15570 15571 15572 15573 15574 15575 15576 15577 15578 15579 15580 15581 15582 15583 15584 15585 15586 15587 15588 15589 15590 15591 15592 15593 15594 15595 15596 15597 15598 15599 15600 15601 15602 15603 15604 15605 15606 15607 15608 15609 15610 15611 15612 15613 15614 15615 15616 15617 15618 15619 15620 15621 15622 15623 15624 15625 15626 15627 15628 15629 15630 15631 15632 15633 15634 15635 15636 15637 15638 15639 15640 15641 15642 15643 15644 15645 15646 15647 15648 15649 15650 15651 15652 15653 15654 15655 15656 15657 15658 15659 15660 15661 15662 15663 15664 15665 15666 15667 15668 15669 15670 15671 15672 15673 15674 15675 15676 15677 15678 15679 15680 15681 15682 15683 15684 15685 15686 15687 15688 15689 15690 15691 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook * Copyright (c) 2018 Covalent IO, Inc. http://covalent.io */ #include <uapi/linux/btf.h> #include <linux/bpf-cgroup.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/bpf_verifier.h> #include <linux/filter.h> #include <net/netlink.h> #include <linux/file.h> #include <linux/vmalloc.h> #include <linux/stringify.h> #include <linux/bsearch.h> #include <linux/sort.h> #include <linux/perf_event.h> #include <linux/ctype.h> #include <linux/error-injection.h> #include <linux/bpf_lsm.h> #include <linux/btf_ids.h> #include <linux/poison.h> #include "disasm.h" static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ [_id] = & _name ## _verifier_ops, #define BPF_MAP_TYPE(_id, _ops) #define BPF_LINK_TYPE(_id, _name) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE }; /* bpf_check() is a static code analyzer that walks eBPF program * instruction by instruction and updates register/stack state. * All paths of conditional branches are analyzed until 'bpf_exit' insn. * * The first pass is depth-first-search to check that the program is a DAG. * It rejects the following programs: * - larger than BPF_MAXINSNS insns * - if loop is present (detected via back-edge) * - unreachable insns exist (shouldn't be a forest. program = one function) * - out of bounds or malformed jumps * The second pass is all possible path descent from the 1st insn. * Since it's analyzing all paths through the program, the length of the * analysis is limited to 64k insn, which may be hit even if total number of * insn is less then 4K, but there are too many branches that change stack/regs. * Number of 'branches to be analyzed' is limited to 1k * * On entry to each instruction, each register has a type, and the instruction * changes the types of the registers depending on instruction semantics. * If instruction is BPF_MOV64_REG(BPF_REG_1, BPF_REG_5), then type of R5 is * copied to R1. * * All registers are 64-bit. * R0 - return register * R1-R5 argument passing registers * R6-R9 callee saved registers * R10 - frame pointer read-only * * At the start of BPF program the register R1 contains a pointer to bpf_context * and has type PTR_TO_CTX. * * Verifier tracks arithmetic operations on pointers in case: * BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), * BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -20), * 1st insn copies R10 (which has FRAME_PTR) type into R1 * and 2nd arithmetic instruction is pattern matched to recognize * that it wants to construct a pointer to some element within stack. * So after 2nd insn, the register R1 has type PTR_TO_STACK * (and -20 constant is saved for further stack bounds checking). * Meaning that this reg is a pointer to stack plus known immediate constant. * * Most of the time the registers have SCALAR_VALUE type, which * means the register has some value, but it's not a valid pointer. * (like pointer plus pointer becomes SCALAR_VALUE type) * * When verifier sees load or store instructions the type of base register * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, PTR_TO_STACK, PTR_TO_SOCKET. These are * four pointer types recognized by check_mem_access() function. * * PTR_TO_MAP_VALUE means that this register is pointing to 'map element value' * and the range of [ptr, ptr + map's value_size) is accessible. * * registers used to pass values to function calls are checked against * function argument constraints. * * ARG_PTR_TO_MAP_KEY is one of such argument constraints. * It means that the register type passed to this function must be * PTR_TO_STACK and it will be used inside the function as * 'pointer to map element key' * * For example the argument constraints for bpf_map_lookup_elem(): * .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, * .arg1_type = ARG_CONST_MAP_PTR, * .arg2_type = ARG_PTR_TO_MAP_KEY, * * ret_type says that this function returns 'pointer to map elem value or null' * function expects 1st argument to be a const pointer to 'struct bpf_map' and * 2nd argument should be a pointer to stack, which will be used inside * the helper function as a pointer to map element key. * * On the kernel side the helper function looks like: * u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) * { * struct bpf_map *map = (struct bpf_map *) (unsigned long) r1; * void *key = (void *) (unsigned long) r2; * void *value; * * here kernel can access 'key' and 'map' pointers safely, knowing that * [key, key + map->key_size) bytes are valid and were initialized on * the stack of eBPF program. * } * * Corresponding eBPF program may look like: * BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), // after this insn R2 type is FRAME_PTR * BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), // after this insn R2 type is PTR_TO_STACK * BPF_LD_MAP_FD(BPF_REG_1, map_fd), // after this insn R1 type is CONST_PTR_TO_MAP * BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), * here verifier looks at prototype of map_lookup_elem() and sees: * .arg1_type == ARG_CONST_MAP_PTR and R1->type == CONST_PTR_TO_MAP, which is ok, * Now verifier knows that this map has key of R1->map_ptr->key_size bytes * * Then .arg2_type == ARG_PTR_TO_MAP_KEY and R2->type == PTR_TO_STACK, ok so far, * Now verifier checks that [R2, R2 + map's key_size) are within stack limits * and were initialized prior to this call. * If it's ok, then verifier allows this BPF_CALL insn and looks at * .ret_type which is RET_PTR_TO_MAP_VALUE_OR_NULL, so it sets * R0->type = PTR_TO_MAP_VALUE_OR_NULL which means bpf_map_lookup_elem() function * returns either pointer to map value or NULL. * * When type PTR_TO_MAP_VALUE_OR_NULL passes through 'if (reg != 0) goto +off' * insn, the register holding that pointer in the true branch changes state to * PTR_TO_MAP_VALUE and the same register changes state to CONST_IMM in the false * branch. See check_cond_jmp_op(). * * After the call R0 is set to return type of the function and registers R1-R5 * are set to NOT_INIT to indicate that they are no longer readable. * * The following reference types represent a potential reference to a kernel * resource which, after first being allocated, must be checked and freed by * the BPF program: * - PTR_TO_SOCKET_OR_NULL, PTR_TO_SOCKET * * When the verifier sees a helper call return a reference type, it allocates a * pointer id for the reference and stores it in the current function state. * Similar to the way that PTR_TO_MAP_VALUE_OR_NULL is converted into * PTR_TO_MAP_VALUE, PTR_TO_SOCKET_OR_NULL becomes PTR_TO_SOCKET when the type * passes through a NULL-check conditional. For the branch wherein the state is * changed to CONST_IMM, the verifier releases the reference. * * For each helper function that allocates a reference, such as * bpf_sk_lookup_tcp(), there is a corresponding release function, such as * bpf_sk_release(). When a reference type passes into the release function, * the verifier also releases the reference. If any unchecked or unreleased * reference remains at the end of the program, the verifier rejects it. */ /* verifier_state + insn_idx are pushed to stack when branch is encountered */ struct bpf_verifier_stack_elem { /* verifer state is 'st' * before processing instruction 'insn_idx' * and after processing instruction 'prev_insn_idx' */ struct bpf_verifier_state st; int insn_idx; int prev_insn_idx; struct bpf_verifier_stack_elem *next; /* length of verifier log at the time this state was pushed on stack */ u32 log_pos; }; #define BPF_COMPLEXITY_LIMIT_JMP_SEQ 8192 #define BPF_COMPLEXITY_LIMIT_STATES 64 #define BPF_MAP_KEY_POISON (1ULL << 63) #define BPF_MAP_KEY_SEEN (1ULL << 62) #define BPF_MAP_PTR_UNPRIV 1UL #define BPF_MAP_PTR_POISON ((void *)((0xeB9FUL << 1) + \ POISON_POINTER_DELTA)) #define BPF_MAP_PTR(X) ((struct bpf_map *)((X) & ~BPF_MAP_PTR_UNPRIV)) static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx); static int release_reference(struct bpf_verifier_env *env, int ref_obj_id); static bool bpf_map_ptr_poisoned(const struct bpf_insn_aux_data *aux) { return BPF_MAP_PTR(aux->map_ptr_state) == BPF_MAP_PTR_POISON; } static bool bpf_map_ptr_unpriv(const struct bpf_insn_aux_data *aux) { return aux->map_ptr_state & BPF_MAP_PTR_UNPRIV; } static void bpf_map_ptr_store(struct bpf_insn_aux_data *aux, const struct bpf_map *map, bool unpriv) { BUILD_BUG_ON((unsigned long)BPF_MAP_PTR_POISON & BPF_MAP_PTR_UNPRIV); unpriv |= bpf_map_ptr_unpriv(aux); aux->map_ptr_state = (unsigned long)map | (unpriv ? BPF_MAP_PTR_UNPRIV : 0UL); } static bool bpf_map_key_poisoned(const struct bpf_insn_aux_data *aux) { return aux->map_key_state & BPF_MAP_KEY_POISON; } static bool bpf_map_key_unseen(const struct bpf_insn_aux_data *aux) { return !(aux->map_key_state & BPF_MAP_KEY_SEEN); } static u64 bpf_map_key_immediate(const struct bpf_insn_aux_data *aux) { return aux->map_key_state & ~(BPF_MAP_KEY_SEEN | BPF_MAP_KEY_POISON); } static void bpf_map_key_store(struct bpf_insn_aux_data *aux, u64 state) { bool poisoned = bpf_map_key_poisoned(aux); aux->map_key_state = state | BPF_MAP_KEY_SEEN | (poisoned ? BPF_MAP_KEY_POISON : 0ULL); } static bool bpf_pseudo_call(const struct bpf_insn *insn) { return insn->code == (BPF_JMP | BPF_CALL) && insn->src_reg == BPF_PSEUDO_CALL; } static bool bpf_pseudo_kfunc_call(const struct bpf_insn *insn) { return insn->code == (BPF_JMP | BPF_CALL) && insn->src_reg == BPF_PSEUDO_KFUNC_CALL; } struct bpf_call_arg_meta { struct bpf_map *map_ptr; bool raw_mode; bool pkt_access; u8 release_regno; int regno; int access_size; int mem_size; u64 msize_max_value; int ref_obj_id; int map_uid; int func_id; struct btf *btf; u32 btf_id; struct btf *ret_btf; u32 ret_btf_id; u32 subprogno; struct bpf_map_value_off_desc *kptr_off_desc; u8 uninit_dynptr_regno; }; struct btf *btf_vmlinux; static DEFINE_MUTEX(bpf_verifier_lock); static const struct bpf_line_info * find_linfo(const struct bpf_verifier_env *env, u32 insn_off) { const struct bpf_line_info *linfo; const struct bpf_prog *prog; u32 i, nr_linfo; prog = env->prog; nr_linfo = prog->aux->nr_linfo; if (!nr_linfo || insn_off >= prog->len) return NULL; linfo = prog->aux->linfo; for (i = 1; i < nr_linfo; i++) if (insn_off < linfo[i].insn_off) break; return &linfo[i - 1]; } __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...) { struct bpf_verifier_env *env = private_data; va_list args; if (!bpf_verifier_log_needed(&env->log)) return; va_start(args, fmt); bpf_verifier_vlog(&env->log, fmt, args); va_end(args); } static const char *ltrim(const char *s) { while (isspace(*s)) s++; return s; } __printf(3, 4) static void verbose_linfo(struct bpf_verifier_env *env, u32 insn_off, const char *prefix_fmt, ...) { const struct bpf_line_info *linfo; if (!bpf_verifier_log_needed(&env->log)) return; linfo = find_linfo(env, insn_off); if (!linfo || linfo == env->prev_linfo) return; if (prefix_fmt) { va_list args; va_start(args, prefix_fmt); bpf_verifier_vlog(&env->log, prefix_fmt, args); va_end(args); } verbose(env, "%s\n", ltrim(btf_name_by_offset(env->prog->aux->btf, linfo->line_off))); env->prev_linfo = linfo; } static void verbose_invalid_scalar(struct bpf_verifier_env *env, struct bpf_reg_state *reg, struct tnum *range, const char *ctx, const char *reg_name) { char tn_buf[48]; verbose(env, "At %s the register %s ", ctx, reg_name); if (!tnum_is_unknown(reg->var_off)) { tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "has value %s", tn_buf); } else { verbose(env, "has unknown scalar value"); } tnum_strn(tn_buf, sizeof(tn_buf), *range); verbose(env, " should have been in %s\n", tn_buf); } static bool type_is_pkt_pointer(enum bpf_reg_type type) { type = base_type(type); return type == PTR_TO_PACKET || type == PTR_TO_PACKET_META; } static bool type_is_sk_pointer(enum bpf_reg_type type) { return type == PTR_TO_SOCKET || type == PTR_TO_SOCK_COMMON || type == PTR_TO_TCP_SOCK || type == PTR_TO_XDP_SOCK; } static bool reg_type_not_null(enum bpf_reg_type type) { return type == PTR_TO_SOCKET || type == PTR_TO_TCP_SOCK || type == PTR_TO_MAP_VALUE || type == PTR_TO_MAP_KEY || type == PTR_TO_SOCK_COMMON; } static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) { return reg->type == PTR_TO_MAP_VALUE && map_value_has_spin_lock(reg->map_ptr); } static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type) { type = base_type(type); return type == PTR_TO_SOCKET || type == PTR_TO_TCP_SOCK || type == PTR_TO_MEM || type == PTR_TO_BTF_ID; } static bool type_is_rdonly_mem(u32 type) { return type & MEM_RDONLY; } static bool type_may_be_null(u32 type) { return type & PTR_MAYBE_NULL; } static bool is_acquire_function(enum bpf_func_id func_id, const struct bpf_map *map) { enum bpf_map_type map_type = map ? map->map_type : BPF_MAP_TYPE_UNSPEC; if (func_id == BPF_FUNC_sk_lookup_tcp || func_id == BPF_FUNC_sk_lookup_udp || func_id == BPF_FUNC_skc_lookup_tcp || func_id == BPF_FUNC_ringbuf_reserve || func_id == BPF_FUNC_kptr_xchg) return true; if (func_id == BPF_FUNC_map_lookup_elem && (map_type == BPF_MAP_TYPE_SOCKMAP || map_type == BPF_MAP_TYPE_SOCKHASH)) return true; return false; } static bool is_ptr_cast_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_tcp_sock || func_id == BPF_FUNC_sk_fullsock || func_id == BPF_FUNC_skc_to_tcp_sock || func_id == BPF_FUNC_skc_to_tcp6_sock || func_id == BPF_FUNC_skc_to_udp6_sock || func_id == BPF_FUNC_skc_to_mptcp_sock || func_id == BPF_FUNC_skc_to_tcp_timewait_sock || func_id == BPF_FUNC_skc_to_tcp_request_sock; } static bool is_dynptr_ref_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_dynptr_data; } static bool is_callback_calling_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_for_each_map_elem || func_id == BPF_FUNC_timer_set_callback || func_id == BPF_FUNC_find_vma || func_id == BPF_FUNC_loop || func_id == BPF_FUNC_user_ringbuf_drain; } static bool helper_multiple_ref_obj_use(enum bpf_func_id func_id, const struct bpf_map *map) { int ref_obj_uses = 0; if (is_ptr_cast_function(func_id)) ref_obj_uses++; if (is_acquire_function(func_id, map)) ref_obj_uses++; if (is_dynptr_ref_function(func_id)) ref_obj_uses++; return ref_obj_uses > 1; } static bool is_cmpxchg_insn(const struct bpf_insn *insn) { return BPF_CLASS(insn->code) == BPF_STX && BPF_MODE(insn->code) == BPF_ATOMIC && insn->imm == BPF_CMPXCHG; } /* string representation of 'enum bpf_reg_type' * * Note that reg_type_str() can not appear more than once in a single verbose() * statement. */ static const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type) { char postfix[16] = {0}, prefix[32] = {0}; static const char * const str[] = { [NOT_INIT] = "?", [SCALAR_VALUE] = "scalar", [PTR_TO_CTX] = "ctx", [CONST_PTR_TO_MAP] = "map_ptr", [PTR_TO_MAP_VALUE] = "map_value", [PTR_TO_STACK] = "fp", [PTR_TO_PACKET] = "pkt", [PTR_TO_PACKET_META] = "pkt_meta", [PTR_TO_PACKET_END] = "pkt_end", [PTR_TO_FLOW_KEYS] = "flow_keys", [PTR_TO_SOCKET] = "sock", [PTR_TO_SOCK_COMMON] = "sock_common", [PTR_TO_TCP_SOCK] = "tcp_sock", [PTR_TO_TP_BUFFER] = "tp_buffer", [PTR_TO_XDP_SOCK] = "xdp_sock", [PTR_TO_BTF_ID] = "ptr_", [PTR_TO_MEM] = "mem", [PTR_TO_BUF] = "buf", [PTR_TO_FUNC] = "func", [PTR_TO_MAP_KEY] = "map_key", [PTR_TO_DYNPTR] = "dynptr_ptr", }; if (type & PTR_MAYBE_NULL) { if (base_type(type) == PTR_TO_BTF_ID) strncpy(postfix, "or_null_", 16); else strncpy(postfix, "_or_null", 16); } if (type & MEM_RDONLY) strncpy(prefix, "rdonly_", 32); if (type & MEM_ALLOC) strncpy(prefix, "alloc_", 32); if (type & MEM_USER) strncpy(prefix, "user_", 32); if (type & MEM_PERCPU) strncpy(prefix, "percpu_", 32); if (type & PTR_UNTRUSTED) strncpy(prefix, "untrusted_", 32); snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s", prefix, str[base_type(type)], postfix); return env->type_str_buf; } static char slot_type_char[] = { [STACK_INVALID] = '?', [STACK_SPILL] = 'r', [STACK_MISC] = 'm', [STACK_ZERO] = '0', [STACK_DYNPTR] = 'd', }; static void print_liveness(struct bpf_verifier_env *env, enum bpf_reg_liveness live) { if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN | REG_LIVE_DONE)) verbose(env, "_"); if (live & REG_LIVE_READ) verbose(env, "r"); if (live & REG_LIVE_WRITTEN) verbose(env, "w"); if (live & REG_LIVE_DONE) verbose(env, "D"); } static int get_spi(s32 off) { return (-off - 1) / BPF_REG_SIZE; } static bool is_spi_bounds_valid(struct bpf_func_state *state, int spi, int nr_slots) { int allocated_slots = state->allocated_stack / BPF_REG_SIZE; /* We need to check that slots between [spi - nr_slots + 1, spi] are * within [0, allocated_stack). * * Please note that the spi grows downwards. For example, a dynptr * takes the size of two stack slots; the first slot will be at * spi and the second slot will be at spi - 1. */ return spi - nr_slots + 1 >= 0 && spi < allocated_slots; } static struct bpf_func_state *func(struct bpf_verifier_env *env, const struct bpf_reg_state *reg) { struct bpf_verifier_state *cur = env->cur_state; return cur->frame[reg->frameno]; } static const char *kernel_type_name(const struct btf* btf, u32 id) { return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off); } static void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno) { env->scratched_regs |= 1U << regno; } static void mark_stack_slot_scratched(struct bpf_verifier_env *env, u32 spi) { env->scratched_stack_slots |= 1ULL << spi; } static bool reg_scratched(const struct bpf_verifier_env *env, u32 regno) { return (env->scratched_regs >> regno) & 1; } static bool stack_slot_scratched(const struct bpf_verifier_env *env, u64 regno) { return (env->scratched_stack_slots >> regno) & 1; } static bool verifier_state_scratched(const struct bpf_verifier_env *env) { return env->scratched_regs || env->scratched_stack_slots; } static void mark_verifier_state_clean(struct bpf_verifier_env *env) { env->scratched_regs = 0U; env->scratched_stack_slots = 0ULL; } /* Used for printing the entire verifier state. */ static void mark_verifier_state_scratched(struct bpf_verifier_env *env) { env->scratched_regs = ~0U; env->scratched_stack_slots = ~0ULL; } static enum bpf_dynptr_type arg_to_dynptr_type(enum bpf_arg_type arg_type) { switch (arg_type & DYNPTR_TYPE_FLAG_MASK) { case DYNPTR_TYPE_LOCAL: return BPF_DYNPTR_TYPE_LOCAL; case DYNPTR_TYPE_RINGBUF: return BPF_DYNPTR_TYPE_RINGBUF; default: return BPF_DYNPTR_TYPE_INVALID; } } static bool dynptr_type_refcounted(enum bpf_dynptr_type type) { return type == BPF_DYNPTR_TYPE_RINGBUF; } static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg, enum bpf_arg_type arg_type, int insn_idx) { struct bpf_func_state *state = func(env, reg); enum bpf_dynptr_type type; int spi, i, id; spi = get_spi(reg->off); if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS)) return -EINVAL; for (i = 0; i < BPF_REG_SIZE; i++) { state->stack[spi].slot_type[i] = STACK_DYNPTR; state->stack[spi - 1].slot_type[i] = STACK_DYNPTR; } type = arg_to_dynptr_type(arg_type); if (type == BPF_DYNPTR_TYPE_INVALID) return -EINVAL; state->stack[spi].spilled_ptr.dynptr.first_slot = true; state->stack[spi].spilled_ptr.dynptr.type = type; state->stack[spi - 1].spilled_ptr.dynptr.type = type; if (dynptr_type_refcounted(type)) { /* The id is used to track proper releasing */ id = acquire_reference_state(env, insn_idx); if (id < 0) return id; state->stack[spi].spilled_ptr.id = id; state->stack[spi - 1].spilled_ptr.id = id; } return 0; } static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); int spi, i; spi = get_spi(reg->off); if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS)) return -EINVAL; for (i = 0; i < BPF_REG_SIZE; i++) { state->stack[spi].slot_type[i] = STACK_INVALID; state->stack[spi - 1].slot_type[i] = STACK_INVALID; } /* Invalidate any slices associated with this dynptr */ if (dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type)) { release_reference(env, state->stack[spi].spilled_ptr.id); state->stack[spi].spilled_ptr.id = 0; state->stack[spi - 1].spilled_ptr.id = 0; } state->stack[spi].spilled_ptr.dynptr.first_slot = false; state->stack[spi].spilled_ptr.dynptr.type = 0; state->stack[spi - 1].spilled_ptr.dynptr.type = 0; return 0; } static bool is_dynptr_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); int spi = get_spi(reg->off); int i; if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS)) return true; for (i = 0; i < BPF_REG_SIZE; i++) { if (state->stack[spi].slot_type[i] == STACK_DYNPTR || state->stack[spi - 1].slot_type[i] == STACK_DYNPTR) return false; } return true; } bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); int spi = get_spi(reg->off); int i; if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS) || !state->stack[spi].spilled_ptr.dynptr.first_slot) return false; for (i = 0; i < BPF_REG_SIZE; i++) { if (state->stack[spi].slot_type[i] != STACK_DYNPTR || state->stack[spi - 1].slot_type[i] != STACK_DYNPTR) return false; } return true; } bool is_dynptr_type_expected(struct bpf_verifier_env *env, struct bpf_reg_state *reg, enum bpf_arg_type arg_type) { struct bpf_func_state *state = func(env, reg); enum bpf_dynptr_type dynptr_type; int spi = get_spi(reg->off); /* ARG_PTR_TO_DYNPTR takes any type of dynptr */ if (arg_type == ARG_PTR_TO_DYNPTR) return true; dynptr_type = arg_to_dynptr_type(arg_type); return state->stack[spi].spilled_ptr.dynptr.type == dynptr_type; } /* The reg state of a pointer or a bounded scalar was saved when * it was spilled to the stack. */ static bool is_spilled_reg(const struct bpf_stack_state *stack) { return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL; } static void scrub_spilled_slot(u8 *stype) { if (*stype != STACK_INVALID) *stype = STACK_MISC; } static void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_state *state, bool print_all) { const struct bpf_reg_state *reg; enum bpf_reg_type t; int i; if (state->frameno) verbose(env, " frame%d:", state->frameno); for (i = 0; i < MAX_BPF_REG; i++) { reg = &state->regs[i]; t = reg->type; if (t == NOT_INIT) continue; if (!print_all && !reg_scratched(env, i)) continue; verbose(env, " R%d", i); print_liveness(env, reg->live); verbose(env, "="); if (t == SCALAR_VALUE && reg->precise) verbose(env, "P"); if ((t == SCALAR_VALUE || t == PTR_TO_STACK) && tnum_is_const(reg->var_off)) { /* reg->off should be 0 for SCALAR_VALUE */ verbose(env, "%s", t == SCALAR_VALUE ? "" : reg_type_str(env, t)); verbose(env, "%lld", reg->var_off.value + reg->off); } else { const char *sep = ""; verbose(env, "%s", reg_type_str(env, t)); if (base_type(t) == PTR_TO_BTF_ID) verbose(env, "%s", kernel_type_name(reg->btf, reg->btf_id)); verbose(env, "("); /* * _a stands for append, was shortened to avoid multiline statements below. * This macro is used to output a comma separated list of attributes. */ #define verbose_a(fmt, ...) ({ verbose(env, "%s" fmt, sep, __VA_ARGS__); sep = ","; }) if (reg->id) verbose_a("id=%d", reg->id); if (reg_type_may_be_refcounted_or_null(t) && reg->ref_obj_id) verbose_a("ref_obj_id=%d", reg->ref_obj_id); if (t != SCALAR_VALUE) verbose_a("off=%d", reg->off); if (type_is_pkt_pointer(t)) verbose_a("r=%d", reg->range); else if (base_type(t) == CONST_PTR_TO_MAP || base_type(t) == PTR_TO_MAP_KEY || base_type(t) == PTR_TO_MAP_VALUE) verbose_a("ks=%d,vs=%d", reg->map_ptr->key_size, reg->map_ptr->value_size); if (tnum_is_const(reg->var_off)) { /* Typically an immediate SCALAR_VALUE, but * could be a pointer whose offset is too big * for reg->off */ verbose_a("imm=%llx", reg->var_off.value); } else { if (reg->smin_value != reg->umin_value && reg->smin_value != S64_MIN) verbose_a("smin=%lld", (long long)reg->smin_value); if (reg->smax_value != reg->umax_value && reg->smax_value != S64_MAX) verbose_a("smax=%lld", (long long)reg->smax_value); if (reg->umin_value != 0) verbose_a("umin=%llu", (unsigned long long)reg->umin_value); if (reg->umax_value != U64_MAX) verbose_a("umax=%llu", (unsigned long long)reg->umax_value); if (!tnum_is_unknown(reg->var_off)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose_a("var_off=%s", tn_buf); } if (reg->s32_min_value != reg->smin_value && reg->s32_min_value != S32_MIN) verbose_a("s32_min=%d", (int)(reg->s32_min_value)); if (reg->s32_max_value != reg->smax_value && reg->s32_max_value != S32_MAX) verbose_a("s32_max=%d", (int)(reg->s32_max_value)); if (reg->u32_min_value != reg->umin_value && reg->u32_min_value != U32_MIN) verbose_a("u32_min=%d", (int)(reg->u32_min_value)); if (reg->u32_max_value != reg->umax_value && reg->u32_max_value != U32_MAX) verbose_a("u32_max=%d", (int)(reg->u32_max_value)); } #undef verbose_a verbose(env, ")"); } } for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { char types_buf[BPF_REG_SIZE + 1]; bool valid = false; int j; for (j = 0; j < BPF_REG_SIZE; j++) { if (state->stack[i].slot_type[j] != STACK_INVALID) valid = true; types_buf[j] = slot_type_char[ state->stack[i].slot_type[j]]; } types_buf[BPF_REG_SIZE] = 0; if (!valid) continue; if (!print_all && !stack_slot_scratched(env, i)) continue; verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); print_liveness(env, state->stack[i].spilled_ptr.live); if (is_spilled_reg(&state->stack[i])) { reg = &state->stack[i].spilled_ptr; t = reg->type; verbose(env, "=%s", t == SCALAR_VALUE ? "" : reg_type_str(env, t)); if (t == SCALAR_VALUE && reg->precise) verbose(env, "P"); if (t == SCALAR_VALUE && tnum_is_const(reg->var_off)) verbose(env, "%lld", reg->var_off.value + reg->off); } else { verbose(env, "=%s", types_buf); } } if (state->acquired_refs && state->refs[0].id) { verbose(env, " refs=%d", state->refs[0].id); for (i = 1; i < state->acquired_refs; i++) if (state->refs[i].id) verbose(env, ",%d", state->refs[i].id); } if (state->in_callback_fn) verbose(env, " cb"); if (state->in_async_callback_fn) verbose(env, " async_cb"); verbose(env, "\n"); if (!print_all) mark_verifier_state_clean(env); } static inline u32 vlog_alignment(u32 pos) { return round_up(max(pos + BPF_LOG_MIN_ALIGNMENT / 2, BPF_LOG_ALIGNMENT), BPF_LOG_MIN_ALIGNMENT) - pos - 1; } static void print_insn_state(struct bpf_verifier_env *env, const struct bpf_func_state *state) { if (env->prev_log_len && env->prev_log_len == env->log.len_used) { /* remove new line character */ bpf_vlog_reset(&env->log, env->prev_log_len - 1); verbose(env, "%*c;", vlog_alignment(env->prev_insn_print_len), ' '); } else { verbose(env, "%d:", env->insn_idx); } print_verifier_state(env, state, false); } /* copy array src of length n * size bytes to dst. dst is reallocated if it's too * small to hold src. This is different from krealloc since we don't want to preserve * the contents of dst. * * Leaves dst untouched if src is NULL or length is zero. Returns NULL if memory could * not be allocated. */ static void *copy_array(void *dst, const void *src, size_t n, size_t size, gfp_t flags) { size_t alloc_bytes; void *orig = dst; size_t bytes; if (ZERO_OR_NULL_PTR(src)) goto out; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; alloc_bytes = max(ksize(orig), kmalloc_size_roundup(bytes)); dst = krealloc(orig, alloc_bytes, flags); if (!dst) { kfree(orig); return NULL; } memcpy(dst, src, bytes); out: return dst ? dst : ZERO_SIZE_PTR; } /* resize an array from old_n items to new_n items. the array is reallocated if it's too * small to hold new_n items. new items are zeroed out if the array grows. * * Contrary to krealloc_array, does not free arr if new_n is zero. */ static void *realloc_array(void *arr, size_t old_n, size_t new_n, size_t size) { size_t alloc_size; void *new_arr; if (!new_n || old_n == new_n) goto out; alloc_size = kmalloc_size_roundup(size_mul(new_n, size)); new_arr = krealloc(arr, alloc_size, GFP_KERNEL); if (!new_arr) { kfree(arr); return NULL; } arr = new_arr; if (new_n > old_n) memset(arr + old_n * size, 0, (new_n - old_n) * size); out: return arr ? arr : ZERO_SIZE_PTR; } static int copy_reference_state(struct bpf_func_state *dst, const struct bpf_func_state *src) { dst->refs = copy_array(dst->refs, src->refs, src->acquired_refs, sizeof(struct bpf_reference_state), GFP_KERNEL); if (!dst->refs) return -ENOMEM; dst->acquired_refs = src->acquired_refs; return 0; } static int copy_stack_state(struct bpf_func_state *dst, const struct bpf_func_state *src) { size_t n = src->allocated_stack / BPF_REG_SIZE; dst->stack = copy_array(dst->stack, src->stack, n, sizeof(struct bpf_stack_state), GFP_KERNEL); if (!dst->stack) return -ENOMEM; dst->allocated_stack = src->allocated_stack; return 0; } static int resize_reference_state(struct bpf_func_state *state, size_t n) { state->refs = realloc_array(state->refs, state->acquired_refs, n, sizeof(struct bpf_reference_state)); if (!state->refs) return -ENOMEM; state->acquired_refs = n; return 0; } static int grow_stack_state(struct bpf_func_state *state, int size) { size_t old_n = state->allocated_stack / BPF_REG_SIZE, n = size / BPF_REG_SIZE; if (old_n >= n) return 0; state->stack = realloc_array(state->stack, old_n, n, sizeof(struct bpf_stack_state)); if (!state->stack) return -ENOMEM; state->allocated_stack = size; return 0; } /* Acquire a pointer id from the env and update the state->refs to include * this new pointer reference. * On success, returns a valid pointer id to associate with the register * On failure, returns a negative errno. */ static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx) { struct bpf_func_state *state = cur_func(env); int new_ofs = state->acquired_refs; int id, err; err = resize_reference_state(state, state->acquired_refs + 1); if (err) return err; id = ++env->id_gen; state->refs[new_ofs].id = id; state->refs[new_ofs].insn_idx = insn_idx; state->refs[new_ofs].callback_ref = state->in_callback_fn ? state->frameno : 0; return id; } /* release function corresponding to acquire_reference_state(). Idempotent. */ static int release_reference_state(struct bpf_func_state *state, int ptr_id) { int i, last_idx; last_idx = state->acquired_refs - 1; for (i = 0; i < state->acquired_refs; i++) { if (state->refs[i].id == ptr_id) { /* Cannot release caller references in callbacks */ if (state->in_callback_fn && state->refs[i].callback_ref != state->frameno) return -EINVAL; if (last_idx && i != last_idx) memcpy(&state->refs[i], &state->refs[last_idx], sizeof(*state->refs)); memset(&state->refs[last_idx], 0, sizeof(*state->refs)); state->acquired_refs--; return 0; } } return -EINVAL; } static void free_func_state(struct bpf_func_state *state) { if (!state) return; kfree(state->refs); kfree(state->stack); kfree(state); } static void clear_jmp_history(struct bpf_verifier_state *state) { kfree(state->jmp_history); state->jmp_history = NULL; state->jmp_history_cnt = 0; } static void free_verifier_state(struct bpf_verifier_state *state, bool free_self) { int i; for (i = 0; i <= state->curframe; i++) { free_func_state(state->frame[i]); state->frame[i] = NULL; } clear_jmp_history(state); if (free_self) kfree(state); } /* copy verifier state from src to dst growing dst stack space * when necessary to accommodate larger src stack */ static int copy_func_state(struct bpf_func_state *dst, const struct bpf_func_state *src) { int err; memcpy(dst, src, offsetof(struct bpf_func_state, acquired_refs)); err = copy_reference_state(dst, src); if (err) return err; return copy_stack_state(dst, src); } static int copy_verifier_state(struct bpf_verifier_state *dst_state, const struct bpf_verifier_state *src) { struct bpf_func_state *dst; int i, err; dst_state->jmp_history = copy_array(dst_state->jmp_history, src->jmp_history, src->jmp_history_cnt, sizeof(struct bpf_idx_pair), GFP_USER); if (!dst_state->jmp_history) return -ENOMEM; dst_state->jmp_history_cnt = src->jmp_history_cnt; /* if dst has more stack frames then src frame, free them */ for (i = src->curframe + 1; i <= dst_state->curframe; i++) { free_func_state(dst_state->frame[i]); dst_state->frame[i] = NULL; } dst_state->speculative = src->speculative; dst_state->curframe = src->curframe; dst_state->active_spin_lock = src->active_spin_lock; dst_state->branches = src->branches; dst_state->parent = src->parent; dst_state->first_insn_idx = src->first_insn_idx; dst_state->last_insn_idx = src->last_insn_idx; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; if (!dst) { dst = kzalloc(sizeof(*dst), GFP_KERNEL); if (!dst) return -ENOMEM; dst_state->frame[i] = dst; } err = copy_func_state(dst, src->frame[i]); if (err) return err; } return 0; } static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { while (st) { u32 br = --st->branches; /* WARN_ON(br > 1) technically makes sense here, * but see comment in push_stack(), hence: */ WARN_ONCE((int)br < 0, "BUG update_branch_counts:branches_to_explore=%d\n", br); if (br) break; st = st->parent; } } static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx, int *insn_idx, bool pop_log) { struct bpf_verifier_state *cur = env->cur_state; struct bpf_verifier_stack_elem *elem, *head = env->head; int err; if (env->head == NULL) return -ENOENT; if (cur) { err = copy_verifier_state(cur, &head->st); if (err) return err; } if (pop_log) bpf_vlog_reset(&env->log, head->log_pos); if (insn_idx) *insn_idx = head->insn_idx; if (prev_insn_idx) *prev_insn_idx = head->prev_insn_idx; elem = head->next; free_verifier_state(&head->st, false); kfree(head); env->head = elem; env->stack_size--; return 0; } static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx, bool speculative) { struct bpf_verifier_state *cur = env->cur_state; struct bpf_verifier_stack_elem *elem; int err; elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL); if (!elem) goto err; elem->insn_idx = insn_idx; elem->prev_insn_idx = prev_insn_idx; elem->next = env->head; elem->log_pos = env->log.len_used; env->head = elem; env->stack_size++; err = copy_verifier_state(&elem->st, cur); if (err) goto err; elem->st.speculative |= speculative; if (env->stack_size > BPF_COMPLEXITY_LIMIT_JMP_SEQ) { verbose(env, "The sequence of %d jumps is too complex.\n", env->stack_size); goto err; } if (elem->st.parent) { ++elem->st.parent->branches; /* WARN_ON(branches > 2) technically makes sense here, * but * 1. speculative states will bump 'branches' for non-branch * instructions * 2. is_state_visited() heuristics may decide not to create * a new state for a sequence of branches and all such current * and cloned states will be pointing to a single parent state * which might have large 'branches' count. */ } return &elem->st; err: free_verifier_state(env->cur_state, true); env->cur_state = NULL; /* pop all elements and return */ while (!pop_stack(env, NULL, NULL, false)); return NULL; } #define CALLER_SAVED_REGS 6 static const int caller_saved[CALLER_SAVED_REGS] = { BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5 }; static void __mark_reg_not_init(const struct bpf_verifier_env *env, struct bpf_reg_state *reg); /* This helper doesn't clear reg->id */ static void ___mark_reg_known(struct bpf_reg_state *reg, u64 imm) { reg->var_off = tnum_const(imm); reg->smin_value = (s64)imm; reg->smax_value = (s64)imm; reg->umin_value = imm; reg->umax_value = imm; reg->s32_min_value = (s32)imm; reg->s32_max_value = (s32)imm; reg->u32_min_value = (u32)imm; reg->u32_max_value = (u32)imm; } /* Mark the unknown part of a register (variable offset or scalar value) as * known to have the value @imm. */ static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm) { /* Clear id, off, and union(map_ptr, range) */ memset(((u8 *)reg) + sizeof(reg->type), 0, offsetof(struct bpf_reg_state, var_off) - sizeof(reg->type)); ___mark_reg_known(reg, imm); } static void __mark_reg32_known(struct bpf_reg_state *reg, u64 imm) { reg->var_off = tnum_const_subreg(reg->var_off, imm); reg->s32_min_value = (s32)imm; reg->s32_max_value = (s32)imm; reg->u32_min_value = (u32)imm; reg->u32_max_value = (u32)imm; } /* Mark the 'variable offset' part of a register as zero. This should be * used only on registers holding a pointer type. */ static void __mark_reg_known_zero(struct bpf_reg_state *reg) { __mark_reg_known(reg, 0); } static void __mark_reg_const_zero(struct bpf_reg_state *reg) { __mark_reg_known(reg, 0); reg->type = SCALAR_VALUE; } static void mark_reg_known_zero(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno) { if (WARN_ON(regno >= MAX_BPF_REG)) { verbose(env, "mark_reg_known_zero(regs, %u)\n", regno); /* Something bad happened, let's kill all regs */ for (regno = 0; regno < MAX_BPF_REG; regno++) __mark_reg_not_init(env, regs + regno); return; } __mark_reg_known_zero(regs + regno); } static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) { if (base_type(reg->type) == PTR_TO_MAP_VALUE) { const struct bpf_map *map = reg->map_ptr; if (map->inner_map_meta) { reg->type = CONST_PTR_TO_MAP; reg->map_ptr = map->inner_map_meta; /* transfer reg's id which is unique for every map_lookup_elem * as UID of the inner map. */ if (map_value_has_timer(map->inner_map_meta)) reg->map_uid = reg->id; } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { reg->type = PTR_TO_XDP_SOCK; } else if (map->map_type == BPF_MAP_TYPE_SOCKMAP || map->map_type == BPF_MAP_TYPE_SOCKHASH) { reg->type = PTR_TO_SOCKET; } else { reg->type = PTR_TO_MAP_VALUE; } return; } reg->type &= ~PTR_MAYBE_NULL; } static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg) { return type_is_pkt_pointer(reg->type); } static bool reg_is_pkt_pointer_any(const struct bpf_reg_state *reg) { return reg_is_pkt_pointer(reg) || reg->type == PTR_TO_PACKET_END; } /* Unmodified PTR_TO_PACKET[_META,_END] register from ctx access. */ static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg, enum bpf_reg_type which) { /* The register can already have a range from prior markings. * This is fine as long as it hasn't been advanced from its * origin. */ return reg->type == which && reg->id == 0 && reg->off == 0 && tnum_equals_const(reg->var_off, 0); } /* Reset the min/max bounds of a register */ static void __mark_reg_unbounded(struct bpf_reg_state *reg) { reg->smin_value = S64_MIN; reg->smax_value = S64_MAX; reg->umin_value = 0; reg->umax_value = U64_MAX; reg->s32_min_value = S32_MIN; reg->s32_max_value = S32_MAX; reg->u32_min_value = 0; reg->u32_max_value = U32_MAX; } static void __mark_reg64_unbounded(struct bpf_reg_state *reg) { reg->smin_value = S64_MIN; reg->smax_value = S64_MAX; reg->umin_value = 0; reg->umax_value = U64_MAX; } static void __mark_reg32_unbounded(struct bpf_reg_state *reg) { reg->s32_min_value = S32_MIN; reg->s32_max_value = S32_MAX; reg->u32_min_value = 0; reg->u32_max_value = U32_MAX; } static void __update_reg32_bounds(struct bpf_reg_state *reg) { struct tnum var32_off = tnum_subreg(reg->var_off); /* min signed is max(sign bit) | min(other bits) */ reg->s32_min_value = max_t(s32, reg->s32_min_value, var32_off.value | (var32_off.mask & S32_MIN)); /* max signed is min(sign bit) | max(other bits) */ reg->s32_max_value = min_t(s32, reg->s32_max_value, var32_off.value | (var32_off.mask & S32_MAX)); reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)var32_off.value); reg->u32_max_value = min(reg->u32_max_value, (u32)(var32_off.value | var32_off.mask)); } static void __update_reg64_bounds(struct bpf_reg_state *reg) { /* min signed is max(sign bit) | min(other bits) */ reg->smin_value = max_t(s64, reg->smin_value, reg->var_off.value | (reg->var_off.mask & S64_MIN)); /* max signed is min(sign bit) | max(other bits) */ reg->smax_value = min_t(s64, reg->smax_value, reg->var_off.value | (reg->var_off.mask & S64_MAX)); reg->umin_value = max(reg->umin_value, reg->var_off.value); reg->umax_value = min(reg->umax_value, reg->var_off.value | reg->var_off.mask); } static void __update_reg_bounds(struct bpf_reg_state *reg) { __update_reg32_bounds(reg); __update_reg64_bounds(reg); } /* Uses signed min/max values to inform unsigned, and vice-versa */ static void __reg32_deduce_bounds(struct bpf_reg_state *reg) { /* Learn sign from signed bounds. * If we cannot cross the sign boundary, then signed and unsigned bounds * are the same, so combine. This works even in the negative case, e.g. * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff. */ if (reg->s32_min_value >= 0 || reg->s32_max_value < 0) { reg->s32_min_value = reg->u32_min_value = max_t(u32, reg->s32_min_value, reg->u32_min_value); reg->s32_max_value = reg->u32_max_value = min_t(u32, reg->s32_max_value, reg->u32_max_value); return; } /* Learn sign from unsigned bounds. Signed bounds cross the sign * boundary, so we must be careful. */ if ((s32)reg->u32_max_value >= 0) { /* Positive. We can't learn anything from the smin, but smax * is positive, hence safe. */ reg->s32_min_value = reg->u32_min_value; reg->s32_max_value = reg->u32_max_value = min_t(u32, reg->s32_max_value, reg->u32_max_value); } else if ((s32)reg->u32_min_value < 0) { /* Negative. We can't learn anything from the smax, but smin * is negative, hence safe. */ reg->s32_min_value = reg->u32_min_value = max_t(u32, reg->s32_min_value, reg->u32_min_value); reg->s32_max_value = reg->u32_max_value; } } static void __reg64_deduce_bounds(struct bpf_reg_state *reg) { /* Learn sign from signed bounds. * If we cannot cross the sign boundary, then signed and unsigned bounds * are the same, so combine. This works even in the negative case, e.g. * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff. */ if (reg->smin_value >= 0 || reg->smax_value < 0) { reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value, reg->umin_value); reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value, reg->umax_value); return; } /* Learn sign from unsigned bounds. Signed bounds cross the sign * boundary, so we must be careful. */ if ((s64)reg->umax_value >= 0) { /* Positive. We can't learn anything from the smin, but smax * is positive, hence safe. */ reg->smin_value = reg->umin_value; reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value, reg->umax_value); } else if ((s64)reg->umin_value < 0) { /* Negative. We can't learn anything from the smax, but smin * is negative, hence safe. */ reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value, reg->umin_value); reg->smax_value = reg->umax_value; } } static void __reg_deduce_bounds(struct bpf_reg_state *reg) { __reg32_deduce_bounds(reg); __reg64_deduce_bounds(reg); } /* Attempts to improve var_off based on unsigned min/max information */ static void __reg_bound_offset(struct bpf_reg_state *reg) { struct tnum var64_off = tnum_intersect(reg->var_off, tnum_range(reg->umin_value, reg->umax_value)); struct tnum var32_off = tnum_intersect(tnum_subreg(var64_off), tnum_range(reg->u32_min_value, reg->u32_max_value)); reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off); } static void reg_bounds_sync(struct bpf_reg_state *reg) { /* We might have learned new bounds from the var_off. */ __update_reg_bounds(reg); /* We might have learned something about the sign bit. */ __reg_deduce_bounds(reg); /* We might have learned some bits from the bounds. */ __reg_bound_offset(reg); /* Intersecting with the old var_off might have improved our bounds * slightly, e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), * then new var_off is (0; 0x7f...fc) which improves our umax. */ __update_reg_bounds(reg); } static bool __reg32_bound_s64(s32 a) { return a >= 0 && a <= S32_MAX; } static void __reg_assign_32_into_64(struct bpf_reg_state *reg) { reg->umin_value = reg->u32_min_value; reg->umax_value = reg->u32_max_value; /* Attempt to pull 32-bit signed bounds into 64-bit bounds but must * be positive otherwise set to worse case bounds and refine later * from tnum. */ if (__reg32_bound_s64(reg->s32_min_value) && __reg32_bound_s64(reg->s32_max_value)) { reg->smin_value = reg->s32_min_value; reg->smax_value = reg->s32_max_value; } else { reg->smin_value = 0; reg->smax_value = U32_MAX; } } static void __reg_combine_32_into_64(struct bpf_reg_state *reg) { /* special case when 64-bit register has upper 32-bit register * zeroed. Typically happens after zext or <<32, >>32 sequence * allowing us to use 32-bit bounds directly, */ if (tnum_equals_const(tnum_clear_subreg(reg->var_off), 0)) { __reg_assign_32_into_64(reg); } else { /* Otherwise the best we can do is push lower 32bit known and * unknown bits into register (var_off set from jmp logic) * then learn as much as possible from the 64-bit tnum * known and unknown bits. The previous smin/smax bounds are * invalid here because of jmp32 compare so mark them unknown * so they do not impact tnum bounds calculation. */ __mark_reg64_unbounded(reg); } reg_bounds_sync(reg); } static bool __reg64_bound_s32(s64 a) { return a >= S32_MIN && a <= S32_MAX; } static bool __reg64_bound_u32(u64 a) { return a >= U32_MIN && a <= U32_MAX; } static void __reg_combine_64_into_32(struct bpf_reg_state *reg) { __mark_reg32_unbounded(reg); if (__reg64_bound_s32(reg->smin_value) && __reg64_bound_s32(reg->smax_value)) { reg->s32_min_value = (s32)reg->smin_value; reg->s32_max_value = (s32)reg->smax_value; } if (__reg64_bound_u32(reg->umin_value) && __reg64_bound_u32(reg->umax_value)) { reg->u32_min_value = (u32)reg->umin_value; reg->u32_max_value = (u32)reg->umax_value; } reg_bounds_sync(reg); } /* Mark a register as having a completely unknown (scalar) value. */ static void __mark_reg_unknown(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) { /* * Clear type, id, off, and union(map_ptr, range) and * padding between 'type' and union */ memset(reg, 0, offsetof(struct bpf_reg_state, var_off)); reg->type = SCALAR_VALUE; reg->var_off = tnum_unknown; reg->frameno = 0; reg->precise = !env->bpf_capable; __mark_reg_unbounded(reg); } static void mark_reg_unknown(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno) { if (WARN_ON(regno >= MAX_BPF_REG)) { verbose(env, "mark_reg_unknown(regs, %u)\n", regno); /* Something bad happened, let's kill all regs except FP */ for (regno = 0; regno < BPF_REG_FP; regno++) __mark_reg_not_init(env, regs + regno); return; } __mark_reg_unknown(env, regs + regno); } static void __mark_reg_not_init(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) { __mark_reg_unknown(env, reg); reg->type = NOT_INIT; } static void mark_reg_not_init(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno) { if (WARN_ON(regno >= MAX_BPF_REG)) { verbose(env, "mark_reg_not_init(regs, %u)\n", regno); /* Something bad happened, let's kill all regs except FP */ for (regno = 0; regno < BPF_REG_FP; regno++) __mark_reg_not_init(env, regs + regno); return; } __mark_reg_not_init(env, regs + regno); } static void mark_btf_ld_reg(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno, enum bpf_reg_type reg_type, struct btf *btf, u32 btf_id, enum bpf_type_flag flag) { if (reg_type == SCALAR_VALUE) { mark_reg_unknown(env, regs, regno); return; } mark_reg_known_zero(env, regs, regno); regs[regno].type = PTR_TO_BTF_ID | flag; regs[regno].btf = btf; regs[regno].btf_id = btf_id; } #define DEF_NOT_SUBREG (0) static void init_reg_state(struct bpf_verifier_env *env, struct bpf_func_state *state) { struct bpf_reg_state *regs = state->regs; int i; for (i = 0; i < MAX_BPF_REG; i++) { mark_reg_not_init(env, regs, i); regs[i].live = REG_LIVE_NONE; regs[i].parent = NULL; regs[i].subreg_def = DEF_NOT_SUBREG; } /* frame pointer */ regs[BPF_REG_FP].type = PTR_TO_STACK; mark_reg_known_zero(env, regs, BPF_REG_FP); regs[BPF_REG_FP].frameno = state->frameno; } #define BPF_MAIN_FUNC (-1) static void init_func_state(struct bpf_verifier_env *env, struct bpf_func_state *state, int callsite, int frameno, int subprogno) { state->callsite = callsite; state->frameno = frameno; state->subprogno = subprogno; state->callback_ret_range = tnum_range(0, 0); init_reg_state(env, state); mark_verifier_state_scratched(env); } /* Similar to push_stack(), but for async callbacks */ static struct bpf_verifier_state *push_async_cb(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx, int subprog) { struct bpf_verifier_stack_elem *elem; struct bpf_func_state *frame; elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL); if (!elem) goto err; elem->insn_idx = insn_idx; elem->prev_insn_idx = prev_insn_idx; elem->next = env->head; elem->log_pos = env->log.len_used; env->head = elem; env->stack_size++; if (env->stack_size > BPF_COMPLEXITY_LIMIT_JMP_SEQ) { verbose(env, "The sequence of %d jumps is too complex for async cb.\n", env->stack_size); goto err; } /* Unlike push_stack() do not copy_verifier_state(). * The caller state doesn't matter. * This is async callback. It starts in a fresh stack. * Initialize it similar to do_check_common(). */ elem->st.branches = 1; frame = kzalloc(sizeof(*frame), GFP_KERNEL); if (!frame) goto err; init_func_state(env, frame, BPF_MAIN_FUNC /* callsite */, 0 /* frameno within this callchain */, subprog /* subprog number within this prog */); elem->st.frame[0] = frame; return &elem->st; err: free_verifier_state(env->cur_state, true); env->cur_state = NULL; /* pop all elements and return */ while (!pop_stack(env, NULL, NULL, false)); return NULL; } enum reg_arg_type { SRC_OP, /* register is used as source operand */ DST_OP, /* register is used as destination operand */ DST_OP_NO_MARK /* same as above, check only, don't mark */ }; static int cmp_subprogs(const void *a, const void *b) { return ((struct bpf_subprog_info *)a)->start - ((struct bpf_subprog_info *)b)->start; } static int find_subprog(struct bpf_verifier_env *env, int off) { struct bpf_subprog_info *p; p = bsearch(&off, env->subprog_info, env->subprog_cnt, sizeof(env->subprog_info[0]), cmp_subprogs); if (!p) return -ENOENT; return p - env->subprog_info; } static int add_subprog(struct bpf_verifier_env *env, int off) { int insn_cnt = env->prog->len; int ret; if (off >= insn_cnt || off < 0) { verbose(env, "call to invalid destination\n"); return -EINVAL; } ret = find_subprog(env, off); if (ret >= 0) return ret; if (env->subprog_cnt >= BPF_MAX_SUBPROGS) { verbose(env, "too many subprograms\n"); return -E2BIG; } /* determine subprog starts. The end is one before the next starts */ env->subprog_info[env->subprog_cnt++].start = off; sort(env->subprog_info, env->subprog_cnt, sizeof(env->subprog_info[0]), cmp_subprogs, NULL); return env->subprog_cnt - 1; } #define MAX_KFUNC_DESCS 256 #define MAX_KFUNC_BTFS 256 struct bpf_kfunc_desc { struct btf_func_model func_model; u32 func_id; s32 imm; u16 offset; }; struct bpf_kfunc_btf { struct btf *btf; struct module *module; u16 offset; }; struct bpf_kfunc_desc_tab { struct bpf_kfunc_desc descs[MAX_KFUNC_DESCS]; u32 nr_descs; }; struct bpf_kfunc_btf_tab { struct bpf_kfunc_btf descs[MAX_KFUNC_BTFS]; u32 nr_descs; }; static int kfunc_desc_cmp_by_id_off(const void *a, const void *b) { const struct bpf_kfunc_desc *d0 = a; const struct bpf_kfunc_desc *d1 = b; /* func_id is not greater than BTF_MAX_TYPE */ return d0->func_id - d1->func_id ?: d0->offset - d1->offset; } static int kfunc_btf_cmp_by_off(const void *a, const void *b) { const struct bpf_kfunc_btf *d0 = a; const struct bpf_kfunc_btf *d1 = b; return d0->offset - d1->offset; } static const struct bpf_kfunc_desc * find_kfunc_desc(const struct bpf_prog *prog, u32 func_id, u16 offset) { struct bpf_kfunc_desc desc = { .func_id = func_id, .offset = offset, }; struct bpf_kfunc_desc_tab *tab; tab = prog->aux->kfunc_tab; return bsearch(&desc, tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_desc_cmp_by_id_off); } static struct btf *__find_kfunc_desc_btf(struct bpf_verifier_env *env, s16 offset) { struct bpf_kfunc_btf kf_btf = { .offset = offset }; struct bpf_kfunc_btf_tab *tab; struct bpf_kfunc_btf *b; struct module *mod; struct btf *btf; int btf_fd; tab = env->prog->aux->kfunc_btf_tab; b = bsearch(&kf_btf, tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_btf_cmp_by_off); if (!b) { if (tab->nr_descs == MAX_KFUNC_BTFS) { verbose(env, "too many different module BTFs\n"); return ERR_PTR(-E2BIG); } if (bpfptr_is_null(env->fd_array)) { verbose(env, "kfunc offset > 0 without fd_array is invalid\n"); return ERR_PTR(-EPROTO); } if (copy_from_bpfptr_offset(&btf_fd, env->fd_array, offset * sizeof(btf_fd), sizeof(btf_fd))) return ERR_PTR(-EFAULT); btf = btf_get_by_fd(btf_fd); if (IS_ERR(btf)) { verbose(env, "invalid module BTF fd specified\n"); return btf; } if (!btf_is_module(btf)) { verbose(env, "BTF fd for kfunc is not a module BTF\n"); btf_put(btf); return ERR_PTR(-EINVAL); } mod = btf_try_get_module(btf); if (!mod) { btf_put(btf); return ERR_PTR(-ENXIO); } b = &tab->descs[tab->nr_descs++]; b->btf = btf; b->module = mod; b->offset = offset; /* sort() reorders entries by value, so b may no longer point * to the right entry after this */ sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_btf_cmp_by_off, NULL); } else { btf = b->btf; } return btf; } void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab) { if (!tab) return; while (tab->nr_descs--) { module_put(tab->descs[tab->nr_descs].module); btf_put(tab->descs[tab->nr_descs].btf); } kfree(tab); } static struct btf *find_kfunc_desc_btf(struct bpf_verifier_env *env, s16 offset) { if (offset) { if (offset < 0) { /* In the future, this can be allowed to increase limit * of fd index into fd_array, interpreted as u16. */ verbose(env, "negative offset disallowed for kernel module function call\n"); return ERR_PTR(-EINVAL); } return __find_kfunc_desc_btf(env, offset); } return btf_vmlinux ?: ERR_PTR(-ENOENT); } static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset) { const struct btf_type *func, *func_proto; struct bpf_kfunc_btf_tab *btf_tab; struct bpf_kfunc_desc_tab *tab; struct bpf_prog_aux *prog_aux; struct bpf_kfunc_desc *desc; const char *func_name; struct btf *desc_btf; unsigned long call_imm; unsigned long addr; int err; prog_aux = env->prog->aux; tab = prog_aux->kfunc_tab; btf_tab = prog_aux->kfunc_btf_tab; if (!tab) { if (!btf_vmlinux) { verbose(env, "calling kernel function is not supported without CONFIG_DEBUG_INFO_BTF\n"); return -ENOTSUPP; } if (!env->prog->jit_requested) { verbose(env, "JIT is required for calling kernel function\n"); return -ENOTSUPP; } if (!bpf_jit_supports_kfunc_call()) { verbose(env, "JIT does not support calling kernel function\n"); return -ENOTSUPP; } if (!env->prog->gpl_compatible) { verbose(env, "cannot call kernel function from non-GPL compatible program\n"); return -EINVAL; } tab = kzalloc(sizeof(*tab), GFP_KERNEL); if (!tab) return -ENOMEM; prog_aux->kfunc_tab = tab; } /* func_id == 0 is always invalid, but instead of returning an error, be * conservative and wait until the code elimination pass before returning * error, so that invalid calls that get pruned out can be in BPF programs * loaded from userspace. It is also required that offset be untouched * for such calls. */ if (!func_id && !offset) return 0; if (!btf_tab && offset) { btf_tab = kzalloc(sizeof(*btf_tab), GFP_KERNEL); if (!btf_tab) return -ENOMEM; prog_aux->kfunc_btf_tab = btf_tab; } desc_btf = find_kfunc_desc_btf(env, offset); if (IS_ERR(desc_btf)) { verbose(env, "failed to find BTF for kernel function\n"); return PTR_ERR(desc_btf); } if (find_kfunc_desc(env->prog, func_id, offset)) return 0; if (tab->nr_descs == MAX_KFUNC_DESCS) { verbose(env, "too many different kernel function calls\n"); return -E2BIG; } func = btf_type_by_id(desc_btf, func_id); if (!func || !btf_type_is_func(func)) { verbose(env, "kernel btf_id %u is not a function\n", func_id); return -EINVAL; } func_proto = btf_type_by_id(desc_btf, func->type); if (!func_proto || !btf_type_is_func_proto(func_proto)) { verbose(env, "kernel function btf_id %u does not have a valid func_proto\n", func_id); return -EINVAL; } func_name = btf_name_by_offset(desc_btf, func->name_off); addr = kallsyms_lookup_name(func_name); if (!addr) { verbose(env, "cannot find address for kernel function %s\n", func_name); return -EINVAL; } call_imm = BPF_CALL_IMM(addr); /* Check whether or not the relative offset overflows desc->imm */ if ((unsigned long)(s32)call_imm != call_imm) { verbose(env, "address of kernel function %s is out of range\n", func_name); return -EINVAL; } desc = &tab->descs[tab->nr_descs++]; desc->func_id = func_id; desc->imm = call_imm; desc->offset = offset; err = btf_distill_func_proto(&env->log, desc_btf, func_proto, func_name, &desc->func_model); if (!err) sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_desc_cmp_by_id_off, NULL); return err; } static int kfunc_desc_cmp_by_imm(const void *a, const void *b) { const struct bpf_kfunc_desc *d0 = a; const struct bpf_kfunc_desc *d1 = b; if (d0->imm > d1->imm) return 1; else if (d0->imm < d1->imm) return -1; return 0; } static void sort_kfunc_descs_by_imm(struct bpf_prog *prog) { struct bpf_kfunc_desc_tab *tab; tab = prog->aux->kfunc_tab; if (!tab) return; sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_desc_cmp_by_imm, NULL); } bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog) { return !!prog->aux->kfunc_tab; } const struct btf_func_model * bpf_jit_find_kfunc_model(const struct bpf_prog *prog, const struct bpf_insn *insn) { const struct bpf_kfunc_desc desc = { .imm = insn->imm, }; const struct bpf_kfunc_desc *res; struct bpf_kfunc_desc_tab *tab; tab = prog->aux->kfunc_tab; res = bsearch(&desc, tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_desc_cmp_by_imm); return res ? &res->func_model : NULL; } static int add_subprog_and_kfunc(struct bpf_verifier_env *env) { struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn *insn = env->prog->insnsi; int i, ret, insn_cnt = env->prog->len; /* Add entry function. */ ret = add_subprog(env, 0); if (ret) return ret; for (i = 0; i < insn_cnt; i++, insn++) { if (!bpf_pseudo_func(insn) && !bpf_pseudo_call(insn) && !bpf_pseudo_kfunc_call(insn)) continue; if (!env->bpf_capable) { verbose(env, "loading/calling other bpf or kernel functions are allowed for CAP_BPF and CAP_SYS_ADMIN\n"); return -EPERM; } if (bpf_pseudo_func(insn) || bpf_pseudo_call(insn)) ret = add_subprog(env, i + insn->imm + 1); else ret = add_kfunc_call(env, insn->imm, insn->off); if (ret < 0) return ret; } /* Add a fake 'exit' subprog which could simplify subprog iteration * logic. 'subprog_cnt' should not be increased. */ subprog[env->subprog_cnt].start = insn_cnt; if (env->log.level & BPF_LOG_LEVEL2) for (i = 0; i < env->subprog_cnt; i++) verbose(env, "func#%d @%d\n", i, subprog[i].start); return 0; } static int check_subprogs(struct bpf_verifier_env *env) { int i, subprog_start, subprog_end, off, cur_subprog = 0; struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; /* now check that all jumps are within the same subprog */ subprog_start = subprog[cur_subprog].start; subprog_end = subprog[cur_subprog + 1].start; for (i = 0; i < insn_cnt; i++) { u8 code = insn[i].code; if (code == (BPF_JMP | BPF_CALL) && insn[i].imm == BPF_FUNC_tail_call && insn[i].src_reg != BPF_PSEUDO_CALL) subprog[cur_subprog].has_tail_call = true; if (BPF_CLASS(code) == BPF_LD && (BPF_MODE(code) == BPF_ABS || BPF_MODE(code) == BPF_IND)) subprog[cur_subprog].has_ld_abs = true; if (BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32) goto next; if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL) goto next; off = i + insn[i].off + 1; if (off < subprog_start || off >= subprog_end) { verbose(env, "jump out of range from insn %d to %d\n", i, off); return -EINVAL; } next: if (i == subprog_end - 1) { /* to avoid fall-through from one subprog into another * the last insn of the subprog should be either exit * or unconditional jump back */ if (code != (BPF_JMP | BPF_EXIT) && code != (BPF_JMP | BPF_JA)) { verbose(env, "last insn is not an exit or jmp\n"); return -EINVAL; } subprog_start = subprog_end; cur_subprog++; if (cur_subprog < env->subprog_cnt) subprog_end = subprog[cur_subprog + 1].start; } } return 0; } /* Parentage chain of this register (or stack slot) should take care of all * issues like callee-saved registers, stack slot allocation time, etc. */ static int mark_reg_read(struct bpf_verifier_env *env, const struct bpf_reg_state *state, struct bpf_reg_state *parent, u8 flag) { bool writes = parent == state->parent; /* Observe write marks */ int cnt = 0; while (parent) { /* if read wasn't screened by an earlier write ... */ if (writes && state->live & REG_LIVE_WRITTEN) break; if (parent->live & REG_LIVE_DONE) { verbose(env, "verifier BUG type %s var_off %lld off %d\n", reg_type_str(env, parent->type), parent->var_off.value, parent->off); return -EFAULT; } /* The first condition is more likely to be true than the * second, checked it first. */ if ((parent->live & REG_LIVE_READ) == flag || parent->live & REG_LIVE_READ64) /* The parentage chain never changes and * this parent was already marked as LIVE_READ. * There is no need to keep walking the chain again and * keep re-marking all parents as LIVE_READ. * This case happens when the same register is read * multiple times without writes into it in-between. * Also, if parent has the stronger REG_LIVE_READ64 set, * then no need to set the weak REG_LIVE_READ32. */ break; /* ... then we depend on parent's value */ parent->live |= flag; /* REG_LIVE_READ64 overrides REG_LIVE_READ32. */ if (flag == REG_LIVE_READ64) parent->live &= ~REG_LIVE_READ32; state = parent; parent = state->parent; writes = true; cnt++; } if (env->longest_mark_read_walk < cnt) env->longest_mark_read_walk = cnt; return 0; } /* This function is supposed to be used by the following 32-bit optimization * code only. It returns TRUE if the source or destination register operates * on 64-bit, otherwise return FALSE. */ static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn, u32 regno, struct bpf_reg_state *reg, enum reg_arg_type t) { u8 code, class, op; code = insn->code; class = BPF_CLASS(code); op = BPF_OP(code); if (class == BPF_JMP) { /* BPF_EXIT for "main" will reach here. Return TRUE * conservatively. */ if (op == BPF_EXIT) return true; if (op == BPF_CALL) { /* BPF to BPF call will reach here because of marking * caller saved clobber with DST_OP_NO_MARK for which we * don't care the register def because they are anyway * marked as NOT_INIT already. */ if (insn->src_reg == BPF_PSEUDO_CALL) return false; /* Helper call will reach here because of arg type * check, conservatively return TRUE. */ if (t == SRC_OP) return true; return false; } } if (class == BPF_ALU64 || class == BPF_JMP || /* BPF_END always use BPF_ALU class. */ (class == BPF_ALU && op == BPF_END && insn->imm == 64)) return true; if (class == BPF_ALU || class == BPF_JMP32) return false; if (class == BPF_LDX) { if (t != SRC_OP) return BPF_SIZE(code) == BPF_DW; /* LDX source must be ptr. */ return true; } if (class == BPF_STX) { /* BPF_STX (including atomic variants) has multiple source * operands, one of which is a ptr. Check whether the caller is * asking about it. */ if (t == SRC_OP && reg->type != SCALAR_VALUE) return true; return BPF_SIZE(code) == BPF_DW; } if (class == BPF_LD) { u8 mode = BPF_MODE(code); /* LD_IMM64 */ if (mode == BPF_IMM) return true; /* Both LD_IND and LD_ABS return 32-bit data. */ if (t != SRC_OP) return false; /* Implicit ctx ptr. */ if (regno == BPF_REG_6) return true; /* Explicit source could be any width. */ return true; } if (class == BPF_ST) /* The only source register for BPF_ST is a ptr. */ return true; /* Conservatively return true at default. */ return true; } /* Return the regno defined by the insn, or -1. */ static int insn_def_regno(const struct bpf_insn *insn) { switch (BPF_CLASS(insn->code)) { case BPF_JMP: case BPF_JMP32: case BPF_ST: return -1; case BPF_STX: if (BPF_MODE(insn->code) == BPF_ATOMIC && (insn->imm & BPF_FETCH)) { if (insn->imm == BPF_CMPXCHG) return BPF_REG_0; else return insn->src_reg; } else { return -1; } default: return insn->dst_reg; } } /* Return TRUE if INSN has defined any 32-bit value explicitly. */ static bool insn_has_def32(struct bpf_verifier_env *env, struct bpf_insn *insn) { int dst_reg = insn_def_regno(insn); if (dst_reg == -1) return false; return !is_reg64(env, insn, dst_reg, NULL, DST_OP); } static void mark_insn_zext(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { s32 def_idx = reg->subreg_def; if (def_idx == DEF_NOT_SUBREG) return; env->insn_aux_data[def_idx - 1].zext_dst = true; /* The dst will be zero extended, so won't be sub-register anymore. */ reg->subreg_def = DEF_NOT_SUBREG; } static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, enum reg_arg_type t) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_insn *insn = env->prog->insnsi + env->insn_idx; struct bpf_reg_state *reg, *regs = state->regs; bool rw64; if (regno >= MAX_BPF_REG) { verbose(env, "R%d is invalid\n", regno); return -EINVAL; } mark_reg_scratched(env, regno); reg = ®s[regno]; rw64 = is_reg64(env, insn, regno, reg, t); if (t == SRC_OP) { /* check whether register used as source operand can be read */ if (reg->type == NOT_INIT) { verbose(env, "R%d !read_ok\n", regno); return -EACCES; } /* We don't need to worry about FP liveness because it's read-only */ if (regno == BPF_REG_FP) return 0; if (rw64) mark_insn_zext(env, reg); return mark_reg_read(env, reg, reg->parent, rw64 ? REG_LIVE_READ64 : REG_LIVE_READ32); } else { /* check whether register used as dest operand can be written to */ if (regno == BPF_REG_FP) { verbose(env, "frame pointer is read only\n"); return -EACCES; } reg->live |= REG_LIVE_WRITTEN; reg->subreg_def = rw64 ? DEF_NOT_SUBREG : env->insn_idx + 1; if (t == DST_OP) mark_reg_unknown(env, regs, regno); } return 0; } /* for any branch, call, exit record the history of jmps in the given state */ static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur) { u32 cnt = cur->jmp_history_cnt; struct bpf_idx_pair *p; size_t alloc_size; cnt++; alloc_size = kmalloc_size_roundup(size_mul(cnt, sizeof(*p))); p = krealloc(cur->jmp_history, alloc_size, GFP_USER); if (!p) return -ENOMEM; p[cnt - 1].idx = env->insn_idx; p[cnt - 1].prev_idx = env->prev_insn_idx; cur->jmp_history = p; cur->jmp_history_cnt = cnt; return 0; } /* Backtrack one insn at a time. If idx is not at the top of recorded * history then previous instruction came from straight line execution. * Return -ENOENT if we exhausted all instructions within given state. * * It's legal to have a bit of a looping with the same starting and ending * insn index within the same state, e.g.: 3->4->5->3, so just because current * instruction index is the same as state's first_idx doesn't mean we are * done. If there is still some jump history left, we should keep going. We * need to take into account that we might have a jump history between given * state's parent and itself, due to checkpointing. In this case, we'll have * history entry recording a jump from last instruction of parent state and * first instruction of given state. */ static int get_prev_insn_idx(struct bpf_verifier_state *st, int i, u32 *history) { u32 cnt = *history; if (i == st->first_insn_idx) { if (cnt == 0) return -ENOENT; if (cnt == 1 && st->jmp_history[0].idx == i) return -ENOENT; } if (cnt && st->jmp_history[cnt - 1].idx == i) { i = st->jmp_history[cnt - 1].prev_idx; (*history)--; } else { i--; } return i; } static const char *disasm_kfunc_name(void *data, const struct bpf_insn *insn) { const struct btf_type *func; struct btf *desc_btf; if (insn->src_reg != BPF_PSEUDO_KFUNC_CALL) return NULL; desc_btf = find_kfunc_desc_btf(data, insn->off); if (IS_ERR(desc_btf)) return "<error>"; func = btf_type_by_id(desc_btf, insn->imm); return btf_name_by_offset(desc_btf, func->name_off); } /* For given verifier state backtrack_insn() is called from the last insn to * the first insn. Its purpose is to compute a bitmask of registers and * stack slots that needs precision in the parent verifier state. */ static int backtrack_insn(struct bpf_verifier_env *env, int idx, u32 *reg_mask, u64 *stack_mask) { const struct bpf_insn_cbs cbs = { .cb_call = disasm_kfunc_name, .cb_print = verbose, .private_data = env, }; struct bpf_insn *insn = env->prog->insnsi + idx; u8 class = BPF_CLASS(insn->code); u8 opcode = BPF_OP(insn->code); u8 mode = BPF_MODE(insn->code); u32 dreg = 1u << insn->dst_reg; u32 sreg = 1u << insn->src_reg; u32 spi; if (insn->code == 0) return 0; if (env->log.level & BPF_LOG_LEVEL2) { verbose(env, "regs=%x stack=%llx before ", *reg_mask, *stack_mask); verbose(env, "%d: ", idx); print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); } if (class == BPF_ALU || class == BPF_ALU64) { if (!(*reg_mask & dreg)) return 0; if (opcode == BPF_END || opcode == BPF_NEG) { /* sreg is reserved and unused * dreg still need precision before this insn */ return 0; } else if (opcode == BPF_MOV) { if (BPF_SRC(insn->code) == BPF_X) { /* dreg = sreg * dreg needs precision after this insn * sreg needs precision before this insn */ *reg_mask &= ~dreg; *reg_mask |= sreg; } else { /* dreg = K * dreg needs precision after this insn. * Corresponding register is already marked * as precise=true in this verifier state. * No further markings in parent are necessary */ *reg_mask &= ~dreg; } } else { if (BPF_SRC(insn->code) == BPF_X) { /* dreg += sreg * both dreg and sreg need precision * before this insn */ *reg_mask |= sreg; } /* else dreg += K * dreg still needs precision before this insn */ } } else if (class == BPF_LDX) { if (!(*reg_mask & dreg)) return 0; *reg_mask &= ~dreg; /* scalars can only be spilled into stack w/o losing precision. * Load from any other memory can be zero extended. * The desire to keep that precision is already indicated * by 'precise' mark in corresponding register of this state. * No further tracking necessary. */ if (insn->src_reg != BPF_REG_FP) return 0; /* dreg = *(u64 *)[fp - off] was a fill from the stack. * that [fp - off] slot contains scalar that needs to be * tracked with precision */ spi = (-insn->off - 1) / BPF_REG_SIZE; if (spi >= 64) { verbose(env, "BUG spi %d\n", spi); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } *stack_mask |= 1ull << spi; } else if (class == BPF_STX || class == BPF_ST) { if (*reg_mask & dreg) /* stx & st shouldn't be using _scalar_ dst_reg * to access memory. It means backtracking * encountered a case of pointer subtraction. */ return -ENOTSUPP; /* scalars can only be spilled into stack */ if (insn->dst_reg != BPF_REG_FP) return 0; spi = (-insn->off - 1) / BPF_REG_SIZE; if (spi >= 64) { verbose(env, "BUG spi %d\n", spi); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } if (!(*stack_mask & (1ull << spi))) return 0; *stack_mask &= ~(1ull << spi); if (class == BPF_STX) *reg_mask |= sreg; } else if (class == BPF_JMP || class == BPF_JMP32) { if (opcode == BPF_CALL) { if (insn->src_reg == BPF_PSEUDO_CALL) return -ENOTSUPP; /* kfunc with imm==0 is invalid and fixup_kfunc_call will * catch this error later. Make backtracking conservative * with ENOTSUPP. */ if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && insn->imm == 0) return -ENOTSUPP; /* BPF helpers that invoke callback subprogs are * equivalent to BPF_PSEUDO_CALL above */ if (insn->src_reg == 0 && is_callback_calling_function(insn->imm)) return -ENOTSUPP; /* regular helper call sets R0 */ *reg_mask &= ~1; if (*reg_mask & 0x3f) { /* if backtracing was looking for registers R1-R5 * they should have been found already. */ verbose(env, "BUG regs %x\n", *reg_mask); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } } else if (opcode == BPF_EXIT) { return -ENOTSUPP; } else if (BPF_SRC(insn->code) == BPF_X) { if (!(*reg_mask & (dreg | sreg))) return 0; /* dreg <cond> sreg * Both dreg and sreg need precision before * this insn. If only sreg was marked precise * before it would be equally necessary to * propagate it to dreg. */ *reg_mask |= (sreg | dreg); /* else dreg <cond> K * Only dreg still needs precision before * this insn, so for the K-based conditional * there is nothing new to be marked. */ } } else if (class == BPF_LD) { if (!(*reg_mask & dreg)) return 0; *reg_mask &= ~dreg; /* It's ld_imm64 or ld_abs or ld_ind. * For ld_imm64 no further tracking of precision * into parent is necessary */ if (mode == BPF_IND || mode == BPF_ABS) /* to be analyzed */ return -ENOTSUPP; } return 0; } /* the scalar precision tracking algorithm: * . at the start all registers have precise=false. * . scalar ranges are tracked as normal through alu and jmp insns. * . once precise value of the scalar register is used in: * . ptr + scalar alu * . if (scalar cond K|scalar) * . helper_call(.., scalar, ...) where ARG_CONST is expected * backtrack through the verifier states and mark all registers and * stack slots with spilled constants that these scalar regisers * should be precise. * . during state pruning two registers (or spilled stack slots) * are equivalent if both are not precise. * * Note the verifier cannot simply walk register parentage chain, * since many different registers and stack slots could have been * used to compute single precise scalar. * * The approach of starting with precise=true for all registers and then * backtrack to mark a register as not precise when the verifier detects * that program doesn't care about specific value (e.g., when helper * takes register as ARG_ANYTHING parameter) is not safe. * * It's ok to walk single parentage chain of the verifier states. * It's possible that this backtracking will go all the way till 1st insn. * All other branches will be explored for needing precision later. * * The backtracking needs to deal with cases like: * R8=map_value(id=0,off=0,ks=4,vs=1952,imm=0) R9_w=map_value(id=0,off=40,ks=4,vs=1952,imm=0) * r9 -= r8 * r5 = r9 * if r5 > 0x79f goto pc+7 * R5_w=inv(id=0,umax_value=1951,var_off=(0x0; 0x7ff)) * r5 += 1 * ... * call bpf_perf_event_output#25 * where .arg5_type = ARG_CONST_SIZE_OR_ZERO * * and this case: * r6 = 1 * call foo // uses callee's r6 inside to compute r0 * r0 += r6 * if r0 == 0 goto * * to track above reg_mask/stack_mask needs to be independent for each frame. * * Also if parent's curframe > frame where backtracking started, * the verifier need to mark registers in both frames, otherwise callees * may incorrectly prune callers. This is similar to * commit 7640ead93924 ("bpf: verifier: make sure callees don't prune with caller differences") * * For now backtracking falls back into conservative marking. */ static void mark_all_scalars_precise(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { struct bpf_func_state *func; struct bpf_reg_state *reg; int i, j; /* big hammer: mark all scalars precise in this path. * pop_stack may still get !precise scalars. * We also skip current state and go straight to first parent state, * because precision markings in current non-checkpointed state are * not needed. See why in the comment in __mark_chain_precision below. */ for (st = st->parent; st; st = st->parent) { for (i = 0; i <= st->curframe; i++) { func = st->frame[i]; for (j = 0; j < BPF_REG_FP; j++) { reg = &func->regs[j]; if (reg->type != SCALAR_VALUE) continue; reg->precise = true; } for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) { if (!is_spilled_reg(&func->stack[j])) continue; reg = &func->stack[j].spilled_ptr; if (reg->type != SCALAR_VALUE) continue; reg->precise = true; } } } } static void mark_all_scalars_imprecise(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { struct bpf_func_state *func; struct bpf_reg_state *reg; int i, j; for (i = 0; i <= st->curframe; i++) { func = st->frame[i]; for (j = 0; j < BPF_REG_FP; j++) { reg = &func->regs[j]; if (reg->type != SCALAR_VALUE) continue; reg->precise = false; } for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) { if (!is_spilled_reg(&func->stack[j])) continue; reg = &func->stack[j].spilled_ptr; if (reg->type != SCALAR_VALUE) continue; reg->precise = false; } } } /* * __mark_chain_precision() backtracks BPF program instruction sequence and * chain of verifier states making sure that register *regno* (if regno >= 0) * and/or stack slot *spi* (if spi >= 0) are marked as precisely tracked * SCALARS, as well as any other registers and slots that contribute to * a tracked state of given registers/stack slots, depending on specific BPF * assembly instructions (see backtrack_insns() for exact instruction handling * logic). This backtracking relies on recorded jmp_history and is able to * traverse entire chain of parent states. This process ends only when all the * necessary registers/slots and their transitive dependencies are marked as * precise. * * One important and subtle aspect is that precise marks *do not matter* in * the currently verified state (current state). It is important to understand * why this is the case. * * First, note that current state is the state that is not yet "checkpointed", * i.e., it is not yet put into env->explored_states, and it has no children * states as well. It's ephemeral, and can end up either a) being discarded if * compatible explored state is found at some point or BPF_EXIT instruction is * reached or b) checkpointed and put into env->explored_states, branching out * into one or more children states. * * In the former case, precise markings in current state are completely * ignored by state comparison code (see regsafe() for details). Only * checkpointed ("old") state precise markings are important, and if old * state's register/slot is precise, regsafe() assumes current state's * register/slot as precise and checks value ranges exactly and precisely. If * states turn out to be compatible, current state's necessary precise * markings and any required parent states' precise markings are enforced * after the fact with propagate_precision() logic, after the fact. But it's * important to realize that in this case, even after marking current state * registers/slots as precise, we immediately discard current state. So what * actually matters is any of the precise markings propagated into current * state's parent states, which are always checkpointed (due to b) case above). * As such, for scenario a) it doesn't matter if current state has precise * markings set or not. * * Now, for the scenario b), checkpointing and forking into child(ren) * state(s). Note that before current state gets to checkpointing step, any * processed instruction always assumes precise SCALAR register/slot * knowledge: if precise value or range is useful to prune jump branch, BPF * verifier takes this opportunity enthusiastically. Similarly, when * register's value is used to calculate offset or memory address, exact * knowledge of SCALAR range is assumed, checked, and enforced. So, similar to * what we mentioned above about state comparison ignoring precise markings * during state comparison, BPF verifier ignores and also assumes precise * markings *at will* during instruction verification process. But as verifier * assumes precision, it also propagates any precision dependencies across * parent states, which are not yet finalized, so can be further restricted * based on new knowledge gained from restrictions enforced by their children * states. This is so that once those parent states are finalized, i.e., when * they have no more active children state, state comparison logic in * is_state_visited() would enforce strict and precise SCALAR ranges, if * required for correctness. * * To build a bit more intuition, note also that once a state is checkpointed, * the path we took to get to that state is not important. This is crucial * property for state pruning. When state is checkpointed and finalized at * some instruction index, it can be correctly and safely used to "short * circuit" any *compatible* state that reaches exactly the same instruction * index. I.e., if we jumped to that instruction from a completely different * code path than original finalized state was derived from, it doesn't * matter, current state can be discarded because from that instruction * forward having a compatible state will ensure we will safely reach the * exit. States describe preconditions for further exploration, but completely * forget the history of how we got here. * * This also means that even if we needed precise SCALAR range to get to * finalized state, but from that point forward *that same* SCALAR register is * never used in a precise context (i.e., it's precise value is not needed for * correctness), it's correct and safe to mark such register as "imprecise" * (i.e., precise marking set to false). This is what we rely on when we do * not set precise marking in current state. If no child state requires * precision for any given SCALAR register, it's safe to dictate that it can * be imprecise. If any child state does require this register to be precise, * we'll mark it precise later retroactively during precise markings * propagation from child state to parent states. * * Skipping precise marking setting in current state is a mild version of * relying on the above observation. But we can utilize this property even * more aggressively by proactively forgetting any precise marking in the * current state (which we inherited from the parent state), right before we * checkpoint it and branch off into new child state. This is done by * mark_all_scalars_imprecise() to hopefully get more permissive and generic * finalized states which help in short circuiting more future states. */ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int regno, int spi) { struct bpf_verifier_state *st = env->cur_state; int first_idx = st->first_insn_idx; int last_idx = env->insn_idx; struct bpf_func_state *func; struct bpf_reg_state *reg; u32 reg_mask = regno >= 0 ? 1u << regno : 0; u64 stack_mask = spi >= 0 ? 1ull << spi : 0; bool skip_first = true; bool new_marks = false; int i, err; if (!env->bpf_capable) return 0; /* Do sanity checks against current state of register and/or stack * slot, but don't set precise flag in current state, as precision * tracking in the current state is unnecessary. */ func = st->frame[frame]; if (regno >= 0) { reg = &func->regs[regno]; if (reg->type != SCALAR_VALUE) { WARN_ONCE(1, "backtracing misuse"); return -EFAULT; } new_marks = true; } while (spi >= 0) { if (!is_spilled_reg(&func->stack[spi])) { stack_mask = 0; break; } reg = &func->stack[spi].spilled_ptr; if (reg->type != SCALAR_VALUE) { stack_mask = 0; break; } new_marks = true; break; } if (!new_marks) return 0; if (!reg_mask && !stack_mask) return 0; for (;;) { DECLARE_BITMAP(mask, 64); u32 history = st->jmp_history_cnt; if (env->log.level & BPF_LOG_LEVEL2) verbose(env, "last_idx %d first_idx %d\n", last_idx, first_idx); if (last_idx < 0) { /* we are at the entry into subprog, which * is expected for global funcs, but only if * requested precise registers are R1-R5 * (which are global func's input arguments) */ if (st->curframe == 0 && st->frame[0]->subprogno > 0 && st->frame[0]->callsite == BPF_MAIN_FUNC && stack_mask == 0 && (reg_mask & ~0x3e) == 0) { bitmap_from_u64(mask, reg_mask); for_each_set_bit(i, mask, 32) { reg = &st->frame[0]->regs[i]; if (reg->type != SCALAR_VALUE) { reg_mask &= ~(1u << i); continue; } reg->precise = true; } return 0; } verbose(env, "BUG backtracing func entry subprog %d reg_mask %x stack_mask %llx\n", st->frame[0]->subprogno, reg_mask, stack_mask); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } for (i = last_idx;;) { if (skip_first) { err = 0; skip_first = false; } else { err = backtrack_insn(env, i, ®_mask, &stack_mask); } if (err == -ENOTSUPP) { mark_all_scalars_precise(env, st); return 0; } else if (err) { return err; } if (!reg_mask && !stack_mask) /* Found assignment(s) into tracked register in this state. * Since this state is already marked, just return. * Nothing to be tracked further in the parent state. */ return 0; i = get_prev_insn_idx(st, i, &history); if (i == -ENOENT) break; if (i >= env->prog->len) { /* This can happen if backtracking reached insn 0 * and there are still reg_mask or stack_mask * to backtrack. * It means the backtracking missed the spot where * particular register was initialized with a constant. */ verbose(env, "BUG backtracking idx %d\n", i); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } } st = st->parent; if (!st) break; new_marks = false; func = st->frame[frame]; bitmap_from_u64(mask, reg_mask); for_each_set_bit(i, mask, 32) { reg = &func->regs[i]; if (reg->type != SCALAR_VALUE) { reg_mask &= ~(1u << i); continue; } if (!reg->precise) new_marks = true; reg->precise = true; } bitmap_from_u64(mask, stack_mask); for_each_set_bit(i, mask, 64) { if (i >= func->allocated_stack / BPF_REG_SIZE) { /* the sequence of instructions: * 2: (bf) r3 = r10 * 3: (7b) *(u64 *)(r3 -8) = r0 * 4: (79) r4 = *(u64 *)(r10 -8) * doesn't contain jmps. It's backtracked * as a single block. * During backtracking insn 3 is not recognized as * stack access, so at the end of backtracking * stack slot fp-8 is still marked in stack_mask. * However the parent state may not have accessed * fp-8 and it's "unallocated" stack space. * In such case fallback to conservative. */ mark_all_scalars_precise(env, st); return 0; } if (!is_spilled_reg(&func->stack[i])) { stack_mask &= ~(1ull << i); continue; } reg = &func->stack[i].spilled_ptr; if (reg->type != SCALAR_VALUE) { stack_mask &= ~(1ull << i); continue; } if (!reg->precise) new_marks = true; reg->precise = true; } if (env->log.level & BPF_LOG_LEVEL2) { verbose(env, "parent %s regs=%x stack=%llx marks:", new_marks ? "didn't have" : "already had", reg_mask, stack_mask); print_verifier_state(env, func, true); } if (!reg_mask && !stack_mask) break; if (!new_marks) break; last_idx = st->last_insn_idx; first_idx = st->first_insn_idx; } return 0; } int mark_chain_precision(struct bpf_verifier_env *env, int regno) { return __mark_chain_precision(env, env->cur_state->curframe, regno, -1); } static int mark_chain_precision_frame(struct bpf_verifier_env *env, int frame, int regno) { return __mark_chain_precision(env, frame, regno, -1); } static int mark_chain_precision_stack_frame(struct bpf_verifier_env *env, int frame, int spi) { return __mark_chain_precision(env, frame, -1, spi); } static bool is_spillable_regtype(enum bpf_reg_type type) { switch (base_type(type)) { case PTR_TO_MAP_VALUE: case PTR_TO_STACK: case PTR_TO_CTX: case PTR_TO_PACKET: case PTR_TO_PACKET_META: case PTR_TO_PACKET_END: case PTR_TO_FLOW_KEYS: case CONST_PTR_TO_MAP: case PTR_TO_SOCKET: case PTR_TO_SOCK_COMMON: case PTR_TO_TCP_SOCK: case PTR_TO_XDP_SOCK: case PTR_TO_BTF_ID: case PTR_TO_BUF: case PTR_TO_MEM: case PTR_TO_FUNC: case PTR_TO_MAP_KEY: return true; default: return false; } } /* Does this register contain a constant zero? */ static bool register_is_null(struct bpf_reg_state *reg) { return reg->type == SCALAR_VALUE && tnum_equals_const(reg->var_off, 0); } static bool register_is_const(struct bpf_reg_state *reg) { return reg->type == SCALAR_VALUE && tnum_is_const(reg->var_off); } static bool __is_scalar_unbounded(struct bpf_reg_state *reg) { return tnum_is_unknown(reg->var_off) && reg->smin_value == S64_MIN && reg->smax_value == S64_MAX && reg->umin_value == 0 && reg->umax_value == U64_MAX && reg->s32_min_value == S32_MIN && reg->s32_max_value == S32_MAX && reg->u32_min_value == 0 && reg->u32_max_value == U32_MAX; } static bool register_is_bounded(struct bpf_reg_state *reg) { return reg->type == SCALAR_VALUE && !__is_scalar_unbounded(reg); } static bool __is_pointer_value(bool allow_ptr_leaks, const struct bpf_reg_state *reg) { if (allow_ptr_leaks) return false; return reg->type != SCALAR_VALUE; } /* Copy src state preserving dst->parent and dst->live fields */ static void copy_register_state(struct bpf_reg_state *dst, const struct bpf_reg_state *src) { struct bpf_reg_state *parent = dst->parent; enum bpf_reg_liveness live = dst->live; *dst = *src; dst->parent = parent; dst->live = live; } static void save_register_state(struct bpf_func_state *state, int spi, struct bpf_reg_state *reg, int size) { int i; copy_register_state(&state->stack[spi].spilled_ptr, reg); if (size == BPF_REG_SIZE) state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; for (i = BPF_REG_SIZE; i > BPF_REG_SIZE - size; i--) state->stack[spi].slot_type[i - 1] = STACK_SPILL; /* size < 8 bytes spill */ for (; i; i--) scrub_spilled_slot(&state->stack[spi].slot_type[i - 1]); } static bool is_bpf_st_mem(struct bpf_insn *insn) { return BPF_CLASS(insn->code) == BPF_ST && BPF_MODE(insn->code) == BPF_MEM; } /* check_stack_{read,write}_fixed_off functions track spill/fill of registers, * stack boundary and alignment are checked in check_mem_access() */ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, /* stack frame we're writing to */ struct bpf_func_state *state, int off, int size, int value_regno, int insn_idx) { struct bpf_func_state *cur; /* state of the current function */ int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err; struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; struct bpf_reg_state *reg = NULL; u32 dst_reg = insn->dst_reg; err = grow_stack_state(state, round_up(slot + 1, BPF_REG_SIZE)); if (err) return err; /* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0, * so it's aligned access and [off, off + size) are within stack limits */ if (!env->allow_ptr_leaks && is_spilled_reg(&state->stack[spi]) && size != BPF_REG_SIZE) { verbose(env, "attempt to corrupt spilled pointer on stack\n"); return -EACCES; } cur = env->cur_state->frame[env->cur_state->curframe]; if (value_regno >= 0) reg = &cur->regs[value_regno]; if (!env->bypass_spec_v4) { bool sanitize = reg && is_spillable_regtype(reg->type); for (i = 0; i < size; i++) { u8 type = state->stack[spi].slot_type[i]; if (type != STACK_MISC && type != STACK_ZERO) { sanitize = true; break; } } if (sanitize) env->insn_aux_data[insn_idx].sanitize_stack_spill = true; } mark_stack_slot_scratched(env, spi); if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) && !register_is_null(reg) && env->bpf_capable) { if (dst_reg != BPF_REG_FP) { /* The backtracking logic can only recognize explicit * stack slot address like [fp - 8]. Other spill of * scalar via different register has to be conservative. * Backtrack from here and mark all registers as precise * that contributed into 'reg' being a constant. */ err = mark_chain_precision(env, value_regno); if (err) return err; } save_register_state(state, spi, reg, size); /* Break the relation on a narrowing spill. */ if (fls64(reg->umax_value) > BITS_PER_BYTE * size) state->stack[spi].spilled_ptr.id = 0; } else if (!reg && !(off % BPF_REG_SIZE) && is_bpf_st_mem(insn) && insn->imm != 0 && env->bpf_capable) { struct bpf_reg_state fake_reg = {}; __mark_reg_known(&fake_reg, insn->imm); fake_reg.type = SCALAR_VALUE; save_register_state(state, spi, &fake_reg, size); } else if (reg && is_spillable_regtype(reg->type)) { /* register containing pointer is being spilled into stack */ if (size != BPF_REG_SIZE) { verbose_linfo(env, insn_idx, "; "); verbose(env, "invalid size of register spill\n"); return -EACCES; } if (state != cur && reg->type == PTR_TO_STACK) { verbose(env, "cannot spill pointers to stack into stack frame of the caller\n"); return -EINVAL; } save_register_state(state, spi, reg, size); } else { u8 type = STACK_MISC; /* regular write of data into stack destroys any spilled ptr */ state->stack[spi].spilled_ptr.type = NOT_INIT; /* Mark slots as STACK_MISC if they belonged to spilled ptr. */ if (is_spilled_reg(&state->stack[spi])) for (i = 0; i < BPF_REG_SIZE; i++) scrub_spilled_slot(&state->stack[spi].slot_type[i]); /* only mark the slot as written if all 8 bytes were written * otherwise read propagation may incorrectly stop too soon * when stack slots are partially written. * This heuristic means that read propagation will be * conservative, since it will add reg_live_read marks * to stack slots all the way to first state when programs * writes+reads less than 8 bytes */ if (size == BPF_REG_SIZE) state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; /* when we zero initialize stack slots mark them as such */ if ((reg && register_is_null(reg)) || (!reg && is_bpf_st_mem(insn) && insn->imm == 0)) { /* backtracking doesn't work for STACK_ZERO yet. */ err = mark_chain_precision(env, value_regno); if (err) return err; type = STACK_ZERO; } /* Mark slots affected by this stack write. */ for (i = 0; i < size; i++) state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] = type; } return 0; } /* Write the stack: 'stack[ptr_regno + off] = value_regno'. 'ptr_regno' is * known to contain a variable offset. * This function checks whether the write is permitted and conservatively * tracks the effects of the write, considering that each stack slot in the * dynamic range is potentially written to. * * 'off' includes 'regno->off'. * 'value_regno' can be -1, meaning that an unknown value is being written to * the stack. * * Spilled pointers in range are not marked as written because we don't know * what's going to be actually written. This means that read propagation for * future reads cannot be terminated by this write. * * For privileged programs, uninitialized stack slots are considered * initialized by this write (even though we don't know exactly what offsets * are going to be written to). The idea is that we don't want the verifier to * reject future reads that access slots written to through variable offsets. */ static int check_stack_write_var_off(struct bpf_verifier_env *env, /* func where register points to */ struct bpf_func_state *state, int ptr_regno, int off, int size, int value_regno, int insn_idx) { struct bpf_func_state *cur; /* state of the current function */ int min_off, max_off; int i, err; struct bpf_reg_state *ptr_reg = NULL, *value_reg = NULL; bool writing_zero = false; /* set if the fact that we're writing a zero is used to let any * stack slots remain STACK_ZERO */ bool zero_used = false; cur = env->cur_state->frame[env->cur_state->curframe]; ptr_reg = &cur->regs[ptr_regno]; min_off = ptr_reg->smin_value + off; max_off = ptr_reg->smax_value + off + size; if (value_regno >= 0) value_reg = &cur->regs[value_regno]; if (value_reg && register_is_null(value_reg)) writing_zero = true; err = grow_stack_state(state, round_up(-min_off, BPF_REG_SIZE)); if (err) return err; /* Variable offset writes destroy any spilled pointers in range. */ for (i = min_off; i < max_off; i++) { u8 new_type, *stype; int slot, spi; slot = -i - 1; spi = slot / BPF_REG_SIZE; stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE]; mark_stack_slot_scratched(env, spi); if (!env->allow_ptr_leaks && *stype != STACK_MISC && *stype != STACK_ZERO) { /* Reject the write if range we may write to has not * been initialized beforehand. If we didn't reject * here, the ptr status would be erased below (even * though not all slots are actually overwritten), * possibly opening the door to leaks. * * We do however catch STACK_INVALID case below, and * only allow reading possibly uninitialized memory * later for CAP_PERFMON, as the write may not happen to * that slot. */ verbose(env, "spilled ptr in range of var-offset stack write; insn %d, ptr off: %d", insn_idx, i); return -EINVAL; } /* Erase all spilled pointers. */ state->stack[spi].spilled_ptr.type = NOT_INIT; /* Update the slot type. */ new_type = STACK_MISC; if (writing_zero && *stype == STACK_ZERO) { new_type = STACK_ZERO; zero_used = true; } /* If the slot is STACK_INVALID, we check whether it's OK to * pretend that it will be initialized by this write. The slot * might not actually be written to, and so if we mark it as * initialized future reads might leak uninitialized memory. * For privileged programs, we will accept such reads to slots * that may or may not be written because, if we're reject * them, the error would be too confusing. */ if (*stype == STACK_INVALID && !env->allow_uninit_stack) { verbose(env, "uninit stack in range of var-offset write prohibited for !root; insn %d, off: %d", insn_idx, i); return -EINVAL; } *stype = new_type; } if (zero_used) { /* backtracking doesn't work for STACK_ZERO yet. */ err = mark_chain_precision(env, value_regno); if (err) return err; } return 0; } /* When register 'dst_regno' is assigned some values from stack[min_off, * max_off), we set the register's type according to the types of the * respective stack slots. If all the stack values are known to be zeros, then * so is the destination reg. Otherwise, the register is considered to be * SCALAR. This function does not deal with register filling; the caller must * ensure that all spilled registers in the stack range have been marked as * read. */ static void mark_reg_stack_read(struct bpf_verifier_env *env, /* func where src register points to */ struct bpf_func_state *ptr_state, int min_off, int max_off, int dst_regno) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; int i, slot, spi; u8 *stype; int zeros = 0; for (i = min_off; i < max_off; i++) { slot = -i - 1; spi = slot / BPF_REG_SIZE; stype = ptr_state->stack[spi].slot_type; if (stype[slot % BPF_REG_SIZE] != STACK_ZERO) break; zeros++; } if (zeros == max_off - min_off) { /* any access_size read into register is zero extended, * so the whole register == const_zero */ __mark_reg_const_zero(&state->regs[dst_regno]); /* backtracking doesn't support STACK_ZERO yet, * so mark it precise here, so that later * backtracking can stop here. * Backtracking may not need this if this register * doesn't participate in pointer adjustment. * Forward propagation of precise flag is not * necessary either. This mark is only to stop * backtracking. Any register that contributed * to const 0 was marked precise before spill. */ state->regs[dst_regno].precise = true; } else { /* have read misc data from the stack */ mark_reg_unknown(env, state->regs, dst_regno); } state->regs[dst_regno].live |= REG_LIVE_WRITTEN; } /* Read the stack at 'off' and put the results into the register indicated by * 'dst_regno'. It handles reg filling if the addressed stack slot is a * spilled reg. * * 'dst_regno' can be -1, meaning that the read value is not going to a * register. * * The access is assumed to be within the current stack bounds. */ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, /* func where src register points to */ struct bpf_func_state *reg_state, int off, int size, int dst_regno) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; int i, slot = -off - 1, spi = slot / BPF_REG_SIZE; struct bpf_reg_state *reg; u8 *stype, type; stype = reg_state->stack[spi].slot_type; reg = ®_state->stack[spi].spilled_ptr; if (is_spilled_reg(®_state->stack[spi])) { u8 spill_size = 1; for (i = BPF_REG_SIZE - 1; i > 0 && stype[i - 1] == STACK_SPILL; i--) spill_size++; if (size != BPF_REG_SIZE || spill_size != BPF_REG_SIZE) { if (reg->type != SCALAR_VALUE) { verbose_linfo(env, env->insn_idx, "; "); verbose(env, "invalid size of register fill\n"); return -EACCES; } mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); if (dst_regno < 0) return 0; if (!(off % BPF_REG_SIZE) && size == spill_size) { /* The earlier check_reg_arg() has decided the * subreg_def for this insn. Save it first. */ s32 subreg_def = state->regs[dst_regno].subreg_def; copy_register_state(&state->regs[dst_regno], reg); state->regs[dst_regno].subreg_def = subreg_def; } else { for (i = 0; i < size; i++) { type = stype[(slot - i) % BPF_REG_SIZE]; if (type == STACK_SPILL) continue; if (type == STACK_MISC) continue; if (type == STACK_INVALID && env->allow_uninit_stack) continue; verbose(env, "invalid read from stack off %d+%d size %d\n", off, i, size); return -EACCES; } mark_reg_unknown(env, state->regs, dst_regno); } state->regs[dst_regno].live |= REG_LIVE_WRITTEN; return 0; } if (dst_regno >= 0) { /* restore register state from stack */ copy_register_state(&state->regs[dst_regno], reg); /* mark reg as written since spilled pointer state likely * has its liveness marks cleared by is_state_visited() * which resets stack/reg liveness for state transitions */ state->regs[dst_regno].live |= REG_LIVE_WRITTEN; } else if (__is_pointer_value(env->allow_ptr_leaks, reg)) { /* If dst_regno==-1, the caller is asking us whether * it is acceptable to use this value as a SCALAR_VALUE * (e.g. for XADD). * We must not allow unprivileged callers to do that * with spilled pointers. */ verbose(env, "leaking pointer from stack off %d\n", off); return -EACCES; } mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); } else { for (i = 0; i < size; i++) { type = stype[(slot - i) % BPF_REG_SIZE]; if (type == STACK_MISC) continue; if (type == STACK_ZERO) continue; if (type == STACK_INVALID && env->allow_uninit_stack) continue; verbose(env, "invalid read from stack off %d+%d size %d\n", off, i, size); return -EACCES; } mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); if (dst_regno >= 0) mark_reg_stack_read(env, reg_state, off, off + size, dst_regno); } return 0; } enum bpf_access_src { ACCESS_DIRECT = 1, /* the access is performed by an instruction */ ACCESS_HELPER = 2, /* the access is performed by a helper */ }; static int check_stack_range_initialized(struct bpf_verifier_env *env, int regno, int off, int access_size, bool zero_size_allowed, enum bpf_access_src type, struct bpf_call_arg_meta *meta); static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno) { return cur_regs(env) + regno; } /* Read the stack at 'ptr_regno + off' and put the result into the register * 'dst_regno'. * 'off' includes the pointer register's fixed offset(i.e. 'ptr_regno.off'), * but not its variable offset. * 'size' is assumed to be <= reg size and the access is assumed to be aligned. * * As opposed to check_stack_read_fixed_off, this function doesn't deal with * filling registers (i.e. reads of spilled register cannot be detected when * the offset is not fixed). We conservatively mark 'dst_regno' as containing * SCALAR_VALUE. That's why we assert that the 'ptr_regno' has a variable * offset; for a fixed offset check_stack_read_fixed_off should be used * instead. */ static int check_stack_read_var_off(struct bpf_verifier_env *env, int ptr_regno, int off, int size, int dst_regno) { /* The state of the source register. */ struct bpf_reg_state *reg = reg_state(env, ptr_regno); struct bpf_func_state *ptr_state = func(env, reg); int err; int min_off, max_off; /* Note that we pass a NULL meta, so raw access will not be permitted. */ err = check_stack_range_initialized(env, ptr_regno, off, size, false, ACCESS_DIRECT, NULL); if (err) return err; min_off = reg->smin_value + off; max_off = reg->smax_value + off; mark_reg_stack_read(env, ptr_state, min_off, max_off + size, dst_regno); return 0; } /* check_stack_read dispatches to check_stack_read_fixed_off or * check_stack_read_var_off. * * The caller must ensure that the offset falls within the allocated stack * bounds. * * 'dst_regno' is a register which will receive the value from the stack. It * can be -1, meaning that the read value is not going to a register. */ static int check_stack_read(struct bpf_verifier_env *env, int ptr_regno, int off, int size, int dst_regno) { struct bpf_reg_state *reg = reg_state(env, ptr_regno); struct bpf_func_state *state = func(env, reg); int err; /* Some accesses are only permitted with a static offset. */ bool var_off = !tnum_is_const(reg->var_off); /* The offset is required to be static when reads don't go to a * register, in order to not leak pointers (see * check_stack_read_fixed_off). */ if (dst_regno < 0 && var_off) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "variable offset stack pointer cannot be passed into helper function; var_off=%s off=%d size=%d\n", tn_buf, off, size); return -EACCES; } /* Variable offset is prohibited for unprivileged mode for simplicity * since it requires corresponding support in Spectre masking for stack * ALU. See also retrieve_ptr_limit(). The check in * check_stack_access_for_ptr_arithmetic() called by * adjust_ptr_min_max_vals() prevents users from creating stack pointers * with variable offsets, therefore no check is required here. Further, * just checking it here would be insufficient as speculative stack * writes could still lead to unsafe speculative behaviour. */ if (!var_off) { off += reg->var_off.value; err = check_stack_read_fixed_off(env, state, off, size, dst_regno); } else { /* Variable offset stack reads need more conservative handling * than fixed offset ones. Note that dst_regno >= 0 on this * branch. */ err = check_stack_read_var_off(env, ptr_regno, off, size, dst_regno); } return err; } /* check_stack_write dispatches to check_stack_write_fixed_off or * check_stack_write_var_off. * * 'ptr_regno' is the register used as a pointer into the stack. * 'off' includes 'ptr_regno->off', but not its variable offset (if any). * 'value_regno' is the register whose value we're writing to the stack. It can * be -1, meaning that we're not writing from a register. * * The caller must ensure that the offset falls within the maximum stack size. */ static int check_stack_write(struct bpf_verifier_env *env, int ptr_regno, int off, int size, int value_regno, int insn_idx) { struct bpf_reg_state *reg = reg_state(env, ptr_regno); struct bpf_func_state *state = func(env, reg); int err; if (tnum_is_const(reg->var_off)) { off += reg->var_off.value; err = check_stack_write_fixed_off(env, state, off, size, value_regno, insn_idx); } else { /* Variable offset stack reads need more conservative handling * than fixed offset ones. */ err = check_stack_write_var_off(env, state, ptr_regno, off, size, value_regno, insn_idx); } return err; } static int check_map_access_type(struct bpf_verifier_env *env, u32 regno, int off, int size, enum bpf_access_type type) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_map *map = regs[regno].map_ptr; u32 cap = bpf_map_flags_to_cap(map); if (type == BPF_WRITE && !(cap & BPF_MAP_CAN_WRITE)) { verbose(env, "write into map forbidden, value_size=%d off=%d size=%d\n", map->value_size, off, size); return -EACCES; } if (type == BPF_READ && !(cap & BPF_MAP_CAN_READ)) { verbose(env, "read from map forbidden, value_size=%d off=%d size=%d\n", map->value_size, off, size); return -EACCES; } return 0; } /* check read/write into memory region (e.g., map value, ringbuf sample, etc) */ static int __check_mem_access(struct bpf_verifier_env *env, int regno, int off, int size, u32 mem_size, bool zero_size_allowed) { bool size_ok = size > 0 || (size == 0 && zero_size_allowed); struct bpf_reg_state *reg; if (off >= 0 && size_ok && (u64)off + size <= mem_size) return 0; reg = &cur_regs(env)[regno]; switch (reg->type) { case PTR_TO_MAP_KEY: verbose(env, "invalid access to map key, key_size=%d off=%d size=%d\n", mem_size, off, size); break; case PTR_TO_MAP_VALUE: verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n", mem_size, off, size); break; case PTR_TO_PACKET: case PTR_TO_PACKET_META: case PTR_TO_PACKET_END: verbose(env, "invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n", off, size, regno, reg->id, off, mem_size); break; case PTR_TO_MEM: default: verbose(env, "invalid access to memory, mem_size=%u off=%d size=%d\n", mem_size, off, size); } return -EACCES; } /* check read/write into a memory region with possible variable offset */ static int check_mem_region_access(struct bpf_verifier_env *env, u32 regno, int off, int size, u32 mem_size, bool zero_size_allowed) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *reg = &state->regs[regno]; int err; /* We may have adjusted the register pointing to memory region, so we * need to try adding each of min_value and max_value to off * to make sure our theoretical access will be safe. * * The minimum value is only important with signed * comparisons where we can't assume the floor of a * value is 0. If we are using signed variables for our * index'es we need to make sure that whatever we use * will have a set floor within our range. */ if (reg->smin_value < 0 && (reg->smin_value == S64_MIN || (off + reg->smin_value != (s64)(s32)(off + reg->smin_value)) || reg->smin_value + off < 0)) { verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; } err = __check_mem_access(env, regno, reg->smin_value + off, size, mem_size, zero_size_allowed); if (err) { verbose(env, "R%d min value is outside of the allowed memory range\n", regno); return err; } /* If we haven't set a max value then we need to bail since we can't be * sure we won't do bad things. * If reg->umax_value + off could overflow, treat that as unbounded too. */ if (reg->umax_value >= BPF_MAX_VAR_OFF) { verbose(env, "R%d unbounded memory access, make sure to bounds check any such access\n", regno); return -EACCES; } err = __check_mem_access(env, regno, reg->umax_value + off, size, mem_size, zero_size_allowed); if (err) { verbose(env, "R%d max value is outside of the allowed memory range\n", regno); return err; } return 0; } static int __check_ptr_off_reg(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, bool fixed_off_ok) { /* Access to this pointer-typed register or passing it to a helper * is only allowed in its original, unmodified form. */ if (reg->off < 0) { verbose(env, "negative offset %s ptr R%d off=%d disallowed\n", reg_type_str(env, reg->type), regno, reg->off); return -EACCES; } if (!fixed_off_ok && reg->off) { verbose(env, "dereference of modified %s ptr R%d off=%d disallowed\n", reg_type_str(env, reg->type), regno, reg->off); return -EACCES; } if (!tnum_is_const(reg->var_off) || reg->var_off.value) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "variable %s access var_off=%s disallowed\n", reg_type_str(env, reg->type), tn_buf); return -EACCES; } return 0; } int check_ptr_off_reg(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno) { return __check_ptr_off_reg(env, reg, regno, false); } static int map_kptr_match_type(struct bpf_verifier_env *env, struct bpf_map_value_off_desc *off_desc, struct bpf_reg_state *reg, u32 regno) { const char *targ_name = kernel_type_name(off_desc->kptr.btf, off_desc->kptr.btf_id); int perm_flags = PTR_MAYBE_NULL; const char *reg_name = ""; /* Only unreferenced case accepts untrusted pointers */ if (off_desc->type == BPF_KPTR_UNREF) perm_flags |= PTR_UNTRUSTED; if (base_type(reg->type) != PTR_TO_BTF_ID || (type_flag(reg->type) & ~perm_flags)) goto bad_type; if (!btf_is_kernel(reg->btf)) { verbose(env, "R%d must point to kernel BTF\n", regno); return -EINVAL; } /* We need to verify reg->type and reg->btf, before accessing reg->btf */ reg_name = kernel_type_name(reg->btf, reg->btf_id); /* For ref_ptr case, release function check should ensure we get one * referenced PTR_TO_BTF_ID, and that its fixed offset is 0. For the * normal store of unreferenced kptr, we must ensure var_off is zero. * Since ref_ptr cannot be accessed directly by BPF insns, checks for * reg->off and reg->ref_obj_id are not needed here. */ if (__check_ptr_off_reg(env, reg, regno, true)) return -EACCES; /* A full type match is needed, as BTF can be vmlinux or module BTF, and * we also need to take into account the reg->off. * * We want to support cases like: * * struct foo { * struct bar br; * struct baz bz; * }; * * struct foo *v; * v = func(); // PTR_TO_BTF_ID * val->foo = v; // reg->off is zero, btf and btf_id match type * val->bar = &v->br; // reg->off is still zero, but we need to retry with * // first member type of struct after comparison fails * val->baz = &v->bz; // reg->off is non-zero, so struct needs to be walked * // to match type * * In the kptr_ref case, check_func_arg_reg_off already ensures reg->off * is zero. We must also ensure that btf_struct_ids_match does not walk * the struct to match type against first member of struct, i.e. reject * second case from above. Hence, when type is BPF_KPTR_REF, we set * strict mode to true for type match. */ if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off, off_desc->kptr.btf, off_desc->kptr.btf_id, off_desc->type == BPF_KPTR_REF)) goto bad_type; return 0; bad_type: verbose(env, "invalid kptr access, R%d type=%s%s ", regno, reg_type_str(env, reg->type), reg_name); verbose(env, "expected=%s%s", reg_type_str(env, PTR_TO_BTF_ID), targ_name); if (off_desc->type == BPF_KPTR_UNREF) verbose(env, " or %s%s\n", reg_type_str(env, PTR_TO_BTF_ID | PTR_UNTRUSTED), targ_name); else verbose(env, "\n"); return -EINVAL; } static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, int value_regno, int insn_idx, struct bpf_map_value_off_desc *off_desc) { struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; int class = BPF_CLASS(insn->code); struct bpf_reg_state *val_reg; /* Things we already checked for in check_map_access and caller: * - Reject cases where variable offset may touch kptr * - size of access (must be BPF_DW) * - tnum_is_const(reg->var_off) * - off_desc->offset == off + reg->var_off.value */ /* Only BPF_[LDX,STX,ST] | BPF_MEM | BPF_DW is supported */ if (BPF_MODE(insn->code) != BPF_MEM) { verbose(env, "kptr in map can only be accessed using BPF_MEM instruction mode\n"); return -EACCES; } /* We only allow loading referenced kptr, since it will be marked as * untrusted, similar to unreferenced kptr. */ if (class != BPF_LDX && off_desc->type == BPF_KPTR_REF) { verbose(env, "store to referenced kptr disallowed\n"); return -EACCES; } if (class == BPF_LDX) { val_reg = reg_state(env, value_regno); /* We can simply mark the value_regno receiving the pointer * value from map as PTR_TO_BTF_ID, with the correct type. */ mark_btf_ld_reg(env, cur_regs(env), value_regno, PTR_TO_BTF_ID, off_desc->kptr.btf, off_desc->kptr.btf_id, PTR_MAYBE_NULL | PTR_UNTRUSTED); /* For mark_ptr_or_null_reg */ val_reg->id = ++env->id_gen; } else if (class == BPF_STX) { val_reg = reg_state(env, value_regno); if (!register_is_null(val_reg) && map_kptr_match_type(env, off_desc, val_reg, value_regno)) return -EACCES; } else if (class == BPF_ST) { if (insn->imm) { verbose(env, "BPF_ST imm must be 0 when storing to kptr at off=%u\n", off_desc->offset); return -EACCES; } } else { verbose(env, "kptr in map can only be accessed using BPF_LDX/BPF_STX/BPF_ST\n"); return -EACCES; } return 0; } /* check read/write into a map element with possible variable offset */ static int check_map_access(struct bpf_verifier_env *env, u32 regno, int off, int size, bool zero_size_allowed, enum bpf_access_src src) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *reg = &state->regs[regno]; struct bpf_map *map = reg->map_ptr; int err; err = check_mem_region_access(env, regno, off, size, map->value_size, zero_size_allowed); if (err) return err; if (map_value_has_spin_lock(map)) { u32 lock = map->spin_lock_off; /* if any part of struct bpf_spin_lock can be touched by * load/store reject this program. * To check that [x1, x2) overlaps with [y1, y2) * it is sufficient to check x1 < y2 && y1 < x2. */ if (reg->smin_value + off < lock + sizeof(struct bpf_spin_lock) && lock < reg->umax_value + off + size) { verbose(env, "bpf_spin_lock cannot be accessed directly by load/store\n"); return -EACCES; } } if (map_value_has_timer(map)) { u32 t = map->timer_off; if (reg->smin_value + off < t + sizeof(struct bpf_timer) && t < reg->umax_value + off + size) { verbose(env, "bpf_timer cannot be accessed directly by load/store\n"); return -EACCES; } } if (map_value_has_kptrs(map)) { struct bpf_map_value_off *tab = map->kptr_off_tab; int i; for (i = 0; i < tab->nr_off; i++) { u32 p = tab->off[i].offset; if (reg->smin_value + off < p + sizeof(u64) && p < reg->umax_value + off + size) { if (src != ACCESS_DIRECT) { verbose(env, "kptr cannot be accessed indirectly by helper\n"); return -EACCES; } if (!tnum_is_const(reg->var_off)) { verbose(env, "kptr access cannot have variable offset\n"); return -EACCES; } if (p != off + reg->var_off.value) { verbose(env, "kptr access misaligned expected=%u off=%llu\n", p, off + reg->var_off.value); return -EACCES; } if (size != bpf_size_to_bytes(BPF_DW)) { verbose(env, "kptr access size must be BPF_DW\n"); return -EACCES; } break; } } } return err; } #define MAX_PACKET_OFF 0xffff static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, const struct bpf_call_arg_meta *meta, enum bpf_access_type t) { enum bpf_prog_type prog_type = resolve_prog_type(env->prog); switch (prog_type) { /* Program types only with direct read access go here! */ case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: case BPF_PROG_TYPE_LWT_SEG6LOCAL: case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_SKB: if (t == BPF_WRITE) return false; fallthrough; /* Program types with direct read + write access go here! */ case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: case BPF_PROG_TYPE_XDP: case BPF_PROG_TYPE_LWT_XMIT: case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: if (meta) return meta->pkt_access; env->seen_direct_write = true; return true; case BPF_PROG_TYPE_CGROUP_SOCKOPT: if (t == BPF_WRITE) env->seen_direct_write = true; return true; default: return false; } } static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, int size, bool zero_size_allowed) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = ®s[regno]; int err; /* We may have added a variable offset to the packet pointer; but any * reg->range we have comes after that. We are only checking the fixed * offset. */ /* We don't allow negative numbers, because we aren't tracking enough * detail to prove they're safe. */ if (reg->smin_value < 0) { verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; } err = reg->range < 0 ? -EINVAL : __check_mem_access(env, regno, off, size, reg->range, zero_size_allowed); if (err) { verbose(env, "R%d offset is outside of the packet\n", regno); return err; } /* __check_mem_access has made sure "off + size - 1" is within u16. * reg->umax_value can't be bigger than MAX_PACKET_OFF which is 0xffff, * otherwise find_good_pkt_pointers would have refused to set range info * that __check_mem_access would have rejected this pkt access. * Therefore, "off + reg->umax_value + size - 1" won't overflow u32. */ env->prog->aux->max_pkt_offset = max_t(u32, env->prog->aux->max_pkt_offset, off + reg->umax_value + size - 1); return err; } /* check access to 'struct bpf_context' fields. Supports fixed offsets only */ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size, enum bpf_access_type t, enum bpf_reg_type *reg_type, struct btf **btf, u32 *btf_id) { struct bpf_insn_access_aux info = { .reg_type = *reg_type, .log = &env->log, }; if (env->ops->is_valid_access && env->ops->is_valid_access(off, size, t, env->prog, &info)) { /* A non zero info.ctx_field_size indicates that this field is a * candidate for later verifier transformation to load the whole * field and then apply a mask when accessed with a narrower * access than actual ctx access size. A zero info.ctx_field_size * will only allow for whole field access and rejects any other * type of narrower access. */ *reg_type = info.reg_type; if (base_type(*reg_type) == PTR_TO_BTF_ID) { *btf = info.btf; *btf_id = info.btf_id; } else { env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; } /* remember the offset of last byte accessed in ctx */ if (env->prog->aux->max_ctx_offset < off + size) env->prog->aux->max_ctx_offset = off + size; return 0; } verbose(env, "invalid bpf_context access off=%d size=%d\n", off, size); return -EACCES; } static int check_flow_keys_access(struct bpf_verifier_env *env, int off, int size) { if (size < 0 || off < 0 || (u64)off + size > sizeof(struct bpf_flow_keys)) { verbose(env, "invalid access to flow keys off=%d size=%d\n", off, size); return -EACCES; } return 0; } static int check_sock_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, int off, int size, enum bpf_access_type t) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = ®s[regno]; struct bpf_insn_access_aux info = {}; bool valid; if (reg->smin_value < 0) { verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; } switch (reg->type) { case PTR_TO_SOCK_COMMON: valid = bpf_sock_common_is_valid_access(off, size, t, &info); break; case PTR_TO_SOCKET: valid = bpf_sock_is_valid_access(off, size, t, &info); break; case PTR_TO_TCP_SOCK: valid = bpf_tcp_sock_is_valid_access(off, size, t, &info); break; case PTR_TO_XDP_SOCK: valid = bpf_xdp_sock_is_valid_access(off, size, t, &info); break; default: valid = false; } if (valid) { env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; return 0; } verbose(env, "R%d invalid %s access off=%d size=%d\n", regno, reg_type_str(env, reg->type), off, size); return -EACCES; } static bool is_pointer_value(struct bpf_verifier_env *env, int regno) { return __is_pointer_value(env->allow_ptr_leaks, reg_state(env, regno)); } static bool is_ctx_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = reg_state(env, regno); return reg->type == PTR_TO_CTX; } static bool is_sk_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = reg_state(env, regno); return type_is_sk_pointer(reg->type); } static bool is_pkt_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = reg_state(env, regno); return type_is_pkt_pointer(reg->type); } static bool is_flow_key_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = reg_state(env, regno); /* Separate to is_ctx_reg() since we still want to allow BPF_ST here. */ return reg->type == PTR_TO_FLOW_KEYS; } static int check_pkt_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int off, int size, bool strict) { struct tnum reg_off; int ip_align; /* Byte size accesses are always allowed. */ if (!strict || size == 1) return 0; /* For platforms that do not have a Kconfig enabling * CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS the value of * NET_IP_ALIGN is universally set to '2'. And on platforms * that do set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS, we get * to this code only in strict mode where we want to emulate * the NET_IP_ALIGN==2 checking. Therefore use an * unconditional IP align value of '2'. */ ip_align = 2; reg_off = tnum_add(reg->var_off, tnum_const(ip_align + reg->off + off)); if (!tnum_is_aligned(reg_off, size)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "misaligned packet access off %d+%s+%d+%d size %d\n", ip_align, tn_buf, reg->off, off, size); return -EACCES; } return 0; } static int check_generic_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, const char *pointer_desc, int off, int size, bool strict) { struct tnum reg_off; /* Byte size accesses are always allowed. */ if (!strict || size == 1) return 0; reg_off = tnum_add(reg->var_off, tnum_const(reg->off + off)); if (!tnum_is_aligned(reg_off, size)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "misaligned %saccess off %s+%d+%d size %d\n", pointer_desc, tn_buf, reg->off, off, size); return -EACCES; } return 0; } static int check_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int off, int size, bool strict_alignment_once) { bool strict = env->strict_alignment || strict_alignment_once; const char *pointer_desc = ""; switch (reg->type) { case PTR_TO_PACKET: case PTR_TO_PACKET_META: /* Special case, because of NET_IP_ALIGN. Given metadata sits * right in front, treat it the very same way. */ return check_pkt_ptr_alignment(env, reg, off, size, strict); case PTR_TO_FLOW_KEYS: pointer_desc = "flow keys "; break; case PTR_TO_MAP_KEY: pointer_desc = "key "; break; case PTR_TO_MAP_VALUE: pointer_desc = "value "; break; case PTR_TO_CTX: pointer_desc = "context "; break; case PTR_TO_STACK: pointer_desc = "stack "; /* The stack spill tracking logic in check_stack_write_fixed_off() * and check_stack_read_fixed_off() relies on stack accesses being * aligned. */ strict = true; break; case PTR_TO_SOCKET: pointer_desc = "sock "; break; case PTR_TO_SOCK_COMMON: pointer_desc = "sock_common "; break; case PTR_TO_TCP_SOCK: pointer_desc = "tcp_sock "; break; case PTR_TO_XDP_SOCK: pointer_desc = "xdp_sock "; break; default: break; } return check_generic_ptr_alignment(env, reg, pointer_desc, off, size, strict); } static int update_stack_depth(struct bpf_verifier_env *env, const struct bpf_func_state *func, int off) { u16 stack = env->subprog_info[func->subprogno].stack_depth; if (stack >= -off) return 0; /* update known max for given subprogram */ env->subprog_info[func->subprogno].stack_depth = -off; return 0; } /* starting from main bpf function walk all instructions of the function * and recursively walk all callees that given function can call. * Ignore jump and exit insns. * Since recursion is prevented by check_cfg() this algorithm * only needs a local stack of MAX_CALL_FRAMES to remember callsites */ static int check_max_stack_depth_subprog(struct bpf_verifier_env *env, int idx) { struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn *insn = env->prog->insnsi; int depth = 0, frame = 0, i, subprog_end; bool tail_call_reachable = false; int ret_insn[MAX_CALL_FRAMES]; int ret_prog[MAX_CALL_FRAMES]; int j; i = subprog[idx].start; process_func: /* protect against potential stack overflow that might happen when * bpf2bpf calls get combined with tailcalls. Limit the caller's stack * depth for such case down to 256 so that the worst case scenario * would result in 8k stack size (32 which is tailcall limit * 256 = * 8k). * * To get the idea what might happen, see an example: * func1 -> sub rsp, 128 * subfunc1 -> sub rsp, 256 * tailcall1 -> add rsp, 256 * func2 -> sub rsp, 192 (total stack size = 128 + 192 = 320) * subfunc2 -> sub rsp, 64 * subfunc22 -> sub rsp, 128 * tailcall2 -> add rsp, 128 * func3 -> sub rsp, 32 (total stack size 128 + 192 + 64 + 32 = 416) * * tailcall will unwind the current stack frame but it will not get rid * of caller's stack as shown on the example above. */ if (idx && subprog[idx].has_tail_call && depth >= 256) { verbose(env, "tail_calls are not allowed when call stack of previous frames is %d bytes. Too large\n", depth); return -EACCES; } /* round up to 32-bytes, since this is granularity * of interpreter stack size */ depth += round_up(max_t(u32, subprog[idx].stack_depth, 1), 32); if (depth > MAX_BPF_STACK) { verbose(env, "combined stack size of %d calls is %d. Too large\n", frame + 1, depth); return -EACCES; } continue_func: subprog_end = subprog[idx + 1].start; for (; i < subprog_end; i++) { int next_insn, sidx; if (!bpf_pseudo_call(insn + i) && !bpf_pseudo_func(insn + i)) continue; /* remember insn and function to return to */ ret_insn[frame] = i + 1; ret_prog[frame] = idx; /* find the callee */ next_insn = i + insn[i].imm + 1; sidx = find_subprog(env, next_insn); if (sidx < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", next_insn); return -EFAULT; } if (subprog[sidx].is_async_cb) { if (subprog[sidx].has_tail_call) { verbose(env, "verifier bug. subprog has tail_call and async cb\n"); return -EFAULT; } /* async callbacks don't increase bpf prog stack size unless called directly */ if (!bpf_pseudo_call(insn + i)) continue; } i = next_insn; idx = sidx; if (subprog[idx].has_tail_call) tail_call_reachable = true; frame++; if (frame >= MAX_CALL_FRAMES) { verbose(env, "the call stack of %d frames is too deep !\n", frame); return -E2BIG; } goto process_func; } /* if tail call got detected across bpf2bpf calls then mark each of the * currently present subprog frames as tail call reachable subprogs; * this info will be utilized by JIT so that we will be preserving the * tail call counter throughout bpf2bpf calls combined with tailcalls */ if (tail_call_reachable) for (j = 0; j < frame; j++) subprog[ret_prog[j]].tail_call_reachable = true; if (subprog[0].tail_call_reachable) env->prog->aux->tail_call_reachable = true; /* end of for() loop means the last insn of the 'subprog' * was reached. Doesn't matter whether it was JA or EXIT */ if (frame == 0) return 0; depth -= round_up(max_t(u32, subprog[idx].stack_depth, 1), 32); frame--; i = ret_insn[frame]; idx = ret_prog[frame]; goto continue_func; } static int check_max_stack_depth(struct bpf_verifier_env *env) { struct bpf_subprog_info *si = env->subprog_info; int ret; for (int i = 0; i < env->subprog_cnt; i++) { if (!i || si[i].is_async_cb) { ret = check_max_stack_depth_subprog(env, i); if (ret < 0) return ret; } continue; } return 0; } #ifndef CONFIG_BPF_JIT_ALWAYS_ON static int get_callee_stack_depth(struct bpf_verifier_env *env, const struct bpf_insn *insn, int idx) { int start = idx + insn->imm + 1, subprog; subprog = find_subprog(env, start); if (subprog < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", start); return -EFAULT; } return env->subprog_info[subprog].stack_depth; } #endif static int __check_buffer_access(struct bpf_verifier_env *env, const char *buf_info, const struct bpf_reg_state *reg, int regno, int off, int size) { if (off < 0) { verbose(env, "R%d invalid %s buffer access: off=%d, size=%d\n", regno, buf_info, off, size); return -EACCES; } if (!tnum_is_const(reg->var_off) || reg->var_off.value) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "R%d invalid variable buffer offset: off=%d, var_off=%s\n", regno, off, tn_buf); return -EACCES; } return 0; } static int check_tp_buffer_access(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, int off, int size) { int err; err = __check_buffer_access(env, "tracepoint", reg, regno, off, size); if (err) return err; if (off + size > env->prog->aux->max_tp_access) env->prog->aux->max_tp_access = off + size; return 0; } static int check_buffer_access(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, int off, int size, bool zero_size_allowed, u32 *max_access) { const char *buf_info = type_is_rdonly_mem(reg->type) ? "rdonly" : "rdwr"; int err; err = __check_buffer_access(env, buf_info, reg, regno, off, size); if (err) return err; if (off + size > *max_access) *max_access = off + size; return 0; } /* BPF architecture zero extends alu32 ops into 64-bit registesr */ static void zext_32_to_64(struct bpf_reg_state *reg) { reg->var_off = tnum_subreg(reg->var_off); __reg_assign_32_into_64(reg); } /* truncate register to smaller size (in bytes) * must be called with size < BPF_REG_SIZE */ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) { u64 mask; /* clear high bits in bit representation */ reg->var_off = tnum_cast(reg->var_off, size); /* fix arithmetic bounds */ mask = ((u64)1 << (size * 8)) - 1; if ((reg->umin_value & ~mask) == (reg->umax_value & ~mask)) { reg->umin_value &= mask; reg->umax_value &= mask; } else { reg->umin_value = 0; reg->umax_value = mask; } reg->smin_value = reg->umin_value; reg->smax_value = reg->umax_value; /* If size is smaller than 32bit register the 32bit register * values are also truncated so we push 64-bit bounds into * 32-bit bounds. Above were truncated < 32-bits already. */ if (size >= 4) return; __reg_combine_64_into_32(reg); } static bool bpf_map_is_rdonly(const struct bpf_map *map) { /* A map is considered read-only if the following condition are true: * * 1) BPF program side cannot change any of the map content. The * BPF_F_RDONLY_PROG flag is throughout the lifetime of a map * and was set at map creation time. * 2) The map value(s) have been initialized from user space by a * loader and then "frozen", such that no new map update/delete * operations from syscall side are possible for the rest of * the map's lifetime from that point onwards. * 3) Any parallel/pending map update/delete operations from syscall * side have been completed. Only after that point, it's safe to * assume that map value(s) are immutable. */ return (map->map_flags & BPF_F_RDONLY_PROG) && READ_ONCE(map->frozen) && !bpf_map_write_active(map); } static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val) { void *ptr; u64 addr; int err; err = map->ops->map_direct_value_addr(map, &addr, off); if (err) return err; ptr = (void *)(long)addr + off; switch (size) { case sizeof(u8): *val = (u64)*(u8 *)ptr; break; case sizeof(u16): *val = (u64)*(u16 *)ptr; break; case sizeof(u32): *val = (u64)*(u32 *)ptr; break; case sizeof(u64): *val = *(u64 *)ptr; break; default: return -EINVAL; } return 0; } static int check_ptr_to_btf_access(struct bpf_verifier_env *env, struct bpf_reg_state *regs, int regno, int off, int size, enum bpf_access_type atype, int value_regno) { struct bpf_reg_state *reg = regs + regno; const struct btf_type *t = btf_type_by_id(reg->btf, reg->btf_id); const char *tname = btf_name_by_offset(reg->btf, t->name_off); enum bpf_type_flag flag = 0; u32 btf_id; int ret; if (off < 0) { verbose(env, "R%d is ptr_%s invalid negative access: off=%d\n", regno, tname, off); return -EACCES; } if (!tnum_is_const(reg->var_off) || reg->var_off.value) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "R%d is ptr_%s invalid variable offset: off=%d, var_off=%s\n", regno, tname, off, tn_buf); return -EACCES; } if (reg->type & MEM_USER) { verbose(env, "R%d is ptr_%s access user memory: off=%d\n", regno, tname, off); return -EACCES; } if (reg->type & MEM_PERCPU) { verbose(env, "R%d is ptr_%s access percpu memory: off=%d\n", regno, tname, off); return -EACCES; } if (env->ops->btf_struct_access) { ret = env->ops->btf_struct_access(&env->log, reg->btf, t, off, size, atype, &btf_id, &flag); } else { if (atype != BPF_READ) { verbose(env, "only read is supported\n"); return -EACCES; } ret = btf_struct_access(&env->log, reg->btf, t, off, size, atype, &btf_id, &flag); } if (ret < 0) return ret; /* If this is an untrusted pointer, all pointers formed by walking it * also inherit the untrusted flag. */ if (type_flag(reg->type) & PTR_UNTRUSTED) flag |= PTR_UNTRUSTED; if (atype == BPF_READ && value_regno >= 0) mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id, flag); return 0; } static int check_ptr_to_map_access(struct bpf_verifier_env *env, struct bpf_reg_state *regs, int regno, int off, int size, enum bpf_access_type atype, int value_regno) { struct bpf_reg_state *reg = regs + regno; struct bpf_map *map = reg->map_ptr; enum bpf_type_flag flag = 0; const struct btf_type *t; const char *tname; u32 btf_id; int ret; if (!btf_vmlinux) { verbose(env, "map_ptr access not supported without CONFIG_DEBUG_INFO_BTF\n"); return -ENOTSUPP; } if (!map->ops->map_btf_id || !*map->ops->map_btf_id) { verbose(env, "map_ptr access not supported for map type %d\n", map->map_type); return -ENOTSUPP; } t = btf_type_by_id(btf_vmlinux, *map->ops->map_btf_id); tname = btf_name_by_offset(btf_vmlinux, t->name_off); if (!env->allow_ptr_to_map_access) { verbose(env, "%s access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n", tname); return -EPERM; } if (off < 0) { verbose(env, "R%d is %s invalid negative access: off=%d\n", regno, tname, off); return -EACCES; } if (atype != BPF_READ) { verbose(env, "only read from %s is supported\n", tname); return -EACCES; } ret = btf_struct_access(&env->log, btf_vmlinux, t, off, size, atype, &btf_id, &flag); if (ret < 0) return ret; if (value_regno >= 0) mark_btf_ld_reg(env, regs, value_regno, ret, btf_vmlinux, btf_id, flag); return 0; } /* Check that the stack access at the given offset is within bounds. The * maximum valid offset is -1. * * The minimum valid offset is -MAX_BPF_STACK for writes, and * -state->allocated_stack for reads. */ static int check_stack_slot_within_bounds(int off, struct bpf_func_state *state, enum bpf_access_type t) { int min_valid_off; if (t == BPF_WRITE) min_valid_off = -MAX_BPF_STACK; else min_valid_off = -state->allocated_stack; if (off < min_valid_off || off > -1) return -EACCES; return 0; } /* Check that the stack access at 'regno + off' falls within the maximum stack * bounds. * * 'off' includes `regno->offset`, but not its dynamic part (if any). */ static int check_stack_access_within_bounds( struct bpf_verifier_env *env, int regno, int off, int access_size, enum bpf_access_src src, enum bpf_access_type type) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = regs + regno; struct bpf_func_state *state = func(env, reg); int min_off, max_off; int err; char *err_extra; if (src == ACCESS_HELPER) /* We don't know if helpers are reading or writing (or both). */ err_extra = " indirect access to"; else if (type == BPF_READ) err_extra = " read from"; else err_extra = " write to"; if (tnum_is_const(reg->var_off)) { min_off = reg->var_off.value + off; max_off = min_off + access_size; } else { if (reg->smax_value >= BPF_MAX_VAR_OFF || reg->smin_value <= -BPF_MAX_VAR_OFF) { verbose(env, "invalid unbounded variable-offset%s stack R%d\n", err_extra, regno); return -EACCES; } min_off = reg->smin_value + off; max_off = reg->smax_value + off + access_size; } err = check_stack_slot_within_bounds(min_off, state, type); if (!err && max_off > 0) err = -EINVAL; /* out of stack access into non-negative offsets */ if (!err && access_size < 0) /* access_size should not be negative (or overflow an int); others checks * along the way should have prevented such an access. */ err = -EFAULT; /* invalid negative access size; integer overflow? */ if (err) { if (tnum_is_const(reg->var_off)) { verbose(env, "invalid%s stack R%d off=%d size=%d\n", err_extra, regno, off, access_size); } else { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "invalid variable-offset%s stack R%d var_off=%s size=%d\n", err_extra, regno, tn_buf, access_size); } } return err; } /* check whether memory at (regno + off) is accessible for t = (read | write) * if t==write, value_regno is a register which value is stored into memory * if t==read, value_regno is a register which will receive the value from memory * if t==write && value_regno==-1, some unknown value is stored into memory * if t==read && value_regno==-1, don't care what we read from memory */ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, int off, int bpf_size, enum bpf_access_type t, int value_regno, bool strict_alignment_once) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = regs + regno; struct bpf_func_state *state; int size, err = 0; size = bpf_size_to_bytes(bpf_size); if (size < 0) return size; /* alignment checks will add in reg->off themselves */ err = check_ptr_alignment(env, reg, off, size, strict_alignment_once); if (err) return err; /* for access checks, reg->off is just part of off */ off += reg->off; if (reg->type == PTR_TO_MAP_KEY) { if (t == BPF_WRITE) { verbose(env, "write to change key R%d not allowed\n", regno); return -EACCES; } err = check_mem_region_access(env, regno, off, size, reg->map_ptr->key_size, false); if (err) return err; if (value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_MAP_VALUE) { struct bpf_map_value_off_desc *kptr_off_desc = NULL; if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into map\n", value_regno); return -EACCES; } err = check_map_access_type(env, regno, off, size, t); if (err) return err; err = check_map_access(env, regno, off, size, false, ACCESS_DIRECT); if (err) return err; if (tnum_is_const(reg->var_off)) kptr_off_desc = bpf_map_kptr_off_contains(reg->map_ptr, off + reg->var_off.value); if (kptr_off_desc) { err = check_map_kptr_access(env, regno, value_regno, insn_idx, kptr_off_desc); } else if (t == BPF_READ && value_regno >= 0) { struct bpf_map *map = reg->map_ptr; /* if map is read-only, track its contents as scalars */ if (tnum_is_const(reg->var_off) && bpf_map_is_rdonly(map) && map->ops->map_direct_value_addr) { int map_off = off + reg->var_off.value; u64 val = 0; err = bpf_map_direct_read(map, map_off, size, &val); if (err) return err; regs[value_regno].type = SCALAR_VALUE; __mark_reg_known(®s[value_regno], val); } else { mark_reg_unknown(env, regs, value_regno); } } } else if (base_type(reg->type) == PTR_TO_MEM) { bool rdonly_mem = type_is_rdonly_mem(reg->type); if (type_may_be_null(reg->type)) { verbose(env, "R%d invalid mem access '%s'\n", regno, reg_type_str(env, reg->type)); return -EACCES; } if (t == BPF_WRITE && rdonly_mem) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; } if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into mem\n", value_regno); return -EACCES; } err = check_mem_region_access(env, regno, off, size, reg->mem_size, false); if (!err && value_regno >= 0 && (t == BPF_READ || rdonly_mem)) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_CTX) { enum bpf_reg_type reg_type = SCALAR_VALUE; struct btf *btf = NULL; u32 btf_id = 0; if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into ctx\n", value_regno); return -EACCES; } err = check_ptr_off_reg(env, reg, regno); if (err < 0) return err; err = check_ctx_access(env, insn_idx, off, size, t, ®_type, &btf, &btf_id); if (err) verbose_linfo(env, insn_idx, "; "); if (!err && t == BPF_READ && value_regno >= 0) { /* ctx access returns either a scalar, or a * PTR_TO_PACKET[_META,_END]. In the latter * case, we know the offset is zero. */ if (reg_type == SCALAR_VALUE) { mark_reg_unknown(env, regs, value_regno); } else { mark_reg_known_zero(env, regs, value_regno); if (type_may_be_null(reg_type)) regs[value_regno].id = ++env->id_gen; /* A load of ctx field could have different * actual load size with the one encoded in the * insn. When the dst is PTR, it is for sure not * a sub-register. */ regs[value_regno].subreg_def = DEF_NOT_SUBREG; if (base_type(reg_type) == PTR_TO_BTF_ID) { regs[value_regno].btf = btf; regs[value_regno].btf_id = btf_id; } } regs[value_regno].type = reg_type; } } else if (reg->type == PTR_TO_STACK) { /* Basic bounds checks. */ err = check_stack_access_within_bounds(env, regno, off, size, ACCESS_DIRECT, t); if (err) return err; state = func(env, reg); err = update_stack_depth(env, state, off); if (err) return err; if (t == BPF_READ) err = check_stack_read(env, regno, off, size, value_regno); else err = check_stack_write(env, regno, off, size, value_regno, insn_idx); } else if (reg_is_pkt_pointer(reg)) { if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) { verbose(env, "cannot write into packet\n"); return -EACCES; } if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into packet\n", value_regno); return -EACCES; } err = check_packet_access(env, regno, off, size, false); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_FLOW_KEYS) { if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose(env, "R%d leaks addr into flow keys\n", value_regno); return -EACCES; } err = check_flow_keys_access(env, off, size); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (type_is_sk_pointer(reg->type)) { if (t == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; } err = check_sock_access(env, insn_idx, regno, off, size, t); if (!err && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_TP_BUFFER) { err = check_tp_buffer_access(env, reg, regno, off, size); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (base_type(reg->type) == PTR_TO_BTF_ID && !type_may_be_null(reg->type)) { err = check_ptr_to_btf_access(env, regs, regno, off, size, t, value_regno); } else if (reg->type == CONST_PTR_TO_MAP) { err = check_ptr_to_map_access(env, regs, regno, off, size, t, value_regno); } else if (base_type(reg->type) == PTR_TO_BUF) { bool rdonly_mem = type_is_rdonly_mem(reg->type); u32 *max_access; if (rdonly_mem) { if (t == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; } max_access = &env->prog->aux->max_rdonly_access; } else { max_access = &env->prog->aux->max_rdwr_access; } err = check_buffer_access(env, reg, regno, off, size, false, max_access); if (!err && value_regno >= 0 && (rdonly_mem || t == BPF_READ)) mark_reg_unknown(env, regs, value_regno); } else { verbose(env, "R%d invalid mem access '%s'\n", regno, reg_type_str(env, reg->type)); return -EACCES; } if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ && regs[value_regno].type == SCALAR_VALUE) { /* b/h/w load zero-extends, mark upper bits as known 0 */ coerce_reg_to_size(®s[value_regno], size); } return err; } static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn) { int load_reg; int err; switch (insn->imm) { case BPF_ADD: case BPF_ADD | BPF_FETCH: case BPF_AND: case BPF_AND | BPF_FETCH: case BPF_OR: case BPF_OR | BPF_FETCH: case BPF_XOR: case BPF_XOR | BPF_FETCH: case BPF_XCHG: case BPF_CMPXCHG: break; default: verbose(env, "BPF_ATOMIC uses invalid atomic opcode %02x\n", insn->imm); return -EINVAL; } if (BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) { verbose(env, "invalid atomic operand size\n"); return -EINVAL; } /* check src1 operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; /* check src2 operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; if (insn->imm == BPF_CMPXCHG) { /* Check comparison of R0 with memory location */ const u32 aux_reg = BPF_REG_0; err = check_reg_arg(env, aux_reg, SRC_OP); if (err) return err; if (is_pointer_value(env, aux_reg)) { verbose(env, "R%d leaks addr into mem\n", aux_reg); return -EACCES; } } if (is_pointer_value(env, insn->src_reg)) { verbose(env, "R%d leaks addr into mem\n", insn->src_reg); return -EACCES; } if (is_ctx_reg(env, insn->dst_reg) || is_pkt_reg(env, insn->dst_reg) || is_flow_key_reg(env, insn->dst_reg) || is_sk_reg(env, insn->dst_reg)) { verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n", insn->dst_reg, reg_type_str(env, reg_state(env, insn->dst_reg)->type)); return -EACCES; } if (insn->imm & BPF_FETCH) { if (insn->imm == BPF_CMPXCHG) load_reg = BPF_REG_0; else load_reg = insn->src_reg; /* check and record load of old value */ err = check_reg_arg(env, load_reg, DST_OP); if (err) return err; } else { /* This instruction accesses a memory location but doesn't * actually load it into a register. */ load_reg = -1; } /* Check whether we can read the memory, with second call for fetch * case to simulate the register fill. */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, -1, true); if (!err && load_reg >= 0) err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, load_reg, true); if (err) return err; /* Check whether we can write into the same memory. */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, -1, true); if (err) return err; return 0; } /* When register 'regno' is used to read the stack (either directly or through * a helper function) make sure that it's within stack boundary and, depending * on the access type, that all elements of the stack are initialized. * * 'off' includes 'regno->off', but not its dynamic part (if any). * * All registers that have been spilled on the stack in the slots within the * read offsets are marked as read. */ static int check_stack_range_initialized( struct bpf_verifier_env *env, int regno, int off, int access_size, bool zero_size_allowed, enum bpf_access_src type, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *reg = reg_state(env, regno); struct bpf_func_state *state = func(env, reg); int err, min_off, max_off, i, j, slot, spi; char *err_extra = type == ACCESS_HELPER ? " indirect" : ""; enum bpf_access_type bounds_check_type; /* Some accesses can write anything into the stack, others are * read-only. */ bool clobber = false; if (access_size == 0 && !zero_size_allowed) { verbose(env, "invalid zero-sized read\n"); return -EACCES; } if (type == ACCESS_HELPER) { /* The bounds checks for writes are more permissive than for * reads. However, if raw_mode is not set, we'll do extra * checks below. */ bounds_check_type = BPF_WRITE; clobber = true; } else { bounds_check_type = BPF_READ; } err = check_stack_access_within_bounds(env, regno, off, access_size, type, bounds_check_type); if (err) return err; if (tnum_is_const(reg->var_off)) { min_off = max_off = reg->var_off.value + off; } else { /* Variable offset is prohibited for unprivileged mode for * simplicity since it requires corresponding support in * Spectre masking for stack ALU. * See also retrieve_ptr_limit(). */ if (!env->bypass_spec_v1) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "R%d%s variable offset stack access prohibited for !root, var_off=%s\n", regno, err_extra, tn_buf); return -EACCES; } /* Only initialized buffer on stack is allowed to be accessed * with variable offset. With uninitialized buffer it's hard to * guarantee that whole memory is marked as initialized on * helper return since specific bounds are unknown what may * cause uninitialized stack leaking. */ if (meta && meta->raw_mode) meta = NULL; min_off = reg->smin_value + off; max_off = reg->smax_value + off; } if (meta && meta->raw_mode) { meta->access_size = access_size; meta->regno = regno; return 0; } for (i = min_off; i < max_off + access_size; i++) { u8 *stype; slot = -i - 1; spi = slot / BPF_REG_SIZE; if (state->allocated_stack <= slot) goto err; stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE]; if (*stype == STACK_MISC) goto mark; if ((*stype == STACK_ZERO) || (*stype == STACK_INVALID && env->allow_uninit_stack)) { if (clobber) { /* helper can write anything into the stack */ *stype = STACK_MISC; } goto mark; } if (is_spilled_reg(&state->stack[spi]) && (state->stack[spi].spilled_ptr.type == SCALAR_VALUE || env->allow_ptr_leaks)) { if (clobber) { __mark_reg_unknown(env, &state->stack[spi].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) scrub_spilled_slot(&state->stack[spi].slot_type[j]); } goto mark; } err: if (tnum_is_const(reg->var_off)) { verbose(env, "invalid%s read from stack R%d off %d+%d size %d\n", err_extra, regno, min_off, i - min_off, access_size); } else { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "invalid%s read from stack R%d var_off %s+%d size %d\n", err_extra, regno, tn_buf, i - min_off, access_size); } return -EACCES; mark: /* reading any byte out of 8-byte 'spill_slot' will cause * the whole slot to be marked as 'read' */ mark_reg_read(env, &state->stack[spi].spilled_ptr, state->stack[spi].spilled_ptr.parent, REG_LIVE_READ64); /* We do not set REG_LIVE_WRITTEN for stack slot, as we can not * be sure that whether stack slot is written to or not. Hence, * we must still conservatively propagate reads upwards even if * helper may write to the entire memory range. */ } return update_stack_depth(env, state, min_off); } static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, int access_size, bool zero_size_allowed, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; u32 *max_access; switch (base_type(reg->type)) { case PTR_TO_PACKET: case PTR_TO_PACKET_META: return check_packet_access(env, regno, reg->off, access_size, zero_size_allowed); case PTR_TO_MAP_KEY: if (meta && meta->raw_mode) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; } return check_mem_region_access(env, regno, reg->off, access_size, reg->map_ptr->key_size, false); case PTR_TO_MAP_VALUE: if (check_map_access_type(env, regno, reg->off, access_size, meta && meta->raw_mode ? BPF_WRITE : BPF_READ)) return -EACCES; return check_map_access(env, regno, reg->off, access_size, zero_size_allowed, ACCESS_HELPER); case PTR_TO_MEM: if (type_is_rdonly_mem(reg->type)) { if (meta && meta->raw_mode) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; } } return check_mem_region_access(env, regno, reg->off, access_size, reg->mem_size, zero_size_allowed); case PTR_TO_BUF: if (type_is_rdonly_mem(reg->type)) { if (meta && meta->raw_mode) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; } max_access = &env->prog->aux->max_rdonly_access; } else { max_access = &env->prog->aux->max_rdwr_access; } return check_buffer_access(env, reg, regno, reg->off, access_size, zero_size_allowed, max_access); case PTR_TO_STACK: return check_stack_range_initialized( env, regno, reg->off, access_size, zero_size_allowed, ACCESS_HELPER, meta); case PTR_TO_CTX: /* in case the function doesn't know how to access the context, * (because we are in a program of type SYSCALL for example), we * can not statically check its size. * Dynamically check it now. */ if (!env->ops->convert_ctx_access) { enum bpf_access_type atype = meta && meta->raw_mode ? BPF_WRITE : BPF_READ; int offset = access_size - 1; /* Allow zero-byte read from PTR_TO_CTX */ if (access_size == 0) return zero_size_allowed ? 0 : -EACCES; return check_mem_access(env, env->insn_idx, regno, offset, BPF_B, atype, -1, false); } fallthrough; default: /* scalar_value or invalid ptr */ /* Allow zero-byte read from NULL, regardless of pointer type */ if (zero_size_allowed && access_size == 0 && register_is_null(reg)) return 0; verbose(env, "R%d type=%s ", regno, reg_type_str(env, reg->type)); verbose(env, "expected=%s\n", reg_type_str(env, PTR_TO_STACK)); return -EACCES; } } static int check_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, bool zero_size_allowed, struct bpf_call_arg_meta *meta) { int err; /* This is used to refine r0 return value bounds for helpers * that enforce this value as an upper bound on return values. * See do_refine_retval_range() for helpers that can refine * the return value. C type of helper is u32 so we pull register * bound from umax_value however, if negative verifier errors * out. Only upper bounds can be learned because retval is an * int type and negative retvals are allowed. */ meta->msize_max_value = reg->umax_value; /* The register is SCALAR_VALUE; the access check * happens using its boundaries. */ if (!tnum_is_const(reg->var_off)) /* For unprivileged variable accesses, disable raw * mode so that the program is required to * initialize all the memory that the helper could * just partially fill up. */ meta = NULL; if (reg->smin_value < 0) { verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n", regno); return -EACCES; } if (reg->umin_value == 0) { err = check_helper_mem_access(env, regno - 1, 0, zero_size_allowed, meta); if (err) return err; } if (reg->umax_value >= BPF_MAX_VAR_SIZ) { verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n", regno); return -EACCES; } err = check_helper_mem_access(env, regno - 1, reg->umax_value, zero_size_allowed, meta); if (!err) err = mark_chain_precision(env, regno); return err; } int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, u32 mem_size) { bool may_be_null = type_may_be_null(reg->type); struct bpf_reg_state saved_reg; struct bpf_call_arg_meta meta; int err; if (register_is_null(reg)) return 0; memset(&meta, 0, sizeof(meta)); /* Assuming that the register contains a value check if the memory * access is safe. Temporarily save and restore the register's state as * the conversion shouldn't be visible to a caller. */ if (may_be_null) { saved_reg = *reg; mark_ptr_not_null_reg(reg); } err = check_helper_mem_access(env, regno, mem_size, true, &meta); /* Check access for BPF_WRITE */ meta.raw_mode = true; err = err ?: check_helper_mem_access(env, regno, mem_size, true, &meta); if (may_be_null) *reg = saved_reg; return err; } int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno) { struct bpf_reg_state *mem_reg = &cur_regs(env)[regno - 1]; bool may_be_null = type_may_be_null(mem_reg->type); struct bpf_reg_state saved_reg; struct bpf_call_arg_meta meta; int err; WARN_ON_ONCE(regno < BPF_REG_2 || regno > BPF_REG_5); memset(&meta, 0, sizeof(meta)); if (may_be_null) { saved_reg = *mem_reg; mark_ptr_not_null_reg(mem_reg); } err = check_mem_size_reg(env, reg, regno, true, &meta); /* Check access for BPF_WRITE */ meta.raw_mode = true; err = err ?: check_mem_size_reg(env, reg, regno, true, &meta); if (may_be_null) *mem_reg = saved_reg; return err; } /* Implementation details: * bpf_map_lookup returns PTR_TO_MAP_VALUE_OR_NULL * Two bpf_map_lookups (even with the same key) will have different reg->id. * For traditional PTR_TO_MAP_VALUE the verifier clears reg->id after * value_or_null->value transition, since the verifier only cares about * the range of access to valid map value pointer and doesn't care about actual * address of the map element. * For maps with 'struct bpf_spin_lock' inside map value the verifier keeps * reg->id > 0 after value_or_null->value transition. By doing so * two bpf_map_lookups will be considered two different pointers that * point to different bpf_spin_locks. * The verifier allows taking only one bpf_spin_lock at a time to avoid * dead-locks. * Since only one bpf_spin_lock is allowed the checks are simpler than * reg_is_refcounted() logic. The verifier needs to remember only * one spin_lock instead of array of acquired_refs. * cur_state->active_spin_lock remembers which map value element got locked * and clears it after bpf_spin_unlock. */ static int process_spin_lock(struct bpf_verifier_env *env, int regno, bool is_lock) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; struct bpf_verifier_state *cur = env->cur_state; bool is_const = tnum_is_const(reg->var_off); struct bpf_map *map = reg->map_ptr; u64 val = reg->var_off.value; if (!is_const) { verbose(env, "R%d doesn't have constant offset. bpf_spin_lock has to be at the constant offset\n", regno); return -EINVAL; } if (!map->btf) { verbose(env, "map '%s' has to have BTF in order to use bpf_spin_lock\n", map->name); return -EINVAL; } if (!map_value_has_spin_lock(map)) { if (map->spin_lock_off == -E2BIG) verbose(env, "map '%s' has more than one 'struct bpf_spin_lock'\n", map->name); else if (map->spin_lock_off == -ENOENT) verbose(env, "map '%s' doesn't have 'struct bpf_spin_lock'\n", map->name); else verbose(env, "map '%s' is not a struct type or bpf_spin_lock is mangled\n", map->name); return -EINVAL; } if (map->spin_lock_off != val + reg->off) { verbose(env, "off %lld doesn't point to 'struct bpf_spin_lock'\n", val + reg->off); return -EINVAL; } if (is_lock) { if (cur->active_spin_lock) { verbose(env, "Locking two bpf_spin_locks are not allowed\n"); return -EINVAL; } cur->active_spin_lock = reg->id; } else { if (!cur->active_spin_lock) { verbose(env, "bpf_spin_unlock without taking a lock\n"); return -EINVAL; } if (cur->active_spin_lock != reg->id) { verbose(env, "bpf_spin_unlock of different lock\n"); return -EINVAL; } cur->active_spin_lock = 0; } return 0; } static int process_timer_func(struct bpf_verifier_env *env, int regno, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; bool is_const = tnum_is_const(reg->var_off); struct bpf_map *map = reg->map_ptr; u64 val = reg->var_off.value; if (!is_const) { verbose(env, "R%d doesn't have constant offset. bpf_timer has to be at the constant offset\n", regno); return -EINVAL; } if (!map->btf) { verbose(env, "map '%s' has to have BTF in order to use bpf_timer\n", map->name); return -EINVAL; } if (!map_value_has_timer(map)) { if (map->timer_off == -E2BIG) verbose(env, "map '%s' has more than one 'struct bpf_timer'\n", map->name); else if (map->timer_off == -ENOENT) verbose(env, "map '%s' doesn't have 'struct bpf_timer'\n", map->name); else verbose(env, "map '%s' is not a struct type or bpf_timer is mangled\n", map->name); return -EINVAL; } if (map->timer_off != val + reg->off) { verbose(env, "off %lld doesn't point to 'struct bpf_timer' that is at %d\n", val + reg->off, map->timer_off); return -EINVAL; } if (meta->map_ptr) { verbose(env, "verifier bug. Two map pointers in a timer helper\n"); return -EFAULT; } meta->map_uid = reg->map_uid; meta->map_ptr = map; return 0; } static int process_kptr_func(struct bpf_verifier_env *env, int regno, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; struct bpf_map_value_off_desc *off_desc; struct bpf_map *map_ptr = reg->map_ptr; u32 kptr_off; int ret; if (!tnum_is_const(reg->var_off)) { verbose(env, "R%d doesn't have constant offset. kptr has to be at the constant offset\n", regno); return -EINVAL; } if (!map_ptr->btf) { verbose(env, "map '%s' has to have BTF in order to use bpf_kptr_xchg\n", map_ptr->name); return -EINVAL; } if (!map_value_has_kptrs(map_ptr)) { ret = PTR_ERR_OR_ZERO(map_ptr->kptr_off_tab); if (ret == -E2BIG) verbose(env, "map '%s' has more than %d kptr\n", map_ptr->name, BPF_MAP_VALUE_OFF_MAX); else if (ret == -EEXIST) verbose(env, "map '%s' has repeating kptr BTF tags\n", map_ptr->name); else verbose(env, "map '%s' has no valid kptr\n", map_ptr->name); return -EINVAL; } meta->map_ptr = map_ptr; kptr_off = reg->off + reg->var_off.value; off_desc = bpf_map_kptr_off_contains(map_ptr, kptr_off); if (!off_desc) { verbose(env, "off=%d doesn't point to kptr\n", kptr_off); return -EACCES; } if (off_desc->type != BPF_KPTR_REF) { verbose(env, "off=%d kptr isn't referenced kptr\n", kptr_off); return -EACCES; } meta->kptr_off_desc = off_desc; return 0; } static bool arg_type_is_mem_size(enum bpf_arg_type type) { return type == ARG_CONST_SIZE || type == ARG_CONST_SIZE_OR_ZERO; } static bool arg_type_is_raw_mem(enum bpf_arg_type type) { return base_type(type) == ARG_PTR_TO_MEM && type & MEM_UNINIT; } static bool arg_type_is_release(enum bpf_arg_type type) { return type & OBJ_RELEASE; } static bool arg_type_is_dynptr(enum bpf_arg_type type) { return base_type(type) == ARG_PTR_TO_DYNPTR; } static int int_ptr_type_to_size(enum bpf_arg_type type) { if (type == ARG_PTR_TO_INT) return sizeof(u32); else if (type == ARG_PTR_TO_LONG) return sizeof(u64); return -EINVAL; } static int resolve_map_arg_type(struct bpf_verifier_env *env, const struct bpf_call_arg_meta *meta, enum bpf_arg_type *arg_type) { if (!meta->map_ptr) { /* kernel subsystem misconfigured verifier */ verbose(env, "invalid map_ptr to access map->type\n"); return -EACCES; } switch (meta->map_ptr->map_type) { case BPF_MAP_TYPE_SOCKMAP: case BPF_MAP_TYPE_SOCKHASH: if (*arg_type == ARG_PTR_TO_MAP_VALUE) { *arg_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON; } else { verbose(env, "invalid arg_type for sockmap/sockhash\n"); return -EINVAL; } break; case BPF_MAP_TYPE_BLOOM_FILTER: if (meta->func_id == BPF_FUNC_map_peek_elem) *arg_type = ARG_PTR_TO_MAP_VALUE; break; default: break; } return 0; } struct bpf_reg_types { const enum bpf_reg_type types[10]; u32 *btf_id; }; static const struct bpf_reg_types map_key_value_types = { .types = { PTR_TO_STACK, PTR_TO_PACKET, PTR_TO_PACKET_META, PTR_TO_MAP_KEY, PTR_TO_MAP_VALUE, }, }; static const struct bpf_reg_types sock_types = { .types = { PTR_TO_SOCK_COMMON, PTR_TO_SOCKET, PTR_TO_TCP_SOCK, PTR_TO_XDP_SOCK, }, }; #ifdef CONFIG_NET static const struct bpf_reg_types btf_id_sock_common_types = { .types = { PTR_TO_SOCK_COMMON, PTR_TO_SOCKET, PTR_TO_TCP_SOCK, PTR_TO_XDP_SOCK, PTR_TO_BTF_ID, }, .btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], }; #endif static const struct bpf_reg_types mem_types = { .types = { PTR_TO_STACK, PTR_TO_PACKET, PTR_TO_PACKET_META, PTR_TO_MAP_KEY, PTR_TO_MAP_VALUE, PTR_TO_MEM, PTR_TO_MEM | MEM_ALLOC, PTR_TO_BUF, }, }; static const struct bpf_reg_types int_ptr_types = { .types = { PTR_TO_STACK, PTR_TO_PACKET, PTR_TO_PACKET_META, PTR_TO_MAP_KEY, PTR_TO_MAP_VALUE, }, }; static const struct bpf_reg_types fullsock_types = { .types = { PTR_TO_SOCKET } }; static const struct bpf_reg_types scalar_types = { .types = { SCALAR_VALUE } }; static const struct bpf_reg_types context_types = { .types = { PTR_TO_CTX } }; static const struct bpf_reg_types alloc_mem_types = { .types = { PTR_TO_MEM | MEM_ALLOC } }; static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } }; static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID } }; static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE } }; static const struct bpf_reg_types percpu_btf_ptr_types = { .types = { PTR_TO_BTF_ID | MEM_PERCPU } }; static const struct bpf_reg_types func_ptr_types = { .types = { PTR_TO_FUNC } }; static const struct bpf_reg_types stack_ptr_types = { .types = { PTR_TO_STACK } }; static const struct bpf_reg_types const_str_ptr_types = { .types = { PTR_TO_MAP_VALUE } }; static const struct bpf_reg_types timer_types = { .types = { PTR_TO_MAP_VALUE } }; static const struct bpf_reg_types kptr_types = { .types = { PTR_TO_MAP_VALUE } }; static const struct bpf_reg_types dynptr_types = { .types = { PTR_TO_STACK, PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL, } }; static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { [ARG_PTR_TO_MAP_KEY] = &map_key_value_types, [ARG_PTR_TO_MAP_VALUE] = &map_key_value_types, [ARG_CONST_SIZE] = &scalar_types, [ARG_CONST_SIZE_OR_ZERO] = &scalar_types, [ARG_CONST_ALLOC_SIZE_OR_ZERO] = &scalar_types, [ARG_CONST_MAP_PTR] = &const_map_ptr_types, [ARG_PTR_TO_CTX] = &context_types, [ARG_PTR_TO_SOCK_COMMON] = &sock_types, #ifdef CONFIG_NET [ARG_PTR_TO_BTF_ID_SOCK_COMMON] = &btf_id_sock_common_types, #endif [ARG_PTR_TO_SOCKET] = &fullsock_types, [ARG_PTR_TO_BTF_ID] = &btf_ptr_types, [ARG_PTR_TO_SPIN_LOCK] = &spin_lock_types, [ARG_PTR_TO_MEM] = &mem_types, [ARG_PTR_TO_ALLOC_MEM] = &alloc_mem_types, [ARG_PTR_TO_INT] = &int_ptr_types, [ARG_PTR_TO_LONG] = &int_ptr_types, [ARG_PTR_TO_PERCPU_BTF_ID] = &percpu_btf_ptr_types, [ARG_PTR_TO_FUNC] = &func_ptr_types, [ARG_PTR_TO_STACK] = &stack_ptr_types, [ARG_PTR_TO_CONST_STR] = &const_str_ptr_types, [ARG_PTR_TO_TIMER] = &timer_types, [ARG_PTR_TO_KPTR] = &kptr_types, [ARG_PTR_TO_DYNPTR] = &dynptr_types, }; static int check_reg_type(struct bpf_verifier_env *env, u32 regno, enum bpf_arg_type arg_type, const u32 *arg_btf_id, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; enum bpf_reg_type expected, type = reg->type; const struct bpf_reg_types *compatible; int i, j; compatible = compatible_reg_types[base_type(arg_type)]; if (!compatible) { verbose(env, "verifier internal error: unsupported arg type %d\n", arg_type); return -EFAULT; } /* ARG_PTR_TO_MEM + RDONLY is compatible with PTR_TO_MEM and PTR_TO_MEM + RDONLY, * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM and NOT with PTR_TO_MEM + RDONLY * * Same for MAYBE_NULL: * * ARG_PTR_TO_MEM + MAYBE_NULL is compatible with PTR_TO_MEM and PTR_TO_MEM + MAYBE_NULL, * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM but NOT with PTR_TO_MEM + MAYBE_NULL * * Therefore we fold these flags depending on the arg_type before comparison. */ if (arg_type & MEM_RDONLY) type &= ~MEM_RDONLY; if (arg_type & PTR_MAYBE_NULL) type &= ~PTR_MAYBE_NULL; for (i = 0; i < ARRAY_SIZE(compatible->types); i++) { expected = compatible->types[i]; if (expected == NOT_INIT) break; if (type == expected) goto found; } verbose(env, "R%d type=%s expected=", regno, reg_type_str(env, reg->type)); for (j = 0; j + 1 < i; j++) verbose(env, "%s, ", reg_type_str(env, compatible->types[j])); verbose(env, "%s\n", reg_type_str(env, compatible->types[j])); return -EACCES; found: if (reg->type == PTR_TO_BTF_ID) { /* For bpf_sk_release, it needs to match against first member * 'struct sock_common', hence make an exception for it. This * allows bpf_sk_release to work for multiple socket types. */ bool strict_type_match = arg_type_is_release(arg_type) && meta->func_id != BPF_FUNC_sk_release; if (!arg_btf_id) { if (!compatible->btf_id) { verbose(env, "verifier internal error: missing arg compatible BTF ID\n"); return -EFAULT; } arg_btf_id = compatible->btf_id; } if (meta->func_id == BPF_FUNC_kptr_xchg) { if (map_kptr_match_type(env, meta->kptr_off_desc, reg, regno)) return -EACCES; } else { if (arg_btf_id == BPF_PTR_POISON) { verbose(env, "verifier internal error:"); verbose(env, "R%d has non-overwritten BPF_PTR_POISON type\n", regno); return -EACCES; } if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off, btf_vmlinux, *arg_btf_id, strict_type_match)) { verbose(env, "R%d is of type %s but %s is expected\n", regno, kernel_type_name(reg->btf, reg->btf_id), kernel_type_name(btf_vmlinux, *arg_btf_id)); return -EACCES; } } } return 0; } int check_func_arg_reg_off(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, enum bpf_arg_type arg_type) { enum bpf_reg_type type = reg->type; bool fixed_off_ok = false; switch ((u32)type) { /* Pointer types where reg offset is explicitly allowed: */ case PTR_TO_STACK: if (arg_type_is_dynptr(arg_type) && reg->off % BPF_REG_SIZE) { verbose(env, "cannot pass in dynptr at an offset\n"); return -EINVAL; } fallthrough; case PTR_TO_PACKET: case PTR_TO_PACKET_META: case PTR_TO_MAP_KEY: case PTR_TO_MAP_VALUE: case PTR_TO_MEM: case PTR_TO_MEM | MEM_RDONLY: case PTR_TO_MEM | MEM_ALLOC: case PTR_TO_BUF: case PTR_TO_BUF | MEM_RDONLY: case SCALAR_VALUE: /* Some of the argument types nevertheless require a * zero register offset. */ if (base_type(arg_type) != ARG_PTR_TO_ALLOC_MEM) return 0; break; /* All the rest must be rejected, except PTR_TO_BTF_ID which allows * fixed offset. */ case PTR_TO_BTF_ID: /* When referenced PTR_TO_BTF_ID is passed to release function, * it's fixed offset must be 0. In the other cases, fixed offset * can be non-zero. */ if (arg_type_is_release(arg_type) && reg->off) { verbose(env, "R%d must have zero offset when passed to release func\n", regno); return -EINVAL; } /* For arg is release pointer, fixed_off_ok must be false, but * we already checked and rejected reg->off != 0 above, so set * to true to allow fixed offset for all other cases. */ fixed_off_ok = true; break; default: break; } return __check_ptr_off_reg(env, reg, regno, fixed_off_ok); } static u32 stack_slot_get_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); int spi = get_spi(reg->off); return state->stack[spi].spilled_ptr.id; } static int check_func_arg(struct bpf_verifier_env *env, u32 arg, struct bpf_call_arg_meta *meta, const struct bpf_func_proto *fn) { u32 regno = BPF_REG_1 + arg; struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; enum bpf_arg_type arg_type = fn->arg_type[arg]; enum bpf_reg_type type = reg->type; u32 *arg_btf_id = NULL; int err = 0; if (arg_type == ARG_DONTCARE) return 0; err = check_reg_arg(env, regno, SRC_OP); if (err) return err; if (arg_type == ARG_ANYTHING) { if (is_pointer_value(env, regno)) { verbose(env, "R%d leaks addr into helper function\n", regno); return -EACCES; } return 0; } if (type_is_pkt_pointer(type) && !may_access_direct_pkt_data(env, meta, BPF_READ)) { verbose(env, "helper access to the packet is not allowed\n"); return -EACCES; } if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE) { err = resolve_map_arg_type(env, meta, &arg_type); if (err) return err; } if (register_is_null(reg) && type_may_be_null(arg_type)) /* A NULL register has a SCALAR_VALUE type, so skip * type checking. */ goto skip_type_check; /* arg_btf_id and arg_size are in a union. */ if (base_type(arg_type) == ARG_PTR_TO_BTF_ID) arg_btf_id = fn->arg_btf_id[arg]; err = check_reg_type(env, regno, arg_type, arg_btf_id, meta); if (err) return err; err = check_func_arg_reg_off(env, reg, regno, arg_type); if (err) return err; skip_type_check: if (arg_type_is_release(arg_type)) { if (arg_type_is_dynptr(arg_type)) { struct bpf_func_state *state = func(env, reg); int spi = get_spi(reg->off); if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS) || !state->stack[spi].spilled_ptr.id) { verbose(env, "arg %d is an unacquired reference\n", regno); return -EINVAL; } } else if (!reg->ref_obj_id && !register_is_null(reg)) { verbose(env, "R%d must be referenced when passed to release function\n", regno); return -EINVAL; } if (meta->release_regno) { verbose(env, "verifier internal error: more than one release argument\n"); return -EFAULT; } meta->release_regno = regno; } if (reg->ref_obj_id) { if (meta->ref_obj_id) { verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", regno, reg->ref_obj_id, meta->ref_obj_id); return -EFAULT; } meta->ref_obj_id = reg->ref_obj_id; } switch (base_type(arg_type)) { case ARG_CONST_MAP_PTR: /* bpf_map_xxx(map_ptr) call: remember that map_ptr */ if (meta->map_ptr) { /* Use map_uid (which is unique id of inner map) to reject: * inner_map1 = bpf_map_lookup_elem(outer_map, key1) * inner_map2 = bpf_map_lookup_elem(outer_map, key2) * if (inner_map1 && inner_map2) { * timer = bpf_map_lookup_elem(inner_map1); * if (timer) * // mismatch would have been allowed * bpf_timer_init(timer, inner_map2); * } * * Comparing map_ptr is enough to distinguish normal and outer maps. */ if (meta->map_ptr != reg->map_ptr || meta->map_uid != reg->map_uid) { verbose(env, "timer pointer in R1 map_uid=%d doesn't match map pointer in R2 map_uid=%d\n", meta->map_uid, reg->map_uid); return -EINVAL; } } meta->map_ptr = reg->map_ptr; meta->map_uid = reg->map_uid; break; case ARG_PTR_TO_MAP_KEY: /* bpf_map_xxx(..., map_ptr, ..., key) call: * check that [key, key + map->key_size) are within * stack limits and initialized */ if (!meta->map_ptr) { /* in function declaration map_ptr must come before * map_key, so that it's verified and known before * we have to check map_key here. Otherwise it means * that kernel subsystem misconfigured verifier */ verbose(env, "invalid map_ptr to access map->key\n"); return -EACCES; } err = check_helper_mem_access(env, regno, meta->map_ptr->key_size, false, NULL); break; case ARG_PTR_TO_MAP_VALUE: if (type_may_be_null(arg_type) && register_is_null(reg)) return 0; /* bpf_map_xxx(..., map_ptr, ..., value) call: * check [value, value + map->value_size) validity */ if (!meta->map_ptr) { /* kernel subsystem misconfigured verifier */ verbose(env, "invalid map_ptr to access map->value\n"); return -EACCES; } meta->raw_mode = arg_type & MEM_UNINIT; err = check_helper_mem_access(env, regno, meta->map_ptr->value_size, false, meta); break; case ARG_PTR_TO_PERCPU_BTF_ID: if (!reg->btf_id) { verbose(env, "Helper has invalid btf_id in R%d\n", regno); return -EACCES; } meta->ret_btf = reg->btf; meta->ret_btf_id = reg->btf_id; break; case ARG_PTR_TO_SPIN_LOCK: if (meta->func_id == BPF_FUNC_spin_lock) { if (process_spin_lock(env, regno, true)) return -EACCES; } else if (meta->func_id == BPF_FUNC_spin_unlock) { if (process_spin_lock(env, regno, false)) return -EACCES; } else { verbose(env, "verifier internal error\n"); return -EFAULT; } break; case ARG_PTR_TO_TIMER: if (process_timer_func(env, regno, meta)) return -EACCES; break; case ARG_PTR_TO_FUNC: meta->subprogno = reg->subprogno; break; case ARG_PTR_TO_MEM: /* The access to this pointer is only checked when we hit the * next is_mem_size argument below. */ meta->raw_mode = arg_type & MEM_UNINIT; if (arg_type & MEM_FIXED_SIZE) { err = check_helper_mem_access(env, regno, fn->arg_size[arg], false, meta); } break; case ARG_CONST_SIZE: err = check_mem_size_reg(env, reg, regno, false, meta); break; case ARG_CONST_SIZE_OR_ZERO: err = check_mem_size_reg(env, reg, regno, true, meta); break; case ARG_PTR_TO_DYNPTR: /* We only need to check for initialized / uninitialized helper * dynptr args if the dynptr is not PTR_TO_DYNPTR, as the * assumption is that if it is, that a helper function * initialized the dynptr on behalf of the BPF program. */ if (base_type(reg->type) == PTR_TO_DYNPTR) break; if (arg_type & MEM_UNINIT) { if (!is_dynptr_reg_valid_uninit(env, reg)) { verbose(env, "Dynptr has to be an uninitialized dynptr\n"); return -EINVAL; } /* We only support one dynptr being uninitialized at the moment, * which is sufficient for the helper functions we have right now. */ if (meta->uninit_dynptr_regno) { verbose(env, "verifier internal error: multiple uninitialized dynptr args\n"); return -EFAULT; } meta->uninit_dynptr_regno = regno; } else if (!is_dynptr_reg_valid_init(env, reg)) { verbose(env, "Expected an initialized dynptr as arg #%d\n", arg + 1); return -EINVAL; } else if (!is_dynptr_type_expected(env, reg, arg_type)) { const char *err_extra = ""; switch (arg_type & DYNPTR_TYPE_FLAG_MASK) { case DYNPTR_TYPE_LOCAL: err_extra = "local"; break; case DYNPTR_TYPE_RINGBUF: err_extra = "ringbuf"; break; default: err_extra = "<unknown>"; break; } verbose(env, "Expected a dynptr of type %s as arg #%d\n", err_extra, arg + 1); return -EINVAL; } break; case ARG_CONST_ALLOC_SIZE_OR_ZERO: if (!tnum_is_const(reg->var_off)) { verbose(env, "R%d is not a known constant'\n", regno); return -EACCES; } meta->mem_size = reg->var_off.value; err = mark_chain_precision(env, regno); if (err) return err; break; case ARG_PTR_TO_INT: case ARG_PTR_TO_LONG: { int size = int_ptr_type_to_size(arg_type); err = check_helper_mem_access(env, regno, size, false, meta); if (err) return err; err = check_ptr_alignment(env, reg, 0, size, true); break; } case ARG_PTR_TO_CONST_STR: { struct bpf_map *map = reg->map_ptr; int map_off; u64 map_addr; char *str_ptr; if (!bpf_map_is_rdonly(map)) { verbose(env, "R%d does not point to a readonly map'\n", regno); return -EACCES; } if (!tnum_is_const(reg->var_off)) { verbose(env, "R%d is not a constant address'\n", regno); return -EACCES; } if (!map->ops->map_direct_value_addr) { verbose(env, "no direct value access support for this map type\n"); return -EACCES; } err = check_map_access(env, regno, reg->off, map->value_size - reg->off, false, ACCESS_HELPER); if (err) return err; map_off = reg->off + reg->var_off.value; err = map->ops->map_direct_value_addr(map, &map_addr, map_off); if (err) { verbose(env, "direct value access on string failed\n"); return err; } str_ptr = (char *)(long)(map_addr); if (!strnchr(str_ptr + map_off, map->value_size - map_off, 0)) { verbose(env, "string is not zero-terminated\n"); return -EINVAL; } break; } case ARG_PTR_TO_KPTR: if (process_kptr_func(env, regno, meta)) return -EACCES; break; } return err; } static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id) { enum bpf_attach_type eatype = env->prog->expected_attach_type; enum bpf_prog_type type = resolve_prog_type(env->prog); if (func_id != BPF_FUNC_map_update_elem && func_id != BPF_FUNC_map_delete_elem) return false; /* It's not possible to get access to a locked struct sock in these * contexts, so updating is safe. */ switch (type) { case BPF_PROG_TYPE_TRACING: if (eatype == BPF_TRACE_ITER) return true; break; case BPF_PROG_TYPE_SOCK_OPS: /* map_update allowed only via dedicated helpers with event type checks */ if (func_id == BPF_FUNC_map_delete_elem) return true; break; case BPF_PROG_TYPE_SOCKET_FILTER: case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: case BPF_PROG_TYPE_XDP: case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_SK_LOOKUP: return true; default: break; } verbose(env, "cannot update sockmap in this context\n"); return false; } static bool allow_tail_call_in_subprogs(struct bpf_verifier_env *env) { return env->prog->jit_requested && bpf_jit_supports_subprog_tailcalls(); } static int check_map_func_compatibility(struct bpf_verifier_env *env, struct bpf_map *map, int func_id) { if (!map) return 0; /* We need a two way check, first is from map perspective ... */ switch (map->map_type) { case BPF_MAP_TYPE_PROG_ARRAY: if (func_id != BPF_FUNC_tail_call) goto error; break; case BPF_MAP_TYPE_PERF_EVENT_ARRAY: if (func_id != BPF_FUNC_perf_event_read && func_id != BPF_FUNC_perf_event_output && func_id != BPF_FUNC_skb_output && func_id != BPF_FUNC_perf_event_read_value && func_id != BPF_FUNC_xdp_output) goto error; break; case BPF_MAP_TYPE_RINGBUF: if (func_id != BPF_FUNC_ringbuf_output && func_id != BPF_FUNC_ringbuf_reserve && func_id != BPF_FUNC_ringbuf_query && func_id != BPF_FUNC_ringbuf_reserve_dynptr && func_id != BPF_FUNC_ringbuf_submit_dynptr && func_id != BPF_FUNC_ringbuf_discard_dynptr) goto error; break; case BPF_MAP_TYPE_USER_RINGBUF: if (func_id != BPF_FUNC_user_ringbuf_drain) goto error; break; case BPF_MAP_TYPE_STACK_TRACE: if (func_id != BPF_FUNC_get_stackid) goto error; break; case BPF_MAP_TYPE_CGROUP_ARRAY: if (func_id != BPF_FUNC_skb_under_cgroup && func_id != BPF_FUNC_current_task_under_cgroup) goto error; break; case BPF_MAP_TYPE_CGROUP_STORAGE: case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: if (func_id != BPF_FUNC_get_local_storage) goto error; break; case BPF_MAP_TYPE_DEVMAP: case BPF_MAP_TYPE_DEVMAP_HASH: if (func_id != BPF_FUNC_redirect_map && func_id != BPF_FUNC_map_lookup_elem) goto error; break; /* Restrict bpf side of cpumap and xskmap, open when use-cases * appear. */ case BPF_MAP_TYPE_CPUMAP: if (func_id != BPF_FUNC_redirect_map) goto error; break; case BPF_MAP_TYPE_XSKMAP: if (func_id != BPF_FUNC_redirect_map && func_id != BPF_FUNC_map_lookup_elem) goto error; break; case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH_OF_MAPS: if (func_id != BPF_FUNC_map_lookup_elem) goto error; break; case BPF_MAP_TYPE_SOCKMAP: if (func_id != BPF_FUNC_sk_redirect_map && func_id != BPF_FUNC_sock_map_update && func_id != BPF_FUNC_msg_redirect_map && func_id != BPF_FUNC_sk_select_reuseport && func_id != BPF_FUNC_map_lookup_elem && !may_update_sockmap(env, func_id)) goto error; break; case BPF_MAP_TYPE_SOCKHASH: if (func_id != BPF_FUNC_sk_redirect_hash && func_id != BPF_FUNC_sock_hash_update && func_id != BPF_FUNC_msg_redirect_hash && func_id != BPF_FUNC_sk_select_reuseport && func_id != BPF_FUNC_map_lookup_elem && !may_update_sockmap(env, func_id)) goto error; break; case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: if (func_id != BPF_FUNC_sk_select_reuseport) goto error; break; case BPF_MAP_TYPE_QUEUE: case BPF_MAP_TYPE_STACK: if (func_id != BPF_FUNC_map_peek_elem && func_id != BPF_FUNC_map_pop_elem && func_id != BPF_FUNC_map_push_elem) goto error; break; case BPF_MAP_TYPE_SK_STORAGE: if (func_id != BPF_FUNC_sk_storage_get && func_id != BPF_FUNC_sk_storage_delete) goto error; break; case BPF_MAP_TYPE_INODE_STORAGE: if (func_id != BPF_FUNC_inode_storage_get && func_id != BPF_FUNC_inode_storage_delete) goto error; break; case BPF_MAP_TYPE_TASK_STORAGE: if (func_id != BPF_FUNC_task_storage_get && func_id != BPF_FUNC_task_storage_delete) goto error; break; case BPF_MAP_TYPE_BLOOM_FILTER: if (func_id != BPF_FUNC_map_peek_elem && func_id != BPF_FUNC_map_push_elem) goto error; break; default: break; } /* ... and second from the function itself. */ switch (func_id) { case BPF_FUNC_tail_call: if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY) goto error; if (env->subprog_cnt > 1 && !allow_tail_call_in_subprogs(env)) { verbose(env, "tail_calls are not allowed in non-JITed programs with bpf-to-bpf calls\n"); return -EINVAL; } break; case BPF_FUNC_perf_event_read: case BPF_FUNC_perf_event_output: case BPF_FUNC_perf_event_read_value: case BPF_FUNC_skb_output: case BPF_FUNC_xdp_output: if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) goto error; break; case BPF_FUNC_ringbuf_output: case BPF_FUNC_ringbuf_reserve: case BPF_FUNC_ringbuf_query: case BPF_FUNC_ringbuf_reserve_dynptr: case BPF_FUNC_ringbuf_submit_dynptr: case BPF_FUNC_ringbuf_discard_dynptr: if (map->map_type != BPF_MAP_TYPE_RINGBUF) goto error; break; case BPF_FUNC_user_ringbuf_drain: if (map->map_type != BPF_MAP_TYPE_USER_RINGBUF) goto error; break; case BPF_FUNC_get_stackid: if (map->map_type != BPF_MAP_TYPE_STACK_TRACE) goto error; break; case BPF_FUNC_current_task_under_cgroup: case BPF_FUNC_skb_under_cgroup: if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY) goto error; break; case BPF_FUNC_redirect_map: if (map->map_type != BPF_MAP_TYPE_DEVMAP && map->map_type != BPF_MAP_TYPE_DEVMAP_HASH && map->map_type != BPF_MAP_TYPE_CPUMAP && map->map_type != BPF_MAP_TYPE_XSKMAP) goto error; break; case BPF_FUNC_sk_redirect_map: case BPF_FUNC_msg_redirect_map: case BPF_FUNC_sock_map_update: if (map->map_type != BPF_MAP_TYPE_SOCKMAP) goto error; break; case BPF_FUNC_sk_redirect_hash: case BPF_FUNC_msg_redirect_hash: case BPF_FUNC_sock_hash_update: if (map->map_type != BPF_MAP_TYPE_SOCKHASH) goto error; break; case BPF_FUNC_get_local_storage: if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && map->map_type != BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) goto error; break; case BPF_FUNC_sk_select_reuseport: if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY && map->map_type != BPF_MAP_TYPE_SOCKMAP && map->map_type != BPF_MAP_TYPE_SOCKHASH) goto error; break; case BPF_FUNC_map_pop_elem: if (map->map_type != BPF_MAP_TYPE_QUEUE && map->map_type != BPF_MAP_TYPE_STACK) goto error; break; case BPF_FUNC_map_peek_elem: case BPF_FUNC_map_push_elem: if (map->map_type != BPF_MAP_TYPE_QUEUE && map->map_type != BPF_MAP_TYPE_STACK && map->map_type != BPF_MAP_TYPE_BLOOM_FILTER) goto error; break; case BPF_FUNC_map_lookup_percpu_elem: if (map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY && map->map_type != BPF_MAP_TYPE_PERCPU_HASH && map->map_type != BPF_MAP_TYPE_LRU_PERCPU_HASH) goto error; break; case BPF_FUNC_sk_storage_get: case BPF_FUNC_sk_storage_delete: if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) goto error; break; case BPF_FUNC_inode_storage_get: case BPF_FUNC_inode_storage_delete: if (map->map_type != BPF_MAP_TYPE_INODE_STORAGE) goto error; break; case BPF_FUNC_task_storage_get: case BPF_FUNC_task_storage_delete: if (map->map_type != BPF_MAP_TYPE_TASK_STORAGE) goto error; break; default: break; } return 0; error: verbose(env, "cannot pass map_type %d into func %s#%d\n", map->map_type, func_id_name(func_id), func_id); return -EINVAL; } static bool check_raw_mode_ok(const struct bpf_func_proto *fn) { int count = 0; if (arg_type_is_raw_mem(fn->arg1_type)) count++; if (arg_type_is_raw_mem(fn->arg2_type)) count++; if (arg_type_is_raw_mem(fn->arg3_type)) count++; if (arg_type_is_raw_mem(fn->arg4_type)) count++; if (arg_type_is_raw_mem(fn->arg5_type)) count++; /* We only support one arg being in raw mode at the moment, * which is sufficient for the helper functions we have * right now. */ return count <= 1; } static bool check_args_pair_invalid(const struct bpf_func_proto *fn, int arg) { bool is_fixed = fn->arg_type[arg] & MEM_FIXED_SIZE; bool has_size = fn->arg_size[arg] != 0; bool is_next_size = false; if (arg + 1 < ARRAY_SIZE(fn->arg_type)) is_next_size = arg_type_is_mem_size(fn->arg_type[arg + 1]); if (base_type(fn->arg_type[arg]) != ARG_PTR_TO_MEM) return is_next_size; return has_size == is_next_size || is_next_size == is_fixed; } static bool check_arg_pair_ok(const struct bpf_func_proto *fn) { /* bpf_xxx(..., buf, len) call will access 'len' * bytes from memory 'buf'. Both arg types need * to be paired, so make sure there's no buggy * helper function specification. */ if (arg_type_is_mem_size(fn->arg1_type) || check_args_pair_invalid(fn, 0) || check_args_pair_invalid(fn, 1) || check_args_pair_invalid(fn, 2) || check_args_pair_invalid(fn, 3) || check_args_pair_invalid(fn, 4)) return false; return true; } static bool check_btf_id_ok(const struct bpf_func_proto *fn) { int i; for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++) { if (base_type(fn->arg_type[i]) == ARG_PTR_TO_BTF_ID && !fn->arg_btf_id[i]) return false; if (base_type(fn->arg_type[i]) != ARG_PTR_TO_BTF_ID && fn->arg_btf_id[i] && /* arg_btf_id and arg_size are in a union. */ (base_type(fn->arg_type[i]) != ARG_PTR_TO_MEM || !(fn->arg_type[i] & MEM_FIXED_SIZE))) return false; } return true; } static int check_func_proto(const struct bpf_func_proto *fn, int func_id) { return check_raw_mode_ok(fn) && check_arg_pair_ok(fn) && check_btf_id_ok(fn) ? 0 : -EINVAL; } /* Packet data might have moved, any old PTR_TO_PACKET[_META,_END] * are now invalid, so turn them into unknown SCALAR_VALUE. */ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) { struct bpf_func_state *state; struct bpf_reg_state *reg; bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ if (reg_is_pkt_pointer_any(reg)) __mark_reg_unknown(env, reg); })); } enum { AT_PKT_END = -1, BEYOND_PKT_END = -2, }; static void mark_pkt_end(struct bpf_verifier_state *vstate, int regn, bool range_open) { struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *reg = &state->regs[regn]; if (reg->type != PTR_TO_PACKET) /* PTR_TO_PACKET_META is not supported yet */ return; /* The 'reg' is pkt > pkt_end or pkt >= pkt_end. * How far beyond pkt_end it goes is unknown. * if (!range_open) it's the case of pkt >= pkt_end * if (range_open) it's the case of pkt > pkt_end * hence this pointer is at least 1 byte bigger than pkt_end */ if (range_open) reg->range = BEYOND_PKT_END; else reg->range = AT_PKT_END; } /* The pointer with the specified id has released its reference to kernel * resources. Identify all copies of the same pointer and clear the reference. */ static int release_reference(struct bpf_verifier_env *env, int ref_obj_id) { struct bpf_func_state *state; struct bpf_reg_state *reg; int err; err = release_reference_state(cur_func(env), ref_obj_id); if (err) return err; bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ if (reg->ref_obj_id == ref_obj_id) { if (!env->allow_ptr_leaks) __mark_reg_not_init(env, reg); else __mark_reg_unknown(env, reg); } })); return 0; } static void clear_caller_saved_regs(struct bpf_verifier_env *env, struct bpf_reg_state *regs) { int i; /* after the call registers r0 - r5 were scratched */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]); check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); } } typedef int (*set_callee_state_fn)(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx); static int set_callee_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx); static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx, int subprog, set_callee_state_fn set_callee_state_cb) { struct bpf_verifier_state *state = env->cur_state; struct bpf_func_info_aux *func_info_aux; struct bpf_func_state *caller, *callee; int err; bool is_global = false; if (state->curframe + 1 >= MAX_CALL_FRAMES) { verbose(env, "the call stack of %d frames is too deep\n", state->curframe + 2); return -E2BIG; } caller = state->frame[state->curframe]; if (state->frame[state->curframe + 1]) { verbose(env, "verifier bug. Frame %d already allocated\n", state->curframe + 1); return -EFAULT; } func_info_aux = env->prog->aux->func_info_aux; if (func_info_aux) is_global = func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL; err = btf_check_subprog_call(env, subprog, caller->regs); if (err == -EFAULT) return err; if (is_global) { if (err) { verbose(env, "Caller passes invalid args into func#%d\n", subprog); return err; } else { if (env->log.level & BPF_LOG_LEVEL) verbose(env, "Func#%d is global and valid. Skipping.\n", subprog); clear_caller_saved_regs(env, caller->regs); /* All global functions return a 64-bit SCALAR_VALUE */ mark_reg_unknown(env, caller->regs, BPF_REG_0); caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG; /* continue with next insn after call */ return 0; } } /* set_callee_state is used for direct subprog calls, but we are * interested in validating only BPF helpers that can call subprogs as * callbacks */ if (set_callee_state_cb != set_callee_state && !is_callback_calling_function(insn->imm)) { verbose(env, "verifier bug: helper %s#%d is not marked as callback-calling\n", func_id_name(insn->imm), insn->imm); return -EFAULT; } if (insn->code == (BPF_JMP | BPF_CALL) && insn->src_reg == 0 && insn->imm == BPF_FUNC_timer_set_callback) { struct bpf_verifier_state *async_cb; /* there is no real recursion here. timer callbacks are async */ env->subprog_info[subprog].is_async_cb = true; async_cb = push_async_cb(env, env->subprog_info[subprog].start, *insn_idx, subprog); if (!async_cb) return -EFAULT; callee = async_cb->frame[0]; callee->async_entry_cnt = caller->async_entry_cnt + 1; /* Convert bpf_timer_set_callback() args into timer callback args */ err = set_callee_state_cb(env, caller, callee, *insn_idx); if (err) return err; clear_caller_saved_regs(env, caller->regs); mark_reg_unknown(env, caller->regs, BPF_REG_0); caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG; /* continue with next insn after call */ return 0; } callee = kzalloc(sizeof(*callee), GFP_KERNEL); if (!callee) return -ENOMEM; state->frame[state->curframe + 1] = callee; /* callee cannot access r0, r6 - r9 for reading and has to write * into its own stack before reading from it. * callee can read/write into caller's stack */ init_func_state(env, callee, /* remember the callsite, it will be used by bpf_exit */ *insn_idx /* callsite */, state->curframe + 1 /* frameno within this callchain */, subprog /* subprog number within this prog */); /* Transfer references to the callee */ err = copy_reference_state(callee, caller); if (err) goto err_out; err = set_callee_state_cb(env, caller, callee, *insn_idx); if (err) goto err_out; clear_caller_saved_regs(env, caller->regs); /* only increment it after check_reg_arg() finished */ state->curframe++; /* and go analyze first insn of the callee */ *insn_idx = env->subprog_info[subprog].start - 1; if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "caller:\n"); print_verifier_state(env, caller, true); verbose(env, "callee:\n"); print_verifier_state(env, callee, true); } return 0; err_out: free_func_state(callee); state->frame[state->curframe + 1] = NULL; return err; } int map_set_for_each_callback_args(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee) { /* bpf_for_each_map_elem(struct bpf_map *map, void *callback_fn, * void *callback_ctx, u64 flags); * callback_fn(struct bpf_map *map, void *key, void *value, * void *callback_ctx); */ callee->regs[BPF_REG_1] = caller->regs[BPF_REG_1]; callee->regs[BPF_REG_2].type = PTR_TO_MAP_KEY; __mark_reg_known_zero(&callee->regs[BPF_REG_2]); callee->regs[BPF_REG_2].map_ptr = caller->regs[BPF_REG_1].map_ptr; callee->regs[BPF_REG_3].type = PTR_TO_MAP_VALUE; __mark_reg_known_zero(&callee->regs[BPF_REG_3]); callee->regs[BPF_REG_3].map_ptr = caller->regs[BPF_REG_1].map_ptr; /* pointer to stack or null */ callee->regs[BPF_REG_4] = caller->regs[BPF_REG_3]; /* unused */ __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); return 0; } static int set_callee_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx) { int i; /* copy r1 - r5 args that callee can access. The copy includes parent * pointers, which connects us up to the liveness chain */ for (i = BPF_REG_1; i <= BPF_REG_5; i++) callee->regs[i] = caller->regs[i]; return 0; } static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx) { int subprog, target_insn; target_insn = *insn_idx + insn->imm + 1; subprog = find_subprog(env, target_insn); if (subprog < 0) { verbose(env, "verifier bug. No program starts at insn %d\n", target_insn); return -EFAULT; } return __check_func_call(env, insn, insn_idx, subprog, set_callee_state); } static int set_map_elem_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx) { struct bpf_insn_aux_data *insn_aux = &env->insn_aux_data[insn_idx]; struct bpf_map *map; int err; if (bpf_map_ptr_poisoned(insn_aux)) { verbose(env, "tail_call abusing map_ptr\n"); return -EINVAL; } map = BPF_MAP_PTR(insn_aux->map_ptr_state); if (!map->ops->map_set_for_each_callback_args || !map->ops->map_for_each_callback) { verbose(env, "callback function not allowed for map\n"); return -ENOTSUPP; } err = map->ops->map_set_for_each_callback_args(env, caller, callee); if (err) return err; callee->in_callback_fn = true; callee->callback_ret_range = tnum_range(0, 1); return 0; } static int set_loop_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx) { /* bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, * u64 flags); * callback_fn(u32 index, void *callback_ctx); */ callee->regs[BPF_REG_1].type = SCALAR_VALUE; callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3]; /* unused */ __mark_reg_not_init(env, &callee->regs[BPF_REG_3]); __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_callback_fn = true; callee->callback_ret_range = tnum_range(0, 1); return 0; } static int set_timer_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx) { struct bpf_map *map_ptr = caller->regs[BPF_REG_1].map_ptr; /* bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn); * callback_fn(struct bpf_map *map, void *key, void *value); */ callee->regs[BPF_REG_1].type = CONST_PTR_TO_MAP; __mark_reg_known_zero(&callee->regs[BPF_REG_1]); callee->regs[BPF_REG_1].map_ptr = map_ptr; callee->regs[BPF_REG_2].type = PTR_TO_MAP_KEY; __mark_reg_known_zero(&callee->regs[BPF_REG_2]); callee->regs[BPF_REG_2].map_ptr = map_ptr; callee->regs[BPF_REG_3].type = PTR_TO_MAP_VALUE; __mark_reg_known_zero(&callee->regs[BPF_REG_3]); callee->regs[BPF_REG_3].map_ptr = map_ptr; /* unused */ __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_async_callback_fn = true; callee->callback_ret_range = tnum_range(0, 1); return 0; } static int set_find_vma_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx) { /* bpf_find_vma(struct task_struct *task, u64 addr, * void *callback_fn, void *callback_ctx, u64 flags) * (callback_fn)(struct task_struct *task, * struct vm_area_struct *vma, void *callback_ctx); */ callee->regs[BPF_REG_1] = caller->regs[BPF_REG_1]; callee->regs[BPF_REG_2].type = PTR_TO_BTF_ID; __mark_reg_known_zero(&callee->regs[BPF_REG_2]); callee->regs[BPF_REG_2].btf = btf_vmlinux; callee->regs[BPF_REG_2].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA], /* pointer to stack or null */ callee->regs[BPF_REG_3] = caller->regs[BPF_REG_4]; /* unused */ __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_callback_fn = true; callee->callback_ret_range = tnum_range(0, 1); return 0; } static int set_user_ringbuf_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx) { /* bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void * callback_ctx, u64 flags); * callback_fn(struct bpf_dynptr_t* dynptr, void *callback_ctx); */ __mark_reg_not_init(env, &callee->regs[BPF_REG_0]); callee->regs[BPF_REG_1].type = PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL; __mark_reg_known_zero(&callee->regs[BPF_REG_1]); callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3]; /* unused */ __mark_reg_not_init(env, &callee->regs[BPF_REG_3]); __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_callback_fn = true; callee->callback_ret_range = tnum_range(0, 1); return 0; } static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) { struct bpf_verifier_state *state = env->cur_state; struct bpf_func_state *caller, *callee; struct bpf_reg_state *r0; int err; callee = state->frame[state->curframe]; r0 = &callee->regs[BPF_REG_0]; if (r0->type == PTR_TO_STACK) { /* technically it's ok to return caller's stack pointer * (or caller's caller's pointer) back to the caller, * since these pointers are valid. Only current stack * pointer will be invalid as soon as function exits, * but let's be conservative */ verbose(env, "cannot return stack pointer to the caller\n"); return -EINVAL; } caller = state->frame[state->curframe - 1]; if (callee->in_callback_fn) { /* enforce R0 return value range [0, 1]. */ struct tnum range = callee->callback_ret_range; if (r0->type != SCALAR_VALUE) { verbose(env, "R0 not a scalar value\n"); return -EACCES; } /* we are going to rely on register's precise value */ err = mark_reg_read(env, r0, r0->parent, REG_LIVE_READ64); err = err ?: mark_chain_precision(env, BPF_REG_0); if (err) return err; if (!tnum_in(range, r0->var_off)) { verbose_invalid_scalar(env, r0, &range, "callback return", "R0"); return -EINVAL; } } else { /* return to the caller whatever r0 had in the callee */ caller->regs[BPF_REG_0] = *r0; } /* callback_fn frame should have released its own additions to parent's * reference state at this point, or check_reference_leak would * complain, hence it must be the same as the caller. There is no need * to copy it back. */ if (!callee->in_callback_fn) { /* Transfer references to the caller */ err = copy_reference_state(caller, callee); if (err) return err; } *insn_idx = callee->callsite + 1; if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "returning from callee:\n"); print_verifier_state(env, callee, true); verbose(env, "to caller at %d:\n", *insn_idx); print_verifier_state(env, caller, true); } /* clear everything in the callee */ free_func_state(callee); state->frame[state->curframe--] = NULL; return 0; } static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type, int func_id, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *ret_reg = ®s[BPF_REG_0]; if (ret_type != RET_INTEGER || (func_id != BPF_FUNC_get_stack && func_id != BPF_FUNC_get_task_stack && func_id != BPF_FUNC_probe_read_str && func_id != BPF_FUNC_probe_read_kernel_str && func_id != BPF_FUNC_probe_read_user_str)) return; ret_reg->smax_value = meta->msize_max_value; ret_reg->s32_max_value = meta->msize_max_value; ret_reg->smin_value = -MAX_ERRNO; ret_reg->s32_min_value = -MAX_ERRNO; reg_bounds_sync(ret_reg); } static int record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, int func_id, int insn_idx) { struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; struct bpf_map *map = meta->map_ptr; if (func_id != BPF_FUNC_tail_call && func_id != BPF_FUNC_map_lookup_elem && func_id != BPF_FUNC_map_update_elem && func_id != BPF_FUNC_map_delete_elem && func_id != BPF_FUNC_map_push_elem && func_id != BPF_FUNC_map_pop_elem && func_id != BPF_FUNC_map_peek_elem && func_id != BPF_FUNC_for_each_map_elem && func_id != BPF_FUNC_redirect_map && func_id != BPF_FUNC_map_lookup_percpu_elem) return 0; if (map == NULL) { verbose(env, "kernel subsystem misconfigured verifier\n"); return -EINVAL; } /* In case of read-only, some additional restrictions * need to be applied in order to prevent altering the * state of the map from program side. */ if ((map->map_flags & BPF_F_RDONLY_PROG) && (func_id == BPF_FUNC_map_delete_elem || func_id == BPF_FUNC_map_update_elem || func_id == BPF_FUNC_map_push_elem || func_id == BPF_FUNC_map_pop_elem)) { verbose(env, "write into map forbidden\n"); return -EACCES; } if (!BPF_MAP_PTR(aux->map_ptr_state)) bpf_map_ptr_store(aux, meta->map_ptr, !meta->map_ptr->bypass_spec_v1); else if (BPF_MAP_PTR(aux->map_ptr_state) != meta->map_ptr) bpf_map_ptr_store(aux, BPF_MAP_PTR_POISON, !meta->map_ptr->bypass_spec_v1); return 0; } static int record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, int func_id, int insn_idx) { struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; struct bpf_reg_state *regs = cur_regs(env), *reg; struct bpf_map *map = meta->map_ptr; u64 val, max; int err; if (func_id != BPF_FUNC_tail_call) return 0; if (!map || map->map_type != BPF_MAP_TYPE_PROG_ARRAY) { verbose(env, "kernel subsystem misconfigured verifier\n"); return -EINVAL; } reg = ®s[BPF_REG_3]; val = reg->var_off.value; max = map->max_entries; if (!(register_is_const(reg) && val < max)) { bpf_map_key_store(aux, BPF_MAP_KEY_POISON); return 0; } err = mark_chain_precision(env, BPF_REG_3); if (err) return err; if (bpf_map_key_unseen(aux)) bpf_map_key_store(aux, val); else if (!bpf_map_key_poisoned(aux) && bpf_map_key_immediate(aux) != val) bpf_map_key_store(aux, BPF_MAP_KEY_POISON); return 0; } static int check_reference_leak(struct bpf_verifier_env *env) { struct bpf_func_state *state = cur_func(env); bool refs_lingering = false; int i; if (state->frameno && !state->in_callback_fn) return 0; for (i = 0; i < state->acquired_refs; i++) { if (state->in_callback_fn && state->refs[i].callback_ref != state->frameno) continue; verbose(env, "Unreleased reference id=%d alloc_insn=%d\n", state->refs[i].id, state->refs[i].insn_idx); refs_lingering = true; } return refs_lingering ? -EINVAL : 0; } static int check_bpf_snprintf_call(struct bpf_verifier_env *env, struct bpf_reg_state *regs) { struct bpf_reg_state *fmt_reg = ®s[BPF_REG_3]; struct bpf_reg_state *data_len_reg = ®s[BPF_REG_5]; struct bpf_map *fmt_map = fmt_reg->map_ptr; struct bpf_bprintf_data data = {}; int err, fmt_map_off, num_args; u64 fmt_addr; char *fmt; /* data must be an array of u64 */ if (data_len_reg->var_off.value % 8) return -EINVAL; num_args = data_len_reg->var_off.value / 8; /* fmt being ARG_PTR_TO_CONST_STR guarantees that var_off is const * and map_direct_value_addr is set. */ fmt_map_off = fmt_reg->off + fmt_reg->var_off.value; err = fmt_map->ops->map_direct_value_addr(fmt_map, &fmt_addr, fmt_map_off); if (err) { verbose(env, "verifier bug\n"); return -EFAULT; } fmt = (char *)(long)fmt_addr + fmt_map_off; /* We are also guaranteed that fmt+fmt_map_off is NULL terminated, we * can focus on validating the format specifiers. */ err = bpf_bprintf_prepare(fmt, UINT_MAX, NULL, num_args, &data); if (err < 0) verbose(env, "Invalid format string\n"); return err; } static int check_get_func_ip(struct bpf_verifier_env *env) { enum bpf_prog_type type = resolve_prog_type(env->prog); int func_id = BPF_FUNC_get_func_ip; if (type == BPF_PROG_TYPE_TRACING) { if (!bpf_prog_has_trampoline(env->prog)) { verbose(env, "func %s#%d supported only for fentry/fexit/fmod_ret programs\n", func_id_name(func_id), func_id); return -ENOTSUPP; } return 0; } else if (type == BPF_PROG_TYPE_KPROBE) { return 0; } verbose(env, "func %s#%d not supported for program type %d\n", func_id_name(func_id), func_id, type); return -ENOTSUPP; } static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env) { return &env->insn_aux_data[env->insn_idx]; } static bool loop_flag_is_zero(struct bpf_verifier_env *env) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = ®s[BPF_REG_4]; bool reg_is_null = register_is_null(reg); if (reg_is_null) mark_chain_precision(env, BPF_REG_4); return reg_is_null; } static void update_loop_inline_state(struct bpf_verifier_env *env, u32 subprogno) { struct bpf_loop_inline_state *state = &cur_aux(env)->loop_inline_state; if (!state->initialized) { state->initialized = 1; state->fit_for_inline = loop_flag_is_zero(env); state->callback_subprogno = subprogno; return; } if (!state->fit_for_inline) return; state->fit_for_inline = (loop_flag_is_zero(env) && state->callback_subprogno == subprogno); } static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx_p) { enum bpf_prog_type prog_type = resolve_prog_type(env->prog); const struct bpf_func_proto *fn = NULL; enum bpf_return_type ret_type; enum bpf_type_flag ret_flag; struct bpf_reg_state *regs; struct bpf_call_arg_meta meta; int insn_idx = *insn_idx_p; bool changes_data; int i, err, func_id; /* find function prototype */ func_id = insn->imm; if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) { verbose(env, "invalid func %s#%d\n", func_id_name(func_id), func_id); return -EINVAL; } if (env->ops->get_func_proto) fn = env->ops->get_func_proto(func_id, env->prog); if (!fn) { verbose(env, "unknown func %s#%d\n", func_id_name(func_id), func_id); return -EINVAL; } /* eBPF programs must be GPL compatible to use GPL-ed functions */ if (!env->prog->gpl_compatible && fn->gpl_only) { verbose(env, "cannot call GPL-restricted function from non-GPL compatible program\n"); return -EINVAL; } if (fn->allowed && !fn->allowed(env->prog)) { verbose(env, "helper call is not allowed in probe\n"); return -EINVAL; } /* With LD_ABS/IND some JITs save/restore skb from r1. */ changes_data = bpf_helper_changes_pkt_data(fn->func); if (changes_data && fn->arg1_type != ARG_PTR_TO_CTX) { verbose(env, "kernel subsystem misconfigured func %s#%d: r1 != ctx\n", func_id_name(func_id), func_id); return -EINVAL; } memset(&meta, 0, sizeof(meta)); meta.pkt_access = fn->pkt_access; err = check_func_proto(fn, func_id); if (err) { verbose(env, "kernel subsystem misconfigured func %s#%d\n", func_id_name(func_id), func_id); return err; } meta.func_id = func_id; /* check args */ for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) { err = check_func_arg(env, i, &meta, fn); if (err) return err; } err = record_func_map(env, &meta, func_id, insn_idx); if (err) return err; err = record_func_key(env, &meta, func_id, insn_idx); if (err) return err; /* Mark slots with STACK_MISC in case of raw mode, stack offset * is inferred from register state. */ for (i = 0; i < meta.access_size; i++) { err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B, BPF_WRITE, -1, false); if (err) return err; } regs = cur_regs(env); if (meta.uninit_dynptr_regno) { /* we write BPF_DW bits (8 bytes) at a time */ for (i = 0; i < BPF_DYNPTR_SIZE; i += 8) { err = check_mem_access(env, insn_idx, meta.uninit_dynptr_regno, i, BPF_DW, BPF_WRITE, -1, false); if (err) return err; } err = mark_stack_slots_dynptr(env, ®s[meta.uninit_dynptr_regno], fn->arg_type[meta.uninit_dynptr_regno - BPF_REG_1], insn_idx); if (err) return err; } if (meta.release_regno) { err = -EINVAL; if (arg_type_is_dynptr(fn->arg_type[meta.release_regno - BPF_REG_1])) err = unmark_stack_slots_dynptr(env, ®s[meta.release_regno]); else if (meta.ref_obj_id) err = release_reference(env, meta.ref_obj_id); /* meta.ref_obj_id can only be 0 if register that is meant to be * released is NULL, which must be > R0. */ else if (register_is_null(®s[meta.release_regno])) err = 0; if (err) { verbose(env, "func %s#%d reference has not been acquired before\n", func_id_name(func_id), func_id); return err; } } switch (func_id) { case BPF_FUNC_tail_call: err = check_reference_leak(env); if (err) { verbose(env, "tail_call would lead to reference leak\n"); return err; } break; case BPF_FUNC_get_local_storage: /* check that flags argument in get_local_storage(map, flags) is 0, * this is required because get_local_storage() can't return an error. */ if (!register_is_null(®s[BPF_REG_2])) { verbose(env, "get_local_storage() doesn't support non-zero flags\n"); return -EINVAL; } break; case BPF_FUNC_for_each_map_elem: err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, set_map_elem_callback_state); break; case BPF_FUNC_timer_set_callback: err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, set_timer_callback_state); break; case BPF_FUNC_find_vma: err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, set_find_vma_callback_state); break; case BPF_FUNC_snprintf: err = check_bpf_snprintf_call(env, regs); break; case BPF_FUNC_loop: update_loop_inline_state(env, meta.subprogno); err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, set_loop_callback_state); break; case BPF_FUNC_dynptr_from_mem: if (regs[BPF_REG_1].type != PTR_TO_MAP_VALUE) { verbose(env, "Unsupported reg type %s for bpf_dynptr_from_mem data\n", reg_type_str(env, regs[BPF_REG_1].type)); return -EACCES; } break; case BPF_FUNC_set_retval: if (prog_type == BPF_PROG_TYPE_LSM && env->prog->expected_attach_type == BPF_LSM_CGROUP) { if (!env->prog->aux->attach_func_proto->type) { /* Make sure programs that attach to void * hooks don't try to modify return value. */ verbose(env, "BPF_LSM_CGROUP that attach to void LSM hooks can't modify return value!\n"); return -EINVAL; } } break; case BPF_FUNC_dynptr_data: for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) { if (arg_type_is_dynptr(fn->arg_type[i])) { struct bpf_reg_state *reg = ®s[BPF_REG_1 + i]; if (meta.ref_obj_id) { verbose(env, "verifier internal error: meta.ref_obj_id already set\n"); return -EFAULT; } if (base_type(reg->type) != PTR_TO_DYNPTR) /* Find the id of the dynptr we're * tracking the reference of */ meta.ref_obj_id = stack_slot_get_id(env, reg); break; } } if (i == MAX_BPF_FUNC_REG_ARGS) { verbose(env, "verifier internal error: no dynptr in bpf_dynptr_data()\n"); return -EFAULT; } break; case BPF_FUNC_user_ringbuf_drain: err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, set_user_ringbuf_callback_state); break; } if (err) return err; /* reset caller saved regs */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]); check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); } /* helper call returns 64-bit value. */ regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG; /* update return register (already marked as written above) */ ret_type = fn->ret_type; ret_flag = type_flag(ret_type); switch (base_type(ret_type)) { case RET_INTEGER: /* sets type to SCALAR_VALUE */ mark_reg_unknown(env, regs, BPF_REG_0); break; case RET_VOID: regs[BPF_REG_0].type = NOT_INIT; break; case RET_PTR_TO_MAP_VALUE: /* There is no offset yet applied, variable or fixed */ mark_reg_known_zero(env, regs, BPF_REG_0); /* remember map_ptr, so that check_map_access() * can check 'value_size' boundary of memory access * to map element returned from bpf_map_lookup_elem() */ if (meta.map_ptr == NULL) { verbose(env, "kernel subsystem misconfigured verifier\n"); return -EINVAL; } regs[BPF_REG_0].map_ptr = meta.map_ptr; regs[BPF_REG_0].map_uid = meta.map_uid; regs[BPF_REG_0].type = PTR_TO_MAP_VALUE | ret_flag; if (!type_may_be_null(ret_type) && map_value_has_spin_lock(meta.map_ptr)) { regs[BPF_REG_0].id = ++env->id_gen; } break; case RET_PTR_TO_SOCKET: mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_SOCKET | ret_flag; break; case RET_PTR_TO_SOCK_COMMON: mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON | ret_flag; break; case RET_PTR_TO_TCP_SOCK: mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_TCP_SOCK | ret_flag; break; case RET_PTR_TO_ALLOC_MEM: mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag; regs[BPF_REG_0].mem_size = meta.mem_size; break; case RET_PTR_TO_MEM_OR_BTF_ID: { const struct btf_type *t; mark_reg_known_zero(env, regs, BPF_REG_0); t = btf_type_skip_modifiers(meta.ret_btf, meta.ret_btf_id, NULL); if (!btf_type_is_struct(t)) { u32 tsize; const struct btf_type *ret; const char *tname; /* resolve the type size of ksym. */ ret = btf_resolve_size(meta.ret_btf, t, &tsize); if (IS_ERR(ret)) { tname = btf_name_by_offset(meta.ret_btf, t->name_off); verbose(env, "unable to resolve the size of type '%s': %ld\n", tname, PTR_ERR(ret)); return -EINVAL; } regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag; regs[BPF_REG_0].mem_size = tsize; } else { /* MEM_RDONLY may be carried from ret_flag, but it * doesn't apply on PTR_TO_BTF_ID. Fold it, otherwise * it will confuse the check of PTR_TO_BTF_ID in * check_mem_access(). */ ret_flag &= ~MEM_RDONLY; regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag; regs[BPF_REG_0].btf = meta.ret_btf; regs[BPF_REG_0].btf_id = meta.ret_btf_id; } break; } case RET_PTR_TO_BTF_ID: { struct btf *ret_btf; int ret_btf_id; mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag; if (func_id == BPF_FUNC_kptr_xchg) { ret_btf = meta.kptr_off_desc->kptr.btf; ret_btf_id = meta.kptr_off_desc->kptr.btf_id; } else { if (fn->ret_btf_id == BPF_PTR_POISON) { verbose(env, "verifier internal error:"); verbose(env, "func %s has non-overwritten BPF_PTR_POISON return type\n", func_id_name(func_id)); return -EINVAL; } ret_btf = btf_vmlinux; ret_btf_id = *fn->ret_btf_id; } if (ret_btf_id == 0) { verbose(env, "invalid return type %u of func %s#%d\n", base_type(ret_type), func_id_name(func_id), func_id); return -EINVAL; } regs[BPF_REG_0].btf = ret_btf; regs[BPF_REG_0].btf_id = ret_btf_id; break; } default: verbose(env, "unknown return type %u of func %s#%d\n", base_type(ret_type), func_id_name(func_id), func_id); return -EINVAL; } if (type_may_be_null(regs[BPF_REG_0].type)) regs[BPF_REG_0].id = ++env->id_gen; if (helper_multiple_ref_obj_use(func_id, meta.map_ptr)) { verbose(env, "verifier internal error: func %s#%d sets ref_obj_id more than once\n", func_id_name(func_id), func_id); return -EFAULT; } if (is_ptr_cast_function(func_id) || is_dynptr_ref_function(func_id)) { /* For release_reference() */ regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id; } else if (is_acquire_function(func_id, meta.map_ptr)) { int id = acquire_reference_state(env, insn_idx); if (id < 0) return id; /* For mark_ptr_or_null_reg() */ regs[BPF_REG_0].id = id; /* For release_reference() */ regs[BPF_REG_0].ref_obj_id = id; } do_refine_retval_range(regs, fn->ret_type, func_id, &meta); err = check_map_func_compatibility(env, meta.map_ptr, func_id); if (err) return err; if ((func_id == BPF_FUNC_get_stack || func_id == BPF_FUNC_get_task_stack) && !env->prog->has_callchain_buf) { const char *err_str; #ifdef CONFIG_PERF_EVENTS err = get_callchain_buffers(sysctl_perf_event_max_stack); err_str = "cannot get callchain buffer for func %s#%d\n"; #else err = -ENOTSUPP; err_str = "func %s#%d not supported without CONFIG_PERF_EVENTS\n"; #endif if (err) { verbose(env, err_str, func_id_name(func_id), func_id); return err; } env->prog->has_callchain_buf = true; } if (func_id == BPF_FUNC_get_stackid || func_id == BPF_FUNC_get_stack) env->prog->call_get_stack = true; if (func_id == BPF_FUNC_get_func_ip) { if (check_get_func_ip(env)) return -ENOTSUPP; env->prog->call_get_func_ip = true; } if (changes_data) clear_all_pkt_pointers(env); return 0; } /* mark_btf_func_reg_size() is used when the reg size is determined by * the BTF func_proto's return value size and argument. */ static void mark_btf_func_reg_size(struct bpf_verifier_env *env, u32 regno, size_t reg_size) { struct bpf_reg_state *reg = &cur_regs(env)[regno]; if (regno == BPF_REG_0) { /* Function return value */ reg->live |= REG_LIVE_WRITTEN; reg->subreg_def = reg_size == sizeof(u64) ? DEF_NOT_SUBREG : env->insn_idx + 1; } else { /* Function argument */ if (reg_size == sizeof(u64)) { mark_insn_zext(env, reg); mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); } else { mark_reg_read(env, reg, reg->parent, REG_LIVE_READ32); } } } static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx_p) { const struct btf_type *t, *func, *func_proto, *ptr_type; struct bpf_reg_state *regs = cur_regs(env); struct bpf_kfunc_arg_meta meta = { 0 }; const char *func_name, *ptr_type_name; u32 i, nargs, func_id, ptr_type_id; int err, insn_idx = *insn_idx_p; const struct btf_param *args; struct btf *desc_btf; u32 *kfunc_flags; bool acq; /* skip for now, but return error when we find this in fixup_kfunc_call */ if (!insn->imm) return 0; desc_btf = find_kfunc_desc_btf(env, insn->off); if (IS_ERR(desc_btf)) return PTR_ERR(desc_btf); func_id = insn->imm; func = btf_type_by_id(desc_btf, func_id); func_name = btf_name_by_offset(desc_btf, func->name_off); func_proto = btf_type_by_id(desc_btf, func->type); kfunc_flags = btf_kfunc_id_set_contains(desc_btf, resolve_prog_type(env->prog), func_id); if (!kfunc_flags) { verbose(env, "calling kernel function %s is not allowed\n", func_name); return -EACCES; } if (*kfunc_flags & KF_DESTRUCTIVE && !capable(CAP_SYS_BOOT)) { verbose(env, "destructive kfunc calls require CAP_SYS_BOOT capabilities\n"); return -EACCES; } acq = *kfunc_flags & KF_ACQUIRE; meta.flags = *kfunc_flags; /* Check the arguments */ err = btf_check_kfunc_arg_match(env, desc_btf, func_id, regs, &meta); if (err < 0) return err; /* In case of release function, we get register number of refcounted * PTR_TO_BTF_ID back from btf_check_kfunc_arg_match, do the release now */ if (err) { err = release_reference(env, regs[err].ref_obj_id); if (err) { verbose(env, "kfunc %s#%d reference has not been acquired before\n", func_name, func_id); return err; } } for (i = 0; i < CALLER_SAVED_REGS; i++) mark_reg_not_init(env, regs, caller_saved[i]); /* Check return type */ t = btf_type_skip_modifiers(desc_btf, func_proto->type, NULL); if (acq && !btf_type_is_struct_ptr(desc_btf, t)) { verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n"); return -EINVAL; } if (btf_type_is_scalar(t)) { mark_reg_unknown(env, regs, BPF_REG_0); mark_btf_func_reg_size(env, BPF_REG_0, t->size); } else if (btf_type_is_ptr(t)) { ptr_type = btf_type_skip_modifiers(desc_btf, t->type, &ptr_type_id); if (!btf_type_is_struct(ptr_type)) { if (!meta.r0_size) { ptr_type_name = btf_name_by_offset(desc_btf, ptr_type->name_off); verbose(env, "kernel function %s returns pointer type %s %s is not supported\n", func_name, btf_type_str(ptr_type), ptr_type_name); return -EINVAL; } mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_MEM; regs[BPF_REG_0].mem_size = meta.r0_size; if (meta.r0_rdonly) regs[BPF_REG_0].type |= MEM_RDONLY; /* Ensures we don't access the memory after a release_reference() */ if (meta.ref_obj_id) regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id; } else { mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].btf = desc_btf; regs[BPF_REG_0].type = PTR_TO_BTF_ID; regs[BPF_REG_0].btf_id = ptr_type_id; } if (*kfunc_flags & KF_RET_NULL) { regs[BPF_REG_0].type |= PTR_MAYBE_NULL; /* For mark_ptr_or_null_reg, see 93c230e3f5bd6 */ regs[BPF_REG_0].id = ++env->id_gen; } mark_btf_func_reg_size(env, BPF_REG_0, sizeof(void *)); if (acq) { int id = acquire_reference_state(env, insn_idx); if (id < 0) return id; regs[BPF_REG_0].id = id; regs[BPF_REG_0].ref_obj_id = id; } } /* else { add_kfunc_call() ensures it is btf_type_is_void(t) } */ nargs = btf_type_vlen(func_proto); args = (const struct btf_param *)(func_proto + 1); for (i = 0; i < nargs; i++) { u32 regno = i + 1; t = btf_type_skip_modifiers(desc_btf, args[i].type, NULL); if (btf_type_is_ptr(t)) mark_btf_func_reg_size(env, regno, sizeof(void *)); else /* scalar. ensured by btf_check_kfunc_arg_match() */ mark_btf_func_reg_size(env, regno, t->size); } return 0; } static bool signed_add_overflows(s64 a, s64 b) { /* Do the add in u64, where overflow is well-defined */ s64 res = (s64)((u64)a + (u64)b); if (b < 0) return res > a; return res < a; } static bool signed_add32_overflows(s32 a, s32 b) { /* Do the add in u32, where overflow is well-defined */ s32 res = (s32)((u32)a + (u32)b); if (b < 0) return res > a; return res < a; } static bool signed_sub_overflows(s64 a, s64 b) { /* Do the sub in u64, where overflow is well-defined */ s64 res = (s64)((u64)a - (u64)b); if (b < 0) return res < a; return res > a; } static bool signed_sub32_overflows(s32 a, s32 b) { /* Do the sub in u32, where overflow is well-defined */ s32 res = (s32)((u32)a - (u32)b); if (b < 0) return res < a; return res > a; } static bool check_reg_sane_offset(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, enum bpf_reg_type type) { bool known = tnum_is_const(reg->var_off); s64 val = reg->var_off.value; s64 smin = reg->smin_value; if (known && (val >= BPF_MAX_VAR_OFF || val <= -BPF_MAX_VAR_OFF)) { verbose(env, "math between %s pointer and %lld is not allowed\n", reg_type_str(env, type), val); return false; } if (reg->off >= BPF_MAX_VAR_OFF || reg->off <= -BPF_MAX_VAR_OFF) { verbose(env, "%s pointer offset %d is not allowed\n", reg_type_str(env, type), reg->off); return false; } if (smin == S64_MIN) { verbose(env, "math between %s pointer and register with unbounded min value is not allowed\n", reg_type_str(env, type)); return false; } if (smin >= BPF_MAX_VAR_OFF || smin <= -BPF_MAX_VAR_OFF) { verbose(env, "value %lld makes %s pointer be out of bounds\n", smin, reg_type_str(env, type)); return false; } return true; } enum { REASON_BOUNDS = -1, REASON_TYPE = -2, REASON_PATHS = -3, REASON_LIMIT = -4, REASON_STACK = -5, }; static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg, u32 *alu_limit, bool mask_to_left) { u32 max = 0, ptr_limit = 0; switch (ptr_reg->type) { case PTR_TO_STACK: /* Offset 0 is out-of-bounds, but acceptable start for the * left direction, see BPF_REG_FP. Also, unknown scalar * offset where we would need to deal with min/max bounds is * currently prohibited for unprivileged. */ max = MAX_BPF_STACK + mask_to_left; ptr_limit = -(ptr_reg->var_off.value + ptr_reg->off); break; case PTR_TO_MAP_VALUE: max = ptr_reg->map_ptr->value_size; ptr_limit = (mask_to_left ? ptr_reg->smin_value : ptr_reg->umax_value) + ptr_reg->off; break; default: return REASON_TYPE; } if (ptr_limit >= max) return REASON_LIMIT; *alu_limit = ptr_limit; return 0; } static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env, const struct bpf_insn *insn) { return env->bypass_spec_v1 || BPF_SRC(insn->code) == BPF_K; } static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux, u32 alu_state, u32 alu_limit) { /* If we arrived here from different branches with different * state or limits to sanitize, then this won't work. */ if (aux->alu_state && (aux->alu_state != alu_state || aux->alu_limit != alu_limit)) return REASON_PATHS; /* Corresponding fixup done in do_misc_fixups(). */ aux->alu_state = alu_state; aux->alu_limit = alu_limit; return 0; } static int sanitize_val_alu(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_insn_aux_data *aux = cur_aux(env); if (can_skip_alu_sanitation(env, insn)) return 0; return update_alu_sanitation_state(aux, BPF_ALU_NON_POINTER, 0); } static bool sanitize_needed(u8 opcode) { return opcode == BPF_ADD || opcode == BPF_SUB; } struct bpf_sanitize_info { struct bpf_insn_aux_data aux; bool mask_to_left; }; static struct bpf_verifier_state * sanitize_speculative_path(struct bpf_verifier_env *env, const struct bpf_insn *insn, u32 next_idx, u32 curr_idx) { struct bpf_verifier_state *branch; struct bpf_reg_state *regs; branch = push_stack(env, next_idx, curr_idx, true); if (branch && insn) { regs = branch->frame[branch->curframe]->regs; if (BPF_SRC(insn->code) == BPF_K) { mark_reg_unknown(env, regs, insn->dst_reg); } else if (BPF_SRC(insn->code) == BPF_X) { mark_reg_unknown(env, regs, insn->dst_reg); mark_reg_unknown(env, regs, insn->src_reg); } } return branch; } static int sanitize_ptr_alu(struct bpf_verifier_env *env, struct bpf_insn *insn, const struct bpf_reg_state *ptr_reg, const struct bpf_reg_state *off_reg, struct bpf_reg_state *dst_reg, struct bpf_sanitize_info *info, const bool commit_window) { struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : &info->aux; struct bpf_verifier_state *vstate = env->cur_state; bool off_is_imm = tnum_is_const(off_reg->var_off); bool off_is_neg = off_reg->smin_value < 0; bool ptr_is_dst_reg = ptr_reg == dst_reg; u8 opcode = BPF_OP(insn->code); u32 alu_state, alu_limit; struct bpf_reg_state tmp; bool ret; int err; if (can_skip_alu_sanitation(env, insn)) return 0; /* We already marked aux for masking from non-speculative * paths, thus we got here in the first place. We only care * to explore bad access from here. */ if (vstate->speculative) goto do_sim; if (!commit_window) { if (!tnum_is_const(off_reg->var_off) && (off_reg->smin_value < 0) != (off_reg->smax_value < 0)) return REASON_BOUNDS; info->mask_to_left = (opcode == BPF_ADD && off_is_neg) || (opcode == BPF_SUB && !off_is_neg); } err = retrieve_ptr_limit(ptr_reg, &alu_limit, info->mask_to_left); if (err < 0) return err; if (commit_window) { /* In commit phase we narrow the masking window based on * the observed pointer move after the simulated operation. */ alu_state = info->aux.alu_state; alu_limit = abs(info->aux.alu_limit - alu_limit); } else { alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0; alu_state |= off_is_imm ? BPF_ALU_IMMEDIATE : 0; alu_state |= ptr_is_dst_reg ? BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST; /* Limit pruning on unknown scalars to enable deep search for * potential masking differences from other program paths. */ if (!off_is_imm) env->explore_alu_limits = true; } err = update_alu_sanitation_state(aux, alu_state, alu_limit); if (err < 0) return err; do_sim: /* If we're in commit phase, we're done here given we already * pushed the truncated dst_reg into the speculative verification * stack. * * Also, when register is a known constant, we rewrite register-based * operation to immediate-based, and thus do not need masking (and as * a consequence, do not need to simulate the zero-truncation either). */ if (commit_window || off_is_imm) return 0; /* Simulate and find potential out-of-bounds access under * speculative execution from truncation as a result of * masking when off was not within expected range. If off * sits in dst, then we temporarily need to move ptr there * to simulate dst (== 0) +/-= ptr. Needed, for example, * for cases where we use K-based arithmetic in one direction * and truncated reg-based in the other in order to explore * bad access. */ if (!ptr_is_dst_reg) { tmp = *dst_reg; copy_register_state(dst_reg, ptr_reg); } ret = sanitize_speculative_path(env, NULL, env->insn_idx + 1, env->insn_idx); if (!ptr_is_dst_reg && ret) *dst_reg = tmp; return !ret ? REASON_STACK : 0; } static void sanitize_mark_insn_seen(struct bpf_verifier_env *env) { struct bpf_verifier_state *vstate = env->cur_state; /* If we simulate paths under speculation, we don't update the * insn as 'seen' such that when we verify unreachable paths in * the non-speculative domain, sanitize_dead_code() can still * rewrite/sanitize them. */ if (!vstate->speculative) env->insn_aux_data[env->insn_idx].seen = env->pass_cnt; } static int sanitize_err(struct bpf_verifier_env *env, const struct bpf_insn *insn, int reason, const struct bpf_reg_state *off_reg, const struct bpf_reg_state *dst_reg) { static const char *err = "pointer arithmetic with it prohibited for !root"; const char *op = BPF_OP(insn->code) == BPF_ADD ? "add" : "sub"; u32 dst = insn->dst_reg, src = insn->src_reg; switch (reason) { case REASON_BOUNDS: verbose(env, "R%d has unknown scalar with mixed signed bounds, %s\n", off_reg == dst_reg ? dst : src, err); break; case REASON_TYPE: verbose(env, "R%d has pointer with unsupported alu operation, %s\n", off_reg == dst_reg ? src : dst, err); break; case REASON_PATHS: verbose(env, "R%d tried to %s from different maps, paths or scalars, %s\n", dst, op, err); break; case REASON_LIMIT: verbose(env, "R%d tried to %s beyond pointer bounds, %s\n", dst, op, err); break; case REASON_STACK: verbose(env, "R%d could not be pushed for speculative verification, %s\n", dst, err); break; default: verbose(env, "verifier internal error: unknown reason (%d)\n", reason); break; } return -EACCES; } /* check that stack access falls within stack limits and that 'reg' doesn't * have a variable offset. * * Variable offset is prohibited for unprivileged mode for simplicity since it * requires corresponding support in Spectre masking for stack ALU. See also * retrieve_ptr_limit(). * * * 'off' includes 'reg->off'. */ static int check_stack_access_for_ptr_arithmetic( struct bpf_verifier_env *env, int regno, const struct bpf_reg_state *reg, int off) { if (!tnum_is_const(reg->var_off)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, "R%d variable stack access prohibited for !root, var_off=%s off=%d\n", regno, tn_buf, off); return -EACCES; } if (off >= 0 || off < -MAX_BPF_STACK) { verbose(env, "R%d stack pointer arithmetic goes out of range, " "prohibited for !root; off=%d\n", regno, off); return -EACCES; } return 0; } static int sanitize_check_bounds(struct bpf_verifier_env *env, const struct bpf_insn *insn, const struct bpf_reg_state *dst_reg) { u32 dst = insn->dst_reg; /* For unprivileged we require that resulting offset must be in bounds * in order to be able to sanitize access later on. */ if (env->bypass_spec_v1) return 0; switch (dst_reg->type) { case PTR_TO_STACK: if (check_stack_access_for_ptr_arithmetic(env, dst, dst_reg, dst_reg->off + dst_reg->var_off.value)) return -EACCES; break; case PTR_TO_MAP_VALUE: if (check_map_access(env, dst, dst_reg->off, 1, false, ACCESS_HELPER)) { verbose(env, "R%d pointer arithmetic of map value goes out of range, " "prohibited for !root\n", dst); return -EACCES; } break; default: break; } return 0; } /* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off. * Caller should also handle BPF_MOV case separately. * If we return -EACCES, caller may want to try again treating pointer as a * scalar. So we only emit a diagnostic if !env->allow_ptr_leaks. */ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn, const struct bpf_reg_state *ptr_reg, const struct bpf_reg_state *off_reg) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *regs = state->regs, *dst_reg; bool known = tnum_is_const(off_reg->var_off); s64 smin_val = off_reg->smin_value, smax_val = off_reg->smax_value, smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value; u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value, umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value; struct bpf_sanitize_info info = {}; u8 opcode = BPF_OP(insn->code); u32 dst = insn->dst_reg; int ret; dst_reg = ®s[dst]; if ((known && (smin_val != smax_val || umin_val != umax_val)) || smin_val > smax_val || umin_val > umax_val) { /* Taint dst register if offset had invalid bounds derived from * e.g. dead branches. */ __mark_reg_unknown(env, dst_reg); return 0; } if (BPF_CLASS(insn->code) != BPF_ALU64) { /* 32-bit ALU ops on pointers produce (meaningless) scalars */ if (opcode == BPF_SUB && env->allow_ptr_leaks) { __mark_reg_unknown(env, dst_reg); return 0; } verbose(env, "R%d 32-bit pointer arithmetic prohibited\n", dst); return -EACCES; } if (ptr_reg->type & PTR_MAYBE_NULL) { verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n", dst, reg_type_str(env, ptr_reg->type)); return -EACCES; } switch (base_type(ptr_reg->type)) { case PTR_TO_FLOW_KEYS: if (known) break; fallthrough; case CONST_PTR_TO_MAP: /* smin_val represents the known value */ if (known && smin_val == 0 && opcode == BPF_ADD) break; fallthrough; case PTR_TO_PACKET_END: case PTR_TO_SOCKET: case PTR_TO_SOCK_COMMON: case PTR_TO_TCP_SOCK: case PTR_TO_XDP_SOCK: verbose(env, "R%d pointer arithmetic on %s prohibited\n", dst, reg_type_str(env, ptr_reg->type)); return -EACCES; default: break; } /* In case of 'scalar += pointer', dst_reg inherits pointer type and id. * The id may be overwritten later if we create a new variable offset. */ dst_reg->type = ptr_reg->type; dst_reg->id = ptr_reg->id; if (!check_reg_sane_offset(env, off_reg, ptr_reg->type) || !check_reg_sane_offset(env, ptr_reg, ptr_reg->type)) return -EINVAL; /* pointer types do not carry 32-bit bounds at the moment. */ __mark_reg32_unbounded(dst_reg); if (sanitize_needed(opcode)) { ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg, &info, false); if (ret < 0) return sanitize_err(env, insn, ret, off_reg, dst_reg); } switch (opcode) { case BPF_ADD: /* We can take a fixed offset as long as it doesn't overflow * the s32 'off' field */ if (known && (ptr_reg->off + smin_val == (s64)(s32)(ptr_reg->off + smin_val))) { /* pointer += K. Accumulate it into fixed offset */ dst_reg->smin_value = smin_ptr; dst_reg->smax_value = smax_ptr; dst_reg->umin_value = umin_ptr; dst_reg->umax_value = umax_ptr; dst_reg->var_off = ptr_reg->var_off; dst_reg->off = ptr_reg->off + smin_val; dst_reg->raw = ptr_reg->raw; break; } /* A new variable offset is created. Note that off_reg->off * == 0, since it's a scalar. * dst_reg gets the pointer type and since some positive * integer value was added to the pointer, give it a new 'id' * if it's a PTR_TO_PACKET. * this creates a new 'base' pointer, off_reg (variable) gets * added into the variable offset, and we copy the fixed offset * from ptr_reg. */ if (signed_add_overflows(smin_ptr, smin_val) || signed_add_overflows(smax_ptr, smax_val)) { dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } else { dst_reg->smin_value = smin_ptr + smin_val; dst_reg->smax_value = smax_ptr + smax_val; } if (umin_ptr + umin_val < umin_ptr || umax_ptr + umax_val < umax_ptr) { dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; } else { dst_reg->umin_value = umin_ptr + umin_val; dst_reg->umax_value = umax_ptr + umax_val; } dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; dst_reg->raw = ptr_reg->raw; if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ memset(&dst_reg->raw, 0, sizeof(dst_reg->raw)); } break; case BPF_SUB: if (dst_reg == off_reg) { /* scalar -= pointer. Creates an unknown scalar */ verbose(env, "R%d tried to subtract pointer from scalar\n", dst); return -EACCES; } /* We don't allow subtraction from FP, because (according to * test_verifier.c test "invalid fp arithmetic", JITs might not * be able to deal with it. */ if (ptr_reg->type == PTR_TO_STACK) { verbose(env, "R%d subtraction from stack pointer prohibited\n", dst); return -EACCES; } if (known && (ptr_reg->off - smin_val == (s64)(s32)(ptr_reg->off - smin_val))) { /* pointer -= K. Subtract it from fixed offset */ dst_reg->smin_value = smin_ptr; dst_reg->smax_value = smax_ptr; dst_reg->umin_value = umin_ptr; dst_reg->umax_value = umax_ptr; dst_reg->var_off = ptr_reg->var_off; dst_reg->id = ptr_reg->id; dst_reg->off = ptr_reg->off - smin_val; dst_reg->raw = ptr_reg->raw; break; } /* A new variable offset is created. If the subtrahend is known * nonnegative, then any reg->range we had before is still good. */ if (signed_sub_overflows(smin_ptr, smax_val) || signed_sub_overflows(smax_ptr, smin_val)) { /* Overflow possible, we know nothing */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } else { dst_reg->smin_value = smin_ptr - smax_val; dst_reg->smax_value = smax_ptr - smin_val; } if (umin_ptr < umax_val) { /* Overflow possible, we know nothing */ dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; } else { /* Cannot overflow (as long as bounds are consistent) */ dst_reg->umin_value = umin_ptr - umax_val; dst_reg->umax_value = umax_ptr - umin_val; } dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; dst_reg->raw = ptr_reg->raw; if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ if (smin_val < 0) memset(&dst_reg->raw, 0, sizeof(dst_reg->raw)); } break; case BPF_AND: case BPF_OR: case BPF_XOR: /* bitwise ops on pointers are troublesome, prohibit. */ verbose(env, "R%d bitwise operator %s on pointer prohibited\n", dst, bpf_alu_string[opcode >> 4]); return -EACCES; default: /* other operators (e.g. MUL,LSH) produce non-pointer results */ verbose(env, "R%d pointer arithmetic with %s operator prohibited\n", dst, bpf_alu_string[opcode >> 4]); return -EACCES; } if (!check_reg_sane_offset(env, dst_reg, ptr_reg->type)) return -EINVAL; reg_bounds_sync(dst_reg); if (sanitize_check_bounds(env, insn, dst_reg) < 0) return -EACCES; if (sanitize_needed(opcode)) { ret = sanitize_ptr_alu(env, insn, dst_reg, off_reg, dst_reg, &info, true); if (ret < 0) return sanitize_err(env, insn, ret, off_reg, dst_reg); } return 0; } static void scalar32_min_max_add(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s32 smin_val = src_reg->s32_min_value; s32 smax_val = src_reg->s32_max_value; u32 umin_val = src_reg->u32_min_value; u32 umax_val = src_reg->u32_max_value; if (signed_add32_overflows(dst_reg->s32_min_value, smin_val) || signed_add32_overflows(dst_reg->s32_max_value, smax_val)) { dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; } else { dst_reg->s32_min_value += smin_val; dst_reg->s32_max_value += smax_val; } if (dst_reg->u32_min_value + umin_val < umin_val || dst_reg->u32_max_value + umax_val < umax_val) { dst_reg->u32_min_value = 0; dst_reg->u32_max_value = U32_MAX; } else { dst_reg->u32_min_value += umin_val; dst_reg->u32_max_value += umax_val; } } static void scalar_min_max_add(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s64 smin_val = src_reg->smin_value; s64 smax_val = src_reg->smax_value; u64 umin_val = src_reg->umin_value; u64 umax_val = src_reg->umax_value; if (signed_add_overflows(dst_reg->smin_value, smin_val) || signed_add_overflows(dst_reg->smax_value, smax_val)) { dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } else { dst_reg->smin_value += smin_val; dst_reg->smax_value += smax_val; } if (dst_reg->umin_value + umin_val < umin_val || dst_reg->umax_value + umax_val < umax_val) { dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; } else { dst_reg->umin_value += umin_val; dst_reg->umax_value += umax_val; } } static void scalar32_min_max_sub(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s32 smin_val = src_reg->s32_min_value; s32 smax_val = src_reg->s32_max_value; u32 umin_val = src_reg->u32_min_value; u32 umax_val = src_reg->u32_max_value; if (signed_sub32_overflows(dst_reg->s32_min_value, smax_val) || signed_sub32_overflows(dst_reg->s32_max_value, smin_val)) { /* Overflow possible, we know nothing */ dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; } else { dst_reg->s32_min_value -= smax_val; dst_reg->s32_max_value -= smin_val; } if (dst_reg->u32_min_value < umax_val) { /* Overflow possible, we know nothing */ dst_reg->u32_min_value = 0; dst_reg->u32_max_value = U32_MAX; } else { /* Cannot overflow (as long as bounds are consistent) */ dst_reg->u32_min_value -= umax_val; dst_reg->u32_max_value -= umin_val; } } static void scalar_min_max_sub(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s64 smin_val = src_reg->smin_value; s64 smax_val = src_reg->smax_value; u64 umin_val = src_reg->umin_value; u64 umax_val = src_reg->umax_value; if (signed_sub_overflows(dst_reg->smin_value, smax_val) || signed_sub_overflows(dst_reg->smax_value, smin_val)) { /* Overflow possible, we know nothing */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } else { dst_reg->smin_value -= smax_val; dst_reg->smax_value -= smin_val; } if (dst_reg->umin_value < umax_val) { /* Overflow possible, we know nothing */ dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; } else { /* Cannot overflow (as long as bounds are consistent) */ dst_reg->umin_value -= umax_val; dst_reg->umax_value -= umin_val; } } static void scalar32_min_max_mul(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s32 smin_val = src_reg->s32_min_value; u32 umin_val = src_reg->u32_min_value; u32 umax_val = src_reg->u32_max_value; if (smin_val < 0 || dst_reg->s32_min_value < 0) { /* Ain't nobody got time to multiply that sign */ __mark_reg32_unbounded(dst_reg); return; } /* Both values are positive, so we can work with unsigned and * copy the result to signed (unless it exceeds S32_MAX). */ if (umax_val > U16_MAX || dst_reg->u32_max_value > U16_MAX) { /* Potential overflow, we know nothing */ __mark_reg32_unbounded(dst_reg); return; } dst_reg->u32_min_value *= umin_val; dst_reg->u32_max_value *= umax_val; if (dst_reg->u32_max_value > S32_MAX) { /* Overflow possible, we know nothing */ dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; } else { dst_reg->s32_min_value = dst_reg->u32_min_value; dst_reg->s32_max_value = dst_reg->u32_max_value; } } static void scalar_min_max_mul(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { s64 smin_val = src_reg->smin_value; u64 umin_val = src_reg->umin_value; u64 umax_val = src_reg->umax_value; if (smin_val < 0 || dst_reg->smin_value < 0) { /* Ain't nobody got time to multiply that sign */ __mark_reg64_unbounded(dst_reg); return; } /* Both values are positive, so we can work with unsigned and * copy the result to signed (unless it exceeds S64_MAX). */ if (umax_val > U32_MAX || dst_reg->umax_value > U32_MAX) { /* Potential overflow, we know nothing */ __mark_reg64_unbounded(dst_reg); return; } dst_reg->umin_value *= umin_val; dst_reg->umax_value *= umax_val; if (dst_reg->umax_value > S64_MAX) { /* Overflow possible, we know nothing */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } else { dst_reg->smin_value = dst_reg->umin_value; dst_reg->smax_value = dst_reg->umax_value; } } static void scalar32_min_max_and(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_subreg_is_const(src_reg->var_off); bool dst_known = tnum_subreg_is_const(dst_reg->var_off); struct tnum var32_off = tnum_subreg(dst_reg->var_off); s32 smin_val = src_reg->s32_min_value; u32 umax_val = src_reg->u32_max_value; if (src_known && dst_known) { __mark_reg32_known(dst_reg, var32_off.value); return; } /* We get our minimum from the var_off, since that's inherently * bitwise. Our maximum is the minimum of the operands' maxima. */ dst_reg->u32_min_value = var32_off.value; dst_reg->u32_max_value = min(dst_reg->u32_max_value, umax_val); if (dst_reg->s32_min_value < 0 || smin_val < 0) { /* Lose signed bounds when ANDing negative numbers, * ain't nobody got time for that. */ dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; } else { /* ANDing two positives gives a positive, so safe to * cast result into s64. */ dst_reg->s32_min_value = dst_reg->u32_min_value; dst_reg->s32_max_value = dst_reg->u32_max_value; } } static void scalar_min_max_and(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_is_const(src_reg->var_off); bool dst_known = tnum_is_const(dst_reg->var_off); s64 smin_val = src_reg->smin_value; u64 umax_val = src_reg->umax_value; if (src_known && dst_known) { __mark_reg_known(dst_reg, dst_reg->var_off.value); return; } /* We get our minimum from the var_off, since that's inherently * bitwise. Our maximum is the minimum of the operands' maxima. */ dst_reg->umin_value = dst_reg->var_off.value; dst_reg->umax_value = min(dst_reg->umax_value, umax_val); if (dst_reg->smin_value < 0 || smin_val < 0) { /* Lose signed bounds when ANDing negative numbers, * ain't nobody got time for that. */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } else { /* ANDing two positives gives a positive, so safe to * cast result into s64. */ dst_reg->smin_value = dst_reg->umin_value; dst_reg->smax_value = dst_reg->umax_value; } /* We may learn something more from the var_off */ __update_reg_bounds(dst_reg); } static void scalar32_min_max_or(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_subreg_is_const(src_reg->var_off); bool dst_known = tnum_subreg_is_const(dst_reg->var_off); struct tnum var32_off = tnum_subreg(dst_reg->var_off); s32 smin_val = src_reg->s32_min_value; u32 umin_val = src_reg->u32_min_value; if (src_known && dst_known) { __mark_reg32_known(dst_reg, var32_off.value); return; } /* We get our maximum from the var_off, and our minimum is the * maximum of the operands' minima */ dst_reg->u32_min_value = max(dst_reg->u32_min_value, umin_val); dst_reg->u32_max_value = var32_off.value | var32_off.mask; if (dst_reg->s32_min_value < 0 || smin_val < 0) { /* Lose signed bounds when ORing negative numbers, * ain't nobody got time for that. */ dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; } else { /* ORing two positives gives a positive, so safe to * cast result into s64. */ dst_reg->s32_min_value = dst_reg->u32_min_value; dst_reg->s32_max_value = dst_reg->u32_max_value; } } static void scalar_min_max_or(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_is_const(src_reg->var_off); bool dst_known = tnum_is_const(dst_reg->var_off); s64 smin_val = src_reg->smin_value; u64 umin_val = src_reg->umin_value; if (src_known && dst_known) { __mark_reg_known(dst_reg, dst_reg->var_off.value); return; } /* We get our maximum from the var_off, and our minimum is the * maximum of the operands' minima */ dst_reg->umin_value = max(dst_reg->umin_value, umin_val); dst_reg->umax_value = dst_reg->var_off.value | dst_reg->var_off.mask; if (dst_reg->smin_value < 0 || smin_val < 0) { /* Lose signed bounds when ORing negative numbers, * ain't nobody got time for that. */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } else { /* ORing two positives gives a positive, so safe to * cast result into s64. */ dst_reg->smin_value = dst_reg->umin_value; dst_reg->smax_value = dst_reg->umax_value; } /* We may learn something more from the var_off */ __update_reg_bounds(dst_reg); } static void scalar32_min_max_xor(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_subreg_is_const(src_reg->var_off); bool dst_known = tnum_subreg_is_const(dst_reg->var_off); struct tnum var32_off = tnum_subreg(dst_reg->var_off); s32 smin_val = src_reg->s32_min_value; if (src_known && dst_known) { __mark_reg32_known(dst_reg, var32_off.value); return; } /* We get both minimum and maximum from the var32_off. */ dst_reg->u32_min_value = var32_off.value; dst_reg->u32_max_value = var32_off.value | var32_off.mask; if (dst_reg->s32_min_value >= 0 && smin_val >= 0) { /* XORing two positive sign numbers gives a positive, * so safe to cast u32 result into s32. */ dst_reg->s32_min_value = dst_reg->u32_min_value; dst_reg->s32_max_value = dst_reg->u32_max_value; } else { dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; } } static void scalar_min_max_xor(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { bool src_known = tnum_is_const(src_reg->var_off); bool dst_known = tnum_is_const(dst_reg->var_off); s64 smin_val = src_reg->smin_value; if (src_known && dst_known) { /* dst_reg->var_off.value has been updated earlier */ __mark_reg_known(dst_reg, dst_reg->var_off.value); return; } /* We get both minimum and maximum from the var_off. */ dst_reg->umin_value = dst_reg->var_off.value; dst_reg->umax_value = dst_reg->var_off.value | dst_reg->var_off.mask; if (dst_reg->smin_value >= 0 && smin_val >= 0) { /* XORing two positive sign numbers gives a positive, * so safe to cast u64 result into s64. */ dst_reg->smin_value = dst_reg->umin_value; dst_reg->smax_value = dst_reg->umax_value; } else { dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; } __update_reg_bounds(dst_reg); } static void __scalar32_min_max_lsh(struct bpf_reg_state *dst_reg, u64 umin_val, u64 umax_val) { /* We lose all sign bit information (except what we can pick * up from var_off) */ dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; /* If we might shift our top bit out, then we know nothing */ if (umax_val > 31 || dst_reg->u32_max_value > 1ULL << (31 - umax_val)) { dst_reg->u32_min_value = 0; dst_reg->u32_max_value = U32_MAX; } else { dst_reg->u32_min_value <<= umin_val; dst_reg->u32_max_value <<= umax_val; } } static void scalar32_min_max_lsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u32 umax_val = src_reg->u32_max_value; u32 umin_val = src_reg->u32_min_value; /* u32 alu operation will zext upper bits */ struct tnum subreg = tnum_subreg(dst_reg->var_off); __scalar32_min_max_lsh(dst_reg, umin_val, umax_val); dst_reg->var_off = tnum_subreg(tnum_lshift(subreg, umin_val)); /* Not required but being careful mark reg64 bounds as unknown so * that we are forced to pick them up from tnum and zext later and * if some path skips this step we are still safe. */ __mark_reg64_unbounded(dst_reg); __update_reg32_bounds(dst_reg); } static void __scalar64_min_max_lsh(struct bpf_reg_state *dst_reg, u64 umin_val, u64 umax_val) { /* Special case <<32 because it is a common compiler pattern to sign * extend subreg by doing <<32 s>>32. In this case if 32bit bounds are * positive we know this shift will also be positive so we can track * bounds correctly. Otherwise we lose all sign bit information except * what we can pick up from var_off. Perhaps we can generalize this * later to shifts of any length. */ if (umin_val == 32 && umax_val == 32 && dst_reg->s32_max_value >= 0) dst_reg->smax_value = (s64)dst_reg->s32_max_value << 32; else dst_reg->smax_value = S64_MAX; if (umin_val == 32 && umax_val == 32 && dst_reg->s32_min_value >= 0) dst_reg->smin_value = (s64)dst_reg->s32_min_value << 32; else dst_reg->smin_value = S64_MIN; /* If we might shift our top bit out, then we know nothing */ if (dst_reg->umax_value > 1ULL << (63 - umax_val)) { dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; } else { dst_reg->umin_value <<= umin_val; dst_reg->umax_value <<= umax_val; } } static void scalar_min_max_lsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u64 umax_val = src_reg->umax_value; u64 umin_val = src_reg->umin_value; /* scalar64 calc uses 32bit unshifted bounds so must be called first */ __scalar64_min_max_lsh(dst_reg, umin_val, umax_val); __scalar32_min_max_lsh(dst_reg, umin_val, umax_val); dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val); /* We may learn something more from the var_off */ __update_reg_bounds(dst_reg); } static void scalar32_min_max_rsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { struct tnum subreg = tnum_subreg(dst_reg->var_off); u32 umax_val = src_reg->u32_max_value; u32 umin_val = src_reg->u32_min_value; /* BPF_RSH is an unsigned shift. If the value in dst_reg might * be negative, then either: * 1) src_reg might be zero, so the sign bit of the result is * unknown, so we lose our signed bounds * 2) it's known negative, thus the unsigned bounds capture the * signed bounds * 3) the signed bounds cross zero, so they tell us nothing * about the result * If the value in dst_reg is known nonnegative, then again the * unsigned bounds capture the signed bounds. * Thus, in all cases it suffices to blow away our signed bounds * and rely on inferring new ones from the unsigned bounds and * var_off of the result. */ dst_reg->s32_min_value = S32_MIN; dst_reg->s32_max_value = S32_MAX; dst_reg->var_off = tnum_rshift(subreg, umin_val); dst_reg->u32_min_value >>= umax_val; dst_reg->u32_max_value >>= umin_val; __mark_reg64_unbounded(dst_reg); __update_reg32_bounds(dst_reg); } static void scalar_min_max_rsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u64 umax_val = src_reg->umax_value; u64 umin_val = src_reg->umin_value; /* BPF_RSH is an unsigned shift. If the value in dst_reg might * be negative, then either: * 1) src_reg might be zero, so the sign bit of the result is * unknown, so we lose our signed bounds * 2) it's known negative, thus the unsigned bounds capture the * signed bounds * 3) the signed bounds cross zero, so they tell us nothing * about the result * If the value in dst_reg is known nonnegative, then again the * unsigned bounds capture the signed bounds. * Thus, in all cases it suffices to blow away our signed bounds * and rely on inferring new ones from the unsigned bounds and * var_off of the result. */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; dst_reg->var_off = tnum_rshift(dst_reg->var_off, umin_val); dst_reg->umin_value >>= umax_val; dst_reg->umax_value >>= umin_val; /* Its not easy to operate on alu32 bounds here because it depends * on bits being shifted in. Take easy way out and mark unbounded * so we can recalculate later from tnum. */ __mark_reg32_unbounded(dst_reg); __update_reg_bounds(dst_reg); } static void scalar32_min_max_arsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u64 umin_val = src_reg->u32_min_value; /* Upon reaching here, src_known is true and * umax_val is equal to umin_val. */ dst_reg->s32_min_value = (u32)(((s32)dst_reg->s32_min_value) >> umin_val); dst_reg->s32_max_value = (u32)(((s32)dst_reg->s32_max_value) >> umin_val); dst_reg->var_off = tnum_arshift(tnum_subreg(dst_reg->var_off), umin_val, 32); /* blow away the dst_reg umin_value/umax_value and rely on * dst_reg var_off to refine the result. */ dst_reg->u32_min_value = 0; dst_reg->u32_max_value = U32_MAX; __mark_reg64_unbounded(dst_reg); __update_reg32_bounds(dst_reg); } static void scalar_min_max_arsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg) { u64 umin_val = src_reg->umin_value; /* Upon reaching here, src_known is true and umax_val is equal * to umin_val. */ dst_reg->smin_value >>= umin_val; dst_reg->smax_value >>= umin_val; dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val, 64); /* blow away the dst_reg umin_value/umax_value and rely on * dst_reg var_off to refine the result. */ dst_reg->umin_value = 0; dst_reg->umax_value = U64_MAX; /* Its not easy to operate on alu32 bounds here because it depends * on bits being shifted in from upper 32-bits. Take easy way out * and mark unbounded so we can recalculate later from tnum. */ __mark_reg32_unbounded(dst_reg); __update_reg_bounds(dst_reg); } /* WARNING: This function does calculations on 64-bit values, but the actual * execution may occur on 32-bit values. Therefore, things like bitshifts * need extra checks in the 32-bit case. */ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn, struct bpf_reg_state *dst_reg, struct bpf_reg_state src_reg) { struct bpf_reg_state *regs = cur_regs(env); u8 opcode = BPF_OP(insn->code); bool src_known; s64 smin_val, smax_val; u64 umin_val, umax_val; s32 s32_min_val, s32_max_val; u32 u32_min_val, u32_max_val; u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32; bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64); int ret; smin_val = src_reg.smin_value; smax_val = src_reg.smax_value; umin_val = src_reg.umin_value; umax_val = src_reg.umax_value; s32_min_val = src_reg.s32_min_value; s32_max_val = src_reg.s32_max_value; u32_min_val = src_reg.u32_min_value; u32_max_val = src_reg.u32_max_value; if (alu32) { src_known = tnum_subreg_is_const(src_reg.var_off); if ((src_known && (s32_min_val != s32_max_val || u32_min_val != u32_max_val)) || s32_min_val > s32_max_val || u32_min_val > u32_max_val) { /* Taint dst register if offset had invalid bounds * derived from e.g. dead branches. */ __mark_reg_unknown(env, dst_reg); return 0; } } else { src_known = tnum_is_const(src_reg.var_off); if ((src_known && (smin_val != smax_val || umin_val != umax_val)) || smin_val > smax_val || umin_val > umax_val) { /* Taint dst register if offset had invalid bounds * derived from e.g. dead branches. */ __mark_reg_unknown(env, dst_reg); return 0; } } if (!src_known && opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) { __mark_reg_unknown(env, dst_reg); return 0; } if (sanitize_needed(opcode)) { ret = sanitize_val_alu(env, insn); if (ret < 0) return sanitize_err(env, insn, ret, NULL, NULL); } /* Calculate sign/unsigned bounds and tnum for alu32 and alu64 bit ops. * There are two classes of instructions: The first class we track both * alu32 and alu64 sign/unsigned bounds independently this provides the * greatest amount of precision when alu operations are mixed with jmp32 * operations. These operations are BPF_ADD, BPF_SUB, BPF_MUL, BPF_ADD, * and BPF_OR. This is possible because these ops have fairly easy to * understand and calculate behavior in both 32-bit and 64-bit alu ops. * See alu32 verifier tests for examples. The second class of * operations, BPF_LSH, BPF_RSH, and BPF_ARSH, however are not so easy * with regards to tracking sign/unsigned bounds because the bits may * cross subreg boundaries in the alu64 case. When this happens we mark * the reg unbounded in the subreg bound space and use the resulting * tnum to calculate an approximation of the sign/unsigned bounds. */ switch (opcode) { case BPF_ADD: scalar32_min_max_add(dst_reg, &src_reg); scalar_min_max_add(dst_reg, &src_reg); dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off); break; case BPF_SUB: scalar32_min_max_sub(dst_reg, &src_reg); scalar_min_max_sub(dst_reg, &src_reg); dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off); break; case BPF_MUL: dst_reg->var_off = tnum_mul(dst_reg->var_off, src_reg.var_off); scalar32_min_max_mul(dst_reg, &src_reg); scalar_min_max_mul(dst_reg, &src_reg); break; case BPF_AND: dst_reg->var_off = tnum_and(dst_reg->var_off, src_reg.var_off); scalar32_min_max_and(dst_reg, &src_reg); scalar_min_max_and(dst_reg, &src_reg); break; case BPF_OR: dst_reg->var_off = tnum_or(dst_reg->var_off, src_reg.var_off); scalar32_min_max_or(dst_reg, &src_reg); scalar_min_max_or(dst_reg, &src_reg); break; case BPF_XOR: dst_reg->var_off = tnum_xor(dst_reg->var_off, src_reg.var_off); scalar32_min_max_xor(dst_reg, &src_reg); scalar_min_max_xor(dst_reg, &src_reg); break; case BPF_LSH: if (umax_val >= insn_bitness) { /* Shifts greater than 31 or 63 are undefined. * This includes shifts by a negative number. */ mark_reg_unknown(env, regs, insn->dst_reg); break; } if (alu32) scalar32_min_max_lsh(dst_reg, &src_reg); else scalar_min_max_lsh(dst_reg, &src_reg); break; case BPF_RSH: if (umax_val >= insn_bitness) { /* Shifts greater than 31 or 63 are undefined. * This includes shifts by a negative number. */ mark_reg_unknown(env, regs, insn->dst_reg); break; } if (alu32) scalar32_min_max_rsh(dst_reg, &src_reg); else scalar_min_max_rsh(dst_reg, &src_reg); break; case BPF_ARSH: if (umax_val >= insn_bitness) { /* Shifts greater than 31 or 63 are undefined. * This includes shifts by a negative number. */ mark_reg_unknown(env, regs, insn->dst_reg); break; } if (alu32) scalar32_min_max_arsh(dst_reg, &src_reg); else scalar_min_max_arsh(dst_reg, &src_reg); break; default: mark_reg_unknown(env, regs, insn->dst_reg); break; } /* ALU32 ops are zero extended into 64bit register */ if (alu32) zext_32_to_64(dst_reg); reg_bounds_sync(dst_reg); return 0; } /* Handles ALU ops other than BPF_END, BPF_NEG and BPF_MOV: computes new min/max * and var_off. */ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_verifier_state *vstate = env->cur_state; struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *regs = state->regs, *dst_reg, *src_reg; struct bpf_reg_state *ptr_reg = NULL, off_reg = {0}; u8 opcode = BPF_OP(insn->code); int err; dst_reg = ®s[insn->dst_reg]; src_reg = NULL; if (dst_reg->type != SCALAR_VALUE) ptr_reg = dst_reg; else /* Make sure ID is cleared otherwise dst_reg min/max could be * incorrectly propagated into other registers by find_equal_scalars() */ dst_reg->id = 0; if (BPF_SRC(insn->code) == BPF_X) { src_reg = ®s[insn->src_reg]; if (src_reg->type != SCALAR_VALUE) { if (dst_reg->type != SCALAR_VALUE) { /* Combining two pointers by any ALU op yields * an arbitrary scalar. Disallow all math except * pointer subtraction */ if (opcode == BPF_SUB && env->allow_ptr_leaks) { mark_reg_unknown(env, regs, insn->dst_reg); return 0; } verbose(env, "R%d pointer %s pointer prohibited\n", insn->dst_reg, bpf_alu_string[opcode >> 4]); return -EACCES; } else { /* scalar += pointer * This is legal, but we have to reverse our * src/dest handling in computing the range */ err = mark_chain_precision(env, insn->dst_reg); if (err) return err; return adjust_ptr_min_max_vals(env, insn, src_reg, dst_reg); } } else if (ptr_reg) { /* pointer += scalar */ err = mark_chain_precision(env, insn->src_reg); if (err) return err; return adjust_ptr_min_max_vals(env, insn, dst_reg, src_reg); } else if (dst_reg->precise) { /* if dst_reg is precise, src_reg should be precise as well */ err = mark_chain_precision(env, insn->src_reg); if (err) return err; } } else { /* Pretend the src is a reg with a known value, since we only * need to be able to read from this state. */ off_reg.type = SCALAR_VALUE; __mark_reg_known(&off_reg, insn->imm); src_reg = &off_reg; if (ptr_reg) /* pointer += K */ return adjust_ptr_min_max_vals(env, insn, ptr_reg, src_reg); } /* Got here implies adding two SCALAR_VALUEs */ if (WARN_ON_ONCE(ptr_reg)) { print_verifier_state(env, state, true); verbose(env, "verifier internal error: unexpected ptr_reg\n"); return -EINVAL; } if (WARN_ON(!src_reg)) { print_verifier_state(env, state, true); verbose(env, "verifier internal error: no src_reg\n"); return -EINVAL; } return adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg); } /* check validity of 32-bit and 64-bit arithmetic operations */ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_reg_state *regs = cur_regs(env); u8 opcode = BPF_OP(insn->code); int err; if (opcode == BPF_END || opcode == BPF_NEG) { if (opcode == BPF_NEG) { if (BPF_SRC(insn->code) != BPF_K || insn->src_reg != BPF_REG_0 || insn->off != 0 || insn->imm != 0) { verbose(env, "BPF_NEG uses reserved fields\n"); return -EINVAL; } } else { if (insn->src_reg != BPF_REG_0 || insn->off != 0 || (insn->imm != 16 && insn->imm != 32 && insn->imm != 64) || BPF_CLASS(insn->code) == BPF_ALU64) { verbose(env, "BPF_END uses reserved fields\n"); return -EINVAL; } } /* check src operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; if (is_pointer_value(env, insn->dst_reg)) { verbose(env, "R%d pointer arithmetic prohibited\n", insn->dst_reg); return -EACCES; } /* check dest operand */ err = check_reg_arg(env, insn->dst_reg, DST_OP); if (err) return err; } else if (opcode == BPF_MOV) { if (BPF_SRC(insn->code) == BPF_X) { if (insn->imm != 0 || insn->off != 0) { verbose(env, "BPF_MOV uses reserved fields\n"); return -EINVAL; } /* check src operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; } else { if (insn->src_reg != BPF_REG_0 || insn->off != 0) { verbose(env, "BPF_MOV uses reserved fields\n"); return -EINVAL; } } /* check dest operand, mark as required later */ err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); if (err) return err; if (BPF_SRC(insn->code) == BPF_X) { struct bpf_reg_state *src_reg = regs + insn->src_reg; struct bpf_reg_state *dst_reg = regs + insn->dst_reg; if (BPF_CLASS(insn->code) == BPF_ALU64) { /* case: R1 = R2 * copy register state to dest reg */ if (src_reg->type == SCALAR_VALUE && !src_reg->id) /* Assign src and dst registers the same ID * that will be used by find_equal_scalars() * to propagate min/max range. */ src_reg->id = ++env->id_gen; copy_register_state(dst_reg, src_reg); dst_reg->live |= REG_LIVE_WRITTEN; dst_reg->subreg_def = DEF_NOT_SUBREG; } else { /* R1 = (u32) R2 */ if (is_pointer_value(env, insn->src_reg)) { verbose(env, "R%d partial copy of pointer\n", insn->src_reg); return -EACCES; } else if (src_reg->type == SCALAR_VALUE) { copy_register_state(dst_reg, src_reg); /* Make sure ID is cleared otherwise * dst_reg min/max could be incorrectly * propagated into src_reg by find_equal_scalars() */ dst_reg->id = 0; dst_reg->live |= REG_LIVE_WRITTEN; dst_reg->subreg_def = env->insn_idx + 1; } else { mark_reg_unknown(env, regs, insn->dst_reg); } zext_32_to_64(dst_reg); reg_bounds_sync(dst_reg); } } else { /* case: R = imm * remember the value we stored into this reg */ /* clear any state __mark_reg_known doesn't set */ mark_reg_unknown(env, regs, insn->dst_reg); regs[insn->dst_reg].type = SCALAR_VALUE; if (BPF_CLASS(insn->code) == BPF_ALU64) { __mark_reg_known(regs + insn->dst_reg, insn->imm); } else { __mark_reg_known(regs + insn->dst_reg, (u32)insn->imm); } } } else if (opcode > BPF_END) { verbose(env, "invalid BPF_ALU opcode %x\n", opcode); return -EINVAL; } else { /* all other ALU ops: and, sub, xor, add, ... */ if (BPF_SRC(insn->code) == BPF_X) { if (insn->imm != 0 || insn->off != 0) { verbose(env, "BPF_ALU uses reserved fields\n"); return -EINVAL; } /* check src1 operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; } else { if (insn->src_reg != BPF_REG_0 || insn->off != 0) { verbose(env, "BPF_ALU uses reserved fields\n"); return -EINVAL; } } /* check src2 operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; if ((opcode == BPF_MOD || opcode == BPF_DIV) && BPF_SRC(insn->code) == BPF_K && insn->imm == 0) { verbose(env, "div by zero\n"); return -EINVAL; } if ((opcode == BPF_LSH || opcode == BPF_RSH || opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) { int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32; if (insn->imm < 0 || insn->imm >= size) { verbose(env, "invalid shift %d\n", insn->imm); return -EINVAL; } } /* check dest operand */ err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); if (err) return err; return adjust_reg_min_max_vals(env, insn); } return 0; } static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, struct bpf_reg_state *dst_reg, enum bpf_reg_type type, bool range_right_open) { struct bpf_func_state *state; struct bpf_reg_state *reg; int new_range; if (dst_reg->off < 0 || (dst_reg->off == 0 && range_right_open)) /* This doesn't give us any range */ return; if (dst_reg->umax_value > MAX_PACKET_OFF || dst_reg->umax_value + dst_reg->off > MAX_PACKET_OFF) /* Risk of overflow. For instance, ptr + (1<<63) may be less * than pkt_end, but that's because it's also less than pkt. */ return; new_range = dst_reg->off; if (range_right_open) new_range++; /* Examples for register markings: * * pkt_data in dst register: * * r2 = r3; * r2 += 8; * if (r2 > pkt_end) goto <handle exception> * <access okay> * * r2 = r3; * r2 += 8; * if (r2 < pkt_end) goto <access okay> * <handle exception> * * Where: * r2 == dst_reg, pkt_end == src_reg * r2=pkt(id=n,off=8,r=0) * r3=pkt(id=n,off=0,r=0) * * pkt_data in src register: * * r2 = r3; * r2 += 8; * if (pkt_end >= r2) goto <access okay> * <handle exception> * * r2 = r3; * r2 += 8; * if (pkt_end <= r2) goto <handle exception> * <access okay> * * Where: * pkt_end == dst_reg, r2 == src_reg * r2=pkt(id=n,off=8,r=0) * r3=pkt(id=n,off=0,r=0) * * Find register r3 and mark its range as r3=pkt(id=n,off=0,r=8) * or r3=pkt(id=n,off=0,r=8-1), so that range of bytes [r3, r3 + 8) * and [r3, r3 + 8-1) respectively is safe to access depending on * the check. */ /* If our ids match, then we must have the same max_value. And we * don't care about the other reg's fixed offset, since if it's too big * the range won't allow anything. * dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16. */ bpf_for_each_reg_in_vstate(vstate, state, reg, ({ if (reg->type == type && reg->id == dst_reg->id) /* keep the maximum range already checked */ reg->range = max(reg->range, new_range); })); } static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode) { struct tnum subreg = tnum_subreg(reg->var_off); s32 sval = (s32)val; switch (opcode) { case BPF_JEQ: if (tnum_is_const(subreg)) return !!tnum_equals_const(subreg, val); break; case BPF_JNE: if (tnum_is_const(subreg)) return !tnum_equals_const(subreg, val); break; case BPF_JSET: if ((~subreg.mask & subreg.value) & val) return 1; if (!((subreg.mask | subreg.value) & val)) return 0; break; case BPF_JGT: if (reg->u32_min_value > val) return 1; else if (reg->u32_max_value <= val) return 0; break; case BPF_JSGT: if (reg->s32_min_value > sval) return 1; else if (reg->s32_max_value <= sval) return 0; break; case BPF_JLT: if (reg->u32_max_value < val) return 1; else if (reg->u32_min_value >= val) return 0; break; case BPF_JSLT: if (reg->s32_max_value < sval) return 1; else if (reg->s32_min_value >= sval) return 0; break; case BPF_JGE: if (reg->u32_min_value >= val) return 1; else if (reg->u32_max_value < val) return 0; break; case BPF_JSGE: if (reg->s32_min_value >= sval) return 1; else if (reg->s32_max_value < sval) return 0; break; case BPF_JLE: if (reg->u32_max_value <= val) return 1; else if (reg->u32_min_value > val) return 0; break; case BPF_JSLE: if (reg->s32_max_value <= sval) return 1; else if (reg->s32_min_value > sval) return 0; break; } return -1; } static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode) { s64 sval = (s64)val; switch (opcode) { case BPF_JEQ: if (tnum_is_const(reg->var_off)) return !!tnum_equals_const(reg->var_off, val); break; case BPF_JNE: if (tnum_is_const(reg->var_off)) return !tnum_equals_const(reg->var_off, val); break; case BPF_JSET: if ((~reg->var_off.mask & reg->var_off.value) & val) return 1; if (!((reg->var_off.mask | reg->var_off.value) & val)) return 0; break; case BPF_JGT: if (reg->umin_value > val) return 1; else if (reg->umax_value <= val) return 0; break; case BPF_JSGT: if (reg->smin_value > sval) return 1; else if (reg->smax_value <= sval) return 0; break; case BPF_JLT: if (reg->umax_value < val) return 1; else if (reg->umin_value >= val) return 0; break; case BPF_JSLT: if (reg->smax_value < sval) return 1; else if (reg->smin_value >= sval) return 0; break; case BPF_JGE: if (reg->umin_value >= val) return 1; else if (reg->umax_value < val) return 0; break; case BPF_JSGE: if (reg->smin_value >= sval) return 1; else if (reg->smax_value < sval) return 0; break; case BPF_JLE: if (reg->umax_value <= val) return 1; else if (reg->umin_value > val) return 0; break; case BPF_JSLE: if (reg->smax_value <= sval) return 1; else if (reg->smin_value > sval) return 0; break; } return -1; } /* compute branch direction of the expression "if (reg opcode val) goto target;" * and return: * 1 - branch will be taken and "goto target" will be executed * 0 - branch will not be taken and fall-through to next insn * -1 - unknown. Example: "if (reg < 5)" is unknown when register value * range [0,10] */ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode, bool is_jmp32) { if (__is_pointer_value(false, reg)) { if (!reg_type_not_null(reg->type)) return -1; /* If pointer is valid tests against zero will fail so we can * use this to direct branch taken. */ if (val != 0) return -1; switch (opcode) { case BPF_JEQ: return 0; case BPF_JNE: return 1; default: return -1; } } if (is_jmp32) return is_branch32_taken(reg, val, opcode); return is_branch64_taken(reg, val, opcode); } static int flip_opcode(u32 opcode) { /* How can we transform "a <op> b" into "b <op> a"? */ static const u8 opcode_flip[16] = { /* these stay the same */ [BPF_JEQ >> 4] = BPF_JEQ, [BPF_JNE >> 4] = BPF_JNE, [BPF_JSET >> 4] = BPF_JSET, /* these swap "lesser" and "greater" (L and G in the opcodes) */ [BPF_JGE >> 4] = BPF_JLE, [BPF_JGT >> 4] = BPF_JLT, [BPF_JLE >> 4] = BPF_JGE, [BPF_JLT >> 4] = BPF_JGT, [BPF_JSGE >> 4] = BPF_JSLE, [BPF_JSGT >> 4] = BPF_JSLT, [BPF_JSLE >> 4] = BPF_JSGE, [BPF_JSLT >> 4] = BPF_JSGT }; return opcode_flip[opcode >> 4]; } static int is_pkt_ptr_branch_taken(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg, u8 opcode) { struct bpf_reg_state *pkt; if (src_reg->type == PTR_TO_PACKET_END) { pkt = dst_reg; } else if (dst_reg->type == PTR_TO_PACKET_END) { pkt = src_reg; opcode = flip_opcode(opcode); } else { return -1; } if (pkt->range >= 0) return -1; switch (opcode) { case BPF_JLE: /* pkt <= pkt_end */ fallthrough; case BPF_JGT: /* pkt > pkt_end */ if (pkt->range == BEYOND_PKT_END) /* pkt has at last one extra byte beyond pkt_end */ return opcode == BPF_JGT; break; case BPF_JLT: /* pkt < pkt_end */ fallthrough; case BPF_JGE: /* pkt >= pkt_end */ if (pkt->range == BEYOND_PKT_END || pkt->range == AT_PKT_END) return opcode == BPF_JGE; break; } return -1; } /* Adjusts the register min/max values in the case that the dst_reg is the * variable register that we are working on, and src_reg is a constant or we're * simply doing a BPF_K check. * In JEQ/JNE cases we also adjust the var_off values. */ static void reg_set_min_max(struct bpf_reg_state *true_reg, struct bpf_reg_state *false_reg, u64 val, u32 val32, u8 opcode, bool is_jmp32) { struct tnum false_32off = tnum_subreg(false_reg->var_off); struct tnum false_64off = false_reg->var_off; struct tnum true_32off = tnum_subreg(true_reg->var_off); struct tnum true_64off = true_reg->var_off; s64 sval = (s64)val; s32 sval32 = (s32)val32; /* If the dst_reg is a pointer, we can't learn anything about its * variable offset from the compare (unless src_reg were a pointer into * the same object, but we don't bother with that. * Since false_reg and true_reg have the same type by construction, we * only need to check one of them for pointerness. */ if (__is_pointer_value(false, false_reg)) return; switch (opcode) { /* JEQ/JNE comparison doesn't change the register equivalence. * * r1 = r2; * if (r1 == 42) goto label; * ... * label: // here both r1 and r2 are known to be 42. * * Hence when marking register as known preserve it's ID. */ case BPF_JEQ: if (is_jmp32) { __mark_reg32_known(true_reg, val32); true_32off = tnum_subreg(true_reg->var_off); } else { ___mark_reg_known(true_reg, val); true_64off = true_reg->var_off; } break; case BPF_JNE: if (is_jmp32) { __mark_reg32_known(false_reg, val32); false_32off = tnum_subreg(false_reg->var_off); } else { ___mark_reg_known(false_reg, val); false_64off = false_reg->var_off; } break; case BPF_JSET: if (is_jmp32) { false_32off = tnum_and(false_32off, tnum_const(~val32)); if (is_power_of_2(val32)) true_32off = tnum_or(true_32off, tnum_const(val32)); } else { false_64off = tnum_and(false_64off, tnum_const(~val)); if (is_power_of_2(val)) true_64off = tnum_or(true_64off, tnum_const(val)); } break; case BPF_JGE: case BPF_JGT: { if (is_jmp32) { u32 false_umax = opcode == BPF_JGT ? val32 : val32 - 1; u32 true_umin = opcode == BPF_JGT ? val32 + 1 : val32; false_reg->u32_max_value = min(false_reg->u32_max_value, false_umax); true_reg->u32_min_value = max(true_reg->u32_min_value, true_umin); } else { u64 false_umax = opcode == BPF_JGT ? val : val - 1; u64 true_umin = opcode == BPF_JGT ? val + 1 : val; false_reg->umax_value = min(false_reg->umax_value, false_umax); true_reg->umin_value = max(true_reg->umin_value, true_umin); } break; } case BPF_JSGE: case BPF_JSGT: { if (is_jmp32) { s32 false_smax = opcode == BPF_JSGT ? sval32 : sval32 - 1; s32 true_smin = opcode == BPF_JSGT ? sval32 + 1 : sval32; false_reg->s32_max_value = min(false_reg->s32_max_value, false_smax); true_reg->s32_min_value = max(true_reg->s32_min_value, true_smin); } else { s64 false_smax = opcode == BPF_JSGT ? sval : sval - 1; s64 true_smin = opcode == BPF_JSGT ? sval + 1 : sval; false_reg->smax_value = min(false_reg->smax_value, false_smax); true_reg->smin_value = max(true_reg->smin_value, true_smin); } break; } case BPF_JLE: case BPF_JLT: { if (is_jmp32) { u32 false_umin = opcode == BPF_JLT ? val32 : val32 + 1; u32 true_umax = opcode == BPF_JLT ? val32 - 1 : val32; false_reg->u32_min_value = max(false_reg->u32_min_value, false_umin); true_reg->u32_max_value = min(true_reg->u32_max_value, true_umax); } else { u64 false_umin = opcode == BPF_JLT ? val : val + 1; u64 true_umax = opcode == BPF_JLT ? val - 1 : val; false_reg->umin_value = max(false_reg->umin_value, false_umin); true_reg->umax_value = min(true_reg->umax_value, true_umax); } break; } case BPF_JSLE: case BPF_JSLT: { if (is_jmp32) { s32 false_smin = opcode == BPF_JSLT ? sval32 : sval32 + 1; s32 true_smax = opcode == BPF_JSLT ? sval32 - 1 : sval32; false_reg->s32_min_value = max(false_reg->s32_min_value, false_smin); true_reg->s32_max_value = min(true_reg->s32_max_value, true_smax); } else { s64 false_smin = opcode == BPF_JSLT ? sval : sval + 1; s64 true_smax = opcode == BPF_JSLT ? sval - 1 : sval; false_reg->smin_value = max(false_reg->smin_value, false_smin); true_reg->smax_value = min(true_reg->smax_value, true_smax); } break; } default: return; } if (is_jmp32) { false_reg->var_off = tnum_or(tnum_clear_subreg(false_64off), tnum_subreg(false_32off)); true_reg->var_off = tnum_or(tnum_clear_subreg(true_64off), tnum_subreg(true_32off)); __reg_combine_32_into_64(false_reg); __reg_combine_32_into_64(true_reg); } else { false_reg->var_off = false_64off; true_reg->var_off = true_64off; __reg_combine_64_into_32(false_reg); __reg_combine_64_into_32(true_reg); } } /* Same as above, but for the case that dst_reg holds a constant and src_reg is * the variable reg. */ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg, struct bpf_reg_state *false_reg, u64 val, u32 val32, u8 opcode, bool is_jmp32) { opcode = flip_opcode(opcode); /* This uses zero as "not present in table"; luckily the zero opcode, * BPF_JA, can't get here. */ if (opcode) reg_set_min_max(true_reg, false_reg, val, val32, opcode, is_jmp32); } /* Regs are known to be equal, so intersect their min/max/var_off */ static void __reg_combine_min_max(struct bpf_reg_state *src_reg, struct bpf_reg_state *dst_reg) { src_reg->umin_value = dst_reg->umin_value = max(src_reg->umin_value, dst_reg->umin_value); src_reg->umax_value = dst_reg->umax_value = min(src_reg->umax_value, dst_reg->umax_value); src_reg->smin_value = dst_reg->smin_value = max(src_reg->smin_value, dst_reg->smin_value); src_reg->smax_value = dst_reg->smax_value = min(src_reg->smax_value, dst_reg->smax_value); src_reg->var_off = dst_reg->var_off = tnum_intersect(src_reg->var_off, dst_reg->var_off); reg_bounds_sync(src_reg); reg_bounds_sync(dst_reg); } static void reg_combine_min_max(struct bpf_reg_state *true_src, struct bpf_reg_state *true_dst, struct bpf_reg_state *false_src, struct bpf_reg_state *false_dst, u8 opcode) { switch (opcode) { case BPF_JEQ: __reg_combine_min_max(true_src, true_dst); break; case BPF_JNE: __reg_combine_min_max(false_src, false_dst); break; } } static void mark_ptr_or_null_reg(struct bpf_func_state *state, struct bpf_reg_state *reg, u32 id, bool is_null) { if (type_may_be_null(reg->type) && reg->id == id && !WARN_ON_ONCE(!reg->id)) { if (WARN_ON_ONCE(reg->smin_value || reg->smax_value || !tnum_equals_const(reg->var_off, 0) || reg->off)) { /* Old offset (both fixed and variable parts) should * have been known-zero, because we don't allow pointer * arithmetic on pointers that might be NULL. If we * see this happening, don't convert the register. */ return; } if (is_null) { reg->type = SCALAR_VALUE; /* We don't need id and ref_obj_id from this point * onwards anymore, thus we should better reset it, * so that state pruning has chances to take effect. */ reg->id = 0; reg->ref_obj_id = 0; return; } mark_ptr_not_null_reg(reg); if (!reg_may_point_to_spin_lock(reg)) { /* For not-NULL ptr, reg->ref_obj_id will be reset * in release_reference(). * * reg->id is still used by spin_lock ptr. Other * than spin_lock ptr type, reg->id can be reset. */ reg->id = 0; } } } /* The logic is similar to find_good_pkt_pointers(), both could eventually * be folded together at some point. */ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno, bool is_null) { struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *regs = state->regs, *reg; u32 ref_obj_id = regs[regno].ref_obj_id; u32 id = regs[regno].id; if (ref_obj_id && ref_obj_id == id && is_null) /* regs[regno] is in the " == NULL" branch. * No one could have freed the reference state before * doing the NULL check. */ WARN_ON_ONCE(release_reference_state(state, id)); bpf_for_each_reg_in_vstate(vstate, state, reg, ({ mark_ptr_or_null_reg(state, reg, id, is_null); })); } static bool try_match_pkt_pointers(const struct bpf_insn *insn, struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg, struct bpf_verifier_state *this_branch, struct bpf_verifier_state *other_branch) { if (BPF_SRC(insn->code) != BPF_X) return false; /* Pointers are always 64-bit. */ if (BPF_CLASS(insn->code) == BPF_JMP32) return false; switch (BPF_OP(insn->code)) { case BPF_JGT: if ((dst_reg->type == PTR_TO_PACKET && src_reg->type == PTR_TO_PACKET_END) || (dst_reg->type == PTR_TO_PACKET_META && reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) { /* pkt_data' > pkt_end, pkt_meta' > pkt_data */ find_good_pkt_pointers(this_branch, dst_reg, dst_reg->type, false); mark_pkt_end(other_branch, insn->dst_reg, true); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && src_reg->type == PTR_TO_PACKET_META)) { /* pkt_end > pkt_data', pkt_data > pkt_meta' */ find_good_pkt_pointers(other_branch, src_reg, src_reg->type, true); mark_pkt_end(this_branch, insn->src_reg, false); } else { return false; } break; case BPF_JLT: if ((dst_reg->type == PTR_TO_PACKET && src_reg->type == PTR_TO_PACKET_END) || (dst_reg->type == PTR_TO_PACKET_META && reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) { /* pkt_data' < pkt_end, pkt_meta' < pkt_data */ find_good_pkt_pointers(other_branch, dst_reg, dst_reg->type, true); mark_pkt_end(this_branch, insn->dst_reg, false); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && src_reg->type == PTR_TO_PACKET_META)) { /* pkt_end < pkt_data', pkt_data > pkt_meta' */ find_good_pkt_pointers(this_branch, src_reg, src_reg->type, false); mark_pkt_end(other_branch, insn->src_reg, true); } else { return false; } break; case BPF_JGE: if ((dst_reg->type == PTR_TO_PACKET && src_reg->type == PTR_TO_PACKET_END) || (dst_reg->type == PTR_TO_PACKET_META && reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) { /* pkt_data' >= pkt_end, pkt_meta' >= pkt_data */ find_good_pkt_pointers(this_branch, dst_reg, dst_reg->type, true); mark_pkt_end(other_branch, insn->dst_reg, false); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && src_reg->type == PTR_TO_PACKET_META)) { /* pkt_end >= pkt_data', pkt_data >= pkt_meta' */ find_good_pkt_pointers(other_branch, src_reg, src_reg->type, false); mark_pkt_end(this_branch, insn->src_reg, true); } else { return false; } break; case BPF_JLE: if ((dst_reg->type == PTR_TO_PACKET && src_reg->type == PTR_TO_PACKET_END) || (dst_reg->type == PTR_TO_PACKET_META && reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) { /* pkt_data' <= pkt_end, pkt_meta' <= pkt_data */ find_good_pkt_pointers(other_branch, dst_reg, dst_reg->type, false); mark_pkt_end(this_branch, insn->dst_reg, true); } else if ((dst_reg->type == PTR_TO_PACKET_END && src_reg->type == PTR_TO_PACKET) || (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && src_reg->type == PTR_TO_PACKET_META)) { /* pkt_end <= pkt_data', pkt_data <= pkt_meta' */ find_good_pkt_pointers(this_branch, src_reg, src_reg->type, true); mark_pkt_end(other_branch, insn->src_reg, false); } else { return false; } break; default: return false; } return true; } static void find_equal_scalars(struct bpf_verifier_state *vstate, struct bpf_reg_state *known_reg) { struct bpf_func_state *state; struct bpf_reg_state *reg; bpf_for_each_reg_in_vstate(vstate, state, reg, ({ if (reg->type == SCALAR_VALUE && reg->id == known_reg->id) { s32 saved_subreg_def = reg->subreg_def; copy_register_state(reg, known_reg); reg->subreg_def = saved_subreg_def; } })); } static int check_cond_jmp_op(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx) { struct bpf_verifier_state *this_branch = env->cur_state; struct bpf_verifier_state *other_branch; struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs; struct bpf_reg_state *dst_reg, *other_branch_regs, *src_reg = NULL; u8 opcode = BPF_OP(insn->code); bool is_jmp32; int pred = -1; int err; /* Only conditional jumps are expected to reach here. */ if (opcode == BPF_JA || opcode > BPF_JSLE) { verbose(env, "invalid BPF_JMP/JMP32 opcode %x\n", opcode); return -EINVAL; } /* check src2 operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; dst_reg = ®s[insn->dst_reg]; if (BPF_SRC(insn->code) == BPF_X) { if (insn->imm != 0) { verbose(env, "BPF_JMP/JMP32 uses reserved fields\n"); return -EINVAL; } /* check src1 operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; src_reg = ®s[insn->src_reg]; if (!(reg_is_pkt_pointer_any(dst_reg) && reg_is_pkt_pointer_any(src_reg)) && is_pointer_value(env, insn->src_reg)) { verbose(env, "R%d pointer comparison prohibited\n", insn->src_reg); return -EACCES; } } else { if (insn->src_reg != BPF_REG_0) { verbose(env, "BPF_JMP/JMP32 uses reserved fields\n"); return -EINVAL; } } is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32; if (BPF_SRC(insn->code) == BPF_K) { pred = is_branch_taken(dst_reg, insn->imm, opcode, is_jmp32); } else if (src_reg->type == SCALAR_VALUE && is_jmp32 && tnum_is_const(tnum_subreg(src_reg->var_off))) { pred = is_branch_taken(dst_reg, tnum_subreg(src_reg->var_off).value, opcode, is_jmp32); } else if (src_reg->type == SCALAR_VALUE && !is_jmp32 && tnum_is_const(src_reg->var_off)) { pred = is_branch_taken(dst_reg, src_reg->var_off.value, opcode, is_jmp32); } else if (reg_is_pkt_pointer_any(dst_reg) && reg_is_pkt_pointer_any(src_reg) && !is_jmp32) { pred = is_pkt_ptr_branch_taken(dst_reg, src_reg, opcode); } if (pred >= 0) { /* If we get here with a dst_reg pointer type it is because * above is_branch_taken() special cased the 0 comparison. */ if (!__is_pointer_value(false, dst_reg)) err = mark_chain_precision(env, insn->dst_reg); if (BPF_SRC(insn->code) == BPF_X && !err && !__is_pointer_value(false, src_reg)) err = mark_chain_precision(env, insn->src_reg); if (err) return err; } if (pred == 1) { /* Only follow the goto, ignore fall-through. If needed, push * the fall-through branch for simulation under speculative * execution. */ if (!env->bypass_spec_v1 && !sanitize_speculative_path(env, insn, *insn_idx + 1, *insn_idx)) return -EFAULT; if (env->log.level & BPF_LOG_LEVEL) print_insn_state(env, this_branch->frame[this_branch->curframe]); *insn_idx += insn->off; return 0; } else if (pred == 0) { /* Only follow the fall-through branch, since that's where the * program will go. If needed, push the goto branch for * simulation under speculative execution. */ if (!env->bypass_spec_v1 && !sanitize_speculative_path(env, insn, *insn_idx + insn->off + 1, *insn_idx)) return -EFAULT; if (env->log.level & BPF_LOG_LEVEL) print_insn_state(env, this_branch->frame[this_branch->curframe]); return 0; } other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx, false); if (!other_branch) return -EFAULT; other_branch_regs = other_branch->frame[other_branch->curframe]->regs; /* detect if we are comparing against a constant value so we can adjust * our min/max values for our dst register. * this is only legit if both are scalars (or pointers to the same * object, I suppose, but we don't support that right now), because * otherwise the different base pointers mean the offsets aren't * comparable. */ if (BPF_SRC(insn->code) == BPF_X) { struct bpf_reg_state *src_reg = ®s[insn->src_reg]; if (dst_reg->type == SCALAR_VALUE && src_reg->type == SCALAR_VALUE) { if (tnum_is_const(src_reg->var_off) || (is_jmp32 && tnum_is_const(tnum_subreg(src_reg->var_off)))) reg_set_min_max(&other_branch_regs[insn->dst_reg], dst_reg, src_reg->var_off.value, tnum_subreg(src_reg->var_off).value, opcode, is_jmp32); else if (tnum_is_const(dst_reg->var_off) || (is_jmp32 && tnum_is_const(tnum_subreg(dst_reg->var_off)))) reg_set_min_max_inv(&other_branch_regs[insn->src_reg], src_reg, dst_reg->var_off.value, tnum_subreg(dst_reg->var_off).value, opcode, is_jmp32); else if (!is_jmp32 && (opcode == BPF_JEQ || opcode == BPF_JNE)) /* Comparing for equality, we can combine knowledge */ reg_combine_min_max(&other_branch_regs[insn->src_reg], &other_branch_regs[insn->dst_reg], src_reg, dst_reg, opcode); if (src_reg->id && !WARN_ON_ONCE(src_reg->id != other_branch_regs[insn->src_reg].id)) { find_equal_scalars(this_branch, src_reg); find_equal_scalars(other_branch, &other_branch_regs[insn->src_reg]); } } } else if (dst_reg->type == SCALAR_VALUE) { reg_set_min_max(&other_branch_regs[insn->dst_reg], dst_reg, insn->imm, (u32)insn->imm, opcode, is_jmp32); } if (dst_reg->type == SCALAR_VALUE && dst_reg->id && !WARN_ON_ONCE(dst_reg->id != other_branch_regs[insn->dst_reg].id)) { find_equal_scalars(this_branch, dst_reg); find_equal_scalars(other_branch, &other_branch_regs[insn->dst_reg]); } /* detect if R == 0 where R is returned from bpf_map_lookup_elem(). * NOTE: these optimizations below are related with pointer comparison * which will never be JMP32. */ if (!is_jmp32 && BPF_SRC(insn->code) == BPF_K && insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) && type_may_be_null(dst_reg->type)) { /* Mark all identical registers in each branch as either * safe or unknown depending R == 0 or R != 0 conditional. */ mark_ptr_or_null_regs(this_branch, insn->dst_reg, opcode == BPF_JNE); mark_ptr_or_null_regs(other_branch, insn->dst_reg, opcode == BPF_JEQ); } else if (!try_match_pkt_pointers(insn, dst_reg, ®s[insn->src_reg], this_branch, other_branch) && is_pointer_value(env, insn->dst_reg)) { verbose(env, "R%d pointer comparison prohibited\n", insn->dst_reg); return -EACCES; } if (env->log.level & BPF_LOG_LEVEL) print_insn_state(env, this_branch->frame[this_branch->curframe]); return 0; } /* verify BPF_LD_IMM64 instruction */ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_insn_aux_data *aux = cur_aux(env); struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *dst_reg; struct bpf_map *map; int err; if (BPF_SIZE(insn->code) != BPF_DW) { verbose(env, "invalid BPF_LD_IMM insn\n"); return -EINVAL; } if (insn->off != 0) { verbose(env, "BPF_LD_IMM64 uses reserved fields\n"); return -EINVAL; } err = check_reg_arg(env, insn->dst_reg, DST_OP); if (err) return err; dst_reg = ®s[insn->dst_reg]; if (insn->src_reg == 0) { u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm; dst_reg->type = SCALAR_VALUE; __mark_reg_known(®s[insn->dst_reg], imm); return 0; } /* All special src_reg cases are listed below. From this point onwards * we either succeed and assign a corresponding dst_reg->type after * zeroing the offset, or fail and reject the program. */ mark_reg_known_zero(env, regs, insn->dst_reg); if (insn->src_reg == BPF_PSEUDO_BTF_ID) { dst_reg->type = aux->btf_var.reg_type; switch (base_type(dst_reg->type)) { case PTR_TO_MEM: dst_reg->mem_size = aux->btf_var.mem_size; break; case PTR_TO_BTF_ID: dst_reg->btf = aux->btf_var.btf; dst_reg->btf_id = aux->btf_var.btf_id; break; default: verbose(env, "bpf verifier is misconfigured\n"); return -EFAULT; } return 0; } if (insn->src_reg == BPF_PSEUDO_FUNC) { struct bpf_prog_aux *aux = env->prog->aux; u32 subprogno = find_subprog(env, env->insn_idx + insn->imm + 1); if (!aux->func_info) { verbose(env, "missing btf func_info\n"); return -EINVAL; } if (aux->func_info_aux[subprogno].linkage != BTF_FUNC_STATIC) { verbose(env, "callback function not static\n"); return -EINVAL; } dst_reg->type = PTR_TO_FUNC; dst_reg->subprogno = subprogno; return 0; } map = env->used_maps[aux->map_index]; dst_reg->map_ptr = map; if (insn->src_reg == BPF_PSEUDO_MAP_VALUE || insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE) { dst_reg->type = PTR_TO_MAP_VALUE; dst_reg->off = aux->map_off; if (map_value_has_spin_lock(map)) dst_reg->id = ++env->id_gen; } else if (insn->src_reg == BPF_PSEUDO_MAP_FD || insn->src_reg == BPF_PSEUDO_MAP_IDX) { dst_reg->type = CONST_PTR_TO_MAP; } else { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } return 0; } static bool may_access_skb(enum bpf_prog_type type) { switch (type) { case BPF_PROG_TYPE_SOCKET_FILTER: case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: return true; default: return false; } } /* verify safety of LD_ABS|LD_IND instructions: * - they can only appear in the programs where ctx == skb * - since they are wrappers of function calls, they scratch R1-R5 registers, * preserve R6-R9, and store return value into R0 * * Implicit input: * ctx == skb == R6 == CTX * * Explicit input: * SRC == any register * IMM == 32-bit immediate * * Output: * R0 - 8/16/32-bit skb data converted to cpu endianness */ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_reg_state *regs = cur_regs(env); static const int ctx_reg = BPF_REG_6; u8 mode = BPF_MODE(insn->code); int i, err; if (!may_access_skb(resolve_prog_type(env->prog))) { verbose(env, "BPF_LD_[ABS|IND] instructions not allowed for this program type\n"); return -EINVAL; } if (!env->ops->gen_ld_abs) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } if (insn->dst_reg != BPF_REG_0 || insn->off != 0 || BPF_SIZE(insn->code) == BPF_DW || (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) { verbose(env, "BPF_LD_[ABS|IND] uses reserved fields\n"); return -EINVAL; } /* check whether implicit source operand (register R6) is readable */ err = check_reg_arg(env, ctx_reg, SRC_OP); if (err) return err; /* Disallow usage of BPF_LD_[ABS|IND] with reference tracking, as * gen_ld_abs() may terminate the program at runtime, leading to * reference leak. */ err = check_reference_leak(env); if (err) { verbose(env, "BPF_LD_[ABS|IND] cannot be mixed with socket references\n"); return err; } if (env->cur_state->active_spin_lock) { verbose(env, "BPF_LD_[ABS|IND] cannot be used inside bpf_spin_lock-ed region\n"); return -EINVAL; } if (regs[ctx_reg].type != PTR_TO_CTX) { verbose(env, "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); return -EINVAL; } if (mode == BPF_IND) { /* check explicit source operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; } err = check_ptr_off_reg(env, ®s[ctx_reg], ctx_reg); if (err < 0) return err; /* reset caller saved regs to unreadable */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]); check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); } /* mark destination R0 register as readable, since it contains * the value fetched from the packet. * Already marked as written above. */ mark_reg_unknown(env, regs, BPF_REG_0); /* ld_abs load up to 32-bit skb data. */ regs[BPF_REG_0].subreg_def = env->insn_idx + 1; return 0; } static int check_return_code(struct bpf_verifier_env *env) { struct tnum enforce_attach_type_range = tnum_unknown; const struct bpf_prog *prog = env->prog; struct bpf_reg_state *reg; struct tnum range = tnum_range(0, 1), const_0 = tnum_const(0); enum bpf_prog_type prog_type = resolve_prog_type(env->prog); int err; struct bpf_func_state *frame = env->cur_state->frame[0]; const bool is_subprog = frame->subprogno; /* LSM and struct_ops func-ptr's return type could be "void" */ if (!is_subprog) { switch (prog_type) { case BPF_PROG_TYPE_LSM: if (prog->expected_attach_type == BPF_LSM_CGROUP) /* See below, can be 0 or 0-1 depending on hook. */ break; fallthrough; case BPF_PROG_TYPE_STRUCT_OPS: if (!prog->aux->attach_func_proto->type) return 0; break; default: break; } } /* eBPF calling convention is such that R0 is used * to return the value from eBPF program. * Make sure that it's readable at this time * of bpf_exit, which means that program wrote * something into it earlier */ err = check_reg_arg(env, BPF_REG_0, SRC_OP); if (err) return err; if (is_pointer_value(env, BPF_REG_0)) { verbose(env, "R0 leaks addr as return value\n"); return -EACCES; } reg = cur_regs(env) + BPF_REG_0; if (frame->in_async_callback_fn) { /* enforce return zero from async callbacks like timer */ if (reg->type != SCALAR_VALUE) { verbose(env, "In async callback the register R0 is not a known value (%s)\n", reg_type_str(env, reg->type)); return -EINVAL; } if (!tnum_in(const_0, reg->var_off)) { verbose_invalid_scalar(env, reg, &const_0, "async callback", "R0"); return -EINVAL; } return 0; } if (is_subprog) { if (reg->type != SCALAR_VALUE) { verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n", reg_type_str(env, reg->type)); return -EINVAL; } return 0; } switch (prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG || env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG || env->prog->expected_attach_type == BPF_CGROUP_INET4_GETPEERNAME || env->prog->expected_attach_type == BPF_CGROUP_INET6_GETPEERNAME || env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME || env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME) range = tnum_range(1, 1); if (env->prog->expected_attach_type == BPF_CGROUP_INET4_BIND || env->prog->expected_attach_type == BPF_CGROUP_INET6_BIND) range = tnum_range(0, 3); break; case BPF_PROG_TYPE_CGROUP_SKB: if (env->prog->expected_attach_type == BPF_CGROUP_INET_EGRESS) { range = tnum_range(0, 3); enforce_attach_type_range = tnum_range(2, 3); } break; case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_CGROUP_SOCKOPT: break; case BPF_PROG_TYPE_RAW_TRACEPOINT: if (!env->prog->aux->attach_btf_id) return 0; range = tnum_const(0); break; case BPF_PROG_TYPE_TRACING: switch (env->prog->expected_attach_type) { case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: range = tnum_const(0); break; case BPF_TRACE_RAW_TP: case BPF_MODIFY_RETURN: return 0; case BPF_TRACE_ITER: break; default: return -ENOTSUPP; } break; case BPF_PROG_TYPE_SK_LOOKUP: range = tnum_range(SK_DROP, SK_PASS); break; case BPF_PROG_TYPE_LSM: if (env->prog->expected_attach_type != BPF_LSM_CGROUP) { /* Regular BPF_PROG_TYPE_LSM programs can return * any value. */ return 0; } if (!env->prog->aux->attach_func_proto->type) { /* Make sure programs that attach to void * hooks don't try to modify return value. */ range = tnum_range(1, 1); } break; case BPF_PROG_TYPE_EXT: /* freplace program can return anything as its return value * depends on the to-be-replaced kernel func or bpf program. */ default: return 0; } if (reg->type != SCALAR_VALUE) { verbose(env, "At program exit the register R0 is not a known value (%s)\n", reg_type_str(env, reg->type)); return -EINVAL; } if (!tnum_in(range, reg->var_off)) { verbose_invalid_scalar(env, reg, &range, "program exit", "R0"); if (prog->expected_attach_type == BPF_LSM_CGROUP && prog_type == BPF_PROG_TYPE_LSM && !prog->aux->attach_func_proto->type) verbose(env, "Note, BPF_LSM_CGROUP that attach to void LSM hooks can't modify return value!\n"); return -EINVAL; } if (!tnum_is_unknown(enforce_attach_type_range) && tnum_in(enforce_attach_type_range, reg->var_off)) env->prog->enforce_expected_attach_type = 1; return 0; } /* non-recursive DFS pseudo code * 1 procedure DFS-iterative(G,v): * 2 label v as discovered * 3 let S be a stack * 4 S.push(v) * 5 while S is not empty * 6 t <- S.pop() * 7 if t is what we're looking for: * 8 return t * 9 for all edges e in G.adjacentEdges(t) do * 10 if edge e is already labelled * 11 continue with the next edge * 12 w <- G.adjacentVertex(t,e) * 13 if vertex w is not discovered and not explored * 14 label e as tree-edge * 15 label w as discovered * 16 S.push(w) * 17 continue at 5 * 18 else if vertex w is discovered * 19 label e as back-edge * 20 else * 21 // vertex w is explored * 22 label e as forward- or cross-edge * 23 label t as explored * 24 S.pop() * * convention: * 0x10 - discovered * 0x11 - discovered and fall-through edge labelled * 0x12 - discovered and fall-through and branch edges labelled * 0x20 - explored */ enum { DISCOVERED = 0x10, EXPLORED = 0x20, FALLTHROUGH = 1, BRANCH = 2, }; static u32 state_htab_size(struct bpf_verifier_env *env) { return env->prog->len; } static struct bpf_verifier_state_list **explored_state( struct bpf_verifier_env *env, int idx) { struct bpf_verifier_state *cur = env->cur_state; struct bpf_func_state *state = cur->frame[cur->curframe]; return &env->explored_states[(idx ^ state->callsite) % state_htab_size(env)]; } static void init_explored_state(struct bpf_verifier_env *env, int idx) { env->insn_aux_data[idx].prune_point = true; } enum { DONE_EXPLORING = 0, KEEP_EXPLORING = 1, }; /* t, w, e - match pseudo-code above: * t - index of current instruction * w - next instruction * e - edge */ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, bool loop_ok) { int *insn_stack = env->cfg.insn_stack; int *insn_state = env->cfg.insn_state; if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH)) return DONE_EXPLORING; if (e == BRANCH && insn_state[t] >= (DISCOVERED | BRANCH)) return DONE_EXPLORING; if (w < 0 || w >= env->prog->len) { verbose_linfo(env, t, "%d: ", t); verbose(env, "jump out of range from insn %d to %d\n", t, w); return -EINVAL; } if (e == BRANCH) /* mark branch target for state pruning */ init_explored_state(env, w); if (insn_state[w] == 0) { /* tree-edge */ insn_state[t] = DISCOVERED | e; insn_state[w] = DISCOVERED; if (env->cfg.cur_stack >= env->prog->len) return -E2BIG; insn_stack[env->cfg.cur_stack++] = w; return KEEP_EXPLORING; } else if ((insn_state[w] & 0xF0) == DISCOVERED) { if (loop_ok && env->bpf_capable) return DONE_EXPLORING; verbose_linfo(env, t, "%d: ", t); verbose_linfo(env, w, "%d: ", w); verbose(env, "back-edge from insn %d to %d\n", t, w); return -EINVAL; } else if (insn_state[w] == EXPLORED) { /* forward- or cross-edge */ insn_state[t] = DISCOVERED | e; } else { verbose(env, "insn state internal bug\n"); return -EFAULT; } return DONE_EXPLORING; } static int visit_func_call_insn(int t, int insn_cnt, struct bpf_insn *insns, struct bpf_verifier_env *env, bool visit_callee) { int ret; ret = push_insn(t, t + 1, FALLTHROUGH, env, false); if (ret) return ret; if (t + 1 < insn_cnt) init_explored_state(env, t + 1); if (visit_callee) { init_explored_state(env, t); ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env, /* It's ok to allow recursion from CFG point of * view. __check_func_call() will do the actual * check. */ bpf_pseudo_func(insns + t)); } return ret; } /* Visits the instruction at index t and returns one of the following: * < 0 - an error occurred * DONE_EXPLORING - the instruction was fully explored * KEEP_EXPLORING - there is still work to be done before it is fully explored */ static int visit_insn(int t, int insn_cnt, struct bpf_verifier_env *env) { struct bpf_insn *insns = env->prog->insnsi; int ret; if (bpf_pseudo_func(insns + t)) return visit_func_call_insn(t, insn_cnt, insns, env, true); /* All non-branch instructions have a single fall-through edge. */ if (BPF_CLASS(insns[t].code) != BPF_JMP && BPF_CLASS(insns[t].code) != BPF_JMP32) return push_insn(t, t + 1, FALLTHROUGH, env, false); switch (BPF_OP(insns[t].code)) { case BPF_EXIT: return DONE_EXPLORING; case BPF_CALL: if (insns[t].imm == BPF_FUNC_timer_set_callback) /* Mark this call insn to trigger is_state_visited() check * before call itself is processed by __check_func_call(). * Otherwise new async state will be pushed for further * exploration. */ init_explored_state(env, t); return visit_func_call_insn(t, insn_cnt, insns, env, insns[t].src_reg == BPF_PSEUDO_CALL); case BPF_JA: if (BPF_SRC(insns[t].code) != BPF_K) return -EINVAL; /* unconditional jump with single edge */ ret = push_insn(t, t + insns[t].off + 1, FALLTHROUGH, env, true); if (ret) return ret; /* unconditional jmp is not a good pruning point, * but it's marked, since backtracking needs * to record jmp history in is_state_visited(). */ init_explored_state(env, t + insns[t].off + 1); /* tell verifier to check for equivalent states * after every call and jump */ if (t + 1 < insn_cnt) init_explored_state(env, t + 1); return ret; default: /* conditional jump with two edges */ init_explored_state(env, t); ret = push_insn(t, t + 1, FALLTHROUGH, env, true); if (ret) return ret; return push_insn(t, t + insns[t].off + 1, BRANCH, env, true); } } /* non-recursive depth-first-search to detect loops in BPF program * loop == back-edge in directed graph */ static int check_cfg(struct bpf_verifier_env *env) { int insn_cnt = env->prog->len; int *insn_stack, *insn_state; int ret = 0; int i; insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL); if (!insn_state) return -ENOMEM; insn_stack = env->cfg.insn_stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL); if (!insn_stack) { kvfree(insn_state); return -ENOMEM; } insn_state[0] = DISCOVERED; /* mark 1st insn as discovered */ insn_stack[0] = 0; /* 0 is the first instruction */ env->cfg.cur_stack = 1; while (env->cfg.cur_stack > 0) { int t = insn_stack[env->cfg.cur_stack - 1]; ret = visit_insn(t, insn_cnt, env); switch (ret) { case DONE_EXPLORING: insn_state[t] = EXPLORED; env->cfg.cur_stack--; break; case KEEP_EXPLORING: break; default: if (ret > 0) { verbose(env, "visit_insn internal bug\n"); ret = -EFAULT; } goto err_free; } } if (env->cfg.cur_stack < 0) { verbose(env, "pop stack internal bug\n"); ret = -EFAULT; goto err_free; } for (i = 0; i < insn_cnt; i++) { if (insn_state[i] != EXPLORED) { verbose(env, "unreachable insn %d\n", i); ret = -EINVAL; goto err_free; } } ret = 0; /* cfg looks good */ err_free: kvfree(insn_state); kvfree(insn_stack); env->cfg.insn_state = env->cfg.insn_stack = NULL; return ret; } static int check_abnormal_return(struct bpf_verifier_env *env) { int i; for (i = 1; i < env->subprog_cnt; i++) { if (env->subprog_info[i].has_ld_abs) { verbose(env, "LD_ABS is not allowed in subprogs without BTF\n"); return -EINVAL; } if (env->subprog_info[i].has_tail_call) { verbose(env, "tail_call is not allowed in subprogs without BTF\n"); return -EINVAL; } } return 0; } /* The minimum supported BTF func info size */ #define MIN_BPF_FUNCINFO_SIZE 8 #define MAX_FUNCINFO_REC_SIZE 252 static int check_btf_func(struct bpf_verifier_env *env, const union bpf_attr *attr, bpfptr_t uattr) { const struct btf_type *type, *func_proto, *ret_type; u32 i, nfuncs, urec_size, min_size; u32 krec_size = sizeof(struct bpf_func_info); struct bpf_func_info *krecord; struct bpf_func_info_aux *info_aux = NULL; struct bpf_prog *prog; const struct btf *btf; bpfptr_t urecord; u32 prev_offset = 0; bool scalar_return; int ret = -ENOMEM; nfuncs = attr->func_info_cnt; if (!nfuncs) { if (check_abnormal_return(env)) return -EINVAL; return 0; } if (nfuncs != env->subprog_cnt) { verbose(env, "number of funcs in func_info doesn't match number of subprogs\n"); return -EINVAL; } urec_size = attr->func_info_rec_size; if (urec_size < MIN_BPF_FUNCINFO_SIZE || urec_size > MAX_FUNCINFO_REC_SIZE || urec_size % sizeof(u32)) { verbose(env, "invalid func info rec size %u\n", urec_size); return -EINVAL; } prog = env->prog; btf = prog->aux->btf; urecord = make_bpfptr(attr->func_info, uattr.is_kernel); min_size = min_t(u32, krec_size, urec_size); krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN); if (!krecord) return -ENOMEM; info_aux = kcalloc(nfuncs, sizeof(*info_aux), GFP_KERNEL | __GFP_NOWARN); if (!info_aux) goto err_free; for (i = 0; i < nfuncs; i++) { ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size); if (ret) { if (ret == -E2BIG) { verbose(env, "nonzero tailing record in func info"); /* set the size kernel expects so loader can zero * out the rest of the record. */ if (copy_to_bpfptr_offset(uattr, offsetof(union bpf_attr, func_info_rec_size), &min_size, sizeof(min_size))) ret = -EFAULT; } goto err_free; } if (copy_from_bpfptr(&krecord[i], urecord, min_size)) { ret = -EFAULT; goto err_free; } /* check insn_off */ ret = -EINVAL; if (i == 0) { if (krecord[i].insn_off) { verbose(env, "nonzero insn_off %u for the first func info record", krecord[i].insn_off); goto err_free; } } else if (krecord[i].insn_off <= prev_offset) { verbose(env, "same or smaller insn offset (%u) than previous func info record (%u)", krecord[i].insn_off, prev_offset); goto err_free; } if (env->subprog_info[i].start != krecord[i].insn_off) { verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n"); goto err_free; } /* check type_id */ type = btf_type_by_id(btf, krecord[i].type_id); if (!type || !btf_type_is_func(type)) { verbose(env, "invalid type id %d in func info", krecord[i].type_id); goto err_free; } info_aux[i].linkage = BTF_INFO_VLEN(type->info); func_proto = btf_type_by_id(btf, type->type); if (unlikely(!func_proto || !btf_type_is_func_proto(func_proto))) /* btf_func_check() already verified it during BTF load */ goto err_free; ret_type = btf_type_skip_modifiers(btf, func_proto->type, NULL); scalar_return = btf_type_is_small_int(ret_type) || btf_is_any_enum(ret_type); if (i && !scalar_return && env->subprog_info[i].has_ld_abs) { verbose(env, "LD_ABS is only allowed in functions that return 'int'.\n"); goto err_free; } if (i && !scalar_return && env->subprog_info[i].has_tail_call) { verbose(env, "tail_call is only allowed in functions that return 'int'.\n"); goto err_free; } prev_offset = krecord[i].insn_off; bpfptr_add(&urecord, urec_size); } prog->aux->func_info = krecord; prog->aux->func_info_cnt = nfuncs; prog->aux->func_info_aux = info_aux; return 0; err_free: kvfree(krecord); kfree(info_aux); return ret; } static void adjust_btf_func(struct bpf_verifier_env *env) { struct bpf_prog_aux *aux = env->prog->aux; int i; if (!aux->func_info) return; for (i = 0; i < env->subprog_cnt; i++) aux->func_info[i].insn_off = env->subprog_info[i].start; } #define MIN_BPF_LINEINFO_SIZE offsetofend(struct bpf_line_info, line_col) #define MAX_LINEINFO_REC_SIZE MAX_FUNCINFO_REC_SIZE static int check_btf_line(struct bpf_verifier_env *env, const union bpf_attr *attr, bpfptr_t uattr) { u32 i, s, nr_linfo, ncopy, expected_size, rec_size, prev_offset = 0; struct bpf_subprog_info *sub; struct bpf_line_info *linfo; struct bpf_prog *prog; const struct btf *btf; bpfptr_t ulinfo; int err; nr_linfo = attr->line_info_cnt; if (!nr_linfo) return 0; if (nr_linfo > INT_MAX / sizeof(struct bpf_line_info)) return -EINVAL; rec_size = attr->line_info_rec_size; if (rec_size < MIN_BPF_LINEINFO_SIZE || rec_size > MAX_LINEINFO_REC_SIZE || rec_size & (sizeof(u32) - 1)) return -EINVAL; /* Need to zero it in case the userspace may * pass in a smaller bpf_line_info object. */ linfo = kvcalloc(nr_linfo, sizeof(struct bpf_line_info), GFP_KERNEL | __GFP_NOWARN); if (!linfo) return -ENOMEM; prog = env->prog; btf = prog->aux->btf; s = 0; sub = env->subprog_info; ulinfo = make_bpfptr(attr->line_info, uattr.is_kernel); expected_size = sizeof(struct bpf_line_info); ncopy = min_t(u32, expected_size, rec_size); for (i = 0; i < nr_linfo; i++) { err = bpf_check_uarg_tail_zero(ulinfo, expected_size, rec_size); if (err) { if (err == -E2BIG) { verbose(env, "nonzero tailing record in line_info"); if (copy_to_bpfptr_offset(uattr, offsetof(union bpf_attr, line_info_rec_size), &expected_size, sizeof(expected_size))) err = -EFAULT; } goto err_free; } if (copy_from_bpfptr(&linfo[i], ulinfo, ncopy)) { err = -EFAULT; goto err_free; } /* * Check insn_off to ensure * 1) strictly increasing AND * 2) bounded by prog->len * * The linfo[0].insn_off == 0 check logically falls into * the later "missing bpf_line_info for func..." case * because the first linfo[0].insn_off must be the * first sub also and the first sub must have * subprog_info[0].start == 0. */ if ((i && linfo[i].insn_off <= prev_offset) || linfo[i].insn_off >= prog->len) { verbose(env, "Invalid line_info[%u].insn_off:%u (prev_offset:%u prog->len:%u)\n", i, linfo[i].insn_off, prev_offset, prog->len); err = -EINVAL; goto err_free; } if (!prog->insnsi[linfo[i].insn_off].code) { verbose(env, "Invalid insn code at line_info[%u].insn_off\n", i); err = -EINVAL; goto err_free; } if (!btf_name_by_offset(btf, linfo[i].line_off) || !btf_name_by_offset(btf, linfo[i].file_name_off)) { verbose(env, "Invalid line_info[%u].line_off or .file_name_off\n", i); err = -EINVAL; goto err_free; } if (s != env->subprog_cnt) { if (linfo[i].insn_off == sub[s].start) { sub[s].linfo_idx = i; s++; } else if (sub[s].start < linfo[i].insn_off) { verbose(env, "missing bpf_line_info for func#%u\n", s); err = -EINVAL; goto err_free; } } prev_offset = linfo[i].insn_off; bpfptr_add(&ulinfo, rec_size); } if (s != env->subprog_cnt) { verbose(env, "missing bpf_line_info for %u funcs starting from func#%u\n", env->subprog_cnt - s, s); err = -EINVAL; goto err_free; } prog->aux->linfo = linfo; prog->aux->nr_linfo = nr_linfo; return 0; err_free: kvfree(linfo); return err; } #define MIN_CORE_RELO_SIZE sizeof(struct bpf_core_relo) #define MAX_CORE_RELO_SIZE MAX_FUNCINFO_REC_SIZE static int check_core_relo(struct bpf_verifier_env *env, const union bpf_attr *attr, bpfptr_t uattr) { u32 i, nr_core_relo, ncopy, expected_size, rec_size; struct bpf_core_relo core_relo = {}; struct bpf_prog *prog = env->prog; const struct btf *btf = prog->aux->btf; struct bpf_core_ctx ctx = { .log = &env->log, .btf = btf, }; bpfptr_t u_core_relo; int err; nr_core_relo = attr->core_relo_cnt; if (!nr_core_relo) return 0; if (nr_core_relo > INT_MAX / sizeof(struct bpf_core_relo)) return -EINVAL; rec_size = attr->core_relo_rec_size; if (rec_size < MIN_CORE_RELO_SIZE || rec_size > MAX_CORE_RELO_SIZE || rec_size % sizeof(u32)) return -EINVAL; u_core_relo = make_bpfptr(attr->core_relos, uattr.is_kernel); expected_size = sizeof(struct bpf_core_relo); ncopy = min_t(u32, expected_size, rec_size); /* Unlike func_info and line_info, copy and apply each CO-RE * relocation record one at a time. */ for (i = 0; i < nr_core_relo; i++) { /* future proofing when sizeof(bpf_core_relo) changes */ err = bpf_check_uarg_tail_zero(u_core_relo, expected_size, rec_size); if (err) { if (err == -E2BIG) { verbose(env, "nonzero tailing record in core_relo"); if (copy_to_bpfptr_offset(uattr, offsetof(union bpf_attr, core_relo_rec_size), &expected_size, sizeof(expected_size))) err = -EFAULT; } break; } if (copy_from_bpfptr(&core_relo, u_core_relo, ncopy)) { err = -EFAULT; break; } if (core_relo.insn_off % 8 || core_relo.insn_off / 8 >= prog->len) { verbose(env, "Invalid core_relo[%u].insn_off:%u prog->len:%u\n", i, core_relo.insn_off, prog->len); err = -EINVAL; break; } err = bpf_core_apply(&ctx, &core_relo, i, &prog->insnsi[core_relo.insn_off / 8]); if (err) break; bpfptr_add(&u_core_relo, rec_size); } return err; } static int check_btf_info(struct bpf_verifier_env *env, const union bpf_attr *attr, bpfptr_t uattr) { struct btf *btf; int err; if (!attr->func_info_cnt && !attr->line_info_cnt) { if (check_abnormal_return(env)) return -EINVAL; return 0; } btf = btf_get_by_fd(attr->prog_btf_fd); if (IS_ERR(btf)) return PTR_ERR(btf); if (btf_is_kernel(btf)) { btf_put(btf); return -EACCES; } env->prog->aux->btf = btf; err = check_btf_func(env, attr, uattr); if (err) return err; err = check_btf_line(env, attr, uattr); if (err) return err; err = check_core_relo(env, attr, uattr); if (err) return err; return 0; } /* check %cur's range satisfies %old's */ static bool range_within(struct bpf_reg_state *old, struct bpf_reg_state *cur) { return old->umin_value <= cur->umin_value && old->umax_value >= cur->umax_value && old->smin_value <= cur->smin_value && old->smax_value >= cur->smax_value && old->u32_min_value <= cur->u32_min_value && old->u32_max_value >= cur->u32_max_value && old->s32_min_value <= cur->s32_min_value && old->s32_max_value >= cur->s32_max_value; } /* If in the old state two registers had the same id, then they need to have * the same id in the new state as well. But that id could be different from * the old state, so we need to track the mapping from old to new ids. * Once we have seen that, say, a reg with old id 5 had new id 9, any subsequent * regs with old id 5 must also have new id 9 for the new state to be safe. But * regs with a different old id could still have new id 9, we don't care about * that. * So we look through our idmap to see if this old id has been seen before. If * so, we require the new id to match; otherwise, we add the id pair to the map. */ static bool check_ids(u32 old_id, u32 cur_id, struct bpf_id_pair *idmap) { unsigned int i; for (i = 0; i < BPF_ID_MAP_SIZE; i++) { if (!idmap[i].old) { /* Reached an empty slot; haven't seen this id before */ idmap[i].old = old_id; idmap[i].cur = cur_id; return true; } if (idmap[i].old == old_id) return idmap[i].cur == cur_id; } /* We ran out of idmap slots, which should be impossible */ WARN_ON_ONCE(1); return false; } static void clean_func_state(struct bpf_verifier_env *env, struct bpf_func_state *st) { enum bpf_reg_liveness live; int i, j; for (i = 0; i < BPF_REG_FP; i++) { live = st->regs[i].live; /* liveness must not touch this register anymore */ st->regs[i].live |= REG_LIVE_DONE; if (!(live & REG_LIVE_READ)) /* since the register is unused, clear its state * to make further comparison simpler */ __mark_reg_not_init(env, &st->regs[i]); } for (i = 0; i < st->allocated_stack / BPF_REG_SIZE; i++) { live = st->stack[i].spilled_ptr.live; /* liveness must not touch this stack slot anymore */ st->stack[i].spilled_ptr.live |= REG_LIVE_DONE; if (!(live & REG_LIVE_READ)) { __mark_reg_not_init(env, &st->stack[i].spilled_ptr); for (j = 0; j < BPF_REG_SIZE; j++) st->stack[i].slot_type[j] = STACK_INVALID; } } } static void clean_verifier_state(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { int i; if (st->frame[0]->regs[0].live & REG_LIVE_DONE) /* all regs in this state in all frames were already marked */ return; for (i = 0; i <= st->curframe; i++) clean_func_state(env, st->frame[i]); } /* the parentage chains form a tree. * the verifier states are added to state lists at given insn and * pushed into state stack for future exploration. * when the verifier reaches bpf_exit insn some of the verifer states * stored in the state lists have their final liveness state already, * but a lot of states will get revised from liveness point of view when * the verifier explores other branches. * Example: * 1: r0 = 1 * 2: if r1 == 100 goto pc+1 * 3: r0 = 2 * 4: exit * when the verifier reaches exit insn the register r0 in the state list of * insn 2 will be seen as !REG_LIVE_READ. Then the verifier pops the other_branch * of insn 2 and goes exploring further. At the insn 4 it will walk the * parentage chain from insn 4 into insn 2 and will mark r0 as REG_LIVE_READ. * * Since the verifier pushes the branch states as it sees them while exploring * the program the condition of walking the branch instruction for the second * time means that all states below this branch were already explored and * their final liveness marks are already propagated. * Hence when the verifier completes the search of state list in is_state_visited() * we can call this clean_live_states() function to mark all liveness states * as REG_LIVE_DONE to indicate that 'parent' pointers of 'struct bpf_reg_state' * will not be used. * This function also clears the registers and stack for states that !READ * to simplify state merging. * * Important note here that walking the same branch instruction in the callee * doesn't meant that the states are DONE. The verifier has to compare * the callsites */ static void clean_live_states(struct bpf_verifier_env *env, int insn, struct bpf_verifier_state *cur) { struct bpf_verifier_state_list *sl; int i; sl = *explored_state(env, insn); while (sl) { if (sl->state.branches) goto next; if (sl->state.insn_idx != insn || sl->state.curframe != cur->curframe) goto next; for (i = 0; i <= cur->curframe; i++) if (sl->state.frame[i]->callsite != cur->frame[i]->callsite) goto next; clean_verifier_state(env, &sl->state); next: sl = sl->next; } } /* Returns true if (rold safe implies rcur safe) */ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, struct bpf_reg_state *rcur, struct bpf_id_pair *idmap) { bool equal; if (!(rold->live & REG_LIVE_READ)) /* explored state didn't use this */ return true; equal = memcmp(rold, rcur, offsetof(struct bpf_reg_state, parent)) == 0; if (rold->type == PTR_TO_STACK) /* two stack pointers are equal only if they're pointing to * the same stack frame, since fp-8 in foo != fp-8 in bar */ return equal && rold->frameno == rcur->frameno; if (equal) return true; if (rold->type == NOT_INIT) /* explored state can't have used this */ return true; if (rcur->type == NOT_INIT) return false; switch (base_type(rold->type)) { case SCALAR_VALUE: if (env->explore_alu_limits) return false; if (rcur->type == SCALAR_VALUE) { if (!rold->precise) return true; /* new val must satisfy old val knowledge */ return range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off); } else { /* We're trying to use a pointer in place of a scalar. * Even if the scalar was unbounded, this could lead to * pointer leaks because scalars are allowed to leak * while pointers are not. We could make this safe in * special cases if root is calling us, but it's * probably not worth the hassle. */ return false; } case PTR_TO_MAP_KEY: case PTR_TO_MAP_VALUE: /* a PTR_TO_MAP_VALUE could be safe to use as a * PTR_TO_MAP_VALUE_OR_NULL into the same map. * However, if the old PTR_TO_MAP_VALUE_OR_NULL then got NULL- * checked, doing so could have affected others with the same * id, and we can't check for that because we lost the id when * we converted to a PTR_TO_MAP_VALUE. */ if (type_may_be_null(rold->type)) { if (!type_may_be_null(rcur->type)) return false; if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, id))) return false; /* Check our ids match any regs they're supposed to */ return check_ids(rold->id, rcur->id, idmap); } /* If the new min/max/var_off satisfy the old ones and * everything else matches, we are OK. * 'id' is not compared, since it's only used for maps with * bpf_spin_lock inside map element and in such cases if * the rest of the prog is valid for one map element then * it's valid for all map elements regardless of the key * used in bpf_map_lookup() */ return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 && range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off); case PTR_TO_PACKET_META: case PTR_TO_PACKET: if (rcur->type != rold->type) return false; /* We must have at least as much range as the old ptr * did, so that any accesses which were safe before are * still safe. This is true even if old range < old off, * since someone could have accessed through (ptr - k), or * even done ptr -= k in a register, to get a safe access. */ if (rold->range > rcur->range) return false; /* If the offsets don't match, we can't trust our alignment; * nor can we be sure that we won't fall out of range. */ if (rold->off != rcur->off) return false; /* id relations must be preserved */ if (rold->id && !check_ids(rold->id, rcur->id, idmap)) return false; /* new val must satisfy old val knowledge */ return range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off); case PTR_TO_CTX: case CONST_PTR_TO_MAP: case PTR_TO_PACKET_END: case PTR_TO_FLOW_KEYS: case PTR_TO_SOCKET: case PTR_TO_SOCK_COMMON: case PTR_TO_TCP_SOCK: case PTR_TO_XDP_SOCK: /* Only valid matches are exact, which memcmp() above * would have accepted */ default: /* Don't know what's going on, just say it's not safe */ return false; } /* Shouldn't get here; if we do, say it's not safe */ WARN_ON_ONCE(1); return false; } static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, struct bpf_func_state *cur, struct bpf_id_pair *idmap) { int i, spi; /* walk slots of the explored stack and ignore any additional * slots in the current stack, since explored(safe) state * didn't use them */ for (i = 0; i < old->allocated_stack; i++) { spi = i / BPF_REG_SIZE; if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ)) { i += BPF_REG_SIZE - 1; /* explored state didn't use this */ continue; } if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID) continue; if (env->allow_uninit_stack && old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_MISC) continue; /* explored stack has more populated slots than current stack * and these slots were used */ if (i >= cur->allocated_stack) return false; /* if old state was safe with misc data in the stack * it will be safe with zero-initialized stack. * The opposite is not true */ if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_MISC && cur->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_ZERO) continue; if (old->stack[spi].slot_type[i % BPF_REG_SIZE] != cur->stack[spi].slot_type[i % BPF_REG_SIZE]) /* Ex: old explored (safe) state has STACK_SPILL in * this stack slot, but current has STACK_MISC -> * this verifier states are not equivalent, * return false to continue verification of this path */ return false; if (i % BPF_REG_SIZE != BPF_REG_SIZE - 1) continue; if (!is_spilled_reg(&old->stack[spi])) continue; if (!regsafe(env, &old->stack[spi].spilled_ptr, &cur->stack[spi].spilled_ptr, idmap)) /* when explored and current stack slot are both storing * spilled registers, check that stored pointers types * are the same as well. * Ex: explored safe path could have stored * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -8} * but current path has stored: * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -16} * such verifier states are not equivalent. * return false to continue verification of this path */ return false; } return true; } static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur) { if (old->acquired_refs != cur->acquired_refs) return false; return !memcmp(old->refs, cur->refs, sizeof(*old->refs) * old->acquired_refs); } /* compare two verifier states * * all states stored in state_list are known to be valid, since * verifier reached 'bpf_exit' instruction through them * * this function is called when verifier exploring different branches of * execution popped from the state stack. If it sees an old state that has * more strict register state and more strict stack state then this execution * branch doesn't need to be explored further, since verifier already * concluded that more strict state leads to valid finish. * * Therefore two states are equivalent if register state is more conservative * and explored stack state is more conservative than the current one. * Example: * explored current * (slot1=INV slot2=MISC) == (slot1=MISC slot2=MISC) * (slot1=MISC slot2=MISC) != (slot1=INV slot2=MISC) * * In other words if current stack state (one being explored) has more * valid slots than old one that already passed validation, it means * the verifier can stop exploring and conclude that current state is valid too * * Similarly with registers. If explored state has register type as invalid * whereas register type in current state is meaningful, it means that * the current state will reach 'bpf_exit' instruction safely */ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_state *old, struct bpf_func_state *cur) { int i; memset(env->idmap_scratch, 0, sizeof(env->idmap_scratch)); for (i = 0; i < MAX_BPF_REG; i++) if (!regsafe(env, &old->regs[i], &cur->regs[i], env->idmap_scratch)) return false; if (!stacksafe(env, old, cur, env->idmap_scratch)) return false; if (!refsafe(old, cur)) return false; return true; } static bool states_equal(struct bpf_verifier_env *env, struct bpf_verifier_state *old, struct bpf_verifier_state *cur) { int i; if (old->curframe != cur->curframe) return false; /* Verification state from speculative execution simulation * must never prune a non-speculative execution one. */ if (old->speculative && !cur->speculative) return false; if (old->active_spin_lock != cur->active_spin_lock) return false; /* for states to be equal callsites have to be the same * and all frame states need to be equivalent */ for (i = 0; i <= old->curframe; i++) { if (old->frame[i]->callsite != cur->frame[i]->callsite) return false; if (!func_states_equal(env, old->frame[i], cur->frame[i])) return false; } return true; } /* Return 0 if no propagation happened. Return negative error code if error * happened. Otherwise, return the propagated bit. */ static int propagate_liveness_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, struct bpf_reg_state *parent_reg) { u8 parent_flag = parent_reg->live & REG_LIVE_READ; u8 flag = reg->live & REG_LIVE_READ; int err; /* When comes here, read flags of PARENT_REG or REG could be any of * REG_LIVE_READ64, REG_LIVE_READ32, REG_LIVE_NONE. There is no need * of propagation if PARENT_REG has strongest REG_LIVE_READ64. */ if (parent_flag == REG_LIVE_READ64 || /* Or if there is no read flag from REG. */ !flag || /* Or if the read flag from REG is the same as PARENT_REG. */ parent_flag == flag) return 0; err = mark_reg_read(env, reg, parent_reg, flag); if (err) return err; return flag; } /* A write screens off any subsequent reads; but write marks come from the * straight-line code between a state and its parent. When we arrive at an * equivalent state (jump target or such) we didn't arrive by the straight-line * code, so read marks in the state must propagate to the parent regardless * of the state's write marks. That's what 'parent == state->parent' comparison * in mark_reg_read() is for. */ static int propagate_liveness(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, struct bpf_verifier_state *vparent) { struct bpf_reg_state *state_reg, *parent_reg; struct bpf_func_state *state, *parent; int i, frame, err = 0; if (vparent->curframe != vstate->curframe) { WARN(1, "propagate_live: parent frame %d current frame %d\n", vparent->curframe, vstate->curframe); return -EFAULT; } /* Propagate read liveness of registers... */ BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG); for (frame = 0; frame <= vstate->curframe; frame++) { parent = vparent->frame[frame]; state = vstate->frame[frame]; parent_reg = parent->regs; state_reg = state->regs; /* We don't need to worry about FP liveness, it's read-only */ for (i = frame < vstate->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++) { err = propagate_liveness_reg(env, &state_reg[i], &parent_reg[i]); if (err < 0) return err; if (err == REG_LIVE_READ64) mark_insn_zext(env, &parent_reg[i]); } /* Propagate stack slots. */ for (i = 0; i < state->allocated_stack / BPF_REG_SIZE && i < parent->allocated_stack / BPF_REG_SIZE; i++) { parent_reg = &parent->stack[i].spilled_ptr; state_reg = &state->stack[i].spilled_ptr; err = propagate_liveness_reg(env, state_reg, parent_reg); if (err < 0) return err; } } return 0; } /* find precise scalars in the previous equivalent state and * propagate them into the current state */ static int propagate_precision(struct bpf_verifier_env *env, const struct bpf_verifier_state *old) { struct bpf_reg_state *state_reg; struct bpf_func_state *state; int i, err = 0, fr; for (fr = old->curframe; fr >= 0; fr--) { state = old->frame[fr]; state_reg = state->regs; for (i = 0; i < BPF_REG_FP; i++, state_reg++) { if (state_reg->type != SCALAR_VALUE || !state_reg->precise || !(state_reg->live & REG_LIVE_READ)) continue; if (env->log.level & BPF_LOG_LEVEL2) verbose(env, "frame %d: propagating r%d\n", fr, i); err = mark_chain_precision_frame(env, fr, i); if (err < 0) return err; } for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { if (!is_spilled_reg(&state->stack[i])) continue; state_reg = &state->stack[i].spilled_ptr; if (state_reg->type != SCALAR_VALUE || !state_reg->precise || !(state_reg->live & REG_LIVE_READ)) continue; if (env->log.level & BPF_LOG_LEVEL2) verbose(env, "frame %d: propagating fp%d\n", fr, (-i - 1) * BPF_REG_SIZE); err = mark_chain_precision_stack_frame(env, fr, i); if (err < 0) return err; } } return 0; } static bool states_maybe_looping(struct bpf_verifier_state *old, struct bpf_verifier_state *cur) { struct bpf_func_state *fold, *fcur; int i, fr = cur->curframe; if (old->curframe != fr) return false; fold = old->frame[fr]; fcur = cur->frame[fr]; for (i = 0; i < MAX_BPF_REG; i++) if (memcmp(&fold->regs[i], &fcur->regs[i], offsetof(struct bpf_reg_state, parent))) return false; return true; } static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) { struct bpf_verifier_state_list *new_sl; struct bpf_verifier_state_list *sl, **pprev; struct bpf_verifier_state *cur = env->cur_state, *new; int i, j, err, states_cnt = 0; bool add_new_state = env->test_state_freq ? true : false; cur->last_insn_idx = env->prev_insn_idx; if (!env->insn_aux_data[insn_idx].prune_point) /* this 'insn_idx' instruction wasn't marked, so we will not * be doing state search here */ return 0; /* bpf progs typically have pruning point every 4 instructions * http://vger.kernel.org/bpfconf2019.html#session-1 * Do not add new state for future pruning if the verifier hasn't seen * at least 2 jumps and at least 8 instructions. * This heuristics helps decrease 'total_states' and 'peak_states' metric. * In tests that amounts to up to 50% reduction into total verifier * memory consumption and 20% verifier time speedup. */ if (env->jmps_processed - env->prev_jmps_processed >= 2 && env->insn_processed - env->prev_insn_processed >= 8) add_new_state = true; pprev = explored_state(env, insn_idx); sl = *pprev; clean_live_states(env, insn_idx, cur); while (sl) { states_cnt++; if (sl->state.insn_idx != insn_idx) goto next; if (sl->state.branches) { struct bpf_func_state *frame = sl->state.frame[sl->state.curframe]; if (frame->in_async_callback_fn && frame->async_entry_cnt != cur->frame[cur->curframe]->async_entry_cnt) { /* Different async_entry_cnt means that the verifier is * processing another entry into async callback. * Seeing the same state is not an indication of infinite * loop or infinite recursion. * But finding the same state doesn't mean that it's safe * to stop processing the current state. The previous state * hasn't yet reached bpf_exit, since state.branches > 0. * Checking in_async_callback_fn alone is not enough either. * Since the verifier still needs to catch infinite loops * inside async callbacks. */ } else if (states_maybe_looping(&sl->state, cur) && states_equal(env, &sl->state, cur)) { verbose_linfo(env, insn_idx, "; "); verbose(env, "infinite loop detected at insn %d\n", insn_idx); return -EINVAL; } /* if the verifier is processing a loop, avoid adding new state * too often, since different loop iterations have distinct * states and may not help future pruning. * This threshold shouldn't be too low to make sure that * a loop with large bound will be rejected quickly. * The most abusive loop will be: * r1 += 1 * if r1 < 1000000 goto pc-2 * 1M insn_procssed limit / 100 == 10k peak states. * This threshold shouldn't be too high either, since states * at the end of the loop are likely to be useful in pruning. */ if (env->jmps_processed - env->prev_jmps_processed < 20 && env->insn_processed - env->prev_insn_processed < 100) add_new_state = false; goto miss; } if (states_equal(env, &sl->state, cur)) { sl->hit_cnt++; /* reached equivalent register/stack state, * prune the search. * Registers read by the continuation are read by us. * If we have any write marks in env->cur_state, they * will prevent corresponding reads in the continuation * from reaching our parent (an explored_state). Our * own state will get the read marks recorded, but * they'll be immediately forgotten as we're pruning * this state and will pop a new one. */ err = propagate_liveness(env, &sl->state, cur); /* if previous state reached the exit with precision and * current state is equivalent to it (except precsion marks) * the precision needs to be propagated back in * the current state. */ err = err ? : push_jmp_history(env, cur); err = err ? : propagate_precision(env, &sl->state); if (err) return err; return 1; } miss: /* when new state is not going to be added do not increase miss count. * Otherwise several loop iterations will remove the state * recorded earlier. The goal of these heuristics is to have * states from some iterations of the loop (some in the beginning * and some at the end) to help pruning. */ if (add_new_state) sl->miss_cnt++; /* heuristic to determine whether this state is beneficial * to keep checking from state equivalence point of view. * Higher numbers increase max_states_per_insn and verification time, * but do not meaningfully decrease insn_processed. */ if (sl->miss_cnt > sl->hit_cnt * 3 + 3) { /* the state is unlikely to be useful. Remove it to * speed up verification */ *pprev = sl->next; if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE) { u32 br = sl->state.branches; WARN_ONCE(br, "BUG live_done but branches_to_explore %d\n", br); free_verifier_state(&sl->state, false); kfree(sl); env->peak_states--; } else { /* cannot free this state, since parentage chain may * walk it later. Add it for free_list instead to * be freed at the end of verification */ sl->next = env->free_list; env->free_list = sl; } sl = *pprev; continue; } next: pprev = &sl->next; sl = *pprev; } if (env->max_states_per_insn < states_cnt) env->max_states_per_insn = states_cnt; if (!env->bpf_capable && states_cnt > BPF_COMPLEXITY_LIMIT_STATES) return push_jmp_history(env, cur); if (!add_new_state) return push_jmp_history(env, cur); /* There were no equivalent states, remember the current one. * Technically the current state is not proven to be safe yet, * but it will either reach outer most bpf_exit (which means it's safe) * or it will be rejected. When there are no loops the verifier won't be * seeing this tuple (frame[0].callsite, frame[1].callsite, .. insn_idx) * again on the way to bpf_exit. * When looping the sl->state.branches will be > 0 and this state * will not be considered for equivalence until branches == 0. */ new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL); if (!new_sl) return -ENOMEM; env->total_states++; env->peak_states++; env->prev_jmps_processed = env->jmps_processed; env->prev_insn_processed = env->insn_processed; /* forget precise markings we inherited, see __mark_chain_precision */ if (env->bpf_capable) mark_all_scalars_imprecise(env, cur); /* add new state to the head of linked list */ new = &new_sl->state; err = copy_verifier_state(new, cur); if (err) { free_verifier_state(new, false); kfree(new_sl); return err; } new->insn_idx = insn_idx; WARN_ONCE(new->branches != 1, "BUG is_state_visited:branches_to_explore=%d insn %d\n", new->branches, insn_idx); cur->parent = new; cur->first_insn_idx = insn_idx; clear_jmp_history(cur); new_sl->next = *explored_state(env, insn_idx); *explored_state(env, insn_idx) = new_sl; /* connect new state to parentage chain. Current frame needs all * registers connected. Only r6 - r9 of the callers are alive (pushed * to the stack implicitly by JITs) so in callers' frames connect just * r6 - r9 as an optimization. Callers will have r1 - r5 connected to * the state of the call instruction (with WRITTEN set), and r0 comes * from callee with its full parentage chain, anyway. */ /* clear write marks in current state: the writes we did are not writes * our child did, so they don't screen off its reads from us. * (There are no read marks in current state, because reads always mark * their parent and current state never has children yet. Only * explored_states can get read marks.) */ for (j = 0; j <= cur->curframe; j++) { for (i = j < cur->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++) cur->frame[j]->regs[i].parent = &new->frame[j]->regs[i]; for (i = 0; i < BPF_REG_FP; i++) cur->frame[j]->regs[i].live = REG_LIVE_NONE; } /* all stack frames are accessible from callee, clear them all */ for (j = 0; j <= cur->curframe; j++) { struct bpf_func_state *frame = cur->frame[j]; struct bpf_func_state *newframe = new->frame[j]; for (i = 0; i < frame->allocated_stack / BPF_REG_SIZE; i++) { frame->stack[i].spilled_ptr.live = REG_LIVE_NONE; frame->stack[i].spilled_ptr.parent = &newframe->stack[i].spilled_ptr; } } return 0; } /* Return true if it's OK to have the same insn return a different type. */ static bool reg_type_mismatch_ok(enum bpf_reg_type type) { switch (base_type(type)) { case PTR_TO_CTX: case PTR_TO_SOCKET: case PTR_TO_SOCK_COMMON: case PTR_TO_TCP_SOCK: case PTR_TO_XDP_SOCK: case PTR_TO_BTF_ID: return false; default: return true; } } /* If an instruction was previously used with particular pointer types, then we * need to be careful to avoid cases such as the below, where it may be ok * for one branch accessing the pointer, but not ok for the other branch: * * R1 = sock_ptr * goto X; * ... * R1 = some_other_valid_ptr; * goto X; * ... * R2 = *(u32 *)(R1 + 0); */ static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev) { return src != prev && (!reg_type_mismatch_ok(src) || !reg_type_mismatch_ok(prev)); } static int do_check(struct bpf_verifier_env *env) { bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); struct bpf_verifier_state *state = env->cur_state; struct bpf_insn *insns = env->prog->insnsi; struct bpf_reg_state *regs; int insn_cnt = env->prog->len; bool do_print_state = false; int prev_insn_idx = -1; for (;;) { struct bpf_insn *insn; u8 class; int err; env->prev_insn_idx = prev_insn_idx; if (env->insn_idx >= insn_cnt) { verbose(env, "invalid insn idx %d insn_cnt %d\n", env->insn_idx, insn_cnt); return -EFAULT; } insn = &insns[env->insn_idx]; class = BPF_CLASS(insn->code); if (++env->insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) { verbose(env, "BPF program is too large. Processed %d insn\n", env->insn_processed); return -E2BIG; } err = is_state_visited(env, env->insn_idx); if (err < 0) return err; if (err == 1) { /* found equivalent state, can prune the search */ if (env->log.level & BPF_LOG_LEVEL) { if (do_print_state) verbose(env, "\nfrom %d to %d%s: safe\n", env->prev_insn_idx, env->insn_idx, env->cur_state->speculative ? " (speculative execution)" : ""); else verbose(env, "%d: safe\n", env->insn_idx); } goto process_bpf_exit; } if (signal_pending(current)) return -EAGAIN; if (need_resched()) cond_resched(); if (env->log.level & BPF_LOG_LEVEL2 && do_print_state) { verbose(env, "\nfrom %d to %d%s:", env->prev_insn_idx, env->insn_idx, env->cur_state->speculative ? " (speculative execution)" : ""); print_verifier_state(env, state->frame[state->curframe], true); do_print_state = false; } if (env->log.level & BPF_LOG_LEVEL) { const struct bpf_insn_cbs cbs = { .cb_call = disasm_kfunc_name, .cb_print = verbose, .private_data = env, }; if (verifier_state_scratched(env)) print_insn_state(env, state->frame[state->curframe]); verbose_linfo(env, env->insn_idx, "; "); env->prev_log_len = env->log.len_used; verbose(env, "%d: ", env->insn_idx); print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); env->prev_insn_print_len = env->log.len_used - env->prev_log_len; env->prev_log_len = env->log.len_used; } if (bpf_prog_is_dev_bound(env->prog->aux)) { err = bpf_prog_offload_verify_insn(env, env->insn_idx, env->prev_insn_idx); if (err) return err; } regs = cur_regs(env); sanitize_mark_insn_seen(env); prev_insn_idx = env->insn_idx; if (class == BPF_ALU || class == BPF_ALU64) { err = check_alu_op(env, insn); if (err) return err; } else if (class == BPF_LDX) { enum bpf_reg_type *prev_src_type, src_reg_type; /* check for reserved fields is already done */ /* check src operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK); if (err) return err; src_reg_type = regs[insn->src_reg].type; /* check that memory (src_reg + off) is readable, * the state of dst_reg will be updated by this func */ err = check_mem_access(env, env->insn_idx, insn->src_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, insn->dst_reg, false); if (err) return err; prev_src_type = &env->insn_aux_data[env->insn_idx].ptr_type; if (*prev_src_type == NOT_INIT) { /* saw a valid insn * dst_reg = *(u32 *)(src_reg + off) * save type to validate intersecting paths */ *prev_src_type = src_reg_type; } else if (reg_type_mismatch(src_reg_type, *prev_src_type)) { /* ABuser program is trying to use the same insn * dst_reg = *(u32*) (src_reg + off) * with different pointer types: * src_reg == ctx in one branch and * src_reg == stack|map in some other branch. * Reject it. */ verbose(env, "same insn cannot be used with different pointers\n"); return -EINVAL; } } else if (class == BPF_STX) { enum bpf_reg_type *prev_dst_type, dst_reg_type; if (BPF_MODE(insn->code) == BPF_ATOMIC) { err = check_atomic(env, env->insn_idx, insn); if (err) return err; env->insn_idx++; continue; } if (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0) { verbose(env, "BPF_STX uses reserved fields\n"); return -EINVAL; } /* check src1 operand */ err = check_reg_arg(env, insn->src_reg, SRC_OP); if (err) return err; /* check src2 operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; dst_reg_type = regs[insn->dst_reg].type; /* check that memory (dst_reg + off) is writeable */ err = check_mem_access(env, env->insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, insn->src_reg, false); if (err) return err; prev_dst_type = &env->insn_aux_data[env->insn_idx].ptr_type; if (*prev_dst_type == NOT_INIT) { *prev_dst_type = dst_reg_type; } else if (reg_type_mismatch(dst_reg_type, *prev_dst_type)) { verbose(env, "same insn cannot be used with different pointers\n"); return -EINVAL; } } else if (class == BPF_ST) { if (BPF_MODE(insn->code) != BPF_MEM || insn->src_reg != BPF_REG_0) { verbose(env, "BPF_ST uses reserved fields\n"); return -EINVAL; } /* check src operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) return err; if (is_ctx_reg(env, insn->dst_reg)) { verbose(env, "BPF_ST stores into R%d %s is not allowed\n", insn->dst_reg, reg_type_str(env, reg_state(env, insn->dst_reg)->type)); return -EACCES; } /* check that memory (dst_reg + off) is writeable */ err = check_mem_access(env, env->insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, -1, false); if (err) return err; } else if (class == BPF_JMP || class == BPF_JMP32) { u8 opcode = BPF_OP(insn->code); env->jmps_processed++; if (opcode == BPF_CALL) { if (BPF_SRC(insn->code) != BPF_K || (insn->src_reg != BPF_PSEUDO_KFUNC_CALL && insn->off != 0) || (insn->src_reg != BPF_REG_0 && insn->src_reg != BPF_PSEUDO_CALL && insn->src_reg != BPF_PSEUDO_KFUNC_CALL) || insn->dst_reg != BPF_REG_0 || class == BPF_JMP32) { verbose(env, "BPF_CALL uses reserved fields\n"); return -EINVAL; } if (env->cur_state->active_spin_lock && (insn->src_reg == BPF_PSEUDO_CALL || insn->imm != BPF_FUNC_spin_unlock)) { verbose(env, "function calls are not allowed while holding a lock\n"); return -EINVAL; } if (insn->src_reg == BPF_PSEUDO_CALL) err = check_func_call(env, insn, &env->insn_idx); else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) err = check_kfunc_call(env, insn, &env->insn_idx); else err = check_helper_call(env, insn, &env->insn_idx); if (err) return err; } else if (opcode == BPF_JA) { if (BPF_SRC(insn->code) != BPF_K || insn->imm != 0 || insn->src_reg != BPF_REG_0 || insn->dst_reg != BPF_REG_0 || class == BPF_JMP32) { verbose(env, "BPF_JA uses reserved fields\n"); return -EINVAL; } env->insn_idx += insn->off + 1; continue; } else if (opcode == BPF_EXIT) { if (BPF_SRC(insn->code) != BPF_K || insn->imm != 0 || insn->src_reg != BPF_REG_0 || insn->dst_reg != BPF_REG_0 || class == BPF_JMP32) { verbose(env, "BPF_EXIT uses reserved fields\n"); return -EINVAL; } if (env->cur_state->active_spin_lock) { verbose(env, "bpf_spin_unlock is missing\n"); return -EINVAL; } /* We must do check_reference_leak here before * prepare_func_exit to handle the case when * state->curframe > 0, it may be a callback * function, for which reference_state must * match caller reference state when it exits. */ err = check_reference_leak(env); if (err) return err; if (state->curframe) { /* exit from nested function */ err = prepare_func_exit(env, &env->insn_idx); if (err) return err; do_print_state = true; continue; } err = check_return_code(env); if (err) return err; process_bpf_exit: mark_verifier_state_scratched(env); update_branch_counts(env, env->cur_state); err = pop_stack(env, &prev_insn_idx, &env->insn_idx, pop_log); if (err < 0) { if (err != -ENOENT) return err; break; } else { do_print_state = true; continue; } } else { err = check_cond_jmp_op(env, insn, &env->insn_idx); if (err) return err; } } else if (class == BPF_LD) { u8 mode = BPF_MODE(insn->code); if (mode == BPF_ABS || mode == BPF_IND) { err = check_ld_abs(env, insn); if (err) return err; } else if (mode == BPF_IMM) { err = check_ld_imm(env, insn); if (err) return err; env->insn_idx++; sanitize_mark_insn_seen(env); } else { verbose(env, "invalid BPF_LD mode\n"); return -EINVAL; } } else { verbose(env, "unknown insn class %d\n", class); return -EINVAL; } env->insn_idx++; } return 0; } static int find_btf_percpu_datasec(struct btf *btf) { const struct btf_type *t; const char *tname; int i, n; /* * Both vmlinux and module each have their own ".data..percpu" * DATASECs in BTF. So for module's case, we need to skip vmlinux BTF * types to look at only module's own BTF types. */ n = btf_nr_types(btf); if (btf_is_module(btf)) i = btf_nr_types(btf_vmlinux); else i = 1; for(; i < n; i++) { t = btf_type_by_id(btf, i); if (BTF_INFO_KIND(t->info) != BTF_KIND_DATASEC) continue; tname = btf_name_by_offset(btf, t->name_off); if (!strcmp(tname, ".data..percpu")) return i; } return -ENOENT; } /* replace pseudo btf_id with kernel symbol address */ static int check_pseudo_btf_id(struct bpf_verifier_env *env, struct bpf_insn *insn, struct bpf_insn_aux_data *aux) { const struct btf_var_secinfo *vsi; const struct btf_type *datasec; struct btf_mod_pair *btf_mod; const struct btf_type *t; const char *sym_name; bool percpu = false; u32 type, id = insn->imm; struct btf *btf; s32 datasec_id; u64 addr; int i, btf_fd, err; btf_fd = insn[1].imm; if (btf_fd) { btf = btf_get_by_fd(btf_fd); if (IS_ERR(btf)) { verbose(env, "invalid module BTF object FD specified.\n"); return -EINVAL; } } else { if (!btf_vmlinux) { verbose(env, "kernel is missing BTF, make sure CONFIG_DEBUG_INFO_BTF=y is specified in Kconfig.\n"); return -EINVAL; } btf = btf_vmlinux; btf_get(btf); } t = btf_type_by_id(btf, id); if (!t) { verbose(env, "ldimm64 insn specifies invalid btf_id %d.\n", id); err = -ENOENT; goto err_put; } if (!btf_type_is_var(t)) { verbose(env, "pseudo btf_id %d in ldimm64 isn't KIND_VAR.\n", id); err = -EINVAL; goto err_put; } sym_name = btf_name_by_offset(btf, t->name_off); addr = kallsyms_lookup_name(sym_name); if (!addr) { verbose(env, "ldimm64 failed to find the address for kernel symbol '%s'.\n", sym_name); err = -ENOENT; goto err_put; } datasec_id = find_btf_percpu_datasec(btf); if (datasec_id > 0) { datasec = btf_type_by_id(btf, datasec_id); for_each_vsi(i, datasec, vsi) { if (vsi->type == id) { percpu = true; break; } } } insn[0].imm = (u32)addr; insn[1].imm = addr >> 32; type = t->type; t = btf_type_skip_modifiers(btf, type, NULL); if (percpu) { aux->btf_var.reg_type = PTR_TO_BTF_ID | MEM_PERCPU; aux->btf_var.btf = btf; aux->btf_var.btf_id = type; } else if (!btf_type_is_struct(t)) { const struct btf_type *ret; const char *tname; u32 tsize; /* resolve the type size of ksym. */ ret = btf_resolve_size(btf, t, &tsize); if (IS_ERR(ret)) { tname = btf_name_by_offset(btf, t->name_off); verbose(env, "ldimm64 unable to resolve the size of type '%s': %ld\n", tname, PTR_ERR(ret)); err = -EINVAL; goto err_put; } aux->btf_var.reg_type = PTR_TO_MEM | MEM_RDONLY; aux->btf_var.mem_size = tsize; } else { aux->btf_var.reg_type = PTR_TO_BTF_ID; aux->btf_var.btf = btf; aux->btf_var.btf_id = type; } /* check whether we recorded this BTF (and maybe module) already */ for (i = 0; i < env->used_btf_cnt; i++) { if (env->used_btfs[i].btf == btf) { btf_put(btf); return 0; } } if (env->used_btf_cnt >= MAX_USED_BTFS) { err = -E2BIG; goto err_put; } btf_mod = &env->used_btfs[env->used_btf_cnt]; btf_mod->btf = btf; btf_mod->module = NULL; /* if we reference variables from kernel module, bump its refcount */ if (btf_is_module(btf)) { btf_mod->module = btf_try_get_module(btf); if (!btf_mod->module) { err = -ENXIO; goto err_put; } } env->used_btf_cnt++; return 0; err_put: btf_put(btf); return err; } static bool is_tracing_prog_type(enum bpf_prog_type type) { switch (type) { case BPF_PROG_TYPE_KPROBE: case BPF_PROG_TYPE_TRACEPOINT: case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: return true; default: return false; } } static int check_map_prog_compatibility(struct bpf_verifier_env *env, struct bpf_map *map, struct bpf_prog *prog) { enum bpf_prog_type prog_type = resolve_prog_type(prog); if (map_value_has_spin_lock(map)) { if (prog_type == BPF_PROG_TYPE_SOCKET_FILTER) { verbose(env, "socket filter progs cannot use bpf_spin_lock yet\n"); return -EINVAL; } if (is_tracing_prog_type(prog_type)) { verbose(env, "tracing progs cannot use bpf_spin_lock yet\n"); return -EINVAL; } if (prog->aux->sleepable) { verbose(env, "sleepable progs cannot use bpf_spin_lock yet\n"); return -EINVAL; } } if (map_value_has_timer(map)) { if (is_tracing_prog_type(prog_type)) { verbose(env, "tracing progs cannot use bpf_timer yet\n"); return -EINVAL; } } if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) && !bpf_offload_prog_map_match(prog, map)) { verbose(env, "offload device mismatch between prog and map\n"); return -EINVAL; } if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { verbose(env, "bpf_struct_ops map cannot be used in prog\n"); return -EINVAL; } if (prog->aux->sleepable) switch (map->map_type) { case BPF_MAP_TYPE_HASH: case BPF_MAP_TYPE_LRU_HASH: case BPF_MAP_TYPE_ARRAY: case BPF_MAP_TYPE_PERCPU_HASH: case BPF_MAP_TYPE_PERCPU_ARRAY: case BPF_MAP_TYPE_LRU_PERCPU_HASH: case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH_OF_MAPS: case BPF_MAP_TYPE_RINGBUF: case BPF_MAP_TYPE_USER_RINGBUF: case BPF_MAP_TYPE_INODE_STORAGE: case BPF_MAP_TYPE_SK_STORAGE: case BPF_MAP_TYPE_TASK_STORAGE: break; default: verbose(env, "Sleepable programs can only use array, hash, and ringbuf maps\n"); return -EINVAL; } return 0; } static bool bpf_map_is_cgroup_storage(struct bpf_map *map) { return (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE || map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE); } /* find and rewrite pseudo imm in ld_imm64 instructions: * * 1. if it accesses map FD, replace it with actual map pointer. * 2. if it accesses btf_id of a VAR, replace it with pointer to the var. * * NOTE: btf_vmlinux is required for converting pseudo btf_id. */ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) { struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; int i, j, err; err = bpf_prog_calc_tag(env->prog); if (err) return err; for (i = 0; i < insn_cnt; i++, insn++) { if (BPF_CLASS(insn->code) == BPF_LDX && (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) { verbose(env, "BPF_LDX uses reserved fields\n"); return -EINVAL; } if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) { struct bpf_insn_aux_data *aux; struct bpf_map *map; struct fd f; u64 addr; u32 fd; if (i == insn_cnt - 1 || insn[1].code != 0 || insn[1].dst_reg != 0 || insn[1].src_reg != 0 || insn[1].off != 0) { verbose(env, "invalid bpf_ld_imm64 insn\n"); return -EINVAL; } if (insn[0].src_reg == 0) /* valid generic load 64-bit imm */ goto next_insn; if (insn[0].src_reg == BPF_PSEUDO_BTF_ID) { aux = &env->insn_aux_data[i]; err = check_pseudo_btf_id(env, insn, aux); if (err) return err; goto next_insn; } if (insn[0].src_reg == BPF_PSEUDO_FUNC) { aux = &env->insn_aux_data[i]; aux->ptr_type = PTR_TO_FUNC; goto next_insn; } /* In final convert_pseudo_ld_imm64() step, this is * converted into regular 64-bit imm load insn. */ switch (insn[0].src_reg) { case BPF_PSEUDO_MAP_VALUE: case BPF_PSEUDO_MAP_IDX_VALUE: break; case BPF_PSEUDO_MAP_FD: case BPF_PSEUDO_MAP_IDX: if (insn[1].imm == 0) break; fallthrough; default: verbose(env, "unrecognized bpf_ld_imm64 insn\n"); return -EINVAL; } switch (insn[0].src_reg) { case BPF_PSEUDO_MAP_IDX_VALUE: case BPF_PSEUDO_MAP_IDX: if (bpfptr_is_null(env->fd_array)) { verbose(env, "fd_idx without fd_array is invalid\n"); return -EPROTO; } if (copy_from_bpfptr_offset(&fd, env->fd_array, insn[0].imm * sizeof(fd), sizeof(fd))) return -EFAULT; break; default: fd = insn[0].imm; break; } f = fdget(fd); map = __bpf_map_get(f); if (IS_ERR(map)) { verbose(env, "fd %d is not pointing to valid bpf_map\n", fd); return PTR_ERR(map); } err = check_map_prog_compatibility(env, map, env->prog); if (err) { fdput(f); return err; } aux = &env->insn_aux_data[i]; if (insn[0].src_reg == BPF_PSEUDO_MAP_FD || insn[0].src_reg == BPF_PSEUDO_MAP_IDX) { addr = (unsigned long)map; } else { u32 off = insn[1].imm; if (off >= BPF_MAX_VAR_OFF) { verbose(env, "direct value offset of %u is not allowed\n", off); fdput(f); return -EINVAL; } if (!map->ops->map_direct_value_addr) { verbose(env, "no direct value access support for this map type\n"); fdput(f); return -EINVAL; } err = map->ops->map_direct_value_addr(map, &addr, off); if (err) { verbose(env, "invalid access to map value pointer, value_size=%u off=%u\n", map->value_size, off); fdput(f); return err; } aux->map_off = off; addr += off; } insn[0].imm = (u32)addr; insn[1].imm = addr >> 32; /* check whether we recorded this map already */ for (j = 0; j < env->used_map_cnt; j++) { if (env->used_maps[j] == map) { aux->map_index = j; fdput(f); goto next_insn; } } if (env->used_map_cnt >= MAX_USED_MAPS) { fdput(f); return -E2BIG; } /* hold the map. If the program is rejected by verifier, * the map will be released by release_maps() or it * will be used by the valid program until it's unloaded * and all maps are released in free_used_maps() */ bpf_map_inc(map); aux->map_index = env->used_map_cnt; env->used_maps[env->used_map_cnt++] = map; if (bpf_map_is_cgroup_storage(map) && bpf_cgroup_storage_assign(env->prog->aux, map)) { verbose(env, "only one cgroup storage of each type is allowed\n"); fdput(f); return -EBUSY; } fdput(f); next_insn: insn++; i++; continue; } /* Basic sanity check before we invest more work here. */ if (!bpf_opcode_in_insntable(insn->code)) { verbose(env, "unknown opcode %02x\n", insn->code); return -EINVAL; } } /* now all pseudo BPF_LD_IMM64 instructions load valid * 'struct bpf_map *' into a register instead of user map_fd. * These pointers will be used later by verifier to validate map access. */ return 0; } /* drop refcnt of maps used by the rejected program */ static void release_maps(struct bpf_verifier_env *env) { __bpf_free_used_maps(env->prog->aux, env->used_maps, env->used_map_cnt); } /* drop refcnt of maps used by the rejected program */ static void release_btfs(struct bpf_verifier_env *env) { __bpf_free_used_btfs(env->prog->aux, env->used_btfs, env->used_btf_cnt); } /* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */ static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env) { struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; int i; for (i = 0; i < insn_cnt; i++, insn++) { if (insn->code != (BPF_LD | BPF_IMM | BPF_DW)) continue; if (insn->src_reg == BPF_PSEUDO_FUNC) continue; insn->src_reg = 0; } } /* single env->prog->insni[off] instruction was replaced with the range * insni[off, off + cnt). Adjust corresponding insn_aux_data by copying * [0, off) and [off, end) to new locations, so the patched range stays zero */ static void adjust_insn_aux_data(struct bpf_verifier_env *env, struct bpf_insn_aux_data *new_data, struct bpf_prog *new_prog, u32 off, u32 cnt) { struct bpf_insn_aux_data *old_data = env->insn_aux_data; struct bpf_insn *insn = new_prog->insnsi; u32 old_seen = old_data[off].seen; u32 prog_len; int i; /* aux info at OFF always needs adjustment, no matter fast path * (cnt == 1) is taken or not. There is no guarantee INSN at OFF is the * original insn at old prog. */ old_data[off].zext_dst = insn_has_def32(env, insn + off + cnt - 1); if (cnt == 1) return; prog_len = new_prog->len; memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off); memcpy(new_data + off + cnt - 1, old_data + off, sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1)); for (i = off; i < off + cnt - 1; i++) { /* Expand insni[off]'s seen count to the patched range. */ new_data[i].seen = old_seen; new_data[i].zext_dst = insn_has_def32(env, insn + i); } env->insn_aux_data = new_data; vfree(old_data); } static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len) { int i; if (len == 1) return; /* NOTE: fake 'exit' subprog should be updated as well. */ for (i = 0; i <= env->subprog_cnt; i++) { if (env->subprog_info[i].start <= off) continue; env->subprog_info[i].start += len - 1; } } static void adjust_poke_descs(struct bpf_prog *prog, u32 off, u32 len) { struct bpf_jit_poke_descriptor *tab = prog->aux->poke_tab; int i, sz = prog->aux->size_poke_tab; struct bpf_jit_poke_descriptor *desc; for (i = 0; i < sz; i++) { desc = &tab[i]; if (desc->insn_idx <= off) continue; desc->insn_idx += len - 1; } } static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off, const struct bpf_insn *patch, u32 len) { struct bpf_prog *new_prog; struct bpf_insn_aux_data *new_data = NULL; if (len > 1) { new_data = vzalloc(array_size(env->prog->len + len - 1, sizeof(struct bpf_insn_aux_data))); if (!new_data) return NULL; } new_prog = bpf_patch_insn_single(env->prog, off, patch, len); if (IS_ERR(new_prog)) { if (PTR_ERR(new_prog) == -ERANGE) verbose(env, "insn %d cannot be patched due to 16-bit range\n", env->insn_aux_data[off].orig_idx); vfree(new_data); return NULL; } adjust_insn_aux_data(env, new_data, new_prog, off, len); adjust_subprog_starts(env, off, len); adjust_poke_descs(new_prog, off, len); return new_prog; } static int adjust_subprog_starts_after_remove(struct bpf_verifier_env *env, u32 off, u32 cnt) { int i, j; /* find first prog starting at or after off (first to remove) */ for (i = 0; i < env->subprog_cnt; i++) if (env->subprog_info[i].start >= off) break; /* find first prog starting at or after off + cnt (first to stay) */ for (j = i; j < env->subprog_cnt; j++) if (env->subprog_info[j].start >= off + cnt) break; /* if j doesn't start exactly at off + cnt, we are just removing * the front of previous prog */ if (env->subprog_info[j].start != off + cnt) j--; if (j > i) { struct bpf_prog_aux *aux = env->prog->aux; int move; /* move fake 'exit' subprog as well */ move = env->subprog_cnt + 1 - j; memmove(env->subprog_info + i, env->subprog_info + j, sizeof(*env->subprog_info) * move); env->subprog_cnt -= j - i; /* remove func_info */ if (aux->func_info) { move = aux->func_info_cnt - j; memmove(aux->func_info + i, aux->func_info + j, sizeof(*aux->func_info) * move); aux->func_info_cnt -= j - i; /* func_info->insn_off is set after all code rewrites, * in adjust_btf_func() - no need to adjust */ } } else { /* convert i from "first prog to remove" to "first to adjust" */ if (env->subprog_info[i].start == off) i++; } /* update fake 'exit' subprog as well */ for (; i <= env->subprog_cnt; i++) env->subprog_info[i].start -= cnt; return 0; } static int bpf_adj_linfo_after_remove(struct bpf_verifier_env *env, u32 off, u32 cnt) { struct bpf_prog *prog = env->prog; u32 i, l_off, l_cnt, nr_linfo; struct bpf_line_info *linfo; nr_linfo = prog->aux->nr_linfo; if (!nr_linfo) return 0; linfo = prog->aux->linfo; /* find first line info to remove, count lines to be removed */ for (i = 0; i < nr_linfo; i++) if (linfo[i].insn_off >= off) break; l_off = i; l_cnt = 0; for (; i < nr_linfo; i++) if (linfo[i].insn_off < off + cnt) l_cnt++; else break; /* First live insn doesn't match first live linfo, it needs to "inherit" * last removed linfo. prog is already modified, so prog->len == off * means no live instructions after (tail of the program was removed). */ if (prog->len != off && l_cnt && (i == nr_linfo || linfo[i].insn_off != off + cnt)) { l_cnt--; linfo[--i].insn_off = off + cnt; } /* remove the line info which refer to the removed instructions */ if (l_cnt) { memmove(linfo + l_off, linfo + i, sizeof(*linfo) * (nr_linfo - i)); prog->aux->nr_linfo -= l_cnt; nr_linfo = prog->aux->nr_linfo; } /* pull all linfo[i].insn_off >= off + cnt in by cnt */ for (i = l_off; i < nr_linfo; i++) linfo[i].insn_off -= cnt; /* fix up all subprogs (incl. 'exit') which start >= off */ for (i = 0; i <= env->subprog_cnt; i++) if (env->subprog_info[i].linfo_idx > l_off) { /* program may have started in the removed region but * may not be fully removed */ if (env->subprog_info[i].linfo_idx >= l_off + l_cnt) env->subprog_info[i].linfo_idx -= l_cnt; else env->subprog_info[i].linfo_idx = l_off; } return 0; } static int verifier_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt) { struct bpf_insn_aux_data *aux_data = env->insn_aux_data; unsigned int orig_prog_len = env->prog->len; int err; if (bpf_prog_is_dev_bound(env->prog->aux)) bpf_prog_offload_remove_insns(env, off, cnt); err = bpf_remove_insns(env->prog, off, cnt); if (err) return err; err = adjust_subprog_starts_after_remove(env, off, cnt); if (err) return err; err = bpf_adj_linfo_after_remove(env, off, cnt); if (err) return err; memmove(aux_data + off, aux_data + off + cnt, sizeof(*aux_data) * (orig_prog_len - off - cnt)); return 0; } /* The verifier does more data flow analysis than llvm and will not * explore branches that are dead at run time. Malicious programs can * have dead code too. Therefore replace all dead at-run-time code * with 'ja -1'. * * Just nops are not optimal, e.g. if they would sit at the end of the * program and through another bug we would manage to jump there, then * we'd execute beyond program memory otherwise. Returning exception * code also wouldn't work since we can have subprogs where the dead * code could be located. */ static void sanitize_dead_code(struct bpf_verifier_env *env) { struct bpf_insn_aux_data *aux_data = env->insn_aux_data; struct bpf_insn trap = BPF_JMP_IMM(BPF_JA, 0, 0, -1); struct bpf_insn *insn = env->prog->insnsi; const int insn_cnt = env->prog->len; int i; for (i = 0; i < insn_cnt; i++) { if (aux_data[i].seen) continue; memcpy(insn + i, &trap, sizeof(trap)); aux_data[i].zext_dst = false; } } static bool insn_is_cond_jump(u8 code) { u8 op; if (BPF_CLASS(code) == BPF_JMP32) return true; if (BPF_CLASS(code) != BPF_JMP) return false; op = BPF_OP(code); return op != BPF_JA && op != BPF_EXIT && op != BPF_CALL; } static void opt_hard_wire_dead_code_branches(struct bpf_verifier_env *env) { struct bpf_insn_aux_data *aux_data = env->insn_aux_data; struct bpf_insn ja = BPF_JMP_IMM(BPF_JA, 0, 0, 0); struct bpf_insn *insn = env->prog->insnsi; const int insn_cnt = env->prog->len; int i; for (i = 0; i < insn_cnt; i++, insn++) { if (!insn_is_cond_jump(insn->code)) continue; if (!aux_data[i + 1].seen) ja.off = insn->off; else if (!aux_data[i + 1 + insn->off].seen) ja.off = 0; else continue; if (bpf_prog_is_dev_bound(env->prog->aux)) bpf_prog_offload_replace_insn(env, i, &ja); memcpy(insn, &ja, sizeof(ja)); } } static int opt_remove_dead_code(struct bpf_verifier_env *env) { struct bpf_insn_aux_data *aux_data = env->insn_aux_data; int insn_cnt = env->prog->len; int i, err; for (i = 0; i < insn_cnt; i++) { int j; j = 0; while (i + j < insn_cnt && !aux_data[i + j].seen) j++; if (!j) continue; err = verifier_remove_insns(env, i, j); if (err) return err; insn_cnt = env->prog->len; } return 0; } static int opt_remove_nops(struct bpf_verifier_env *env) { const struct bpf_insn ja = BPF_JMP_IMM(BPF_JA, 0, 0, 0); struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; int i, err; for (i = 0; i < insn_cnt; i++) { if (memcmp(&insn[i], &ja, sizeof(ja))) continue; err = verifier_remove_insns(env, i, 1); if (err) return err; insn_cnt--; i--; } return 0; } static int opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env, const union bpf_attr *attr) { struct bpf_insn *patch, zext_patch[2], rnd_hi32_patch[4]; struct bpf_insn_aux_data *aux = env->insn_aux_data; int i, patch_len, delta = 0, len = env->prog->len; struct bpf_insn *insns = env->prog->insnsi; struct bpf_prog *new_prog; bool rnd_hi32; rnd_hi32 = attr->prog_flags & BPF_F_TEST_RND_HI32; zext_patch[1] = BPF_ZEXT_REG(0); rnd_hi32_patch[1] = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, 0); rnd_hi32_patch[2] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_AX, 32); rnd_hi32_patch[3] = BPF_ALU64_REG(BPF_OR, 0, BPF_REG_AX); for (i = 0; i < len; i++) { int adj_idx = i + delta; struct bpf_insn insn; int load_reg; insn = insns[adj_idx]; load_reg = insn_def_regno(&insn); if (!aux[adj_idx].zext_dst) { u8 code, class; u32 imm_rnd; if (!rnd_hi32) continue; code = insn.code; class = BPF_CLASS(code); if (load_reg == -1) continue; /* NOTE: arg "reg" (the fourth one) is only used for * BPF_STX + SRC_OP, so it is safe to pass NULL * here. */ if (is_reg64(env, &insn, load_reg, NULL, DST_OP)) { if (class == BPF_LD && BPF_MODE(code) == BPF_IMM) i++; continue; } /* ctx load could be transformed into wider load. */ if (class == BPF_LDX && aux[adj_idx].ptr_type == PTR_TO_CTX) continue; imm_rnd = get_random_u32(); rnd_hi32_patch[0] = insn; rnd_hi32_patch[1].imm = imm_rnd; rnd_hi32_patch[3].dst_reg = load_reg; patch = rnd_hi32_patch; patch_len = 4; goto apply_patch_buffer; } /* Add in an zero-extend instruction if a) the JIT has requested * it or b) it's a CMPXCHG. * * The latter is because: BPF_CMPXCHG always loads a value into * R0, therefore always zero-extends. However some archs' * equivalent instruction only does this load when the * comparison is successful. This detail of CMPXCHG is * orthogonal to the general zero-extension behaviour of the * CPU, so it's treated independently of bpf_jit_needs_zext. */ if (!bpf_jit_needs_zext() && !is_cmpxchg_insn(&insn)) continue; /* Zero-extension is done by the caller. */ if (bpf_pseudo_kfunc_call(&insn)) continue; if (WARN_ON(load_reg == -1)) { verbose(env, "verifier bug. zext_dst is set, but no reg is defined\n"); return -EFAULT; } zext_patch[0] = insn; zext_patch[1].dst_reg = load_reg; zext_patch[1].src_reg = load_reg; patch = zext_patch; patch_len = 2; apply_patch_buffer: new_prog = bpf_patch_insn_data(env, adj_idx, patch, patch_len); if (!new_prog) return -ENOMEM; env->prog = new_prog; insns = new_prog->insnsi; aux = env->insn_aux_data; delta += patch_len - 1; } return 0; } /* convert load instructions that access fields of a context type into a * sequence of instructions that access fields of the underlying structure: * struct __sk_buff -> struct sk_buff * struct bpf_sock_ops -> struct sock */ static int convert_ctx_accesses(struct bpf_verifier_env *env) { const struct bpf_verifier_ops *ops = env->ops; int i, cnt, size, ctx_field_size, delta = 0; const int insn_cnt = env->prog->len; struct bpf_insn insn_buf[16], *insn; u32 target_size, size_default, off; struct bpf_prog *new_prog; enum bpf_access_type type; bool is_narrower_load; if (ops->gen_prologue || env->seen_direct_write) { if (!ops->gen_prologue) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } cnt = ops->gen_prologue(insn_buf, env->seen_direct_write, env->prog); if (cnt >= ARRAY_SIZE(insn_buf)) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } else if (cnt) { new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt); if (!new_prog) return -ENOMEM; env->prog = new_prog; delta += cnt - 1; } } if (bpf_prog_is_dev_bound(env->prog->aux)) return 0; insn = env->prog->insnsi + delta; for (i = 0; i < insn_cnt; i++, insn++) { bpf_convert_ctx_access_t convert_ctx_access; bool ctx_access; if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) || insn->code == (BPF_LDX | BPF_MEM | BPF_H) || insn->code == (BPF_LDX | BPF_MEM | BPF_W) || insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) { type = BPF_READ; ctx_access = true; } else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) || insn->code == (BPF_STX | BPF_MEM | BPF_H) || insn->code == (BPF_STX | BPF_MEM | BPF_W) || insn->code == (BPF_STX | BPF_MEM | BPF_DW) || insn->code == (BPF_ST | BPF_MEM | BPF_B) || insn->code == (BPF_ST | BPF_MEM | BPF_H) || insn->code == (BPF_ST | BPF_MEM | BPF_W) || insn->code == (BPF_ST | BPF_MEM | BPF_DW)) { type = BPF_WRITE; ctx_access = BPF_CLASS(insn->code) == BPF_STX; } else { continue; } if (type == BPF_WRITE && env->insn_aux_data[i + delta].sanitize_stack_spill) { struct bpf_insn patch[] = { *insn, BPF_ST_NOSPEC(), }; cnt = ARRAY_SIZE(patch); new_prog = bpf_patch_insn_data(env, i + delta, patch, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = new_prog; insn = new_prog->insnsi + i + delta; continue; } if (!ctx_access) continue; switch ((int)env->insn_aux_data[i + delta].ptr_type) { case PTR_TO_CTX: if (!ops->convert_ctx_access) continue; convert_ctx_access = ops->convert_ctx_access; break; case PTR_TO_SOCKET: case PTR_TO_SOCK_COMMON: convert_ctx_access = bpf_sock_convert_ctx_access; break; case PTR_TO_TCP_SOCK: convert_ctx_access = bpf_tcp_sock_convert_ctx_access; break; case PTR_TO_XDP_SOCK: convert_ctx_access = bpf_xdp_sock_convert_ctx_access; break; case PTR_TO_BTF_ID: case PTR_TO_BTF_ID | PTR_UNTRUSTED: if (type == BPF_READ) { insn->code = BPF_LDX | BPF_PROBE_MEM | BPF_SIZE((insn)->code); env->prog->aux->num_exentries++; } continue; default: continue; } ctx_field_size = env->insn_aux_data[i + delta].ctx_field_size; size = BPF_LDST_BYTES(insn); /* If the read access is a narrower load of the field, * convert to a 4/8-byte load, to minimum program type specific * convert_ctx_access changes. If conversion is successful, * we will apply proper mask to the result. */ is_narrower_load = size < ctx_field_size; size_default = bpf_ctx_off_adjust_machine(ctx_field_size); off = insn->off; if (is_narrower_load) { u8 size_code; if (type == BPF_WRITE) { verbose(env, "bpf verifier narrow ctx access misconfigured\n"); return -EINVAL; } size_code = BPF_H; if (ctx_field_size == 4) size_code = BPF_W; else if (ctx_field_size == 8) size_code = BPF_DW; insn->off = off & ~(size_default - 1); insn->code = BPF_LDX | BPF_MEM | size_code; } target_size = 0; cnt = convert_ctx_access(type, insn, insn_buf, env->prog, &target_size); if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf) || (ctx_field_size && !target_size)) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } if (is_narrower_load && size < target_size) { u8 shift = bpf_ctx_narrow_access_offset( off, size, size_default) * 8; if (shift && cnt + 1 >= ARRAY_SIZE(insn_buf)) { verbose(env, "bpf verifier narrow ctx load misconfigured\n"); return -EINVAL; } if (ctx_field_size <= 4) { if (shift) insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH, insn->dst_reg, shift); insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg, (1 << size * 8) - 1); } else { if (shift) insn_buf[cnt++] = BPF_ALU64_IMM(BPF_RSH, insn->dst_reg, shift); insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg, (1ULL << size * 8) - 1); } } new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; /* keep walking new program and skip insns we just inserted */ env->prog = new_prog; insn = new_prog->insnsi + i + delta; } return 0; } static int jit_subprogs(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog, **func, *tmp; int i, j, subprog_start, subprog_end = 0, len, subprog; struct bpf_map *map_ptr; struct bpf_insn *insn; void *old_bpf_func; int err, num_exentries; if (env->subprog_cnt <= 1) return 0; for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { if (!bpf_pseudo_func(insn) && !bpf_pseudo_call(insn)) continue; /* Upon error here we cannot fall back to interpreter but * need a hard reject of the program. Thus -EFAULT is * propagated in any case. */ subprog = find_subprog(env, i + insn->imm + 1); if (subprog < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", i + insn->imm + 1); return -EFAULT; } /* temporarily remember subprog id inside insn instead of * aux_data, since next loop will split up all insns into funcs */ insn->off = subprog; /* remember original imm in case JIT fails and fallback * to interpreter will be needed */ env->insn_aux_data[i].call_imm = insn->imm; /* point imm to __bpf_call_base+1 from JITs point of view */ insn->imm = 1; if (bpf_pseudo_func(insn)) /* jit (e.g. x86_64) may emit fewer instructions * if it learns a u32 imm is the same as a u64 imm. * Force a non zero here. */ insn[1].imm = 1; } err = bpf_prog_alloc_jited_linfo(prog); if (err) goto out_undo_insn; err = -ENOMEM; func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL); if (!func) goto out_undo_insn; for (i = 0; i < env->subprog_cnt; i++) { subprog_start = subprog_end; subprog_end = env->subprog_info[i + 1].start; len = subprog_end - subprog_start; /* bpf_prog_run() doesn't call subprogs directly, * hence main prog stats include the runtime of subprogs. * subprogs don't have IDs and not reachable via prog_get_next_id * func[i]->stats will never be accessed and stays NULL */ func[i] = bpf_prog_alloc_no_stats(bpf_prog_size(len), GFP_USER); if (!func[i]) goto out_free; memcpy(func[i]->insnsi, &prog->insnsi[subprog_start], len * sizeof(struct bpf_insn)); func[i]->type = prog->type; func[i]->len = len; if (bpf_prog_calc_tag(func[i])) goto out_free; func[i]->is_func = 1; func[i]->aux->func_idx = i; /* Below members will be freed only at prog->aux */ func[i]->aux->btf = prog->aux->btf; func[i]->aux->func_info = prog->aux->func_info; func[i]->aux->func_info_cnt = prog->aux->func_info_cnt; func[i]->aux->poke_tab = prog->aux->poke_tab; func[i]->aux->size_poke_tab = prog->aux->size_poke_tab; for (j = 0; j < prog->aux->size_poke_tab; j++) { struct bpf_jit_poke_descriptor *poke; poke = &prog->aux->poke_tab[j]; if (poke->insn_idx < subprog_end && poke->insn_idx >= subprog_start) poke->aux = func[i]->aux; } func[i]->aux->name[0] = 'F'; func[i]->aux->stack_depth = env->subprog_info[i].stack_depth; func[i]->jit_requested = 1; func[i]->blinding_requested = prog->blinding_requested; func[i]->aux->kfunc_tab = prog->aux->kfunc_tab; func[i]->aux->kfunc_btf_tab = prog->aux->kfunc_btf_tab; func[i]->aux->linfo = prog->aux->linfo; func[i]->aux->nr_linfo = prog->aux->nr_linfo; func[i]->aux->jited_linfo = prog->aux->jited_linfo; func[i]->aux->linfo_idx = env->subprog_info[i].linfo_idx; num_exentries = 0; insn = func[i]->insnsi; for (j = 0; j < func[i]->len; j++, insn++) { if (BPF_CLASS(insn->code) == BPF_LDX && BPF_MODE(insn->code) == BPF_PROBE_MEM) num_exentries++; } func[i]->aux->num_exentries = num_exentries; func[i]->aux->tail_call_reachable = env->subprog_info[i].tail_call_reachable; func[i] = bpf_int_jit_compile(func[i]); if (!func[i]->jited) { err = -ENOTSUPP; goto out_free; } cond_resched(); } /* at this point all bpf functions were successfully JITed * now populate all bpf_calls with correct addresses and * run last pass of JIT */ for (i = 0; i < env->subprog_cnt; i++) { insn = func[i]->insnsi; for (j = 0; j < func[i]->len; j++, insn++) { if (bpf_pseudo_func(insn)) { subprog = insn->off; insn[0].imm = (u32)(long)func[subprog]->bpf_func; insn[1].imm = ((u64)(long)func[subprog]->bpf_func) >> 32; continue; } if (!bpf_pseudo_call(insn)) continue; subprog = insn->off; insn->imm = BPF_CALL_IMM(func[subprog]->bpf_func); } /* we use the aux data to keep a list of the start addresses * of the JITed images for each function in the program * * for some architectures, such as powerpc64, the imm field * might not be large enough to hold the offset of the start * address of the callee's JITed image from __bpf_call_base * * in such cases, we can lookup the start address of a callee * by using its subprog id, available from the off field of * the call instruction, as an index for this list */ func[i]->aux->func = func; func[i]->aux->func_cnt = env->subprog_cnt; } for (i = 0; i < env->subprog_cnt; i++) { old_bpf_func = func[i]->bpf_func; tmp = bpf_int_jit_compile(func[i]); if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) { verbose(env, "JIT doesn't support bpf-to-bpf calls\n"); err = -ENOTSUPP; goto out_free; } cond_resched(); } /* finally lock prog and jit images for all functions and * populate kallsysm. Begin at the first subprogram, since * bpf_prog_load will add the kallsyms for the main program. */ for (i = 1; i < env->subprog_cnt; i++) { err = bpf_prog_lock_ro(func[i]); if (err) goto out_free; } for (i = 1; i < env->subprog_cnt; i++) bpf_prog_kallsyms_add(func[i]); /* Last step: make now unused interpreter insns from main * prog consistent for later dump requests, so they can * later look the same as if they were interpreted only. */ for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { if (bpf_pseudo_func(insn)) { insn[0].imm = env->insn_aux_data[i].call_imm; insn[1].imm = insn->off; insn->off = 0; continue; } if (!bpf_pseudo_call(insn)) continue; insn->off = env->insn_aux_data[i].call_imm; subprog = find_subprog(env, i + insn->off + 1); insn->imm = subprog; } prog->jited = 1; prog->bpf_func = func[0]->bpf_func; prog->jited_len = func[0]->jited_len; prog->aux->extable = func[0]->aux->extable; prog->aux->num_exentries = func[0]->aux->num_exentries; prog->aux->func = func; prog->aux->func_cnt = env->subprog_cnt; bpf_prog_jit_attempt_done(prog); return 0; out_free: /* We failed JIT'ing, so at this point we need to unregister poke * descriptors from subprogs, so that kernel is not attempting to * patch it anymore as we're freeing the subprog JIT memory. */ for (i = 0; i < prog->aux->size_poke_tab; i++) { map_ptr = prog->aux->poke_tab[i].tail_call.map; map_ptr->ops->map_poke_untrack(map_ptr, prog->aux); } /* At this point we're guaranteed that poke descriptors are not * live anymore. We can just unlink its descriptor table as it's * released with the main prog. */ for (i = 0; i < env->subprog_cnt; i++) { if (!func[i]) continue; func[i]->aux->poke_tab = NULL; bpf_jit_free(func[i]); } kfree(func); out_undo_insn: /* cleanup main prog to be interpreted */ prog->jit_requested = 0; prog->blinding_requested = 0; for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { if (!bpf_pseudo_call(insn)) continue; insn->off = 0; insn->imm = env->insn_aux_data[i].call_imm; } bpf_prog_jit_attempt_done(prog); return err; } static int fixup_call_args(struct bpf_verifier_env *env) { #ifndef CONFIG_BPF_JIT_ALWAYS_ON struct bpf_prog *prog = env->prog; struct bpf_insn *insn = prog->insnsi; bool has_kfunc_call = bpf_prog_has_kfunc_call(prog); int i, depth; #endif int err = 0; if (env->prog->jit_requested && !bpf_prog_is_dev_bound(env->prog->aux)) { err = jit_subprogs(env); if (err == 0) return 0; if (err == -EFAULT) return err; } #ifndef CONFIG_BPF_JIT_ALWAYS_ON if (has_kfunc_call) { verbose(env, "calling kernel functions are not allowed in non-JITed programs\n"); return -EINVAL; } if (env->subprog_cnt > 1 && env->prog->aux->tail_call_reachable) { /* When JIT fails the progs with bpf2bpf calls and tail_calls * have to be rejected, since interpreter doesn't support them yet. */ verbose(env, "tail_calls are not allowed in non-JITed programs with bpf-to-bpf calls\n"); return -EINVAL; } for (i = 0; i < prog->len; i++, insn++) { if (bpf_pseudo_func(insn)) { /* When JIT fails the progs with callback calls * have to be rejected, since interpreter doesn't support them yet. */ verbose(env, "callbacks are not allowed in non-JITed programs\n"); return -EINVAL; } if (!bpf_pseudo_call(insn)) continue; depth = get_callee_stack_depth(env, insn, i); if (depth < 0) return depth; bpf_patch_call_args(insn, depth); } err = 0; #endif return err; } static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn) { const struct bpf_kfunc_desc *desc; if (!insn->imm) { verbose(env, "invalid kernel function call not eliminated in verifier pass\n"); return -EINVAL; } /* insn->imm has the btf func_id. Replace it with * an address (relative to __bpf_base_call). */ desc = find_kfunc_desc(env->prog, insn->imm, insn->off); if (!desc) { verbose(env, "verifier internal error: kernel function descriptor not found for func_id %u\n", insn->imm); return -EFAULT; } insn->imm = desc->imm; return 0; } /* Do various post-verification rewrites in a single program pass. * These rewrites simplify JIT and interpreter implementations. */ static int do_misc_fixups(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; enum bpf_attach_type eatype = prog->expected_attach_type; enum bpf_prog_type prog_type = resolve_prog_type(prog); struct bpf_insn *insn = prog->insnsi; const struct bpf_func_proto *fn; const int insn_cnt = prog->len; const struct bpf_map_ops *ops; struct bpf_insn_aux_data *aux; struct bpf_insn insn_buf[16]; struct bpf_prog *new_prog; struct bpf_map *map_ptr; int i, ret, cnt, delta = 0; for (i = 0; i < insn_cnt; i++, insn++) { /* Make divide-by-zero exceptions impossible. */ if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) || insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) || insn->code == (BPF_ALU | BPF_MOD | BPF_X) || insn->code == (BPF_ALU | BPF_DIV | BPF_X)) { bool is64 = BPF_CLASS(insn->code) == BPF_ALU64; bool isdiv = BPF_OP(insn->code) == BPF_DIV; struct bpf_insn *patchlet; struct bpf_insn chk_and_div[] = { /* [R,W]x div 0 -> 0 */ BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | BPF_JNE | BPF_K, insn->src_reg, 0, 2, 0), BPF_ALU32_REG(BPF_XOR, insn->dst_reg, insn->dst_reg), BPF_JMP_IMM(BPF_JA, 0, 0, 1), *insn, }; struct bpf_insn chk_and_mod[] = { /* [R,W]x mod 0 -> [R,W]x */ BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) | BPF_JEQ | BPF_K, insn->src_reg, 0, 1 + (is64 ? 0 : 1), 0), *insn, BPF_JMP_IMM(BPF_JA, 0, 0, 1), BPF_MOV32_REG(insn->dst_reg, insn->dst_reg), }; patchlet = isdiv ? chk_and_div : chk_and_mod; cnt = isdiv ? ARRAY_SIZE(chk_and_div) : ARRAY_SIZE(chk_and_mod) - (is64 ? 2 : 0); new_prog = bpf_patch_insn_data(env, i + delta, patchlet, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; continue; } /* Implement LD_ABS and LD_IND with a rewrite, if supported by the program type. */ if (BPF_CLASS(insn->code) == BPF_LD && (BPF_MODE(insn->code) == BPF_ABS || BPF_MODE(insn->code) == BPF_IND)) { cnt = env->ops->gen_ld_abs(insn, insn_buf); if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; continue; } /* Rewrite pointer arithmetic to mitigate speculation attacks. */ if (insn->code == (BPF_ALU64 | BPF_ADD | BPF_X) || insn->code == (BPF_ALU64 | BPF_SUB | BPF_X)) { const u8 code_add = BPF_ALU64 | BPF_ADD | BPF_X; const u8 code_sub = BPF_ALU64 | BPF_SUB | BPF_X; struct bpf_insn *patch = &insn_buf[0]; bool issrc, isneg, isimm; u32 off_reg; aux = &env->insn_aux_data[i + delta]; if (!aux->alu_state || aux->alu_state == BPF_ALU_NON_POINTER) continue; isneg = aux->alu_state & BPF_ALU_NEG_VALUE; issrc = (aux->alu_state & BPF_ALU_SANITIZE) == BPF_ALU_SANITIZE_SRC; isimm = aux->alu_state & BPF_ALU_IMMEDIATE; off_reg = issrc ? insn->src_reg : insn->dst_reg; if (isimm) { *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit); } else { if (isneg) *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1); *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit); *patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg); *patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg); *patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0); *patch++ = BPF_ALU64_IMM(BPF_ARSH, BPF_REG_AX, 63); *patch++ = BPF_ALU64_REG(BPF_AND, BPF_REG_AX, off_reg); } if (!issrc) *patch++ = BPF_MOV64_REG(insn->dst_reg, insn->src_reg); insn->src_reg = BPF_REG_AX; if (isneg) insn->code = insn->code == code_add ? code_sub : code_add; *patch++ = *insn; if (issrc && isneg && !isimm) *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1); cnt = patch - insn_buf; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; continue; } if (insn->code != (BPF_JMP | BPF_CALL)) continue; if (insn->src_reg == BPF_PSEUDO_CALL) continue; if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { ret = fixup_kfunc_call(env, insn); if (ret) return ret; continue; } if (insn->imm == BPF_FUNC_get_route_realm) prog->dst_needed = 1; if (insn->imm == BPF_FUNC_get_prandom_u32) bpf_user_rnd_init_once(); if (insn->imm == BPF_FUNC_override_return) prog->kprobe_override = 1; if (insn->imm == BPF_FUNC_tail_call) { /* If we tail call into other programs, we * cannot make any assumptions since they can * be replaced dynamically during runtime in * the program array. */ prog->cb_access = 1; if (!allow_tail_call_in_subprogs(env)) prog->aux->stack_depth = MAX_BPF_STACK; prog->aux->max_pkt_offset = MAX_PACKET_OFF; /* mark bpf_tail_call as different opcode to avoid * conditional branch in the interpreter for every normal * call and to prevent accidental JITing by JIT compiler * that doesn't support bpf_tail_call yet */ insn->imm = 0; insn->code = BPF_JMP | BPF_TAIL_CALL; aux = &env->insn_aux_data[i + delta]; if (env->bpf_capable && !prog->blinding_requested && prog->jit_requested && !bpf_map_key_poisoned(aux) && !bpf_map_ptr_poisoned(aux) && !bpf_map_ptr_unpriv(aux)) { struct bpf_jit_poke_descriptor desc = { .reason = BPF_POKE_REASON_TAIL_CALL, .tail_call.map = BPF_MAP_PTR(aux->map_ptr_state), .tail_call.key = bpf_map_key_immediate(aux), .insn_idx = i + delta, }; ret = bpf_jit_add_poke_descriptor(prog, &desc); if (ret < 0) { verbose(env, "adding tail call poke descriptor failed\n"); return ret; } insn->imm = ret + 1; continue; } if (!bpf_map_ptr_unpriv(aux)) continue; /* instead of changing every JIT dealing with tail_call * emit two extra insns: * if (index >= max_entries) goto out; * index &= array->index_mask; * to avoid out-of-bounds cpu speculation */ if (bpf_map_ptr_poisoned(aux)) { verbose(env, "tail_call abusing map_ptr\n"); return -EINVAL; } map_ptr = BPF_MAP_PTR(aux->map_ptr_state); insn_buf[0] = BPF_JMP_IMM(BPF_JGE, BPF_REG_3, map_ptr->max_entries, 2); insn_buf[1] = BPF_ALU32_IMM(BPF_AND, BPF_REG_3, container_of(map_ptr, struct bpf_array, map)->index_mask); insn_buf[2] = *insn; cnt = 3; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; continue; } if (insn->imm == BPF_FUNC_timer_set_callback) { /* The verifier will process callback_fn as many times as necessary * with different maps and the register states prepared by * set_timer_callback_state will be accurate. * * The following use case is valid: * map1 is shared by prog1, prog2, prog3. * prog1 calls bpf_timer_init for some map1 elements * prog2 calls bpf_timer_set_callback for some map1 elements. * Those that were not bpf_timer_init-ed will return -EINVAL. * prog3 calls bpf_timer_start for some map1 elements. * Those that were not both bpf_timer_init-ed and * bpf_timer_set_callback-ed will return -EINVAL. */ struct bpf_insn ld_addrs[2] = { BPF_LD_IMM64(BPF_REG_3, (long)prog->aux), }; insn_buf[0] = ld_addrs[0]; insn_buf[1] = ld_addrs[1]; insn_buf[2] = *insn; cnt = 3; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto patch_call_imm; } if (insn->imm == BPF_FUNC_task_storage_get || insn->imm == BPF_FUNC_sk_storage_get || insn->imm == BPF_FUNC_inode_storage_get) { if (env->prog->aux->sleepable) insn_buf[0] = BPF_MOV64_IMM(BPF_REG_5, (__force __s32)GFP_KERNEL); else insn_buf[0] = BPF_MOV64_IMM(BPF_REG_5, (__force __s32)GFP_ATOMIC); insn_buf[1] = *insn; cnt = 2; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; goto patch_call_imm; } /* BPF_EMIT_CALL() assumptions in some of the map_gen_lookup * and other inlining handlers are currently limited to 64 bit * only. */ if (prog->jit_requested && BITS_PER_LONG == 64 && (insn->imm == BPF_FUNC_map_lookup_elem || insn->imm == BPF_FUNC_map_update_elem || insn->imm == BPF_FUNC_map_delete_elem || insn->imm == BPF_FUNC_map_push_elem || insn->imm == BPF_FUNC_map_pop_elem || insn->imm == BPF_FUNC_map_peek_elem || insn->imm == BPF_FUNC_redirect_map || insn->imm == BPF_FUNC_for_each_map_elem || insn->imm == BPF_FUNC_map_lookup_percpu_elem)) { aux = &env->insn_aux_data[i + delta]; if (bpf_map_ptr_poisoned(aux)) goto patch_call_imm; map_ptr = BPF_MAP_PTR(aux->map_ptr_state); ops = map_ptr->ops; if (insn->imm == BPF_FUNC_map_lookup_elem && ops->map_gen_lookup) { cnt = ops->map_gen_lookup(map_ptr, insn_buf); if (cnt == -EOPNOTSUPP) goto patch_map_ops_generic; if (cnt <= 0 || cnt >= ARRAY_SIZE(insn_buf)) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; continue; } BUILD_BUG_ON(!__same_type(ops->map_lookup_elem, (void *(*)(struct bpf_map *map, void *key))NULL)); BUILD_BUG_ON(!__same_type(ops->map_delete_elem, (int (*)(struct bpf_map *map, void *key))NULL)); BUILD_BUG_ON(!__same_type(ops->map_update_elem, (int (*)(struct bpf_map *map, void *key, void *value, u64 flags))NULL)); BUILD_BUG_ON(!__same_type(ops->map_push_elem, (int (*)(struct bpf_map *map, void *value, u64 flags))NULL)); BUILD_BUG_ON(!__same_type(ops->map_pop_elem, (int (*)(struct bpf_map *map, void *value))NULL)); BUILD_BUG_ON(!__same_type(ops->map_peek_elem, (int (*)(struct bpf_map *map, void *value))NULL)); BUILD_BUG_ON(!__same_type(ops->map_redirect, (int (*)(struct bpf_map *map, u32 ifindex, u64 flags))NULL)); BUILD_BUG_ON(!__same_type(ops->map_for_each_callback, (int (*)(struct bpf_map *map, bpf_callback_t callback_fn, void *callback_ctx, u64 flags))NULL)); BUILD_BUG_ON(!__same_type(ops->map_lookup_percpu_elem, (void *(*)(struct bpf_map *map, void *key, u32 cpu))NULL)); patch_map_ops_generic: switch (insn->imm) { case BPF_FUNC_map_lookup_elem: insn->imm = BPF_CALL_IMM(ops->map_lookup_elem); continue; case BPF_FUNC_map_update_elem: insn->imm = BPF_CALL_IMM(ops->map_update_elem); continue; case BPF_FUNC_map_delete_elem: insn->imm = BPF_CALL_IMM(ops->map_delete_elem); continue; case BPF_FUNC_map_push_elem: insn->imm = BPF_CALL_IMM(ops->map_push_elem); continue; case BPF_FUNC_map_pop_elem: insn->imm = BPF_CALL_IMM(ops->map_pop_elem); continue; case BPF_FUNC_map_peek_elem: insn->imm = BPF_CALL_IMM(ops->map_peek_elem); continue; case BPF_FUNC_redirect_map: insn->imm = BPF_CALL_IMM(ops->map_redirect); continue; case BPF_FUNC_for_each_map_elem: insn->imm = BPF_CALL_IMM(ops->map_for_each_callback); continue; case BPF_FUNC_map_lookup_percpu_elem: insn->imm = BPF_CALL_IMM(ops->map_lookup_percpu_elem); continue; } goto patch_call_imm; } /* Implement bpf_jiffies64 inline. */ if (prog->jit_requested && BITS_PER_LONG == 64 && insn->imm == BPF_FUNC_jiffies64) { struct bpf_insn ld_jiffies_addr[2] = { BPF_LD_IMM64(BPF_REG_0, (unsigned long)&jiffies), }; insn_buf[0] = ld_jiffies_addr[0]; insn_buf[1] = ld_jiffies_addr[1]; insn_buf[2] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0); cnt = 3; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; continue; } /* Implement bpf_get_func_arg inline. */ if (prog_type == BPF_PROG_TYPE_TRACING && insn->imm == BPF_FUNC_get_func_arg) { /* Load nr_args from ctx - 8 */ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); insn_buf[1] = BPF_JMP32_REG(BPF_JGE, BPF_REG_2, BPF_REG_0, 6); insn_buf[2] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 3); insn_buf[3] = BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1); insn_buf[4] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0); insn_buf[5] = BPF_STX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0); insn_buf[6] = BPF_MOV64_IMM(BPF_REG_0, 0); insn_buf[7] = BPF_JMP_A(1); insn_buf[8] = BPF_MOV64_IMM(BPF_REG_0, -EINVAL); cnt = 9; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; continue; } /* Implement bpf_get_func_ret inline. */ if (prog_type == BPF_PROG_TYPE_TRACING && insn->imm == BPF_FUNC_get_func_ret) { if (eatype == BPF_TRACE_FEXIT || eatype == BPF_MODIFY_RETURN) { /* Load nr_args from ctx - 8 */ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); insn_buf[1] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 3); insn_buf[2] = BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1); insn_buf[3] = BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0); insn_buf[4] = BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_3, 0); insn_buf[5] = BPF_MOV64_IMM(BPF_REG_0, 0); cnt = 6; } else { insn_buf[0] = BPF_MOV64_IMM(BPF_REG_0, -EOPNOTSUPP); cnt = 1; } new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; continue; } /* Implement get_func_arg_cnt inline. */ if (prog_type == BPF_PROG_TYPE_TRACING && insn->imm == BPF_FUNC_get_func_arg_cnt) { /* Load nr_args from ctx - 8 */ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, 1); if (!new_prog) return -ENOMEM; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; continue; } /* Implement bpf_get_func_ip inline. */ if (prog_type == BPF_PROG_TYPE_TRACING && insn->imm == BPF_FUNC_get_func_ip) { /* Load IP address from ctx - 16 */ insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -16); new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, 1); if (!new_prog) return -ENOMEM; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; continue; } patch_call_imm: fn = env->ops->get_func_proto(insn->imm, env->prog); /* all functions that have prototype and verifier allowed * programs to call them, must be real in-kernel functions */ if (!fn->func) { verbose(env, "kernel subsystem misconfigured func %s#%d\n", func_id_name(insn->imm), insn->imm); return -EFAULT; } insn->imm = fn->func - __bpf_call_base; } /* Since poke tab is now finalized, publish aux to tracker. */ for (i = 0; i < prog->aux->size_poke_tab; i++) { map_ptr = prog->aux->poke_tab[i].tail_call.map; if (!map_ptr->ops->map_poke_track || !map_ptr->ops->map_poke_untrack || !map_ptr->ops->map_poke_run) { verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } ret = map_ptr->ops->map_poke_track(map_ptr, prog->aux); if (ret < 0) { verbose(env, "tracking tail call prog failed\n"); return ret; } } sort_kfunc_descs_by_imm(env->prog); return 0; } static struct bpf_prog *inline_bpf_loop(struct bpf_verifier_env *env, int position, s32 stack_base, u32 callback_subprogno, u32 *cnt) { s32 r6_offset = stack_base + 0 * BPF_REG_SIZE; s32 r7_offset = stack_base + 1 * BPF_REG_SIZE; s32 r8_offset = stack_base + 2 * BPF_REG_SIZE; int reg_loop_max = BPF_REG_6; int reg_loop_cnt = BPF_REG_7; int reg_loop_ctx = BPF_REG_8; struct bpf_prog *new_prog; u32 callback_start; u32 call_insn_offset; s32 callback_offset; /* This represents an inlined version of bpf_iter.c:bpf_loop, * be careful to modify this code in sync. */ struct bpf_insn insn_buf[] = { /* Return error and jump to the end of the patch if * expected number of iterations is too big. */ BPF_JMP_IMM(BPF_JLE, BPF_REG_1, BPF_MAX_LOOPS, 2), BPF_MOV32_IMM(BPF_REG_0, -E2BIG), BPF_JMP_IMM(BPF_JA, 0, 0, 16), /* spill R6, R7, R8 to use these as loop vars */ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, r6_offset), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_7, r7_offset), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_8, r8_offset), /* initialize loop vars */ BPF_MOV64_REG(reg_loop_max, BPF_REG_1), BPF_MOV32_IMM(reg_loop_cnt, 0), BPF_MOV64_REG(reg_loop_ctx, BPF_REG_3), /* loop header, * if reg_loop_cnt >= reg_loop_max skip the loop body */ BPF_JMP_REG(BPF_JGE, reg_loop_cnt, reg_loop_max, 5), /* callback call, * correct callback offset would be set after patching */ BPF_MOV64_REG(BPF_REG_1, reg_loop_cnt), BPF_MOV64_REG(BPF_REG_2, reg_loop_ctx), BPF_CALL_REL(0), /* increment loop counter */ BPF_ALU64_IMM(BPF_ADD, reg_loop_cnt, 1), /* jump to loop header if callback returned 0 */ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, -6), /* return value of bpf_loop, * set R0 to the number of iterations */ BPF_MOV64_REG(BPF_REG_0, reg_loop_cnt), /* restore original values of R6, R7, R8 */ BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_10, r6_offset), BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_10, r7_offset), BPF_LDX_MEM(BPF_DW, BPF_REG_8, BPF_REG_10, r8_offset), }; *cnt = ARRAY_SIZE(insn_buf); new_prog = bpf_patch_insn_data(env, position, insn_buf, *cnt); if (!new_prog) return new_prog; /* callback start is known only after patching */ callback_start = env->subprog_info[callback_subprogno].start; /* Note: insn_buf[12] is an offset of BPF_CALL_REL instruction */ call_insn_offset = position + 12; callback_offset = callback_start - call_insn_offset - 1; new_prog->insnsi[call_insn_offset].imm = callback_offset; return new_prog; } static bool is_bpf_loop_call(struct bpf_insn *insn) { return insn->code == (BPF_JMP | BPF_CALL) && insn->src_reg == 0 && insn->imm == BPF_FUNC_loop; } /* For all sub-programs in the program (including main) check * insn_aux_data to see if there are bpf_loop calls that require * inlining. If such calls are found the calls are replaced with a * sequence of instructions produced by `inline_bpf_loop` function and * subprog stack_depth is increased by the size of 3 registers. * This stack space is used to spill values of the R6, R7, R8. These * registers are used to store the loop bound, counter and context * variables. */ static int optimize_bpf_loop(struct bpf_verifier_env *env) { struct bpf_subprog_info *subprogs = env->subprog_info; int i, cur_subprog = 0, cnt, delta = 0; struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; u16 stack_depth = subprogs[cur_subprog].stack_depth; u16 stack_depth_roundup = round_up(stack_depth, 8) - stack_depth; u16 stack_depth_extra = 0; for (i = 0; i < insn_cnt; i++, insn++) { struct bpf_loop_inline_state *inline_state = &env->insn_aux_data[i + delta].loop_inline_state; if (is_bpf_loop_call(insn) && inline_state->fit_for_inline) { struct bpf_prog *new_prog; stack_depth_extra = BPF_REG_SIZE * 3 + stack_depth_roundup; new_prog = inline_bpf_loop(env, i + delta, -(stack_depth + stack_depth_extra), inline_state->callback_subprogno, &cnt); if (!new_prog) return -ENOMEM; delta += cnt - 1; env->prog = new_prog; insn = new_prog->insnsi + i + delta; } if (subprogs[cur_subprog + 1].start == i + delta + 1) { subprogs[cur_subprog].stack_depth += stack_depth_extra; cur_subprog++; stack_depth = subprogs[cur_subprog].stack_depth; stack_depth_roundup = round_up(stack_depth, 8) - stack_depth; stack_depth_extra = 0; } } env->prog->aux->stack_depth = env->subprog_info[0].stack_depth; return 0; } static void free_states(struct bpf_verifier_env *env) { struct bpf_verifier_state_list *sl, *sln; int i; sl = env->free_list; while (sl) { sln = sl->next; free_verifier_state(&sl->state, false); kfree(sl); sl = sln; } env->free_list = NULL; if (!env->explored_states) return; for (i = 0; i < state_htab_size(env); i++) { sl = env->explored_states[i]; while (sl) { sln = sl->next; free_verifier_state(&sl->state, false); kfree(sl); sl = sln; } env->explored_states[i] = NULL; } } static int do_check_common(struct bpf_verifier_env *env, int subprog) { bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); struct bpf_verifier_state *state; struct bpf_reg_state *regs; int ret, i; env->prev_linfo = NULL; env->pass_cnt++; state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL); if (!state) return -ENOMEM; state->curframe = 0; state->speculative = false; state->branches = 1; state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL); if (!state->frame[0]) { kfree(state); return -ENOMEM; } env->cur_state = state; init_func_state(env, state->frame[0], BPF_MAIN_FUNC /* callsite */, 0 /* frameno */, subprog); state->first_insn_idx = env->subprog_info[subprog].start; state->last_insn_idx = -1; regs = state->frame[state->curframe]->regs; if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) { ret = btf_prepare_func_args(env, subprog, regs); if (ret) goto out; for (i = BPF_REG_1; i <= BPF_REG_5; i++) { if (regs[i].type == PTR_TO_CTX) mark_reg_known_zero(env, regs, i); else if (regs[i].type == SCALAR_VALUE) mark_reg_unknown(env, regs, i); else if (base_type(regs[i].type) == PTR_TO_MEM) { const u32 mem_size = regs[i].mem_size; mark_reg_known_zero(env, regs, i); regs[i].mem_size = mem_size; regs[i].id = ++env->id_gen; } } } else { /* 1st arg to a function */ regs[BPF_REG_1].type = PTR_TO_CTX; mark_reg_known_zero(env, regs, BPF_REG_1); ret = btf_check_subprog_arg_match(env, subprog, regs); if (ret == -EFAULT) /* unlikely verifier bug. abort. * ret == 0 and ret < 0 are sadly acceptable for * main() function due to backward compatibility. * Like socket filter program may be written as: * int bpf_prog(struct pt_regs *ctx) * and never dereference that ctx in the program. * 'struct pt_regs' is a type mismatch for socket * filter that should be using 'struct __sk_buff'. */ goto out; } ret = do_check(env); out: /* check for NULL is necessary, since cur_state can be freed inside * do_check() under memory pressure. */ if (env->cur_state) { free_verifier_state(env->cur_state, true); env->cur_state = NULL; } while (!pop_stack(env, NULL, NULL, false)); if (!ret && pop_log) bpf_vlog_reset(&env->log, 0); free_states(env); return ret; } /* Verify all global functions in a BPF program one by one based on their BTF. * All global functions must pass verification. Otherwise the whole program is rejected. * Consider: * int bar(int); * int foo(int f) * { * return bar(f); * } * int bar(int b) * { * ... * } * foo() will be verified first for R1=any_scalar_value. During verification it * will be assumed that bar() already verified successfully and call to bar() * from foo() will be checked for type match only. Later bar() will be verified * independently to check that it's safe for R1=any_scalar_value. */ static int do_check_subprogs(struct bpf_verifier_env *env) { struct bpf_prog_aux *aux = env->prog->aux; int i, ret; if (!aux->func_info) return 0; for (i = 1; i < env->subprog_cnt; i++) { if (aux->func_info_aux[i].linkage != BTF_FUNC_GLOBAL) continue; env->insn_idx = env->subprog_info[i].start; WARN_ON_ONCE(env->insn_idx == 0); ret = do_check_common(env, i); if (ret) { return ret; } else if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "Func#%d is safe for any args that match its prototype\n", i); } } return 0; } static int do_check_main(struct bpf_verifier_env *env) { int ret; env->insn_idx = 0; ret = do_check_common(env, 0); if (!ret) env->prog->aux->stack_depth = env->subprog_info[0].stack_depth; return ret; } static void print_verification_stats(struct bpf_verifier_env *env) { int i; if (env->log.level & BPF_LOG_STATS) { verbose(env, "verification time %lld usec\n", div_u64(env->verification_time, 1000)); verbose(env, "stack depth "); for (i = 0; i < env->subprog_cnt; i++) { u32 depth = env->subprog_info[i].stack_depth; verbose(env, "%d", depth); if (i + 1 < env->subprog_cnt) verbose(env, "+"); } verbose(env, "\n"); } verbose(env, "processed %d insns (limit %d) max_states_per_insn %d " "total_states %d peak_states %d mark_read %d\n", env->insn_processed, BPF_COMPLEXITY_LIMIT_INSNS, env->max_states_per_insn, env->total_states, env->peak_states, env->longest_mark_read_walk); } static int check_struct_ops_btf_id(struct bpf_verifier_env *env) { const struct btf_type *t, *func_proto; const struct bpf_struct_ops *st_ops; const struct btf_member *member; struct bpf_prog *prog = env->prog; u32 btf_id, member_idx; const char *mname; if (!prog->gpl_compatible) { verbose(env, "struct ops programs must have a GPL compatible license\n"); return -EINVAL; } btf_id = prog->aux->attach_btf_id; st_ops = bpf_struct_ops_find(btf_id); if (!st_ops) { verbose(env, "attach_btf_id %u is not a supported struct\n", btf_id); return -ENOTSUPP; } t = st_ops->type; member_idx = prog->expected_attach_type; if (member_idx >= btf_type_vlen(t)) { verbose(env, "attach to invalid member idx %u of struct %s\n", member_idx, st_ops->name); return -EINVAL; } member = &btf_type_member(t)[member_idx]; mname = btf_name_by_offset(btf_vmlinux, member->name_off); func_proto = btf_type_resolve_func_ptr(btf_vmlinux, member->type, NULL); if (!func_proto) { verbose(env, "attach to invalid member %s(@idx %u) of struct %s\n", mname, member_idx, st_ops->name); return -EINVAL; } if (st_ops->check_member) { int err = st_ops->check_member(t, member); if (err) { verbose(env, "attach to unsupported member %s of struct %s\n", mname, st_ops->name); return err; } } prog->aux->attach_func_proto = func_proto; prog->aux->attach_func_name = mname; env->ops = st_ops->verifier_ops; return 0; } #define SECURITY_PREFIX "security_" static int check_attach_modify_return(unsigned long addr, const char *func_name) { if (within_error_injection_list(addr) || !strncmp(SECURITY_PREFIX, func_name, sizeof(SECURITY_PREFIX) - 1)) return 0; return -EINVAL; } /* list of non-sleepable functions that are otherwise on * ALLOW_ERROR_INJECTION list */ BTF_SET_START(btf_non_sleepable_error_inject) /* Three functions below can be called from sleepable and non-sleepable context. * Assume non-sleepable from bpf safety point of view. */ BTF_ID(func, __filemap_add_folio) BTF_ID(func, should_fail_alloc_page) BTF_ID(func, should_failslab) BTF_SET_END(btf_non_sleepable_error_inject) static int check_non_sleepable_error_inject(u32 btf_id) { return btf_id_set_contains(&btf_non_sleepable_error_inject, btf_id); } int bpf_check_attach_target(struct bpf_verifier_log *log, const struct bpf_prog *prog, const struct bpf_prog *tgt_prog, u32 btf_id, struct bpf_attach_target_info *tgt_info) { bool prog_extension = prog->type == BPF_PROG_TYPE_EXT; const char prefix[] = "btf_trace_"; int ret = 0, subprog = -1, i; const struct btf_type *t; bool conservative = true; const char *tname; struct btf *btf; long addr = 0; if (!btf_id) { bpf_log(log, "Tracing programs must provide btf_id\n"); return -EINVAL; } btf = tgt_prog ? tgt_prog->aux->btf : prog->aux->attach_btf; if (!btf) { bpf_log(log, "FENTRY/FEXIT program can only be attached to another program annotated with BTF\n"); return -EINVAL; } t = btf_type_by_id(btf, btf_id); if (!t) { bpf_log(log, "attach_btf_id %u is invalid\n", btf_id); return -EINVAL; } tname = btf_name_by_offset(btf, t->name_off); if (!tname) { bpf_log(log, "attach_btf_id %u doesn't have a name\n", btf_id); return -EINVAL; } if (tgt_prog) { struct bpf_prog_aux *aux = tgt_prog->aux; for (i = 0; i < aux->func_info_cnt; i++) if (aux->func_info[i].type_id == btf_id) { subprog = i; break; } if (subprog == -1) { bpf_log(log, "Subprog %s doesn't exist\n", tname); return -EINVAL; } conservative = aux->func_info_aux[subprog].unreliable; if (prog_extension) { if (conservative) { bpf_log(log, "Cannot replace static functions\n"); return -EINVAL; } if (!prog->jit_requested) { bpf_log(log, "Extension programs should be JITed\n"); return -EINVAL; } } if (!tgt_prog->jited) { bpf_log(log, "Can attach to only JITed progs\n"); return -EINVAL; } if (tgt_prog->type == prog->type) { /* Cannot fentry/fexit another fentry/fexit program. * Cannot attach program extension to another extension. * It's ok to attach fentry/fexit to extension program. */ bpf_log(log, "Cannot recursively attach\n"); return -EINVAL; } if (tgt_prog->type == BPF_PROG_TYPE_TRACING && prog_extension && (tgt_prog->expected_attach_type == BPF_TRACE_FENTRY || tgt_prog->expected_attach_type == BPF_TRACE_FEXIT)) { /* Program extensions can extend all program types * except fentry/fexit. The reason is the following. * The fentry/fexit programs are used for performance * analysis, stats and can be attached to any program * type except themselves. When extension program is * replacing XDP function it is necessary to allow * performance analysis of all functions. Both original * XDP program and its program extension. Hence * attaching fentry/fexit to BPF_PROG_TYPE_EXT is * allowed. If extending of fentry/fexit was allowed it * would be possible to create long call chain * fentry->extension->fentry->extension beyond * reasonable stack size. Hence extending fentry is not * allowed. */ bpf_log(log, "Cannot extend fentry/fexit\n"); return -EINVAL; } } else { if (prog_extension) { bpf_log(log, "Cannot replace kernel functions\n"); return -EINVAL; } } switch (prog->expected_attach_type) { case BPF_TRACE_RAW_TP: if (tgt_prog) { bpf_log(log, "Only FENTRY/FEXIT progs are attachable to another BPF prog\n"); return -EINVAL; } if (!btf_type_is_typedef(t)) { bpf_log(log, "attach_btf_id %u is not a typedef\n", btf_id); return -EINVAL; } if (strncmp(prefix, tname, sizeof(prefix) - 1)) { bpf_log(log, "attach_btf_id %u points to wrong type name %s\n", btf_id, tname); return -EINVAL; } tname += sizeof(prefix) - 1; t = btf_type_by_id(btf, t->type); if (!btf_type_is_ptr(t)) /* should never happen in valid vmlinux build */ return -EINVAL; t = btf_type_by_id(btf, t->type); if (!btf_type_is_func_proto(t)) /* should never happen in valid vmlinux build */ return -EINVAL; break; case BPF_TRACE_ITER: if (!btf_type_is_func(t)) { bpf_log(log, "attach_btf_id %u is not a function\n", btf_id); return -EINVAL; } t = btf_type_by_id(btf, t->type); if (!btf_type_is_func_proto(t)) return -EINVAL; ret = btf_distill_func_proto(log, btf, t, tname, &tgt_info->fmodel); if (ret) return ret; break; default: if (!prog_extension) return -EINVAL; fallthrough; case BPF_MODIFY_RETURN: case BPF_LSM_MAC: case BPF_LSM_CGROUP: case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: if (!btf_type_is_func(t)) { bpf_log(log, "attach_btf_id %u is not a function\n", btf_id); return -EINVAL; } if (prog_extension && btf_check_type_match(log, prog, btf, t)) return -EINVAL; t = btf_type_by_id(btf, t->type); if (!btf_type_is_func_proto(t)) return -EINVAL; if ((prog->aux->saved_dst_prog_type || prog->aux->saved_dst_attach_type) && (!tgt_prog || prog->aux->saved_dst_prog_type != tgt_prog->type || prog->aux->saved_dst_attach_type != tgt_prog->expected_attach_type)) return -EINVAL; if (tgt_prog && conservative) t = NULL; ret = btf_distill_func_proto(log, btf, t, tname, &tgt_info->fmodel); if (ret < 0) return ret; if (tgt_prog) { if (subprog == 0) addr = (long) tgt_prog->bpf_func; else addr = (long) tgt_prog->aux->func[subprog]->bpf_func; } else { addr = kallsyms_lookup_name(tname); if (!addr) { bpf_log(log, "The address of function %s cannot be found\n", tname); return -ENOENT; } } if (prog->aux->sleepable) { ret = -EINVAL; switch (prog->type) { case BPF_PROG_TYPE_TRACING: /* fentry/fexit/fmod_ret progs can be sleepable only if they are * attached to ALLOW_ERROR_INJECTION and are not in denylist. */ if (!check_non_sleepable_error_inject(btf_id) && within_error_injection_list(addr)) ret = 0; break; case BPF_PROG_TYPE_LSM: /* LSM progs check that they are attached to bpf_lsm_*() funcs. * Only some of them are sleepable. */ if (bpf_lsm_is_sleepable_hook(btf_id)) ret = 0; break; default: break; } if (ret) { bpf_log(log, "%s is not sleepable\n", tname); return ret; } } else if (prog->expected_attach_type == BPF_MODIFY_RETURN) { if (tgt_prog) { bpf_log(log, "can't modify return codes of BPF programs\n"); return -EINVAL; } ret = check_attach_modify_return(addr, tname); if (ret) { bpf_log(log, "%s() is not modifiable\n", tname); return ret; } } break; } tgt_info->tgt_addr = addr; tgt_info->tgt_name = tname; tgt_info->tgt_type = t; return 0; } BTF_SET_START(btf_id_deny) BTF_ID_UNUSED #ifdef CONFIG_SMP BTF_ID(func, migrate_disable) BTF_ID(func, migrate_enable) #endif #if !defined CONFIG_PREEMPT_RCU && !defined CONFIG_TINY_RCU BTF_ID(func, rcu_read_unlock_strict) #endif #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_TRACE_PREEMPT_TOGGLE) BTF_ID(func, preempt_count_add) BTF_ID(func, preempt_count_sub) #endif BTF_SET_END(btf_id_deny) static int check_attach_btf_id(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; struct bpf_prog *tgt_prog = prog->aux->dst_prog; struct bpf_attach_target_info tgt_info = {}; u32 btf_id = prog->aux->attach_btf_id; struct bpf_trampoline *tr; int ret; u64 key; if (prog->type == BPF_PROG_TYPE_SYSCALL) { if (prog->aux->sleepable) /* attach_btf_id checked to be zero already */ return 0; verbose(env, "Syscall programs can only be sleepable\n"); return -EINVAL; } if (prog->aux->sleepable && prog->type != BPF_PROG_TYPE_TRACING && prog->type != BPF_PROG_TYPE_LSM && prog->type != BPF_PROG_TYPE_KPROBE) { verbose(env, "Only fentry/fexit/fmod_ret, lsm, and kprobe/uprobe programs can be sleepable\n"); return -EINVAL; } if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) return check_struct_ops_btf_id(env); if (prog->type != BPF_PROG_TYPE_TRACING && prog->type != BPF_PROG_TYPE_LSM && prog->type != BPF_PROG_TYPE_EXT) return 0; ret = bpf_check_attach_target(&env->log, prog, tgt_prog, btf_id, &tgt_info); if (ret) return ret; if (tgt_prog && prog->type == BPF_PROG_TYPE_EXT) { /* to make freplace equivalent to their targets, they need to * inherit env->ops and expected_attach_type for the rest of the * verification */ env->ops = bpf_verifier_ops[tgt_prog->type]; prog->expected_attach_type = tgt_prog->expected_attach_type; } /* store info about the attachment target that will be used later */ prog->aux->attach_func_proto = tgt_info.tgt_type; prog->aux->attach_func_name = tgt_info.tgt_name; if (tgt_prog) { prog->aux->saved_dst_prog_type = tgt_prog->type; prog->aux->saved_dst_attach_type = tgt_prog->expected_attach_type; } if (prog->expected_attach_type == BPF_TRACE_RAW_TP) { prog->aux->attach_btf_trace = true; return 0; } else if (prog->expected_attach_type == BPF_TRACE_ITER) { if (!bpf_iter_prog_supported(prog)) return -EINVAL; return 0; } if (prog->type == BPF_PROG_TYPE_LSM) { ret = bpf_lsm_verify_prog(&env->log, prog); if (ret < 0) return ret; } else if (prog->type == BPF_PROG_TYPE_TRACING && btf_id_set_contains(&btf_id_deny, btf_id)) { return -EINVAL; } key = bpf_trampoline_compute_key(tgt_prog, prog->aux->attach_btf, btf_id); tr = bpf_trampoline_get(key, &tgt_info); if (!tr) return -ENOMEM; if (tgt_prog && tgt_prog->aux->tail_call_reachable) tr->flags = BPF_TRAMP_F_TAIL_CALL_CTX; prog->aux->dst_trampoline = tr; return 0; } struct btf *bpf_get_btf_vmlinux(void) { if (!btf_vmlinux && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) { mutex_lock(&bpf_verifier_lock); if (!btf_vmlinux) btf_vmlinux = btf_parse_vmlinux(); mutex_unlock(&bpf_verifier_lock); } return btf_vmlinux; } int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) { u64 start_time = ktime_get_ns(); struct bpf_verifier_env *env; struct bpf_verifier_log *log; int i, len, ret = -EINVAL; bool is_priv; /* no program is valid */ if (ARRAY_SIZE(bpf_verifier_ops) == 0) return -EINVAL; /* 'struct bpf_verifier_env' can be global, but since it's not small, * allocate/free it every time bpf_check() is called */ env = kvzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL); if (!env) return -ENOMEM; log = &env->log; len = (*prog)->len; env->insn_aux_data = vzalloc(array_size(sizeof(struct bpf_insn_aux_data), len)); ret = -ENOMEM; if (!env->insn_aux_data) goto err_free_env; for (i = 0; i < len; i++) env->insn_aux_data[i].orig_idx = i; env->prog = *prog; env->ops = bpf_verifier_ops[env->prog->type]; env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel); is_priv = bpf_capable(); bpf_get_btf_vmlinux(); /* grab the mutex to protect few globals used by verifier */ if (!is_priv) mutex_lock(&bpf_verifier_lock); if (attr->log_level || attr->log_buf || attr->log_size) { /* user requested verbose verifier output * and supplied buffer to store the verification trace */ log->level = attr->log_level; log->ubuf = (char __user *) (unsigned long) attr->log_buf; log->len_total = attr->log_size; /* log attributes have to be sane */ if (!bpf_verifier_log_attr_valid(log)) { ret = -EINVAL; goto err_unlock; } } mark_verifier_state_clean(env); if (IS_ERR(btf_vmlinux)) { /* Either gcc or pahole or kernel are broken. */ verbose(env, "in-kernel BTF is malformed\n"); ret = PTR_ERR(btf_vmlinux); goto skip_full_check; } env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT); if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) env->strict_alignment = true; if (attr->prog_flags & BPF_F_ANY_ALIGNMENT) env->strict_alignment = false; env->allow_ptr_leaks = bpf_allow_ptr_leaks(); env->allow_uninit_stack = bpf_allow_uninit_stack(); env->allow_ptr_to_map_access = bpf_allow_ptr_to_map_access(); env->bypass_spec_v1 = bpf_bypass_spec_v1(); env->bypass_spec_v4 = bpf_bypass_spec_v4(); env->bpf_capable = bpf_capable(); if (is_priv) env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; env->explored_states = kvcalloc(state_htab_size(env), sizeof(struct bpf_verifier_state_list *), GFP_USER); ret = -ENOMEM; if (!env->explored_states) goto skip_full_check; ret = add_subprog_and_kfunc(env); if (ret < 0) goto skip_full_check; ret = check_subprogs(env); if (ret < 0) goto skip_full_check; ret = check_btf_info(env, attr, uattr); if (ret < 0) goto skip_full_check; ret = check_attach_btf_id(env); if (ret) goto skip_full_check; ret = resolve_pseudo_ldimm64(env); if (ret < 0) goto skip_full_check; if (bpf_prog_is_dev_bound(env->prog->aux)) { ret = bpf_prog_offload_verifier_prep(env->prog); if (ret) goto skip_full_check; } ret = check_cfg(env); if (ret < 0) goto skip_full_check; ret = do_check_subprogs(env); ret = ret ?: do_check_main(env); if (ret == 0 && bpf_prog_is_dev_bound(env->prog->aux)) ret = bpf_prog_offload_finalize(env); skip_full_check: kvfree(env->explored_states); if (ret == 0) ret = check_max_stack_depth(env); /* instruction rewrites happen after this point */ if (ret == 0) ret = optimize_bpf_loop(env); if (is_priv) { if (ret == 0) opt_hard_wire_dead_code_branches(env); if (ret == 0) ret = opt_remove_dead_code(env); if (ret == 0) ret = opt_remove_nops(env); } else { if (ret == 0) sanitize_dead_code(env); } if (ret == 0) /* program is valid, convert *(u32*)(ctx + off) accesses */ ret = convert_ctx_accesses(env); if (ret == 0) ret = do_misc_fixups(env); /* do 32-bit optimization after insn patching has done so those patched * insns could be handled correctly. */ if (ret == 0 && !bpf_prog_is_dev_bound(env->prog->aux)) { ret = opt_subreg_zext_lo32_rnd_hi32(env, attr); env->prog->aux->verifier_zext = bpf_jit_needs_zext() ? !ret : false; } if (ret == 0) ret = fixup_call_args(env); env->verification_time = ktime_get_ns() - start_time; print_verification_stats(env); env->prog->aux->verified_insns = env->insn_processed; if (log->level && bpf_verifier_log_full(log)) ret = -ENOSPC; if (log->level && !log->ubuf) { ret = -EFAULT; goto err_release_maps; } if (ret) goto err_release_maps; if (env->used_map_cnt) { /* if program passed verifier, update used_maps in bpf_prog_info */ env->prog->aux->used_maps = kmalloc_array(env->used_map_cnt, sizeof(env->used_maps[0]), GFP_KERNEL); if (!env->prog->aux->used_maps) { ret = -ENOMEM; goto err_release_maps; } memcpy(env->prog->aux->used_maps, env->used_maps, sizeof(env->used_maps[0]) * env->used_map_cnt); env->prog->aux->used_map_cnt = env->used_map_cnt; } if (env->used_btf_cnt) { /* if program passed verifier, update used_btfs in bpf_prog_aux */ env->prog->aux->used_btfs = kmalloc_array(env->used_btf_cnt, sizeof(env->used_btfs[0]), GFP_KERNEL); if (!env->prog->aux->used_btfs) { ret = -ENOMEM; goto err_release_maps; } memcpy(env->prog->aux->used_btfs, env->used_btfs, sizeof(env->used_btfs[0]) * env->used_btf_cnt); env->prog->aux->used_btf_cnt = env->used_btf_cnt; } if (env->used_map_cnt || env->used_btf_cnt) { /* program is valid. Convert pseudo bpf_ld_imm64 into generic * bpf_ld_imm64 instructions */ convert_pseudo_ld_imm64(env); } adjust_btf_func(env); err_release_maps: if (!env->prog->aux->used_maps) /* if we didn't copy map pointers into bpf_prog_info, release * them now. Otherwise free_used_maps() will release them. */ release_maps(env); if (!env->prog->aux->used_btfs) release_btfs(env); /* extension progs temporarily inherit the attach_type of their targets for verification purposes, so set it back to zero before returning */ if (env->prog->type == BPF_PROG_TYPE_EXT) env->prog->expected_attach_type = 0; *prog = env->prog; err_unlock: if (!is_priv) mutex_unlock(&bpf_verifier_lock); vfree(env->insn_aux_data); err_free_env: kvfree(env); return ret; } |
| 515 515 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * drivers/base/power/wakeup.c - System wakeup events framework * * Copyright (c) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc. */ #define pr_fmt(fmt) "PM: " fmt #include <linux/device.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/capability.h> #include <linux/export.h> #include <linux/suspend.h> #include <linux/seq_file.h> #include <linux/debugfs.h> #include <linux/pm_wakeirq.h> #include <linux/irq.h> #include <linux/irqdesc.h> #include <linux/wakeup_reason.h> #include <trace/events/power.h> #include "power.h" #ifndef CONFIG_SUSPEND suspend_state_t pm_suspend_target_state; #define pm_suspend_target_state (PM_SUSPEND_ON) #endif #define list_for_each_entry_rcu_locked(pos, head, member) \ list_for_each_entry_rcu(pos, head, member, \ srcu_read_lock_held(&wakeup_srcu)) /* * If set, the suspend/hibernate code will abort transitions to a sleep state * if wakeup events are registered during or immediately before the transition. */ bool events_check_enabled __read_mostly; /* First wakeup IRQ seen by the kernel in the last cycle. */ static unsigned int wakeup_irq[2] __read_mostly; static DEFINE_RAW_SPINLOCK(wakeup_irq_lock); /* If greater than 0 and the system is suspending, terminate the suspend. */ static atomic_t pm_abort_suspend __read_mostly; /* * Combined counters of registered wakeup events and wakeup events in progress. * They need to be modified together atomically, so it's better to use one * atomic variable to hold them both. */ static atomic_t combined_event_count = ATOMIC_INIT(0); #define IN_PROGRESS_BITS (sizeof(int) * 4) #define MAX_IN_PROGRESS ((1 << IN_PROGRESS_BITS) - 1) static void split_counters(unsigned int *cnt, unsigned int *inpr) { unsigned int comb = atomic_read(&combined_event_count); *cnt = (comb >> IN_PROGRESS_BITS); *inpr = comb & MAX_IN_PROGRESS; } /* A preserved old value of the events counter. */ static unsigned int saved_count; static DEFINE_RAW_SPINLOCK(events_lock); static void pm_wakeup_timer_fn(struct timer_list *t); static LIST_HEAD(wakeup_sources); static DECLARE_WAIT_QUEUE_HEAD(wakeup_count_wait_queue); DEFINE_STATIC_SRCU(wakeup_srcu); static struct wakeup_source deleted_ws = { .name = "deleted", .lock = __SPIN_LOCK_UNLOCKED(deleted_ws.lock), }; static DEFINE_IDA(wakeup_ida); /** * wakeup_source_create - Create a struct wakeup_source object. * @name: Name of the new wakeup source. */ struct wakeup_source *wakeup_source_create(const char *name) { struct wakeup_source *ws; const char *ws_name; int id; ws = kzalloc(sizeof(*ws), GFP_KERNEL); if (!ws) goto err_ws; ws_name = kstrdup_const(name, GFP_KERNEL); if (!ws_name) goto err_name; ws->name = ws_name; id = ida_alloc(&wakeup_ida, GFP_KERNEL); if (id < 0) goto err_id; ws->id = id; return ws; err_id: kfree_const(ws->name); err_name: kfree(ws); err_ws: return NULL; } EXPORT_SYMBOL_GPL(wakeup_source_create); /* * Record wakeup_source statistics being deleted into a dummy wakeup_source. */ static void wakeup_source_record(struct wakeup_source *ws) { unsigned long flags; spin_lock_irqsave(&deleted_ws.lock, flags); if (ws->event_count) { deleted_ws.total_time = ktime_add(deleted_ws.total_time, ws->total_time); deleted_ws.prevent_sleep_time = ktime_add(deleted_ws.prevent_sleep_time, ws->prevent_sleep_time); deleted_ws.max_time = ktime_compare(deleted_ws.max_time, ws->max_time) > 0 ? deleted_ws.max_time : ws->max_time; deleted_ws.event_count += ws->event_count; deleted_ws.active_count += ws->active_count; deleted_ws.relax_count += ws->relax_count; deleted_ws.expire_count += ws->expire_count; deleted_ws.wakeup_count += ws->wakeup_count; } spin_unlock_irqrestore(&deleted_ws.lock, flags); } static void wakeup_source_free(struct wakeup_source *ws) { ida_free(&wakeup_ida, ws->id); kfree_const(ws->name); kfree(ws); } /** * wakeup_source_destroy - Destroy a struct wakeup_source object. * @ws: Wakeup source to destroy. * * Use only for wakeup source objects created with wakeup_source_create(). */ void wakeup_source_destroy(struct wakeup_source *ws) { if (!ws) return; __pm_relax(ws); wakeup_source_record(ws); wakeup_source_free(ws); } EXPORT_SYMBOL_GPL(wakeup_source_destroy); /** * wakeup_source_add - Add given object to the list of wakeup sources. * @ws: Wakeup source object to add to the list. */ void wakeup_source_add(struct wakeup_source *ws) { unsigned long flags; if (WARN_ON(!ws)) return; spin_lock_init(&ws->lock); timer_setup(&ws->timer, pm_wakeup_timer_fn, 0); ws->active = false; raw_spin_lock_irqsave(&events_lock, flags); list_add_rcu(&ws->entry, &wakeup_sources); raw_spin_unlock_irqrestore(&events_lock, flags); } EXPORT_SYMBOL_GPL(wakeup_source_add); /** * wakeup_source_remove - Remove given object from the wakeup sources list. * @ws: Wakeup source object to remove from the list. */ void wakeup_source_remove(struct wakeup_source *ws) { unsigned long flags; if (WARN_ON(!ws)) return; raw_spin_lock_irqsave(&events_lock, flags); list_del_rcu(&ws->entry); raw_spin_unlock_irqrestore(&events_lock, flags); synchronize_srcu(&wakeup_srcu); del_timer_sync(&ws->timer); /* * Clear timer.function to make wakeup_source_not_registered() treat * this wakeup source as not registered. */ ws->timer.function = NULL; } EXPORT_SYMBOL_GPL(wakeup_source_remove); /** * wakeup_source_register - Create wakeup source and add it to the list. * @dev: Device this wakeup source is associated with (or NULL if virtual). * @name: Name of the wakeup source to register. */ struct wakeup_source *wakeup_source_register(struct device *dev, const char *name) { struct wakeup_source *ws; int ret; ws = wakeup_source_create(name); if (ws) { if (!dev || device_is_registered(dev)) { ret = wakeup_source_sysfs_add(dev, ws); if (ret) { wakeup_source_free(ws); return NULL; } } wakeup_source_add(ws); } return ws; } EXPORT_SYMBOL_GPL(wakeup_source_register); /** * wakeup_source_unregister - Remove wakeup source from the list and remove it. * @ws: Wakeup source object to unregister. */ void wakeup_source_unregister(struct wakeup_source *ws) { if (ws) { wakeup_source_remove(ws); if (ws->dev) wakeup_source_sysfs_remove(ws); wakeup_source_destroy(ws); } } EXPORT_SYMBOL_GPL(wakeup_source_unregister); /** * wakeup_sources_read_lock - Lock wakeup source list for read. * * Returns an index of srcu lock for struct wakeup_srcu. * This index must be passed to the matching wakeup_sources_read_unlock(). */ int wakeup_sources_read_lock(void) { return srcu_read_lock(&wakeup_srcu); } EXPORT_SYMBOL_GPL(wakeup_sources_read_lock); /** * wakeup_sources_read_unlock - Unlock wakeup source list. * @idx: return value from corresponding wakeup_sources_read_lock() */ void wakeup_sources_read_unlock(int idx) { srcu_read_unlock(&wakeup_srcu, idx); } EXPORT_SYMBOL_GPL(wakeup_sources_read_unlock); /** * wakeup_sources_walk_start - Begin a walk on wakeup source list * * Returns first object of the list of wakeup sources. * * Note that to be safe, wakeup sources list needs to be locked by calling * wakeup_source_read_lock() for this. */ struct wakeup_source *wakeup_sources_walk_start(void) { struct list_head *ws_head = &wakeup_sources; return list_entry_rcu(ws_head->next, struct wakeup_source, entry); } EXPORT_SYMBOL_GPL(wakeup_sources_walk_start); /** * wakeup_sources_walk_next - Get next wakeup source from the list * @ws: Previous wakeup source object * * Note that to be safe, wakeup sources list needs to be locked by calling * wakeup_source_read_lock() for this. */ struct wakeup_source *wakeup_sources_walk_next(struct wakeup_source *ws) { struct list_head *ws_head = &wakeup_sources; return list_next_or_null_rcu(ws_head, &ws->entry, struct wakeup_source, entry); } EXPORT_SYMBOL_GPL(wakeup_sources_walk_next); /** * device_wakeup_attach - Attach a wakeup source object to a device object. * @dev: Device to handle. * @ws: Wakeup source object to attach to @dev. * * This causes @dev to be treated as a wakeup device. */ static int device_wakeup_attach(struct device *dev, struct wakeup_source *ws) { spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { spin_unlock_irq(&dev->power.lock); return -EEXIST; } dev->power.wakeup = ws; if (dev->power.wakeirq) device_wakeup_attach_irq(dev, dev->power.wakeirq); spin_unlock_irq(&dev->power.lock); return 0; } /** * device_wakeup_enable - Enable given device to be a wakeup source. * @dev: Device to handle. * * Create a wakeup source object, register it and attach it to @dev. */ int device_wakeup_enable(struct device *dev) { struct wakeup_source *ws; int ret; if (!dev || !dev->power.can_wakeup) return -EINVAL; if (pm_suspend_target_state != PM_SUSPEND_ON) dev_dbg(dev, "Suspicious %s() during system transition!\n", __func__); ws = wakeup_source_register(dev, dev_name(dev)); if (!ws) return -ENOMEM; ret = device_wakeup_attach(dev, ws); if (ret) wakeup_source_unregister(ws); return ret; } EXPORT_SYMBOL_GPL(device_wakeup_enable); /** * device_wakeup_attach_irq - Attach a wakeirq to a wakeup source * @dev: Device to handle * @wakeirq: Device specific wakeirq entry * * Attach a device wakeirq to the wakeup source so the device * wake IRQ can be configured automatically for suspend and * resume. * * Call under the device's power.lock lock. */ void device_wakeup_attach_irq(struct device *dev, struct wake_irq *wakeirq) { struct wakeup_source *ws; ws = dev->power.wakeup; if (!ws) return; if (ws->wakeirq) dev_err(dev, "Leftover wakeup IRQ found, overriding\n"); ws->wakeirq = wakeirq; } /** * device_wakeup_detach_irq - Detach a wakeirq from a wakeup source * @dev: Device to handle * * Removes a device wakeirq from the wakeup source. * * Call under the device's power.lock lock. */ void device_wakeup_detach_irq(struct device *dev) { struct wakeup_source *ws; ws = dev->power.wakeup; if (ws) ws->wakeirq = NULL; } /** * device_wakeup_arm_wake_irqs - * * Iterates over the list of device wakeirqs to arm them. */ void device_wakeup_arm_wake_irqs(void) { struct wakeup_source *ws; int srcuidx; srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) dev_pm_arm_wake_irq(ws->wakeirq); srcu_read_unlock(&wakeup_srcu, srcuidx); } /** * device_wakeup_disarm_wake_irqs - * * Iterates over the list of device wakeirqs to disarm them. */ void device_wakeup_disarm_wake_irqs(void) { struct wakeup_source *ws; int srcuidx; srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) dev_pm_disarm_wake_irq(ws->wakeirq); srcu_read_unlock(&wakeup_srcu, srcuidx); } /** * device_wakeup_detach - Detach a device's wakeup source object from it. * @dev: Device to detach the wakeup source object from. * * After it returns, @dev will not be treated as a wakeup device any more. */ static struct wakeup_source *device_wakeup_detach(struct device *dev) { struct wakeup_source *ws; spin_lock_irq(&dev->power.lock); ws = dev->power.wakeup; dev->power.wakeup = NULL; spin_unlock_irq(&dev->power.lock); return ws; } /** * device_wakeup_disable - Do not regard a device as a wakeup source any more. * @dev: Device to handle. * * Detach the @dev's wakeup source object from it, unregister this wakeup source * object and destroy it. */ int device_wakeup_disable(struct device *dev) { struct wakeup_source *ws; if (!dev || !dev->power.can_wakeup) return -EINVAL; ws = device_wakeup_detach(dev); wakeup_source_unregister(ws); return 0; } EXPORT_SYMBOL_GPL(device_wakeup_disable); /** * device_set_wakeup_capable - Set/reset device wakeup capability flag. * @dev: Device to handle. * @capable: Whether or not @dev is capable of waking up the system from sleep. * * If @capable is set, set the @dev's power.can_wakeup flag and add its * wakeup-related attributes to sysfs. Otherwise, unset the @dev's * power.can_wakeup flag and remove its wakeup-related attributes from sysfs. * * This function may sleep and it can't be called from any context where * sleeping is not allowed. */ void device_set_wakeup_capable(struct device *dev, bool capable) { if (!!dev->power.can_wakeup == !!capable) return; dev->power.can_wakeup = capable; if (device_is_registered(dev) && !list_empty(&dev->power.entry)) { if (capable) { int ret = wakeup_sysfs_add(dev); if (ret) dev_info(dev, "Wakeup sysfs attributes not added\n"); } else { wakeup_sysfs_remove(dev); } } } EXPORT_SYMBOL_GPL(device_set_wakeup_capable); /** * device_set_wakeup_enable - Enable or disable a device to wake up the system. * @dev: Device to handle. * @enable: enable/disable flag */ int device_set_wakeup_enable(struct device *dev, bool enable) { return enable ? device_wakeup_enable(dev) : device_wakeup_disable(dev); } EXPORT_SYMBOL_GPL(device_set_wakeup_enable); /** * wakeup_source_not_registered - validate the given wakeup source. * @ws: Wakeup source to be validated. */ static bool wakeup_source_not_registered(struct wakeup_source *ws) { /* * Use timer struct to check if the given source is initialized * by wakeup_source_add. */ return ws->timer.function != pm_wakeup_timer_fn; } /* * The functions below use the observation that each wakeup event starts a * period in which the system should not be suspended. The moment this period * will end depends on how the wakeup event is going to be processed after being * detected and all of the possible cases can be divided into two distinct * groups. * * First, a wakeup event may be detected by the same functional unit that will * carry out the entire processing of it and possibly will pass it to user space * for further processing. In that case the functional unit that has detected * the event may later "close" the "no suspend" period associated with it * directly as soon as it has been dealt with. The pair of pm_stay_awake() and * pm_relax(), balanced with each other, is supposed to be used in such * situations. * * Second, a wakeup event may be detected by one functional unit and processed * by another one. In that case the unit that has detected it cannot really * "close" the "no suspend" period associated with it, unless it knows in * advance what's going to happen to the event during processing. This * knowledge, however, may not be available to it, so it can simply specify time * to wait before the system can be suspended and pass it as the second * argument of pm_wakeup_event(). * * It is valid to call pm_relax() after pm_wakeup_event(), in which case the * "no suspend" period will be ended either by the pm_relax(), or by the timer * function executed when the timer expires, whichever comes first. */ /** * wakeup_source_activate - Mark given wakeup source as active. * @ws: Wakeup source to handle. * * Update the @ws' statistics and, if @ws has just been activated, notify the PM * core of the event by incrementing the counter of the wakeup events being * processed. */ static void wakeup_source_activate(struct wakeup_source *ws) { unsigned int cec; if (WARN_ONCE(wakeup_source_not_registered(ws), "unregistered wakeup source\n")) return; ws->active = true; ws->active_count++; ws->last_time = ktime_get(); if (ws->autosleep_enabled) ws->start_prevent_time = ws->last_time; /* Increment the counter of events in progress. */ cec = atomic_inc_return(&combined_event_count); trace_wakeup_source_activate(ws->name, cec); } /** * wakeup_source_report_event - Report wakeup event using the given source. * @ws: Wakeup source to report the event for. * @hard: If set, abort suspends in progress and wake up from suspend-to-idle. */ static void wakeup_source_report_event(struct wakeup_source *ws, bool hard) { ws->event_count++; /* This is racy, but the counter is approximate anyway. */ if (events_check_enabled) ws->wakeup_count++; if (!ws->active) wakeup_source_activate(ws); if (hard) pm_system_wakeup(); } /** * __pm_stay_awake - Notify the PM core of a wakeup event. * @ws: Wakeup source object associated with the source of the event. * * It is safe to call this function from interrupt context. */ void __pm_stay_awake(struct wakeup_source *ws) { unsigned long flags; if (!ws) return; spin_lock_irqsave(&ws->lock, flags); wakeup_source_report_event(ws, false); del_timer(&ws->timer); ws->timer_expires = 0; spin_unlock_irqrestore(&ws->lock, flags); } EXPORT_SYMBOL_GPL(__pm_stay_awake); /** * pm_stay_awake - Notify the PM core that a wakeup event is being processed. * @dev: Device the wakeup event is related to. * * Notify the PM core of a wakeup event (signaled by @dev) by calling * __pm_stay_awake for the @dev's wakeup source object. * * Call this function after detecting of a wakeup event if pm_relax() is going * to be called directly after processing the event (and possibly passing it to * user space for further processing). */ void pm_stay_awake(struct device *dev) { unsigned long flags; if (!dev) return; spin_lock_irqsave(&dev->power.lock, flags); __pm_stay_awake(dev->power.wakeup); spin_unlock_irqrestore(&dev->power.lock, flags); } EXPORT_SYMBOL_GPL(pm_stay_awake); #ifdef CONFIG_PM_AUTOSLEEP static void update_prevent_sleep_time(struct wakeup_source *ws, ktime_t now) { ktime_t delta = ktime_sub(now, ws->start_prevent_time); ws->prevent_sleep_time = ktime_add(ws->prevent_sleep_time, delta); } #else static inline void update_prevent_sleep_time(struct wakeup_source *ws, ktime_t now) {} #endif /** * wakeup_source_deactivate - Mark given wakeup source as inactive. * @ws: Wakeup source to handle. * * Update the @ws' statistics and notify the PM core that the wakeup source has * become inactive by decrementing the counter of wakeup events being processed * and incrementing the counter of registered wakeup events. */ static void wakeup_source_deactivate(struct wakeup_source *ws) { unsigned int cnt, inpr, cec; ktime_t duration; ktime_t now; ws->relax_count++; /* * __pm_relax() may be called directly or from a timer function. * If it is called directly right after the timer function has been * started, but before the timer function calls __pm_relax(), it is * possible that __pm_stay_awake() will be called in the meantime and * will set ws->active. Then, ws->active may be cleared immediately * by the __pm_relax() called from the timer function, but in such a * case ws->relax_count will be different from ws->active_count. */ if (ws->relax_count != ws->active_count) { ws->relax_count--; return; } ws->active = false; now = ktime_get(); duration = ktime_sub(now, ws->last_time); ws->total_time = ktime_add(ws->total_time, duration); if (ktime_to_ns(duration) > ktime_to_ns(ws->max_time)) ws->max_time = duration; ws->last_time = now; del_timer(&ws->timer); ws->timer_expires = 0; if (ws->autosleep_enabled) update_prevent_sleep_time(ws, now); /* * Increment the counter of registered wakeup events and decrement the * counter of wakeup events in progress simultaneously. */ cec = atomic_add_return(MAX_IN_PROGRESS, &combined_event_count); trace_wakeup_source_deactivate(ws->name, cec); split_counters(&cnt, &inpr); if (!inpr && waitqueue_active(&wakeup_count_wait_queue)) wake_up(&wakeup_count_wait_queue); } /** * __pm_relax - Notify the PM core that processing of a wakeup event has ended. * @ws: Wakeup source object associated with the source of the event. * * Call this function for wakeup events whose processing started with calling * __pm_stay_awake(). * * It is safe to call it from interrupt context. */ void __pm_relax(struct wakeup_source *ws) { unsigned long flags; if (!ws) return; spin_lock_irqsave(&ws->lock, flags); if (ws->active) wakeup_source_deactivate(ws); spin_unlock_irqrestore(&ws->lock, flags); } EXPORT_SYMBOL_GPL(__pm_relax); /** * pm_relax - Notify the PM core that processing of a wakeup event has ended. * @dev: Device that signaled the event. * * Execute __pm_relax() for the @dev's wakeup source object. */ void pm_relax(struct device *dev) { unsigned long flags; if (!dev) return; spin_lock_irqsave(&dev->power.lock, flags); __pm_relax(dev->power.wakeup); spin_unlock_irqrestore(&dev->power.lock, flags); } EXPORT_SYMBOL_GPL(pm_relax); /** * pm_wakeup_timer_fn - Delayed finalization of a wakeup event. * @t: timer list * * Call wakeup_source_deactivate() for the wakeup source whose address is stored * in @data if it is currently active and its timer has not been canceled and * the expiration time of the timer is not in future. */ static void pm_wakeup_timer_fn(struct timer_list *t) { struct wakeup_source *ws = from_timer(ws, t, timer); unsigned long flags; spin_lock_irqsave(&ws->lock, flags); if (ws->active && ws->timer_expires && time_after_eq(jiffies, ws->timer_expires)) { wakeup_source_deactivate(ws); ws->expire_count++; } spin_unlock_irqrestore(&ws->lock, flags); } /** * pm_wakeup_ws_event - Notify the PM core of a wakeup event. * @ws: Wakeup source object associated with the event source. * @msec: Anticipated event processing time (in milliseconds). * @hard: If set, abort suspends in progress and wake up from suspend-to-idle. * * Notify the PM core of a wakeup event whose source is @ws that will take * approximately @msec milliseconds to be processed by the kernel. If @ws is * not active, activate it. If @msec is nonzero, set up the @ws' timer to * execute pm_wakeup_timer_fn() in future. * * It is safe to call this function from interrupt context. */ void pm_wakeup_ws_event(struct wakeup_source *ws, unsigned int msec, bool hard) { unsigned long flags; unsigned long expires; if (!ws) return; spin_lock_irqsave(&ws->lock, flags); wakeup_source_report_event(ws, hard); if (!msec) { wakeup_source_deactivate(ws); goto unlock; } expires = jiffies + msecs_to_jiffies(msec); if (!expires) expires = 1; if (!ws->timer_expires || time_after(expires, ws->timer_expires)) { mod_timer(&ws->timer, expires); ws->timer_expires = expires; } unlock: spin_unlock_irqrestore(&ws->lock, flags); } EXPORT_SYMBOL_GPL(pm_wakeup_ws_event); /** * pm_wakeup_dev_event - Notify the PM core of a wakeup event. * @dev: Device the wakeup event is related to. * @msec: Anticipated event processing time (in milliseconds). * @hard: If set, abort suspends in progress and wake up from suspend-to-idle. * * Call pm_wakeup_ws_event() for the @dev's wakeup source object. */ void pm_wakeup_dev_event(struct device *dev, unsigned int msec, bool hard) { unsigned long flags; if (!dev) return; spin_lock_irqsave(&dev->power.lock, flags); pm_wakeup_ws_event(dev->power.wakeup, msec, hard); spin_unlock_irqrestore(&dev->power.lock, flags); } EXPORT_SYMBOL_GPL(pm_wakeup_dev_event); void pm_get_active_wakeup_sources(char *pending_wakeup_source, size_t max) { struct wakeup_source *ws, *last_active_ws = NULL; int len = 0; bool active = false; rcu_read_lock(); list_for_each_entry_rcu(ws, &wakeup_sources, entry) { if (ws->active && len < max) { if (!active) len += scnprintf(pending_wakeup_source, max, "Pending Wakeup Sources: "); len += scnprintf(pending_wakeup_source + len, max - len, "%s ", ws->name); active = true; } else if (!active && (!last_active_ws || ktime_to_ns(ws->last_time) > ktime_to_ns(last_active_ws->last_time))) { last_active_ws = ws; } } if (!active && last_active_ws) { scnprintf(pending_wakeup_source, max, "Last active Wakeup Source: %s", last_active_ws->name); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(pm_get_active_wakeup_sources); void pm_print_active_wakeup_sources(void) { struct wakeup_source *ws; int srcuidx, active = 0; struct wakeup_source *last_activity_ws = NULL; srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) { if (ws->active) { pm_pr_dbg("active wakeup source: %s\n", ws->name); active = 1; } else if (!active && (!last_activity_ws || ktime_to_ns(ws->last_time) > ktime_to_ns(last_activity_ws->last_time))) { last_activity_ws = ws; } } if (!active && last_activity_ws) pm_pr_dbg("last active wakeup source: %s\n", last_activity_ws->name); srcu_read_unlock(&wakeup_srcu, srcuidx); } EXPORT_SYMBOL_GPL(pm_print_active_wakeup_sources); /** * pm_wakeup_pending - Check if power transition in progress should be aborted. * * Compare the current number of registered wakeup events with its preserved * value from the past and return true if new wakeup events have been registered * since the old value was stored. Also return true if the current number of * wakeup events being processed is different from zero. */ bool pm_wakeup_pending(void) { unsigned long flags; bool ret = false; char suspend_abort[MAX_SUSPEND_ABORT_LEN]; raw_spin_lock_irqsave(&events_lock, flags); if (events_check_enabled) { unsigned int cnt, inpr; split_counters(&cnt, &inpr); ret = (cnt != saved_count || inpr > 0); events_check_enabled = !ret; } raw_spin_unlock_irqrestore(&events_lock, flags); if (ret) { pm_pr_dbg("Wakeup pending, aborting suspend\n"); pm_print_active_wakeup_sources(); pm_get_active_wakeup_sources(suspend_abort, MAX_SUSPEND_ABORT_LEN); log_suspend_abort_reason(suspend_abort); pr_info("PM: %s\n", suspend_abort); } return ret || atomic_read(&pm_abort_suspend) > 0; } EXPORT_SYMBOL_GPL(pm_wakeup_pending); void pm_system_wakeup(void) { atomic_inc(&pm_abort_suspend); s2idle_wake(); } EXPORT_SYMBOL_GPL(pm_system_wakeup); void pm_system_cancel_wakeup(void) { atomic_dec_if_positive(&pm_abort_suspend); } void pm_wakeup_clear(unsigned int irq_number) { raw_spin_lock_irq(&wakeup_irq_lock); if (irq_number && wakeup_irq[0] == irq_number) wakeup_irq[0] = wakeup_irq[1]; else wakeup_irq[0] = 0; wakeup_irq[1] = 0; raw_spin_unlock_irq(&wakeup_irq_lock); if (!irq_number) atomic_set(&pm_abort_suspend, 0); } void pm_system_irq_wakeup(unsigned int irq_number) { unsigned long flags; raw_spin_lock_irqsave(&wakeup_irq_lock, flags); if (wakeup_irq[0] == 0) wakeup_irq[0] = irq_number; else if (wakeup_irq[1] == 0) wakeup_irq[1] = irq_number; else irq_number = 0; pm_pr_dbg("Triggering wakeup from IRQ %d\n", irq_number); raw_spin_unlock_irqrestore(&wakeup_irq_lock, flags); if (irq_number) { struct irq_desc *desc; const char *name = "null"; desc = irq_to_desc(irq_number); if (desc == NULL) name = "stray irq"; else if (desc->action && desc->action->name) name = desc->action->name; log_irq_wakeup_reason(irq_number); pr_warn("%s: %d triggered %s\n", __func__, irq_number, name); pm_system_wakeup(); } } unsigned int pm_wakeup_irq(void) { return wakeup_irq[0]; } EXPORT_SYMBOL_GPL(pm_wakeup_irq); /** * pm_get_wakeup_count - Read the number of registered wakeup events. * @count: Address to store the value at. * @block: Whether or not to block. * * Store the number of registered wakeup events at the address in @count. If * @block is set, block until the current number of wakeup events being * processed is zero. * * Return 'false' if the current number of wakeup events being processed is * nonzero. Otherwise return 'true'. */ bool pm_get_wakeup_count(unsigned int *count, bool block) { unsigned int cnt, inpr; if (block) { DEFINE_WAIT(wait); for (;;) { prepare_to_wait(&wakeup_count_wait_queue, &wait, TASK_INTERRUPTIBLE); split_counters(&cnt, &inpr); if (inpr == 0 || signal_pending(current)) break; pm_print_active_wakeup_sources(); schedule(); } finish_wait(&wakeup_count_wait_queue, &wait); } split_counters(&cnt, &inpr); *count = cnt; return !inpr; } /** * pm_save_wakeup_count - Save the current number of registered wakeup events. * @count: Value to compare with the current number of registered wakeup events. * * If @count is equal to the current number of registered wakeup events and the * current number of wakeup events being processed is zero, store @count as the * old number of registered wakeup events for pm_check_wakeup_events(), enable * wakeup events detection and return 'true'. Otherwise disable wakeup events * detection and return 'false'. */ bool pm_save_wakeup_count(unsigned int count) { unsigned int cnt, inpr; unsigned long flags; events_check_enabled = false; raw_spin_lock_irqsave(&events_lock, flags); split_counters(&cnt, &inpr); if (cnt == count && inpr == 0) { saved_count = count; events_check_enabled = true; } raw_spin_unlock_irqrestore(&events_lock, flags); return events_check_enabled; } #ifdef CONFIG_PM_AUTOSLEEP /** * pm_wakep_autosleep_enabled - Modify autosleep_enabled for all wakeup sources. * @set: Whether to set or to clear the autosleep_enabled flags. */ void pm_wakep_autosleep_enabled(bool set) { struct wakeup_source *ws; ktime_t now = ktime_get(); int srcuidx; srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) { spin_lock_irq(&ws->lock); if (ws->autosleep_enabled != set) { ws->autosleep_enabled = set; if (ws->active) { if (set) ws->start_prevent_time = now; else update_prevent_sleep_time(ws, now); } } spin_unlock_irq(&ws->lock); } srcu_read_unlock(&wakeup_srcu, srcuidx); } #endif /* CONFIG_PM_AUTOSLEEP */ /** * print_wakeup_source_stats - Print wakeup source statistics information. * @m: seq_file to print the statistics into. * @ws: Wakeup source object to print the statistics for. */ static int print_wakeup_source_stats(struct seq_file *m, struct wakeup_source *ws) { unsigned long flags; ktime_t total_time; ktime_t max_time; unsigned long active_count; ktime_t active_time; ktime_t prevent_sleep_time; spin_lock_irqsave(&ws->lock, flags); total_time = ws->total_time; max_time = ws->max_time; prevent_sleep_time = ws->prevent_sleep_time; active_count = ws->active_count; if (ws->active) { ktime_t now = ktime_get(); active_time = ktime_sub(now, ws->last_time); total_time = ktime_add(total_time, active_time); if (active_time > max_time) max_time = active_time; if (ws->autosleep_enabled) prevent_sleep_time = ktime_add(prevent_sleep_time, ktime_sub(now, ws->start_prevent_time)); } else { active_time = 0; } seq_printf(m, "%-12s\t%lu\t\t%lu\t\t%lu\t\t%lu\t\t%lld\t\t%lld\t\t%lld\t\t%lld\t\t%lld\n", ws->name, active_count, ws->event_count, ws->wakeup_count, ws->expire_count, ktime_to_ms(active_time), ktime_to_ms(total_time), ktime_to_ms(max_time), ktime_to_ms(ws->last_time), ktime_to_ms(prevent_sleep_time)); spin_unlock_irqrestore(&ws->lock, flags); return 0; } static void *wakeup_sources_stats_seq_start(struct seq_file *m, loff_t *pos) { struct wakeup_source *ws; loff_t n = *pos; int *srcuidx = m->private; if (n == 0) { seq_puts(m, "name\t\tactive_count\tevent_count\twakeup_count\t" "expire_count\tactive_since\ttotal_time\tmax_time\t" "last_change\tprevent_suspend_time\n"); } *srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) { if (n-- <= 0) return ws; } return NULL; } static void *wakeup_sources_stats_seq_next(struct seq_file *m, void *v, loff_t *pos) { struct wakeup_source *ws = v; struct wakeup_source *next_ws = NULL; ++(*pos); list_for_each_entry_continue_rcu(ws, &wakeup_sources, entry) { next_ws = ws; break; } if (!next_ws) print_wakeup_source_stats(m, &deleted_ws); return next_ws; } static void wakeup_sources_stats_seq_stop(struct seq_file *m, void *v) { int *srcuidx = m->private; srcu_read_unlock(&wakeup_srcu, *srcuidx); } /** * wakeup_sources_stats_seq_show - Print wakeup sources statistics information. * @m: seq_file to print the statistics into. * @v: wakeup_source of each iteration */ static int wakeup_sources_stats_seq_show(struct seq_file *m, void *v) { struct wakeup_source *ws = v; print_wakeup_source_stats(m, ws); return 0; } static const struct seq_operations wakeup_sources_stats_seq_ops = { .start = wakeup_sources_stats_seq_start, .next = wakeup_sources_stats_seq_next, .stop = wakeup_sources_stats_seq_stop, .show = wakeup_sources_stats_seq_show, }; static int wakeup_sources_stats_open(struct inode *inode, struct file *file) { return seq_open_private(file, &wakeup_sources_stats_seq_ops, sizeof(int)); } static const struct file_operations wakeup_sources_stats_fops = { .owner = THIS_MODULE, .open = wakeup_sources_stats_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release_private, }; static int __init wakeup_sources_debugfs_init(void) { debugfs_create_file("wakeup_sources", 0444, NULL, NULL, &wakeup_sources_stats_fops); return 0; } postcore_initcall(wakeup_sources_debugfs_init); |
| 526 640 640 640 640 640 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 | #include <linux/rtnetlink.h> #include <linux/notifier.h> #include <linux/rcupdate.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/fib_notifier.h> static unsigned int fib_notifier_net_id; struct fib_notifier_net { struct list_head fib_notifier_ops; struct atomic_notifier_head fib_chain; }; int call_fib_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info) { int err; err = nb->notifier_call(nb, event_type, info); return notifier_to_errno(err); } EXPORT_SYMBOL(call_fib_notifier); int call_fib_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info) { struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); int err; err = atomic_notifier_call_chain(&fn_net->fib_chain, event_type, info); return notifier_to_errno(err); } EXPORT_SYMBOL(call_fib_notifiers); static unsigned int fib_seq_sum(struct net *net) { struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); struct fib_notifier_ops *ops; unsigned int fib_seq = 0; rtnl_lock(); rcu_read_lock(); list_for_each_entry_rcu(ops, &fn_net->fib_notifier_ops, list) { if (!try_module_get(ops->owner)) continue; fib_seq += ops->fib_seq_read(net); module_put(ops->owner); } rcu_read_unlock(); rtnl_unlock(); return fib_seq; } static int fib_net_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); struct fib_notifier_ops *ops; int err = 0; rcu_read_lock(); list_for_each_entry_rcu(ops, &fn_net->fib_notifier_ops, list) { if (!try_module_get(ops->owner)) continue; err = ops->fib_dump(net, nb, extack); module_put(ops->owner); if (err) goto unlock; } unlock: rcu_read_unlock(); return err; } static bool fib_dump_is_consistent(struct net *net, struct notifier_block *nb, void (*cb)(struct notifier_block *nb), unsigned int fib_seq) { struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); atomic_notifier_chain_register(&fn_net->fib_chain, nb); if (fib_seq == fib_seq_sum(net)) return true; atomic_notifier_chain_unregister(&fn_net->fib_chain, nb); if (cb) cb(nb); return false; } #define FIB_DUMP_MAX_RETRIES 5 int register_fib_notifier(struct net *net, struct notifier_block *nb, void (*cb)(struct notifier_block *nb), struct netlink_ext_ack *extack) { int retries = 0; int err; do { unsigned int fib_seq = fib_seq_sum(net); err = fib_net_dump(net, nb, extack); if (err) return err; if (fib_dump_is_consistent(net, nb, cb, fib_seq)) return 0; } while (++retries < FIB_DUMP_MAX_RETRIES); return -EBUSY; } EXPORT_SYMBOL(register_fib_notifier); int unregister_fib_notifier(struct net *net, struct notifier_block *nb) { struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); return atomic_notifier_chain_unregister(&fn_net->fib_chain, nb); } EXPORT_SYMBOL(unregister_fib_notifier); static int __fib_notifier_ops_register(struct fib_notifier_ops *ops, struct net *net) { struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); struct fib_notifier_ops *o; list_for_each_entry(o, &fn_net->fib_notifier_ops, list) if (ops->family == o->family) return -EEXIST; list_add_tail_rcu(&ops->list, &fn_net->fib_notifier_ops); return 0; } struct fib_notifier_ops * fib_notifier_ops_register(const struct fib_notifier_ops *tmpl, struct net *net) { struct fib_notifier_ops *ops; int err; ops = kmemdup(tmpl, sizeof(*ops), GFP_KERNEL); if (!ops) return ERR_PTR(-ENOMEM); err = __fib_notifier_ops_register(ops, net); if (err) goto err_register; return ops; err_register: kfree(ops); return ERR_PTR(err); } EXPORT_SYMBOL(fib_notifier_ops_register); void fib_notifier_ops_unregister(struct fib_notifier_ops *ops) { list_del_rcu(&ops->list); kfree_rcu(ops, rcu); } EXPORT_SYMBOL(fib_notifier_ops_unregister); static int __net_init fib_notifier_net_init(struct net *net) { struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); INIT_LIST_HEAD(&fn_net->fib_notifier_ops); ATOMIC_INIT_NOTIFIER_HEAD(&fn_net->fib_chain); return 0; } static void __net_exit fib_notifier_net_exit(struct net *net) { struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); WARN_ON_ONCE(!list_empty(&fn_net->fib_notifier_ops)); } static struct pernet_operations fib_notifier_net_ops = { .init = fib_notifier_net_init, .exit = fib_notifier_net_exit, .id = &fib_notifier_net_id, .size = sizeof(struct fib_notifier_net), }; static int __init fib_notifier_init(void) { return register_pernet_subsys(&fib_notifier_net_ops); } subsys_initcall(fib_notifier_init); |
| 21 52 408 43 44 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 | /* SPDX-License-Identifier: GPL-2.0-only */ /* include/net/xdp.h * * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. */ #ifndef __LINUX_NET_XDP_H__ #define __LINUX_NET_XDP_H__ #include <linux/skbuff.h> /* skb_shared_info */ /** * DOC: XDP RX-queue information * * The XDP RX-queue info (xdp_rxq_info) is associated with the driver * level RX-ring queues. It is information that is specific to how * the driver have configured a given RX-ring queue. * * Each xdp_buff frame received in the driver carries a (pointer) * reference to this xdp_rxq_info structure. This provides the XDP * data-path read-access to RX-info for both kernel and bpf-side * (limited subset). * * For now, direct access is only safe while running in NAPI/softirq * context. Contents are read-mostly and must not be updated during * driver NAPI/softirq poll. * * The driver usage API is a register and unregister API. * * The struct is not directly tied to the XDP prog. A new XDP prog * can be attached as long as it doesn't change the underlying * RX-ring. If the RX-ring does change significantly, the NIC driver * naturally need to stop the RX-ring before purging and reallocating * memory. In that process the driver MUST call unregister (which * also applies for driver shutdown and unload). The register API is * also mandatory during RX-ring setup. */ enum xdp_mem_type { MEM_TYPE_PAGE_SHARED = 0, /* Split-page refcnt based model */ MEM_TYPE_PAGE_ORDER0, /* Orig XDP full page model */ MEM_TYPE_PAGE_POOL, MEM_TYPE_XSK_BUFF_POOL, MEM_TYPE_MAX, }; /* XDP flags for ndo_xdp_xmit */ #define XDP_XMIT_FLUSH (1U << 0) /* doorbell signal consumer */ #define XDP_XMIT_FLAGS_MASK XDP_XMIT_FLUSH struct xdp_mem_info { u32 type; /* enum xdp_mem_type, but known size type */ u32 id; }; struct page_pool; struct xdp_rxq_info { struct net_device *dev; u32 queue_index; u32 reg_state; struct xdp_mem_info mem; unsigned int napi_id; u32 frag_size; } ____cacheline_aligned; /* perf critical, avoid false-sharing */ struct xdp_txq_info { struct net_device *dev; }; enum xdp_buff_flags { XDP_FLAGS_HAS_FRAGS = BIT(0), /* non-linear xdp buff */ XDP_FLAGS_FRAGS_PF_MEMALLOC = BIT(1), /* xdp paged memory is under * pressure */ }; struct xdp_buff { void *data; void *data_end; void *data_meta; void *data_hard_start; struct xdp_rxq_info *rxq; struct xdp_txq_info *txq; u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/ u32 flags; /* supported values defined in xdp_buff_flags */ }; static __always_inline bool xdp_buff_has_frags(struct xdp_buff *xdp) { return !!(xdp->flags & XDP_FLAGS_HAS_FRAGS); } static __always_inline void xdp_buff_set_frags_flag(struct xdp_buff *xdp) { xdp->flags |= XDP_FLAGS_HAS_FRAGS; } static __always_inline void xdp_buff_clear_frags_flag(struct xdp_buff *xdp) { xdp->flags &= ~XDP_FLAGS_HAS_FRAGS; } static __always_inline bool xdp_buff_is_frag_pfmemalloc(struct xdp_buff *xdp) { return !!(xdp->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); } static __always_inline void xdp_buff_set_frag_pfmemalloc(struct xdp_buff *xdp) { xdp->flags |= XDP_FLAGS_FRAGS_PF_MEMALLOC; } static __always_inline void xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq) { xdp->frame_sz = frame_sz; xdp->rxq = rxq; xdp->flags = 0; } static __always_inline void xdp_prepare_buff(struct xdp_buff *xdp, unsigned char *hard_start, int headroom, int data_len, const bool meta_valid) { unsigned char *data = hard_start + headroom; xdp->data_hard_start = hard_start; xdp->data = data; xdp->data_end = data + data_len; xdp->data_meta = meta_valid ? data : data + 1; } /* Reserve memory area at end-of data area. * * This macro reserves tailroom in the XDP buffer by limiting the * XDP/BPF data access to data_hard_end. Notice same area (and size) * is used for XDP_PASS, when constructing the SKB via build_skb(). */ #define xdp_data_hard_end(xdp) \ ((xdp)->data_hard_start + (xdp)->frame_sz - \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) static inline struct skb_shared_info * xdp_get_shared_info_from_buff(struct xdp_buff *xdp) { return (struct skb_shared_info *)xdp_data_hard_end(xdp); } static __always_inline unsigned int xdp_get_buff_len(struct xdp_buff *xdp) { unsigned int len = xdp->data_end - xdp->data; struct skb_shared_info *sinfo; if (likely(!xdp_buff_has_frags(xdp))) goto out; sinfo = xdp_get_shared_info_from_buff(xdp); len += sinfo->xdp_frags_size; out: return len; } struct xdp_frame { void *data; u16 len; u16 headroom; u32 metasize; /* uses lower 8-bits */ /* Lifetime of xdp_rxq_info is limited to NAPI/enqueue time, * while mem info is valid on remote CPU. */ struct xdp_mem_info mem; struct net_device *dev_rx; /* used by cpumap */ u32 frame_sz; u32 flags; /* supported values defined in xdp_buff_flags */ }; static __always_inline bool xdp_frame_has_frags(struct xdp_frame *frame) { return !!(frame->flags & XDP_FLAGS_HAS_FRAGS); } static __always_inline bool xdp_frame_is_frag_pfmemalloc(struct xdp_frame *frame) { return !!(frame->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); } #define XDP_BULK_QUEUE_SIZE 16 struct xdp_frame_bulk { int count; void *xa; void *q[XDP_BULK_QUEUE_SIZE]; }; static __always_inline void xdp_frame_bulk_init(struct xdp_frame_bulk *bq) { /* bq->count will be zero'ed when bq->xa gets updated */ bq->xa = NULL; } static inline struct skb_shared_info * xdp_get_shared_info_from_frame(struct xdp_frame *frame) { void *data_hard_start = frame->data - frame->headroom - sizeof(*frame); return (struct skb_shared_info *)(data_hard_start + frame->frame_sz - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); } struct xdp_cpumap_stats { unsigned int redirect; unsigned int pass; unsigned int drop; }; /* Clear kernel pointers in xdp_frame */ static inline void xdp_scrub_frame(struct xdp_frame *frame) { frame->data = NULL; frame->dev_rx = NULL; } static inline void xdp_update_skb_shared_info(struct sk_buff *skb, u8 nr_frags, unsigned int size, unsigned int truesize, bool pfmemalloc) { skb_shinfo(skb)->nr_frags = nr_frags; skb->len += size; skb->data_len += size; skb->truesize += truesize; skb->pfmemalloc |= pfmemalloc; } /* Avoids inlining WARN macro in fast-path */ void xdp_warn(const char *msg, const char *func, const int line); #define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__) struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp); struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct sk_buff *skb, struct net_device *dev); struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct net_device *dev); int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp); struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf); static inline void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) { xdp->data_hard_start = frame->data - frame->headroom - sizeof(*frame); xdp->data = frame->data; xdp->data_end = frame->data + frame->len; xdp->data_meta = frame->data - frame->metasize; xdp->frame_sz = frame->frame_sz; xdp->flags = frame->flags; } static inline int xdp_update_frame_from_buff(struct xdp_buff *xdp, struct xdp_frame *xdp_frame) { int metasize, headroom; /* Assure headroom is available for storing info */ headroom = xdp->data - xdp->data_hard_start; metasize = xdp->data - xdp->data_meta; metasize = metasize > 0 ? metasize : 0; if (unlikely((headroom - metasize) < sizeof(*xdp_frame))) return -ENOSPC; /* Catch if driver didn't reserve tailroom for skb_shared_info */ if (unlikely(xdp->data_end > xdp_data_hard_end(xdp))) { XDP_WARN("Driver BUG: missing reserved tailroom"); return -ENOSPC; } xdp_frame->data = xdp->data; xdp_frame->len = xdp->data_end - xdp->data; xdp_frame->headroom = headroom - sizeof(*xdp_frame); xdp_frame->metasize = metasize; xdp_frame->frame_sz = xdp->frame_sz; xdp_frame->flags = xdp->flags; return 0; } /* Convert xdp_buff to xdp_frame */ static inline struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp) { struct xdp_frame *xdp_frame; if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) return xdp_convert_zc_to_xdp_frame(xdp); /* Store info in top of packet */ xdp_frame = xdp->data_hard_start; if (unlikely(xdp_update_frame_from_buff(xdp, xdp_frame) < 0)) return NULL; /* rxq only valid until napi_schedule ends, convert to xdp_mem_info */ xdp_frame->mem = xdp->rxq->mem; return xdp_frame; } void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, struct xdp_buff *xdp); void xdp_return_frame(struct xdp_frame *xdpf); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf); void xdp_return_buff(struct xdp_buff *xdp); void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq); void xdp_return_frame_bulk(struct xdp_frame *xdpf, struct xdp_frame_bulk *bq); /* When sending xdp_frame into the network stack, then there is no * return point callback, which is needed to release e.g. DMA-mapping * resources with page_pool. Thus, have explicit function to release * frame resources. */ void __xdp_release_frame(void *data, struct xdp_mem_info *mem); static inline void xdp_release_frame(struct xdp_frame *xdpf) { struct xdp_mem_info *mem = &xdpf->mem; struct skb_shared_info *sinfo; int i; /* Curr only page_pool needs this */ if (mem->type != MEM_TYPE_PAGE_POOL) return; if (likely(!xdp_frame_has_frags(xdpf))) goto out; sinfo = xdp_get_shared_info_from_frame(xdpf); for (i = 0; i < sinfo->nr_frags; i++) { struct page *page = skb_frag_page(&sinfo->frags[i]); __xdp_release_frame(page_address(page), mem); } out: __xdp_release_frame(xdpf->data, mem); } static __always_inline unsigned int xdp_get_frame_len(struct xdp_frame *xdpf) { struct skb_shared_info *sinfo; unsigned int len = xdpf->len; if (likely(!xdp_frame_has_frags(xdpf))) goto out; sinfo = xdp_get_shared_info_from_frame(xdpf); len += sinfo->xdp_frags_size; out: return len; } int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index, unsigned int napi_id, u32 frag_size); static inline int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index, unsigned int napi_id) { return __xdp_rxq_info_reg(xdp_rxq, dev, queue_index, napi_id, 0); } void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq); void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq); int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, enum xdp_mem_type type, void *allocator); void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq); int xdp_reg_mem_model(struct xdp_mem_info *mem, enum xdp_mem_type type, void *allocator); void xdp_unreg_mem_model(struct xdp_mem_info *mem); /* Drivers not supporting XDP metadata can use this helper, which * rejects any room expansion for metadata as a result. */ static __always_inline void xdp_set_data_meta_invalid(struct xdp_buff *xdp) { xdp->data_meta = xdp->data + 1; } static __always_inline bool xdp_data_meta_unsupported(const struct xdp_buff *xdp) { return unlikely(xdp->data_meta > xdp->data); } static inline bool xdp_metalen_invalid(unsigned long metalen) { return (metalen & (sizeof(__u32) - 1)) || (metalen > 32); } struct xdp_attachment_info { struct bpf_prog *prog; u32 flags; }; struct netdev_bpf; void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf); #define DEV_MAP_BULK_SIZE XDP_BULK_QUEUE_SIZE #endif /* __LINUX_NET_XDP_H__ */ |
| 226 931 1946 570 112 5 200 200 51 51 51 1838 1839 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0+ */ #ifndef _LINUX_XARRAY_H #define _LINUX_XARRAY_H /* * eXtensible Arrays * Copyright (c) 2017 Microsoft Corporation * Author: Matthew Wilcox <willy@infradead.org> * * See Documentation/core-api/xarray.rst for how to use the XArray. */ #include <linux/bitmap.h> #include <linux/bug.h> #include <linux/compiler.h> #include <linux/gfp.h> #include <linux/kconfig.h> #include <linux/kernel.h> #include <linux/rcupdate.h> #include <linux/sched/mm.h> #include <linux/spinlock.h> #include <linux/types.h> /* * The bottom two bits of the entry determine how the XArray interprets * the contents: * * 00: Pointer entry * 10: Internal entry * x1: Value entry or tagged pointer * * Attempting to store internal entries in the XArray is a bug. * * Most internal entries are pointers to the next node in the tree. * The following internal entries have a special meaning: * * 0-62: Sibling entries * 256: Retry entry * 257: Zero entry * * Errors are also represented as internal entries, but use the negative * space (-4094 to -2). They're never stored in the slots array; only * returned by the normal API. */ #define BITS_PER_XA_VALUE (BITS_PER_LONG - 1) /** * xa_mk_value() - Create an XArray entry from an integer. * @v: Value to store in XArray. * * Context: Any context. * Return: An entry suitable for storing in the XArray. */ static inline void *xa_mk_value(unsigned long v) { WARN_ON((long)v < 0); return (void *)((v << 1) | 1); } /** * xa_to_value() - Get value stored in an XArray entry. * @entry: XArray entry. * * Context: Any context. * Return: The value stored in the XArray entry. */ static inline unsigned long xa_to_value(const void *entry) { return (unsigned long)entry >> 1; } /** * xa_is_value() - Determine if an entry is a value. * @entry: XArray entry. * * Context: Any context. * Return: True if the entry is a value, false if it is a pointer. */ static inline bool xa_is_value(const void *entry) { return (unsigned long)entry & 1; } /** * xa_tag_pointer() - Create an XArray entry for a tagged pointer. * @p: Plain pointer. * @tag: Tag value (0, 1 or 3). * * If the user of the XArray prefers, they can tag their pointers instead * of storing value entries. Three tags are available (0, 1 and 3). * These are distinct from the xa_mark_t as they are not replicated up * through the array and cannot be searched for. * * Context: Any context. * Return: An XArray entry. */ static inline void *xa_tag_pointer(void *p, unsigned long tag) { return (void *)((unsigned long)p | tag); } /** * xa_untag_pointer() - Turn an XArray entry into a plain pointer. * @entry: XArray entry. * * If you have stored a tagged pointer in the XArray, call this function * to get the untagged version of the pointer. * * Context: Any context. * Return: A pointer. */ static inline void *xa_untag_pointer(void *entry) { return (void *)((unsigned long)entry & ~3UL); } /** * xa_pointer_tag() - Get the tag stored in an XArray entry. * @entry: XArray entry. * * If you have stored a tagged pointer in the XArray, call this function * to get the tag of that pointer. * * Context: Any context. * Return: A tag. */ static inline unsigned int xa_pointer_tag(void *entry) { return (unsigned long)entry & 3UL; } /* * xa_mk_internal() - Create an internal entry. * @v: Value to turn into an internal entry. * * Internal entries are used for a number of purposes. Entries 0-255 are * used for sibling entries (only 0-62 are used by the current code). 256 * is used for the retry entry. 257 is used for the reserved / zero entry. * Negative internal entries are used to represent errnos. Node pointers * are also tagged as internal entries in some situations. * * Context: Any context. * Return: An XArray internal entry corresponding to this value. */ static inline void *xa_mk_internal(unsigned long v) { return (void *)((v << 2) | 2); } /* * xa_to_internal() - Extract the value from an internal entry. * @entry: XArray entry. * * Context: Any context. * Return: The value which was stored in the internal entry. */ static inline unsigned long xa_to_internal(const void *entry) { return (unsigned long)entry >> 2; } /* * xa_is_internal() - Is the entry an internal entry? * @entry: XArray entry. * * Context: Any context. * Return: %true if the entry is an internal entry. */ static inline bool xa_is_internal(const void *entry) { return ((unsigned long)entry & 3) == 2; } #define XA_ZERO_ENTRY xa_mk_internal(257) /** * xa_is_zero() - Is the entry a zero entry? * @entry: Entry retrieved from the XArray * * The normal API will return NULL as the contents of a slot containing * a zero entry. You can only see zero entries by using the advanced API. * * Return: %true if the entry is a zero entry. */ static inline bool xa_is_zero(const void *entry) { return unlikely(entry == XA_ZERO_ENTRY); } /** * xa_is_err() - Report whether an XArray operation returned an error * @entry: Result from calling an XArray function * * If an XArray operation cannot complete an operation, it will return * a special value indicating an error. This function tells you * whether an error occurred; xa_err() tells you which error occurred. * * Context: Any context. * Return: %true if the entry indicates an error. */ static inline bool xa_is_err(const void *entry) { return unlikely(xa_is_internal(entry) && entry >= xa_mk_internal(-MAX_ERRNO)); } /** * xa_err() - Turn an XArray result into an errno. * @entry: Result from calling an XArray function. * * If an XArray operation cannot complete an operation, it will return * a special pointer value which encodes an errno. This function extracts * the errno from the pointer value, or returns 0 if the pointer does not * represent an errno. * * Context: Any context. * Return: A negative errno or 0. */ static inline int xa_err(void *entry) { /* xa_to_internal() would not do sign extension. */ if (xa_is_err(entry)) return (long)entry >> 2; return 0; } /** * struct xa_limit - Represents a range of IDs. * @min: The lowest ID to allocate (inclusive). * @max: The maximum ID to allocate (inclusive). * * This structure is used either directly or via the XA_LIMIT() macro * to communicate the range of IDs that are valid for allocation. * Three common ranges are predefined for you: * * xa_limit_32b - [0 - UINT_MAX] * * xa_limit_31b - [0 - INT_MAX] * * xa_limit_16b - [0 - USHRT_MAX] */ struct xa_limit { u32 max; u32 min; }; #define XA_LIMIT(_min, _max) (struct xa_limit) { .min = _min, .max = _max } #define xa_limit_32b XA_LIMIT(0, UINT_MAX) #define xa_limit_31b XA_LIMIT(0, INT_MAX) #define xa_limit_16b XA_LIMIT(0, USHRT_MAX) typedef unsigned __bitwise xa_mark_t; #define XA_MARK_0 ((__force xa_mark_t)0U) #define XA_MARK_1 ((__force xa_mark_t)1U) #define XA_MARK_2 ((__force xa_mark_t)2U) #define XA_PRESENT ((__force xa_mark_t)8U) #define XA_MARK_MAX XA_MARK_2 #define XA_FREE_MARK XA_MARK_0 enum xa_lock_type { XA_LOCK_IRQ = 1, XA_LOCK_BH = 2, }; /* * Values for xa_flags. The radix tree stores its GFP flags in the xa_flags, * and we remain compatible with that. */ #define XA_FLAGS_LOCK_IRQ ((__force gfp_t)XA_LOCK_IRQ) #define XA_FLAGS_LOCK_BH ((__force gfp_t)XA_LOCK_BH) #define XA_FLAGS_TRACK_FREE ((__force gfp_t)4U) #define XA_FLAGS_ZERO_BUSY ((__force gfp_t)8U) #define XA_FLAGS_ALLOC_WRAPPED ((__force gfp_t)16U) #define XA_FLAGS_ACCOUNT ((__force gfp_t)32U) #define XA_FLAGS_MARK(mark) ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \ (__force unsigned)(mark))) /* ALLOC is for a normal 0-based alloc. ALLOC1 is for an 1-based alloc */ #define XA_FLAGS_ALLOC (XA_FLAGS_TRACK_FREE | XA_FLAGS_MARK(XA_FREE_MARK)) #define XA_FLAGS_ALLOC1 (XA_FLAGS_TRACK_FREE | XA_FLAGS_ZERO_BUSY) /** * struct xarray - The anchor of the XArray. * @xa_lock: Lock that protects the contents of the XArray. * * To use the xarray, define it statically or embed it in your data structure. * It is a very small data structure, so it does not usually make sense to * allocate it separately and keep a pointer to it in your data structure. * * You may use the xa_lock to protect your own data structures as well. */ /* * If all of the entries in the array are NULL, @xa_head is a NULL pointer. * If the only non-NULL entry in the array is at index 0, @xa_head is that * entry. If any other entry in the array is non-NULL, @xa_head points * to an @xa_node. */ struct xarray { spinlock_t xa_lock; /* private: The rest of the data structure is not to be used directly. */ gfp_t xa_flags; void __rcu * xa_head; }; #define XARRAY_INIT(name, flags) { \ .xa_lock = __SPIN_LOCK_UNLOCKED(name.xa_lock), \ .xa_flags = flags, \ .xa_head = NULL, \ } /** * DEFINE_XARRAY_FLAGS() - Define an XArray with custom flags. * @name: A string that names your XArray. * @flags: XA_FLAG values. * * This is intended for file scope definitions of XArrays. It declares * and initialises an empty XArray with the chosen name and flags. It is * equivalent to calling xa_init_flags() on the array, but it does the * initialisation at compiletime instead of runtime. */ #define DEFINE_XARRAY_FLAGS(name, flags) \ struct xarray name = XARRAY_INIT(name, flags) /** * DEFINE_XARRAY() - Define an XArray. * @name: A string that names your XArray. * * This is intended for file scope definitions of XArrays. It declares * and initialises an empty XArray with the chosen name. It is equivalent * to calling xa_init() on the array, but it does the initialisation at * compiletime instead of runtime. */ #define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0) /** * DEFINE_XARRAY_ALLOC() - Define an XArray which allocates IDs starting at 0. * @name: A string that names your XArray. * * This is intended for file scope definitions of allocating XArrays. * See also DEFINE_XARRAY(). */ #define DEFINE_XARRAY_ALLOC(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC) /** * DEFINE_XARRAY_ALLOC1() - Define an XArray which allocates IDs starting at 1. * @name: A string that names your XArray. * * This is intended for file scope definitions of allocating XArrays. * See also DEFINE_XARRAY(). */ #define DEFINE_XARRAY_ALLOC1(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC1) void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *xa_erase(struct xarray *, unsigned long index); void *xa_store_range(struct xarray *, unsigned long first, unsigned long last, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); void *xa_find(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); void *xa_find_after(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); unsigned int xa_extract(struct xarray *, void **dst, unsigned long start, unsigned long max, unsigned int n, xa_mark_t); void xa_destroy(struct xarray *); /** * xa_init_flags() - Initialise an empty XArray with flags. * @xa: XArray. * @flags: XA_FLAG values. * * If you need to initialise an XArray with special flags (eg you need * to take the lock from interrupt context), use this function instead * of xa_init(). * * Context: Any context. */ static inline void xa_init_flags(struct xarray *xa, gfp_t flags) { spin_lock_init(&xa->xa_lock); xa->xa_flags = flags; xa->xa_head = NULL; } /** * xa_init() - Initialise an empty XArray. * @xa: XArray. * * An empty XArray is full of NULL entries. * * Context: Any context. */ static inline void xa_init(struct xarray *xa) { xa_init_flags(xa, 0); } /** * xa_empty() - Determine if an array has any present entries. * @xa: XArray. * * Context: Any context. * Return: %true if the array contains only NULL pointers. */ static inline bool xa_empty(const struct xarray *xa) { return xa->xa_head == NULL; } /** * xa_marked() - Inquire whether any entry in this array has a mark set * @xa: Array * @mark: Mark value * * Context: Any context. * Return: %true if any entry has this mark set. */ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) { return xa->xa_flags & XA_FLAGS_MARK(mark); } /** * xa_for_each_range() - Iterate over a portion of an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @start: First index to retrieve from array. * @last: Last index to retrieve from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you * want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set * to NULL and @index will have a value less than or equal to max. * * xa_for_each_range() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). * xa_for_each_range() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each() iterator instead. * The xas_for_each() iterator will expand into more inline code than * xa_for_each_range(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_range(xa, index, entry, start, last) \ for (index = start, \ entry = xa_find(xa, &index, last, XA_PRESENT); \ entry; \ entry = xa_find_after(xa, &index, last, XA_PRESENT)) /** * xa_for_each_start() - Iterate over a portion of an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @start: First index to retrieve from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you * want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set * to NULL and @index will have a value less than or equal to max. * * xa_for_each_start() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). * xa_for_each_start() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each() iterator instead. * The xas_for_each() iterator will expand into more inline code than * xa_for_each_start(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_start(xa, index, entry, start) \ xa_for_each_range(xa, index, entry, start, ULONG_MAX) /** * xa_for_each() - Iterate over present entries in an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you want * to skip or reprocess indices. It is safe to modify the array during the * iteration. At the end of the iteration, @entry will be set to NULL and * @index will have a value less than or equal to max. * * xa_for_each() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). xa_for_each() * will spin if it hits a retry entry; if you intend to see retry entries, * you should use the xas_for_each() iterator instead. The xas_for_each() * iterator will expand into more inline code than xa_for_each(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each(xa, index, entry) \ xa_for_each_start(xa, index, entry, 0) /** * xa_for_each_marked() - Iterate over marked entries in an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @filter: Selection criterion. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. The iteration will skip all entries in the array * which do not match @filter. You may modify @index during the iteration * if you want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set to * NULL and @index will have a value less than or equal to max. * * xa_for_each_marked() is O(n.log(n)) while xas_for_each_marked() is O(n). * You have to handle your own locking with xas_for_each(), and if you have * to unlock after each iteration, it will also end up being O(n.log(n)). * xa_for_each_marked() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each_marked() iterator * instead. The xas_for_each_marked() iterator will expand into more inline * code than xa_for_each_marked(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_marked(xa, index, entry, filter) \ for (index = 0, entry = xa_find(xa, &index, ULONG_MAX, filter); \ entry; entry = xa_find_after(xa, &index, ULONG_MAX, filter)) #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) #define xa_lock_bh(xa) spin_lock_bh(&(xa)->xa_lock) #define xa_unlock_bh(xa) spin_unlock_bh(&(xa)->xa_lock) #define xa_lock_irq(xa) spin_lock_irq(&(xa)->xa_lock) #define xa_unlock_irq(xa) spin_unlock_irq(&(xa)->xa_lock) #define xa_lock_irqsave(xa, flags) \ spin_lock_irqsave(&(xa)->xa_lock, flags) #define xa_unlock_irqrestore(xa, flags) \ spin_unlock_irqrestore(&(xa)->xa_lock, flags) #define xa_lock_nested(xa, subclass) \ spin_lock_nested(&(xa)->xa_lock, subclass) #define xa_lock_bh_nested(xa, subclass) \ spin_lock_bh_nested(&(xa)->xa_lock, subclass) #define xa_lock_irq_nested(xa, subclass) \ spin_lock_irq_nested(&(xa)->xa_lock, subclass) #define xa_lock_irqsave_nested(xa, flags, subclass) \ spin_lock_irqsave_nested(&(xa)->xa_lock, flags, subclass) /* * Versions of the normal API which require the caller to hold the * xa_lock. If the GFP flags allow it, they will drop the lock to * allocate memory, then reacquire it afterwards. These functions * may also re-enable interrupts if the XArray flags indicate the * locking should be interrupt safe. */ void *__xa_erase(struct xarray *, unsigned long index); void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); int __must_check __xa_insert(struct xarray *, unsigned long index, void *entry, gfp_t); int __must_check __xa_alloc(struct xarray *, u32 *id, void *entry, struct xa_limit, gfp_t); int __must_check __xa_alloc_cyclic(struct xarray *, u32 *id, void *entry, struct xa_limit, u32 *next, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); /** * xa_store_bh() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * This function is like calling xa_store() except it disables softirqs * while holding the array lock. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: The old entry at this index or xa_err() if an error happened. */ static inline void *xa_store_bh(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_bh(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock_bh(xa); return curr; } /** * xa_store_irq() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * This function is like calling xa_store() except it disables interrupts * while holding the array lock. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: The old entry at this index or xa_err() if an error happened. */ static inline void *xa_store_irq(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_irq(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock_irq(xa); return curr; } /** * xa_erase_bh() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: The entry which used to be at this index. */ static inline void *xa_erase_bh(struct xarray *xa, unsigned long index) { void *entry; xa_lock_bh(xa); entry = __xa_erase(xa, index); xa_unlock_bh(xa); return entry; } /** * xa_erase_irq() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: The entry which used to be at this index. */ static inline void *xa_erase_irq(struct xarray *xa, unsigned long index) { void *entry; xa_lock_irq(xa); entry = __xa_erase(xa, index); xa_unlock_irq(xa); return entry; } /** * xa_cmpxchg() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * If the entry at @index is the same as @old, replace it with @entry. * If the return value is equal to @old, then the exchange was successful. * * Context: Any context. Takes and releases the xa_lock. May sleep * if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock(xa); return curr; } /** * xa_cmpxchg_bh() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * This function is like calling xa_cmpxchg() except it disables softirqs * while holding the array lock. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg_bh(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_bh(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock_bh(xa); return curr; } /** * xa_cmpxchg_irq() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * This function is like calling xa_cmpxchg() except it disables interrupts * while holding the array lock. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg_irq(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_irq(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock_irq(xa); return curr; } /** * xa_insert() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; might_alloc(gfp); xa_lock(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock(xa); return err; } /** * xa_insert_bh() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert_bh(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_bh(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock_bh(xa); return err; } /** * xa_insert_irq() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert_irq(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_irq(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock_irq(xa); return err; } /** * xa_alloc() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline __must_check int xa_alloc(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; might_alloc(gfp); xa_lock(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock(xa); return err; } /** * xa_alloc_bh() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline int __must_check xa_alloc_bh(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_bh(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock_bh(xa); return err; } /** * xa_alloc_irq() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline int __must_check xa_alloc_irq(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_irq(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock_irq(xa); return err; } /** * xa_alloc_cyclic() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; might_alloc(gfp); xa_lock(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock(xa); return err; } /** * xa_alloc_cyclic_bh() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic_bh(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_bh(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock_bh(xa); return err; } /** * xa_alloc_cyclic_irq() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic_irq(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_irq(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock_irq(xa); return err; } /** * xa_reserve() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * Ensures there is somewhere to store an entry at @index in the array. * If there is already something stored at @index, this function does * nothing. If there was nothing there, the entry is marked as reserved. * Loading from a reserved entry returns a %NULL pointer. * * If you do not use the entry that you have reserved, call xa_release() * or xa_erase() to free any unnecessary memory. * * Context: Any context. Takes and releases the xa_lock. * May sleep if the @gfp flags permit. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_reserve_bh() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * A softirq-disabling version of xa_reserve(). * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve_bh(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg_bh(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_reserve_irq() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * An interrupt-disabling version of xa_reserve(). * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve_irq(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg_irq(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_release() - Release a reserved entry. * @xa: XArray. * @index: Index of entry. * * After calling xa_reserve(), you can call this function to release the * reservation. If the entry at @index has been stored to, this function * will do nothing. */ static inline void xa_release(struct xarray *xa, unsigned long index) { xa_cmpxchg(xa, index, XA_ZERO_ENTRY, NULL, 0); } /* Everything below here is the Advanced API. Proceed with caution. */ /* * The xarray is constructed out of a set of 'chunks' of pointers. Choosing * the best chunk size requires some tradeoffs. A power of two recommends * itself so that we can walk the tree based purely on shifts and masks. * Generally, the larger the better; as the number of slots per level of the * tree increases, the less tall the tree needs to be. But that needs to be * balanced against the memory consumption of each node. On a 64-bit system, * xa_node is currently 576 bytes, and we get 7 of them per 4kB page. If we * doubled the number of slots per node, we'd get only 3 nodes per 4kB page. */ #ifndef XA_CHUNK_SHIFT #define XA_CHUNK_SHIFT (CONFIG_BASE_SMALL ? 4 : 6) #endif #define XA_CHUNK_SIZE (1UL << XA_CHUNK_SHIFT) #define XA_CHUNK_MASK (XA_CHUNK_SIZE - 1) #define XA_MAX_MARKS 3 #define XA_MARK_LONGS DIV_ROUND_UP(XA_CHUNK_SIZE, BITS_PER_LONG) /* * @count is the count of every non-NULL element in the ->slots array * whether that is a value entry, a retry entry, a user pointer, * a sibling entry or a pointer to the next level of the tree. * @nr_values is the count of every element in ->slots which is * either a value entry or a sibling of a value entry. */ struct xa_node { unsigned char shift; /* Bits remaining in each slot */ unsigned char offset; /* Slot offset in parent */ unsigned char count; /* Total entry count */ unsigned char nr_values; /* Value entry count */ struct xa_node __rcu *parent; /* NULL at top of tree */ struct xarray *array; /* The array we belong to */ union { struct list_head private_list; /* For tree user */ struct rcu_head rcu_head; /* Used when freeing node */ }; void __rcu *slots[XA_CHUNK_SIZE]; union { unsigned long tags[XA_MAX_MARKS][XA_MARK_LONGS]; unsigned long marks[XA_MAX_MARKS][XA_MARK_LONGS]; }; }; void xa_dump(const struct xarray *); void xa_dump_node(const struct xa_node *); #ifdef XA_DEBUG #define XA_BUG_ON(xa, x) do { \ if (x) { \ xa_dump(xa); \ BUG(); \ } \ } while (0) #define XA_NODE_BUG_ON(node, x) do { \ if (x) { \ if (node) xa_dump_node(node); \ BUG(); \ } \ } while (0) #else #define XA_BUG_ON(xa, x) do { } while (0) #define XA_NODE_BUG_ON(node, x) do { } while (0) #endif /* Private */ static inline void *xa_head(const struct xarray *xa) { return rcu_dereference_check(xa->xa_head, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_head_locked(const struct xarray *xa) { return rcu_dereference_protected(xa->xa_head, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_entry(const struct xarray *xa, const struct xa_node *node, unsigned int offset) { XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE); return rcu_dereference_check(node->slots[offset], lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_entry_locked(const struct xarray *xa, const struct xa_node *node, unsigned int offset) { XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE); return rcu_dereference_protected(node->slots[offset], lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline struct xa_node *xa_parent(const struct xarray *xa, const struct xa_node *node) { return rcu_dereference_check(node->parent, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline struct xa_node *xa_parent_locked(const struct xarray *xa, const struct xa_node *node) { return rcu_dereference_protected(node->parent, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_mk_node(const struct xa_node *node) { return (void *)((unsigned long)node | 2); } /* Private */ static inline struct xa_node *xa_to_node(const void *entry) { return (struct xa_node *)((unsigned long)entry - 2); } /* Private */ static inline bool xa_is_node(const void *entry) { return xa_is_internal(entry) && (unsigned long)entry > 4096; } /* Private */ static inline void *xa_mk_sibling(unsigned int offset) { return xa_mk_internal(offset); } /* Private */ static inline unsigned long xa_to_sibling(const void *entry) { return xa_to_internal(entry); } /** * xa_is_sibling() - Is the entry a sibling entry? * @entry: Entry retrieved from the XArray * * Return: %true if the entry is a sibling entry. */ static inline bool xa_is_sibling(const void *entry) { return IS_ENABLED(CONFIG_XARRAY_MULTI) && xa_is_internal(entry) && (entry < xa_mk_sibling(XA_CHUNK_SIZE - 1)); } #define XA_RETRY_ENTRY xa_mk_internal(256) /** * xa_is_retry() - Is the entry a retry entry? * @entry: Entry retrieved from the XArray * * Return: %true if the entry is a retry entry. */ static inline bool xa_is_retry(const void *entry) { return unlikely(entry == XA_RETRY_ENTRY); } /** * xa_is_advanced() - Is the entry only permitted for the advanced API? * @entry: Entry to be stored in the XArray. * * Return: %true if the entry cannot be stored by the normal API. */ static inline bool xa_is_advanced(const void *entry) { return xa_is_internal(entry) && (entry <= XA_RETRY_ENTRY); } /** * typedef xa_update_node_t - A callback function from the XArray. * @node: The node which is being processed * * This function is called every time the XArray updates the count of * present and value entries in a node. It allows advanced users to * maintain the private_list in the node. * * Context: The xa_lock is held and interrupts may be disabled. * Implementations should not drop the xa_lock, nor re-enable * interrupts. */ typedef void (*xa_update_node_t)(struct xa_node *node); void xa_delete_node(struct xa_node *, xa_update_node_t); /* * The xa_state is opaque to its users. It contains various different pieces * of state involved in the current operation on the XArray. It should be * declared on the stack and passed between the various internal routines. * The various elements in it should not be accessed directly, but only * through the provided accessor functions. The below documentation is for * the benefit of those working on the code, not for users of the XArray. * * @xa_node usually points to the xa_node containing the slot we're operating * on (and @xa_offset is the offset in the slots array). If there is a * single entry in the array at index 0, there are no allocated xa_nodes to * point to, and so we store %NULL in @xa_node. @xa_node is set to * the value %XAS_RESTART if the xa_state is not walked to the correct * position in the tree of nodes for this operation. If an error occurs * during an operation, it is set to an %XAS_ERROR value. If we run off the * end of the allocated nodes, it is set to %XAS_BOUNDS. */ struct xa_state { struct xarray *xa; unsigned long xa_index; unsigned char xa_shift; unsigned char xa_sibs; unsigned char xa_offset; unsigned char xa_pad; /* Helps gcc generate better code */ struct xa_node *xa_node; struct xa_node *xa_alloc; xa_update_node_t xa_update; struct list_lru *xa_lru; }; /* * We encode errnos in the xas->xa_node. If an error has happened, we need to * drop the lock to fix it, and once we've done so the xa_state is invalid. */ #define XA_ERROR(errno) ((struct xa_node *)(((unsigned long)errno << 2) | 2UL)) #define XAS_BOUNDS ((struct xa_node *)1UL) #define XAS_RESTART ((struct xa_node *)3UL) #define __XA_STATE(array, index, shift, sibs) { \ .xa = array, \ .xa_index = index, \ .xa_shift = shift, \ .xa_sibs = sibs, \ .xa_offset = 0, \ .xa_pad = 0, \ .xa_node = XAS_RESTART, \ .xa_alloc = NULL, \ .xa_update = NULL, \ .xa_lru = NULL, \ } /** * XA_STATE() - Declare an XArray operation state. * @name: Name of this operation state (usually xas). * @array: Array to operate on. * @index: Initial index of interest. * * Declare and initialise an xa_state on the stack. */ #define XA_STATE(name, array, index) \ struct xa_state name = __XA_STATE(array, index, 0, 0) /** * XA_STATE_ORDER() - Declare an XArray operation state. * @name: Name of this operation state (usually xas). * @array: Array to operate on. * @index: Initial index of interest. * @order: Order of entry. * * Declare and initialise an xa_state on the stack. This variant of * XA_STATE() allows you to specify the 'order' of the element you * want to operate on.` */ #define XA_STATE_ORDER(name, array, index, order) \ struct xa_state name = __XA_STATE(array, \ (index >> order) << order, \ order - (order % XA_CHUNK_SHIFT), \ (1U << (order % XA_CHUNK_SHIFT)) - 1) #define xas_marked(xas, mark) xa_marked((xas)->xa, (mark)) #define xas_trylock(xas) xa_trylock((xas)->xa) #define xas_lock(xas) xa_lock((xas)->xa) #define xas_unlock(xas) xa_unlock((xas)->xa) #define xas_lock_bh(xas) xa_lock_bh((xas)->xa) #define xas_unlock_bh(xas) xa_unlock_bh((xas)->xa) #define xas_lock_irq(xas) xa_lock_irq((xas)->xa) #define xas_unlock_irq(xas) xa_unlock_irq((xas)->xa) #define xas_lock_irqsave(xas, flags) \ xa_lock_irqsave((xas)->xa, flags) #define xas_unlock_irqrestore(xas, flags) \ xa_unlock_irqrestore((xas)->xa, flags) /** * xas_error() - Return an errno stored in the xa_state. * @xas: XArray operation state. * * Return: 0 if no error has been noted. A negative errno if one has. */ static inline int xas_error(const struct xa_state *xas) { return xa_err(xas->xa_node); } /** * xas_set_err() - Note an error in the xa_state. * @xas: XArray operation state. * @err: Negative error number. * * Only call this function with a negative @err; zero or positive errors * will probably not behave the way you think they should. If you want * to clear the error from an xa_state, use xas_reset(). */ static inline void xas_set_err(struct xa_state *xas, long err) { xas->xa_node = XA_ERROR(err); } /** * xas_invalid() - Is the xas in a retry or error state? * @xas: XArray operation state. * * Return: %true if the xas cannot be used for operations. */ static inline bool xas_invalid(const struct xa_state *xas) { return (unsigned long)xas->xa_node & 3; } /** * xas_valid() - Is the xas a valid cursor into the array? * @xas: XArray operation state. * * Return: %true if the xas can be used for operations. */ static inline bool xas_valid(const struct xa_state *xas) { return !xas_invalid(xas); } /** * xas_is_node() - Does the xas point to a node? * @xas: XArray operation state. * * Return: %true if the xas currently references a node. */ static inline bool xas_is_node(const struct xa_state *xas) { return xas_valid(xas) && xas->xa_node; } /* True if the pointer is something other than a node */ static inline bool xas_not_node(struct xa_node *node) { return ((unsigned long)node & 3) || !node; } /* True if the node represents RESTART or an error */ static inline bool xas_frozen(struct xa_node *node) { return (unsigned long)node & 2; } /* True if the node represents head-of-tree, RESTART or BOUNDS */ static inline bool xas_top(struct xa_node *node) { return node <= XAS_RESTART; } /** * xas_reset() - Reset an XArray operation state. * @xas: XArray operation state. * * Resets the error or walk state of the @xas so future walks of the * array will start from the root. Use this if you have dropped the * xarray lock and want to reuse the xa_state. * * Context: Any context. */ static inline void xas_reset(struct xa_state *xas) { xas->xa_node = XAS_RESTART; } /** * xas_retry() - Retry the operation if appropriate. * @xas: XArray operation state. * @entry: Entry from xarray. * * The advanced functions may sometimes return an internal entry, such as * a retry entry or a zero entry. This function sets up the @xas to restart * the walk from the head of the array if needed. * * Context: Any context. * Return: true if the operation needs to be retried. */ static inline bool xas_retry(struct xa_state *xas, const void *entry) { if (xa_is_zero(entry)) return true; if (!xa_is_retry(entry)) return false; xas_reset(xas); return true; } void *xas_load(struct xa_state *); void *xas_store(struct xa_state *, void *entry); void *xas_find(struct xa_state *, unsigned long max); void *xas_find_conflict(struct xa_state *); bool xas_get_mark(const struct xa_state *, xa_mark_t); void xas_set_mark(const struct xa_state *, xa_mark_t); void xas_clear_mark(const struct xa_state *, xa_mark_t); void *xas_find_marked(struct xa_state *, unsigned long max, xa_mark_t); void xas_init_marks(const struct xa_state *); bool xas_nomem(struct xa_state *, gfp_t); void xas_destroy(struct xa_state *); void xas_pause(struct xa_state *); void xas_create_range(struct xa_state *); #ifdef CONFIG_XARRAY_MULTI int xa_get_order(struct xarray *, unsigned long index); int xas_get_order(struct xa_state *xas); void xas_split(struct xa_state *, void *entry, unsigned int order); void xas_split_alloc(struct xa_state *, void *entry, unsigned int order, gfp_t); #else static inline int xa_get_order(struct xarray *xa, unsigned long index) { return 0; } static inline int xas_get_order(struct xa_state *xas) { return 0; } static inline void xas_split(struct xa_state *xas, void *entry, unsigned int order) { xas_store(xas, entry); } static inline void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order, gfp_t gfp) { } #endif /** * xas_reload() - Refetch an entry from the xarray. * @xas: XArray operation state. * * Use this function to check that a previously loaded entry still has * the same value. This is useful for the lockless pagecache lookup where * we walk the array with only the RCU lock to protect us, lock the page, * then check that the page hasn't moved since we looked it up. * * The caller guarantees that @xas is still valid. If it may be in an * error or restart state, call xas_load() instead. * * Return: The entry at this location in the xarray. */ static inline void *xas_reload(struct xa_state *xas) { struct xa_node *node = xas->xa_node; void *entry; char offset; if (!node) return xa_head(xas->xa); if (IS_ENABLED(CONFIG_XARRAY_MULTI)) { offset = (xas->xa_index >> node->shift) & XA_CHUNK_MASK; entry = xa_entry(xas->xa, node, offset); if (!xa_is_sibling(entry)) return entry; offset = xa_to_sibling(entry); } else { offset = xas->xa_offset; } return xa_entry(xas->xa, node, offset); } /** * xas_set() - Set up XArray operation state for a different index. * @xas: XArray operation state. * @index: New index into the XArray. * * Move the operation state to refer to a different index. This will * have the effect of starting a walk from the top; see xas_next() * to move to an adjacent index. */ static inline void xas_set(struct xa_state *xas, unsigned long index) { xas->xa_index = index; xas->xa_node = XAS_RESTART; } /** * xas_advance() - Skip over sibling entries. * @xas: XArray operation state. * @index: Index of last sibling entry. * * Move the operation state to refer to the last sibling entry. * This is useful for loops that normally want to see sibling * entries but sometimes want to skip them. Use xas_set() if you * want to move to an index which is not part of this entry. */ static inline void xas_advance(struct xa_state *xas, unsigned long index) { unsigned char shift = xas_is_node(xas) ? xas->xa_node->shift : 0; xas->xa_index = index; xas->xa_offset = (index >> shift) & XA_CHUNK_MASK; } /** * xas_set_order() - Set up XArray operation state for a multislot entry. * @xas: XArray operation state. * @index: Target of the operation. * @order: Entry occupies 2^@order indices. */ static inline void xas_set_order(struct xa_state *xas, unsigned long index, unsigned int order) { #ifdef CONFIG_XARRAY_MULTI xas->xa_index = order < BITS_PER_LONG ? (index >> order) << order : 0; xas->xa_shift = order - (order % XA_CHUNK_SHIFT); xas->xa_sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; xas->xa_node = XAS_RESTART; #else BUG_ON(order > 0); xas_set(xas, index); #endif } /** * xas_set_update() - Set up XArray operation state for a callback. * @xas: XArray operation state. * @update: Function to call when updating a node. * * The XArray can notify a caller after it has updated an xa_node. * This is advanced functionality and is only needed by the page cache. */ static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update) { xas->xa_update = update; } static inline void xas_set_lru(struct xa_state *xas, struct list_lru *lru) { xas->xa_lru = lru; } /** * xas_next_entry() - Advance iterator to next present entry. * @xas: XArray operation state. * @max: Highest index to return. * * xas_next_entry() is an inline function to optimise xarray traversal for * speed. It is equivalent to calling xas_find(), and will call xas_find() * for all the hard cases. * * Return: The next present entry after the one currently referred to by @xas. */ static inline void *xas_next_entry(struct xa_state *xas, unsigned long max) { struct xa_node *node = xas->xa_node; void *entry; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK))) return xas_find(xas, max); do { if (unlikely(xas->xa_index >= max)) return xas_find(xas, max); if (unlikely(xas->xa_offset == XA_CHUNK_MASK)) return xas_find(xas, max); entry = xa_entry(xas->xa, node, xas->xa_offset + 1); if (unlikely(xa_is_internal(entry))) return xas_find(xas, max); xas->xa_offset++; xas->xa_index++; } while (!entry); return entry; } /* Private */ static inline unsigned int xas_find_chunk(struct xa_state *xas, bool advance, xa_mark_t mark) { unsigned long *addr = xas->xa_node->marks[(__force unsigned)mark]; unsigned int offset = xas->xa_offset; if (advance) offset++; if (XA_CHUNK_SIZE == BITS_PER_LONG) { if (offset < XA_CHUNK_SIZE) { unsigned long data = *addr & (~0UL << offset); if (data) return __ffs(data); } return XA_CHUNK_SIZE; } return find_next_bit(addr, XA_CHUNK_SIZE, offset); } /** * xas_next_marked() - Advance iterator to next marked entry. * @xas: XArray operation state. * @max: Highest index to return. * @mark: Mark to search for. * * xas_next_marked() is an inline function to optimise xarray traversal for * speed. It is equivalent to calling xas_find_marked(), and will call * xas_find_marked() for all the hard cases. * * Return: The next marked entry after the one currently referred to by @xas. */ static inline void *xas_next_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) { struct xa_node *node = xas->xa_node; void *entry; unsigned int offset; if (unlikely(xas_not_node(node) || node->shift)) return xas_find_marked(xas, max, mark); offset = xas_find_chunk(xas, true, mark); xas->xa_offset = offset; xas->xa_index = (xas->xa_index & ~XA_CHUNK_MASK) + offset; if (xas->xa_index > max) return NULL; if (offset == XA_CHUNK_SIZE) return xas_find_marked(xas, max, mark); entry = xa_entry(xas->xa, node, offset); if (!entry) return xas_find_marked(xas, max, mark); return entry; } /* * If iterating while holding a lock, drop the lock and reschedule * every %XA_CHECK_SCHED loops. */ enum { XA_CHECK_SCHED = 4096, }; /** * xas_for_each() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * @max: Maximum index to retrieve from array. * * The loop body will be executed for each entry present in the xarray * between the current xas position and @max. @entry will be set to * the entry retrieved from the xarray. It is safe to delete entries * from the array in the loop body. You should hold either the RCU lock * or the xa_lock while iterating. If you need to drop the lock, call * xas_pause() first. */ #define xas_for_each(xas, entry, max) \ for (entry = xas_find(xas, max); entry; \ entry = xas_next_entry(xas, max)) /** * xas_for_each_marked() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * @max: Maximum index to retrieve from array. * @mark: Mark to search for. * * The loop body will be executed for each marked entry in the xarray * between the current xas position and @max. @entry will be set to * the entry retrieved from the xarray. It is safe to delete entries * from the array in the loop body. You should hold either the RCU lock * or the xa_lock while iterating. If you need to drop the lock, call * xas_pause() first. */ #define xas_for_each_marked(xas, entry, max, mark) \ for (entry = xas_find_marked(xas, max, mark); entry; \ entry = xas_next_marked(xas, max, mark)) /** * xas_for_each_conflict() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * * The loop body will be executed for each entry in the XArray that * lies within the range specified by @xas. If the loop terminates * normally, @entry will be %NULL. The user may break out of the loop, * which will leave @entry set to the conflicting entry. The caller * may also call xa_set_err() to exit the loop while setting an error * to record the reason. */ #define xas_for_each_conflict(xas, entry) \ while ((entry = xas_find_conflict(xas))) void *__xas_next(struct xa_state *); void *__xas_prev(struct xa_state *); /** * xas_prev() - Move iterator to previous index. * @xas: XArray operation state. * * If the @xas was in an error state, it will remain in an error state * and this function will return %NULL. If the @xas has never been walked, * it will have the effect of calling xas_load(). Otherwise one will be * subtracted from the index and the state will be walked to the correct * location in the array for the next operation. * * If the iterator was referencing index 0, this function wraps * around to %ULONG_MAX. * * Return: The entry at the new index. This may be %NULL or an internal * entry. */ static inline void *xas_prev(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset == 0)) return __xas_prev(xas); xas->xa_index--; xas->xa_offset--; return xa_entry(xas->xa, node, xas->xa_offset); } /** * xas_next() - Move state to next index. * @xas: XArray operation state. * * If the @xas was in an error state, it will remain in an error state * and this function will return %NULL. If the @xas has never been walked, * it will have the effect of calling xas_load(). Otherwise one will be * added to the index and the state will be walked to the correct * location in the array for the next operation. * * If the iterator was referencing index %ULONG_MAX, this function wraps * around to 0. * * Return: The entry at the new index. This may be %NULL or an internal * entry. */ static inline void *xas_next(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset == XA_CHUNK_MASK)) return __xas_next(xas); xas->xa_index++; xas->xa_offset++; return xa_entry(xas->xa, node, xas->xa_offset); } #endif /* _LINUX_XARRAY_H */ |
| 890 500 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_UTSNAME_H #define _LINUX_UTSNAME_H #include <linux/sched.h> #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/err.h> #include <uapi/linux/utsname.h> enum uts_proc { UTS_PROC_ARCH, UTS_PROC_OSTYPE, UTS_PROC_OSRELEASE, UTS_PROC_VERSION, UTS_PROC_HOSTNAME, UTS_PROC_DOMAINNAME, }; struct user_namespace; extern struct user_namespace init_user_ns; struct uts_namespace { struct new_utsname name; struct user_namespace *user_ns; struct ucounts *ucounts; struct ns_common ns; } __randomize_layout; extern struct uts_namespace init_uts_ns; #ifdef CONFIG_UTS_NS static inline void get_uts_ns(struct uts_namespace *ns) { refcount_inc(&ns->ns.count); } extern struct uts_namespace *copy_utsname(unsigned long flags, struct user_namespace *user_ns, struct uts_namespace *old_ns); extern void free_uts_ns(struct uts_namespace *ns); static inline void put_uts_ns(struct uts_namespace *ns) { if (refcount_dec_and_test(&ns->ns.count)) free_uts_ns(ns); } void uts_ns_init(void); #else static inline void get_uts_ns(struct uts_namespace *ns) { } static inline void put_uts_ns(struct uts_namespace *ns) { } static inline struct uts_namespace *copy_utsname(unsigned long flags, struct user_namespace *user_ns, struct uts_namespace *old_ns) { if (flags & CLONE_NEWUTS) return ERR_PTR(-EINVAL); return old_ns; } static inline void uts_ns_init(void) { } #endif #ifdef CONFIG_PROC_SYSCTL extern void uts_proc_notify(enum uts_proc proc); #else static inline void uts_proc_notify(enum uts_proc proc) { } #endif static inline struct new_utsname *utsname(void) { return ¤t->nsproxy->uts_ns->name; } static inline struct new_utsname *init_utsname(void) { return &init_uts_ns.name; } extern struct rw_semaphore uts_sem; #endif /* _LINUX_UTSNAME_H */ |
| 1675 1675 591 591 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 | // SPDX-License-Identifier: GPL-2.0 /* * fs/sysfs/dir.c - sysfs core and dir operation implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007 Tejun Heo <teheo@suse.de> * * Please see Documentation/filesystems/sysfs.rst for more information. */ #define pr_fmt(fmt) "sysfs: " fmt #include <linux/fs.h> #include <linux/kobject.h> #include <linux/slab.h> #include "sysfs.h" DEFINE_SPINLOCK(sysfs_symlink_target_lock); void sysfs_warn_dup(struct kernfs_node *parent, const char *name) { char *buf; buf = kzalloc(PATH_MAX, GFP_KERNEL); if (buf) kernfs_path(parent, buf, PATH_MAX); pr_warn("cannot create duplicate filename '%s/%s'\n", buf, name); dump_stack(); kfree(buf); } /** * sysfs_create_dir_ns - create a directory for an object with a namespace tag * @kobj: object we're creating directory for * @ns: the namespace tag to use */ int sysfs_create_dir_ns(struct kobject *kobj, const void *ns) { struct kernfs_node *parent, *kn; kuid_t uid; kgid_t gid; if (WARN_ON(!kobj)) return -EINVAL; if (kobj->parent) parent = kobj->parent->sd; else parent = sysfs_root_kn; if (!parent) return -ENOENT; kobject_get_ownership(kobj, &uid, &gid); kn = kernfs_create_dir_ns(parent, kobject_name(kobj), 0755, uid, gid, kobj, ns); if (IS_ERR(kn)) { if (PTR_ERR(kn) == -EEXIST) sysfs_warn_dup(parent, kobject_name(kobj)); return PTR_ERR(kn); } kobj->sd = kn; return 0; } /** * sysfs_remove_dir - remove an object's directory. * @kobj: object. * * The only thing special about this is that we remove any files in * the directory before we remove the directory, and we've inlined * what used to be sysfs_rmdir() below, instead of calling separately. */ void sysfs_remove_dir(struct kobject *kobj) { struct kernfs_node *kn = kobj->sd; /* * In general, kboject owner is responsible for ensuring removal * doesn't race with other operations and sysfs doesn't provide any * protection; however, when @kobj is used as a symlink target, the * symlinking entity usually doesn't own @kobj and thus has no * control over removal. @kobj->sd may be removed anytime * and symlink code may end up dereferencing an already freed node. * * sysfs_symlink_target_lock synchronizes @kobj->sd * disassociation against symlink operations so that symlink code * can safely dereference @kobj->sd. */ spin_lock(&sysfs_symlink_target_lock); kobj->sd = NULL; spin_unlock(&sysfs_symlink_target_lock); if (kn) { WARN_ON_ONCE(kernfs_type(kn) != KERNFS_DIR); kernfs_remove(kn); } } int sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name, const void *new_ns) { struct kernfs_node *parent; int ret; parent = kernfs_get_parent(kobj->sd); ret = kernfs_rename_ns(kobj->sd, parent, new_name, new_ns); kernfs_put(parent); return ret; } int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj, const void *new_ns) { struct kernfs_node *kn = kobj->sd; struct kernfs_node *new_parent; new_parent = new_parent_kobj && new_parent_kobj->sd ? new_parent_kobj->sd : sysfs_root_kn; return kernfs_rename_ns(kn, new_parent, kn->name, new_ns); } /** * sysfs_create_mount_point - create an always empty directory * @parent_kobj: kobject that will contain this always empty directory * @name: The name of the always empty directory to add */ int sysfs_create_mount_point(struct kobject *parent_kobj, const char *name) { struct kernfs_node *kn, *parent = parent_kobj->sd; kn = kernfs_create_empty_dir(parent, name); if (IS_ERR(kn)) { if (PTR_ERR(kn) == -EEXIST) sysfs_warn_dup(parent, name); return PTR_ERR(kn); } return 0; } EXPORT_SYMBOL_GPL(sysfs_create_mount_point); /** * sysfs_remove_mount_point - remove an always empty directory. * @parent_kobj: kobject that will contain this always empty directory * @name: The name of the always empty directory to remove * */ void sysfs_remove_mount_point(struct kobject *parent_kobj, const char *name) { struct kernfs_node *parent = parent_kobj->sd; kernfs_remove_by_name_ns(parent, name, NULL); } EXPORT_SYMBOL_GPL(sysfs_remove_mount_point); |
| 515 515 515 515 515 515 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 | // SPDX-License-Identifier: GPL-2.0 /* * Devices PM QoS constraints management * * Copyright (C) 2011 Texas Instruments, Inc. * * This module exposes the interface to kernel space for specifying * per-device PM QoS dependencies. It provides infrastructure for registration * of: * * Dependents on a QoS value : register requests * Watchers of QoS value : get notified when target QoS value changes * * This QoS design is best effort based. Dependents register their QoS needs. * Watchers register to keep track of the current QoS needs of the system. * Watchers can register a per-device notification callback using the * dev_pm_qos_*_notifier API. The notification chain data is stored in the * per-device constraint data struct. * * Note about the per-device constraint data struct allocation: * . The per-device constraints data struct ptr is stored into the device * dev_pm_info. * . To minimize the data usage by the per-device constraints, the data struct * is only allocated at the first call to dev_pm_qos_add_request. * . The data is later free'd when the device is removed from the system. * . A global mutex protects the constraints users from the data being * allocated and free'd. */ #include <linux/pm_qos.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/device.h> #include <linux/mutex.h> #include <linux/export.h> #include <linux/pm_runtime.h> #include <linux/err.h> #include <trace/events/power.h> #include "power.h" static DEFINE_MUTEX(dev_pm_qos_mtx); static DEFINE_MUTEX(dev_pm_qos_sysfs_mtx); /** * __dev_pm_qos_flags - Check PM QoS flags for a given device. * @dev: Device to check the PM QoS flags for. * @mask: Flags to check against. * * This routine must be called with dev->power.lock held. */ enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev, s32 mask) { struct dev_pm_qos *qos = dev->power.qos; struct pm_qos_flags *pqf; s32 val; lockdep_assert_held(&dev->power.lock); if (IS_ERR_OR_NULL(qos)) return PM_QOS_FLAGS_UNDEFINED; pqf = &qos->flags; if (list_empty(&pqf->list)) return PM_QOS_FLAGS_UNDEFINED; val = pqf->effective_flags & mask; if (val) return (val == mask) ? PM_QOS_FLAGS_ALL : PM_QOS_FLAGS_SOME; return PM_QOS_FLAGS_NONE; } /** * dev_pm_qos_flags - Check PM QoS flags for a given device (locked). * @dev: Device to check the PM QoS flags for. * @mask: Flags to check against. */ enum pm_qos_flags_status dev_pm_qos_flags(struct device *dev, s32 mask) { unsigned long irqflags; enum pm_qos_flags_status ret; spin_lock_irqsave(&dev->power.lock, irqflags); ret = __dev_pm_qos_flags(dev, mask); spin_unlock_irqrestore(&dev->power.lock, irqflags); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_flags); /** * __dev_pm_qos_resume_latency - Get resume latency constraint for a given device. * @dev: Device to get the PM QoS constraint value for. * * This routine must be called with dev->power.lock held. */ s32 __dev_pm_qos_resume_latency(struct device *dev) { lockdep_assert_held(&dev->power.lock); return dev_pm_qos_raw_resume_latency(dev); } /** * dev_pm_qos_read_value - Get PM QoS constraint for a given device (locked). * @dev: Device to get the PM QoS constraint value for. * @type: QoS request type. */ s32 dev_pm_qos_read_value(struct device *dev, enum dev_pm_qos_req_type type) { struct dev_pm_qos *qos = dev->power.qos; unsigned long flags; s32 ret; spin_lock_irqsave(&dev->power.lock, flags); switch (type) { case DEV_PM_QOS_RESUME_LATENCY: ret = IS_ERR_OR_NULL(qos) ? PM_QOS_RESUME_LATENCY_NO_CONSTRAINT : pm_qos_read_value(&qos->resume_latency); break; case DEV_PM_QOS_MIN_FREQUENCY: ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE : freq_qos_read_value(&qos->freq, FREQ_QOS_MIN); break; case DEV_PM_QOS_MAX_FREQUENCY: ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE : freq_qos_read_value(&qos->freq, FREQ_QOS_MAX); break; default: WARN_ON(1); ret = 0; } spin_unlock_irqrestore(&dev->power.lock, flags); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_read_value); /** * apply_constraint - Add/modify/remove device PM QoS request. * @req: Constraint request to apply * @action: Action to perform (add/update/remove). * @value: Value to assign to the QoS request. * * Internal function to update the constraints list using the PM QoS core * code and if needed call the per-device callbacks. */ static int apply_constraint(struct dev_pm_qos_request *req, enum pm_qos_req_action action, s32 value) { struct dev_pm_qos *qos = req->dev->power.qos; int ret; switch(req->type) { case DEV_PM_QOS_RESUME_LATENCY: if (WARN_ON(action != PM_QOS_REMOVE_REQ && value < 0)) value = 0; ret = pm_qos_update_target(&qos->resume_latency, &req->data.pnode, action, value); break; case DEV_PM_QOS_LATENCY_TOLERANCE: ret = pm_qos_update_target(&qos->latency_tolerance, &req->data.pnode, action, value); if (ret) { value = pm_qos_read_value(&qos->latency_tolerance); req->dev->power.set_latency_tolerance(req->dev, value); } break; case DEV_PM_QOS_MIN_FREQUENCY: case DEV_PM_QOS_MAX_FREQUENCY: ret = freq_qos_apply(&req->data.freq, action, value); break; case DEV_PM_QOS_FLAGS: ret = pm_qos_update_flags(&qos->flags, &req->data.flr, action, value); break; default: ret = -EINVAL; } return ret; } /* * dev_pm_qos_constraints_allocate * @dev: device to allocate data for * * Called at the first call to add_request, for constraint data allocation * Must be called with the dev_pm_qos_mtx mutex held */ static int dev_pm_qos_constraints_allocate(struct device *dev) { struct dev_pm_qos *qos; struct pm_qos_constraints *c; struct blocking_notifier_head *n; qos = kzalloc(sizeof(*qos), GFP_KERNEL); if (!qos) return -ENOMEM; n = kzalloc(3 * sizeof(*n), GFP_KERNEL); if (!n) { kfree(qos); return -ENOMEM; } c = &qos->resume_latency; plist_head_init(&c->list); c->target_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE; c->default_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE; c->no_constraint_value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; c->type = PM_QOS_MIN; c->notifiers = n; BLOCKING_INIT_NOTIFIER_HEAD(n); c = &qos->latency_tolerance; plist_head_init(&c->list); c->target_value = PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE; c->default_value = PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE; c->no_constraint_value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT; c->type = PM_QOS_MIN; freq_constraints_init(&qos->freq); INIT_LIST_HEAD(&qos->flags.list); spin_lock_irq(&dev->power.lock); dev->power.qos = qos; spin_unlock_irq(&dev->power.lock); return 0; } static void __dev_pm_qos_hide_latency_limit(struct device *dev); static void __dev_pm_qos_hide_flags(struct device *dev); /** * dev_pm_qos_constraints_destroy * @dev: target device * * Called from the device PM subsystem on device removal under device_pm_lock(). */ void dev_pm_qos_constraints_destroy(struct device *dev) { struct dev_pm_qos *qos; struct dev_pm_qos_request *req, *tmp; struct pm_qos_constraints *c; struct pm_qos_flags *f; mutex_lock(&dev_pm_qos_sysfs_mtx); /* * If the device's PM QoS resume latency limit or PM QoS flags have been * exposed to user space, they have to be hidden at this point. */ pm_qos_sysfs_remove_resume_latency(dev); pm_qos_sysfs_remove_flags(dev); mutex_lock(&dev_pm_qos_mtx); __dev_pm_qos_hide_latency_limit(dev); __dev_pm_qos_hide_flags(dev); qos = dev->power.qos; if (!qos) goto out; /* Flush the constraints lists for the device. */ c = &qos->resume_latency; plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) { /* * Update constraints list and call the notification * callbacks if needed */ apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); } c = &qos->latency_tolerance; plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) { apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); } c = &qos->freq.min_freq; plist_for_each_entry_safe(req, tmp, &c->list, data.freq.pnode) { apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); } c = &qos->freq.max_freq; plist_for_each_entry_safe(req, tmp, &c->list, data.freq.pnode) { apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); } f = &qos->flags; list_for_each_entry_safe(req, tmp, &f->list, data.flr.node) { apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); } spin_lock_irq(&dev->power.lock); dev->power.qos = ERR_PTR(-ENODEV); spin_unlock_irq(&dev->power.lock); kfree(qos->resume_latency.notifiers); kfree(qos); out: mutex_unlock(&dev_pm_qos_mtx); mutex_unlock(&dev_pm_qos_sysfs_mtx); } static bool dev_pm_qos_invalid_req_type(struct device *dev, enum dev_pm_qos_req_type type) { return type == DEV_PM_QOS_LATENCY_TOLERANCE && !dev->power.set_latency_tolerance; } static int __dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req, enum dev_pm_qos_req_type type, s32 value) { int ret = 0; if (!dev || !req || dev_pm_qos_invalid_req_type(dev, type)) return -EINVAL; if (WARN(dev_pm_qos_request_active(req), "%s() called for already added request\n", __func__)) return -EINVAL; if (IS_ERR(dev->power.qos)) ret = -ENODEV; else if (!dev->power.qos) ret = dev_pm_qos_constraints_allocate(dev); trace_dev_pm_qos_add_request(dev_name(dev), type, value); if (ret) return ret; req->dev = dev; req->type = type; if (req->type == DEV_PM_QOS_MIN_FREQUENCY) ret = freq_qos_add_request(&dev->power.qos->freq, &req->data.freq, FREQ_QOS_MIN, value); else if (req->type == DEV_PM_QOS_MAX_FREQUENCY) ret = freq_qos_add_request(&dev->power.qos->freq, &req->data.freq, FREQ_QOS_MAX, value); else ret = apply_constraint(req, PM_QOS_ADD_REQ, value); return ret; } /** * dev_pm_qos_add_request - inserts new qos request into the list * @dev: target device for the constraint * @req: pointer to a preallocated handle * @type: type of the request * @value: defines the qos request * * This function inserts a new entry in the device constraints list of * requested qos performance characteristics. It recomputes the aggregate * QoS expectations of parameters and initializes the dev_pm_qos_request * handle. Caller needs to save this handle for later use in updates and * removal. * * Returns 1 if the aggregated constraint value has changed, * 0 if the aggregated constraint value has not changed, * -EINVAL in case of wrong parameters, -ENOMEM if there's not enough memory * to allocate for data structures, -ENODEV if the device has just been removed * from the system. * * Callers should ensure that the target device is not RPM_SUSPENDED before * using this function for requests of type DEV_PM_QOS_FLAGS. */ int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req, enum dev_pm_qos_req_type type, s32 value) { int ret; mutex_lock(&dev_pm_qos_mtx); ret = __dev_pm_qos_add_request(dev, req, type, value); mutex_unlock(&dev_pm_qos_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_add_request); /** * __dev_pm_qos_update_request - Modify an existing device PM QoS request. * @req : PM QoS request to modify. * @new_value: New value to request. */ static int __dev_pm_qos_update_request(struct dev_pm_qos_request *req, s32 new_value) { s32 curr_value; int ret = 0; if (!req) /*guard against callers passing in null */ return -EINVAL; if (WARN(!dev_pm_qos_request_active(req), "%s() called for unknown object\n", __func__)) return -EINVAL; if (IS_ERR_OR_NULL(req->dev->power.qos)) return -ENODEV; switch(req->type) { case DEV_PM_QOS_RESUME_LATENCY: case DEV_PM_QOS_LATENCY_TOLERANCE: curr_value = req->data.pnode.prio; break; case DEV_PM_QOS_MIN_FREQUENCY: case DEV_PM_QOS_MAX_FREQUENCY: curr_value = req->data.freq.pnode.prio; break; case DEV_PM_QOS_FLAGS: curr_value = req->data.flr.flags; break; default: return -EINVAL; } trace_dev_pm_qos_update_request(dev_name(req->dev), req->type, new_value); if (curr_value != new_value) ret = apply_constraint(req, PM_QOS_UPDATE_REQ, new_value); return ret; } /** * dev_pm_qos_update_request - modifies an existing qos request * @req : handle to list element holding a dev_pm_qos request to use * @new_value: defines the qos request * * Updates an existing dev PM qos request along with updating the * target value. * * Attempts are made to make this code callable on hot code paths. * * Returns 1 if the aggregated constraint value has changed, * 0 if the aggregated constraint value has not changed, * -EINVAL in case of wrong parameters, -ENODEV if the device has been * removed from the system * * Callers should ensure that the target device is not RPM_SUSPENDED before * using this function for requests of type DEV_PM_QOS_FLAGS. */ int dev_pm_qos_update_request(struct dev_pm_qos_request *req, s32 new_value) { int ret; mutex_lock(&dev_pm_qos_mtx); ret = __dev_pm_qos_update_request(req, new_value); mutex_unlock(&dev_pm_qos_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_update_request); static int __dev_pm_qos_remove_request(struct dev_pm_qos_request *req) { int ret; if (!req) /*guard against callers passing in null */ return -EINVAL; if (WARN(!dev_pm_qos_request_active(req), "%s() called for unknown object\n", __func__)) return -EINVAL; if (IS_ERR_OR_NULL(req->dev->power.qos)) return -ENODEV; trace_dev_pm_qos_remove_request(dev_name(req->dev), req->type, PM_QOS_DEFAULT_VALUE); ret = apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); return ret; } /** * dev_pm_qos_remove_request - modifies an existing qos request * @req: handle to request list element * * Will remove pm qos request from the list of constraints and * recompute the current target value. Call this on slow code paths. * * Returns 1 if the aggregated constraint value has changed, * 0 if the aggregated constraint value has not changed, * -EINVAL in case of wrong parameters, -ENODEV if the device has been * removed from the system * * Callers should ensure that the target device is not RPM_SUSPENDED before * using this function for requests of type DEV_PM_QOS_FLAGS. */ int dev_pm_qos_remove_request(struct dev_pm_qos_request *req) { int ret; mutex_lock(&dev_pm_qos_mtx); ret = __dev_pm_qos_remove_request(req); mutex_unlock(&dev_pm_qos_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_remove_request); /** * dev_pm_qos_add_notifier - sets notification entry for changes to target value * of per-device PM QoS constraints * * @dev: target device for the constraint * @notifier: notifier block managed by caller. * @type: request type. * * Will register the notifier into a notification chain that gets called * upon changes to the target value for the device. * * If the device's constraints object doesn't exist when this routine is called, * it will be created (or error code will be returned if that fails). */ int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier, enum dev_pm_qos_req_type type) { int ret = 0; mutex_lock(&dev_pm_qos_mtx); if (IS_ERR(dev->power.qos)) ret = -ENODEV; else if (!dev->power.qos) ret = dev_pm_qos_constraints_allocate(dev); if (ret) goto unlock; switch (type) { case DEV_PM_QOS_RESUME_LATENCY: ret = blocking_notifier_chain_register(dev->power.qos->resume_latency.notifiers, notifier); break; case DEV_PM_QOS_MIN_FREQUENCY: ret = freq_qos_add_notifier(&dev->power.qos->freq, FREQ_QOS_MIN, notifier); break; case DEV_PM_QOS_MAX_FREQUENCY: ret = freq_qos_add_notifier(&dev->power.qos->freq, FREQ_QOS_MAX, notifier); break; default: WARN_ON(1); ret = -EINVAL; } unlock: mutex_unlock(&dev_pm_qos_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_add_notifier); /** * dev_pm_qos_remove_notifier - deletes notification for changes to target value * of per-device PM QoS constraints * * @dev: target device for the constraint * @notifier: notifier block to be removed. * @type: request type. * * Will remove the notifier from the notification chain that gets called * upon changes to the target value. */ int dev_pm_qos_remove_notifier(struct device *dev, struct notifier_block *notifier, enum dev_pm_qos_req_type type) { int ret = 0; mutex_lock(&dev_pm_qos_mtx); /* Silently return if the constraints object is not present. */ if (IS_ERR_OR_NULL(dev->power.qos)) goto unlock; switch (type) { case DEV_PM_QOS_RESUME_LATENCY: ret = blocking_notifier_chain_unregister(dev->power.qos->resume_latency.notifiers, notifier); break; case DEV_PM_QOS_MIN_FREQUENCY: ret = freq_qos_remove_notifier(&dev->power.qos->freq, FREQ_QOS_MIN, notifier); break; case DEV_PM_QOS_MAX_FREQUENCY: ret = freq_qos_remove_notifier(&dev->power.qos->freq, FREQ_QOS_MAX, notifier); break; default: WARN_ON(1); ret = -EINVAL; } unlock: mutex_unlock(&dev_pm_qos_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_remove_notifier); /** * dev_pm_qos_add_ancestor_request - Add PM QoS request for device's ancestor. * @dev: Device whose ancestor to add the request for. * @req: Pointer to the preallocated handle. * @type: Type of the request. * @value: Constraint latency value. */ int dev_pm_qos_add_ancestor_request(struct device *dev, struct dev_pm_qos_request *req, enum dev_pm_qos_req_type type, s32 value) { struct device *ancestor = dev->parent; int ret = -ENODEV; switch (type) { case DEV_PM_QOS_RESUME_LATENCY: while (ancestor && !ancestor->power.ignore_children) ancestor = ancestor->parent; break; case DEV_PM_QOS_LATENCY_TOLERANCE: while (ancestor && !ancestor->power.set_latency_tolerance) ancestor = ancestor->parent; break; default: ancestor = NULL; } if (ancestor) ret = dev_pm_qos_add_request(ancestor, req, type, value); if (ret < 0) req->dev = NULL; return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_add_ancestor_request); static void __dev_pm_qos_drop_user_request(struct device *dev, enum dev_pm_qos_req_type type) { struct dev_pm_qos_request *req = NULL; switch(type) { case DEV_PM_QOS_RESUME_LATENCY: req = dev->power.qos->resume_latency_req; dev->power.qos->resume_latency_req = NULL; break; case DEV_PM_QOS_LATENCY_TOLERANCE: req = dev->power.qos->latency_tolerance_req; dev->power.qos->latency_tolerance_req = NULL; break; case DEV_PM_QOS_FLAGS: req = dev->power.qos->flags_req; dev->power.qos->flags_req = NULL; break; default: WARN_ON(1); return; } __dev_pm_qos_remove_request(req); kfree(req); } static void dev_pm_qos_drop_user_request(struct device *dev, enum dev_pm_qos_req_type type) { mutex_lock(&dev_pm_qos_mtx); __dev_pm_qos_drop_user_request(dev, type); mutex_unlock(&dev_pm_qos_mtx); } /** * dev_pm_qos_expose_latency_limit - Expose PM QoS latency limit to user space. * @dev: Device whose PM QoS latency limit is to be exposed to user space. * @value: Initial value of the latency limit. */ int dev_pm_qos_expose_latency_limit(struct device *dev, s32 value) { struct dev_pm_qos_request *req; int ret; if (!device_is_registered(dev) || value < 0) return -EINVAL; req = kzalloc(sizeof(*req), GFP_KERNEL); if (!req) return -ENOMEM; ret = dev_pm_qos_add_request(dev, req, DEV_PM_QOS_RESUME_LATENCY, value); if (ret < 0) { kfree(req); return ret; } mutex_lock(&dev_pm_qos_sysfs_mtx); mutex_lock(&dev_pm_qos_mtx); if (IS_ERR_OR_NULL(dev->power.qos)) ret = -ENODEV; else if (dev->power.qos->resume_latency_req) ret = -EEXIST; if (ret < 0) { __dev_pm_qos_remove_request(req); kfree(req); mutex_unlock(&dev_pm_qos_mtx); goto out; } dev->power.qos->resume_latency_req = req; mutex_unlock(&dev_pm_qos_mtx); ret = pm_qos_sysfs_add_resume_latency(dev); if (ret) dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_RESUME_LATENCY); out: mutex_unlock(&dev_pm_qos_sysfs_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_expose_latency_limit); static void __dev_pm_qos_hide_latency_limit(struct device *dev) { if (!IS_ERR_OR_NULL(dev->power.qos) && dev->power.qos->resume_latency_req) __dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_RESUME_LATENCY); } /** * dev_pm_qos_hide_latency_limit - Hide PM QoS latency limit from user space. * @dev: Device whose PM QoS latency limit is to be hidden from user space. */ void dev_pm_qos_hide_latency_limit(struct device *dev) { mutex_lock(&dev_pm_qos_sysfs_mtx); pm_qos_sysfs_remove_resume_latency(dev); mutex_lock(&dev_pm_qos_mtx); __dev_pm_qos_hide_latency_limit(dev); mutex_unlock(&dev_pm_qos_mtx); mutex_unlock(&dev_pm_qos_sysfs_mtx); } EXPORT_SYMBOL_GPL(dev_pm_qos_hide_latency_limit); /** * dev_pm_qos_expose_flags - Expose PM QoS flags of a device to user space. * @dev: Device whose PM QoS flags are to be exposed to user space. * @val: Initial values of the flags. */ int dev_pm_qos_expose_flags(struct device *dev, s32 val) { struct dev_pm_qos_request *req; int ret; if (!device_is_registered(dev)) return -EINVAL; req = kzalloc(sizeof(*req), GFP_KERNEL); if (!req) return -ENOMEM; ret = dev_pm_qos_add_request(dev, req, DEV_PM_QOS_FLAGS, val); if (ret < 0) { kfree(req); return ret; } pm_runtime_get_sync(dev); mutex_lock(&dev_pm_qos_sysfs_mtx); mutex_lock(&dev_pm_qos_mtx); if (IS_ERR_OR_NULL(dev->power.qos)) ret = -ENODEV; else if (dev->power.qos->flags_req) ret = -EEXIST; if (ret < 0) { __dev_pm_qos_remove_request(req); kfree(req); mutex_unlock(&dev_pm_qos_mtx); goto out; } dev->power.qos->flags_req = req; mutex_unlock(&dev_pm_qos_mtx); ret = pm_qos_sysfs_add_flags(dev); if (ret) dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_FLAGS); out: mutex_unlock(&dev_pm_qos_sysfs_mtx); pm_runtime_put(dev); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_expose_flags); static void __dev_pm_qos_hide_flags(struct device *dev) { if (!IS_ERR_OR_NULL(dev->power.qos) && dev->power.qos->flags_req) __dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_FLAGS); } /** * dev_pm_qos_hide_flags - Hide PM QoS flags of a device from user space. * @dev: Device whose PM QoS flags are to be hidden from user space. */ void dev_pm_qos_hide_flags(struct device *dev) { pm_runtime_get_sync(dev); mutex_lock(&dev_pm_qos_sysfs_mtx); pm_qos_sysfs_remove_flags(dev); mutex_lock(&dev_pm_qos_mtx); __dev_pm_qos_hide_flags(dev); mutex_unlock(&dev_pm_qos_mtx); mutex_unlock(&dev_pm_qos_sysfs_mtx); pm_runtime_put(dev); } EXPORT_SYMBOL_GPL(dev_pm_qos_hide_flags); /** * dev_pm_qos_update_flags - Update PM QoS flags request owned by user space. * @dev: Device to update the PM QoS flags request for. * @mask: Flags to set/clear. * @set: Whether to set or clear the flags (true means set). */ int dev_pm_qos_update_flags(struct device *dev, s32 mask, bool set) { s32 value; int ret; pm_runtime_get_sync(dev); mutex_lock(&dev_pm_qos_mtx); if (IS_ERR_OR_NULL(dev->power.qos) || !dev->power.qos->flags_req) { ret = -EINVAL; goto out; } value = dev_pm_qos_requested_flags(dev); if (set) value |= mask; else value &= ~mask; ret = __dev_pm_qos_update_request(dev->power.qos->flags_req, value); out: mutex_unlock(&dev_pm_qos_mtx); pm_runtime_put(dev); return ret; } /** * dev_pm_qos_get_user_latency_tolerance - Get user space latency tolerance. * @dev: Device to obtain the user space latency tolerance for. */ s32 dev_pm_qos_get_user_latency_tolerance(struct device *dev) { s32 ret; mutex_lock(&dev_pm_qos_mtx); ret = IS_ERR_OR_NULL(dev->power.qos) || !dev->power.qos->latency_tolerance_req ? PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT : dev->power.qos->latency_tolerance_req->data.pnode.prio; mutex_unlock(&dev_pm_qos_mtx); return ret; } /** * dev_pm_qos_update_user_latency_tolerance - Update user space latency tolerance. * @dev: Device to update the user space latency tolerance for. * @val: New user space latency tolerance for @dev (negative values disable). */ int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val) { int ret; mutex_lock(&dev_pm_qos_mtx); if (IS_ERR_OR_NULL(dev->power.qos) || !dev->power.qos->latency_tolerance_req) { struct dev_pm_qos_request *req; if (val < 0) { if (val == PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT) ret = 0; else ret = -EINVAL; goto out; } req = kzalloc(sizeof(*req), GFP_KERNEL); if (!req) { ret = -ENOMEM; goto out; } ret = __dev_pm_qos_add_request(dev, req, DEV_PM_QOS_LATENCY_TOLERANCE, val); if (ret < 0) { kfree(req); goto out; } dev->power.qos->latency_tolerance_req = req; } else { if (val < 0) { __dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_LATENCY_TOLERANCE); ret = 0; } else { ret = __dev_pm_qos_update_request(dev->power.qos->latency_tolerance_req, val); } } out: mutex_unlock(&dev_pm_qos_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_update_user_latency_tolerance); /** * dev_pm_qos_expose_latency_tolerance - Expose latency tolerance to userspace * @dev: Device whose latency tolerance to expose */ int dev_pm_qos_expose_latency_tolerance(struct device *dev) { int ret; if (!dev->power.set_latency_tolerance) return -EINVAL; mutex_lock(&dev_pm_qos_sysfs_mtx); ret = pm_qos_sysfs_add_latency_tolerance(dev); mutex_unlock(&dev_pm_qos_sysfs_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_expose_latency_tolerance); /** * dev_pm_qos_hide_latency_tolerance - Hide latency tolerance from userspace * @dev: Device whose latency tolerance to hide */ void dev_pm_qos_hide_latency_tolerance(struct device *dev) { mutex_lock(&dev_pm_qos_sysfs_mtx); pm_qos_sysfs_remove_latency_tolerance(dev); mutex_unlock(&dev_pm_qos_sysfs_mtx); /* Remove the request from user space now */ pm_runtime_get_sync(dev); dev_pm_qos_update_user_latency_tolerance(dev, PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT); pm_runtime_put(dev); } EXPORT_SYMBOL_GPL(dev_pm_qos_hide_latency_tolerance); |
| 168 2067 51 3 1338 720 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. NET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the Ethernet handlers. * * Version: @(#)eth.h 1.0.4 05/13/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * * Relocated to include/linux where it belongs by Alan Cox * <gw4pts@gw4pts.ampr.org> */ #ifndef _LINUX_ETHERDEVICE_H #define _LINUX_ETHERDEVICE_H #include <linux/if_ether.h> #include <linux/netdevice.h> #include <linux/random.h> #include <linux/crc32.h> #include <asm/unaligned.h> #include <asm/bitsperlong.h> #ifdef __KERNEL__ struct device; struct fwnode_handle; int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr); int platform_get_ethdev_address(struct device *dev, struct net_device *netdev); unsigned char *arch_get_platform_mac_address(void); int nvmem_get_mac_address(struct device *dev, void *addrbuf); int device_get_mac_address(struct device *dev, char *addr); int device_get_ethdev_address(struct device *dev, struct net_device *netdev); int fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr); u32 eth_get_headlen(const struct net_device *dev, const void *data, u32 len); __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); extern const struct header_ops eth_header_ops; int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned len); int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr); int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16 type); void eth_header_cache_update(struct hh_cache *hh, const struct net_device *dev, const unsigned char *haddr); __be16 eth_header_parse_protocol(const struct sk_buff *skb); int eth_prepare_mac_addr_change(struct net_device *dev, void *p); void eth_commit_mac_addr_change(struct net_device *dev, void *p); int eth_mac_addr(struct net_device *dev, void *p); int eth_validate_addr(struct net_device *dev); struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs, unsigned int rxqs); #define alloc_etherdev(sizeof_priv) alloc_etherdev_mq(sizeof_priv, 1) #define alloc_etherdev_mq(sizeof_priv, count) alloc_etherdev_mqs(sizeof_priv, count, count) struct net_device *devm_alloc_etherdev_mqs(struct device *dev, int sizeof_priv, unsigned int txqs, unsigned int rxqs); #define devm_alloc_etherdev(dev, sizeof_priv) devm_alloc_etherdev_mqs(dev, sizeof_priv, 1, 1) struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb); int eth_gro_complete(struct sk_buff *skb, int nhoff); /* Reserved Ethernet Addresses per IEEE 802.1Q */ static const u8 eth_reserved_addr_base[ETH_ALEN] __aligned(2) = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 }; #define eth_stp_addr eth_reserved_addr_base /** * is_link_local_ether_addr - Determine if given Ethernet address is link-local * @addr: Pointer to a six-byte array containing the Ethernet address * * Return true if address is link local reserved addr (01:80:c2:00:00:0X) per * IEEE 802.1Q 8.6.3 Frame filtering. * * Please note: addr must be aligned to u16. */ static inline bool is_link_local_ether_addr(const u8 *addr) { __be16 *a = (__be16 *)addr; static const __be16 *b = (const __be16 *)eth_reserved_addr_base; static const __be16 m = cpu_to_be16(0xfff0); #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return (((*(const u32 *)addr) ^ (*(const u32 *)b)) | (__force int)((a[2] ^ b[2]) & m)) == 0; #else return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | ((a[2] ^ b[2]) & m)) == 0; #endif } /** * is_zero_ether_addr - Determine if give Ethernet address is all zeros. * @addr: Pointer to a six-byte array containing the Ethernet address * * Return true if the address is all zeroes. * * Please note: addr must be aligned to u16. */ static inline bool is_zero_ether_addr(const u8 *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return ((*(const u32 *)addr) | (*(const u16 *)(addr + 4))) == 0; #else return (*(const u16 *)(addr + 0) | *(const u16 *)(addr + 2) | *(const u16 *)(addr + 4)) == 0; #endif } /** * is_multicast_ether_addr - Determine if the Ethernet address is a multicast. * @addr: Pointer to a six-byte array containing the Ethernet address * * Return true if the address is a multicast address. * By definition the broadcast address is also a multicast address. */ static inline bool is_multicast_ether_addr(const u8 *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) u32 a = *(const u32 *)addr; #else u16 a = *(const u16 *)addr; #endif #ifdef __BIG_ENDIAN return 0x01 & (a >> ((sizeof(a) * 8) - 8)); #else return 0x01 & a; #endif } static inline bool is_multicast_ether_addr_64bits(const u8 *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 #ifdef __BIG_ENDIAN return 0x01 & ((*(const u64 *)addr) >> 56); #else return 0x01 & (*(const u64 *)addr); #endif #else return is_multicast_ether_addr(addr); #endif } /** * is_local_ether_addr - Determine if the Ethernet address is locally-assigned one (IEEE 802). * @addr: Pointer to a six-byte array containing the Ethernet address * * Return true if the address is a local address. */ static inline bool is_local_ether_addr(const u8 *addr) { return 0x02 & addr[0]; } /** * is_broadcast_ether_addr - Determine if the Ethernet address is broadcast * @addr: Pointer to a six-byte array containing the Ethernet address * * Return true if the address is the broadcast address. * * Please note: addr must be aligned to u16. */ static inline bool is_broadcast_ether_addr(const u8 *addr) { return (*(const u16 *)(addr + 0) & *(const u16 *)(addr + 2) & *(const u16 *)(addr + 4)) == 0xffff; } /** * is_unicast_ether_addr - Determine if the Ethernet address is unicast * @addr: Pointer to a six-byte array containing the Ethernet address * * Return true if the address is a unicast address. */ static inline bool is_unicast_ether_addr(const u8 *addr) { return !is_multicast_ether_addr(addr); } /** * is_valid_ether_addr - Determine if the given Ethernet address is valid * @addr: Pointer to a six-byte array containing the Ethernet address * * Check that the Ethernet address (MAC) is not 00:00:00:00:00:00, is not * a multicast address, and is not FF:FF:FF:FF:FF:FF. * * Return true if the address is valid. * * Please note: addr must be aligned to u16. */ static inline bool is_valid_ether_addr(const u8 *addr) { /* FF:FF:FF:FF:FF:FF is a multicast address so we don't need to * explicitly check for it here. */ return !is_multicast_ether_addr(addr) && !is_zero_ether_addr(addr); } /** * eth_proto_is_802_3 - Determine if a given Ethertype/length is a protocol * @proto: Ethertype/length value to be tested * * Check that the value from the Ethertype/length field is a valid Ethertype. * * Return true if the valid is an 802.3 supported Ethertype. */ static inline bool eth_proto_is_802_3(__be16 proto) { #ifndef __BIG_ENDIAN /* if CPU is little endian mask off bits representing LSB */ proto &= htons(0xFF00); #endif /* cast both to u16 and compare since LSB can be ignored */ return (__force u16)proto >= (__force u16)htons(ETH_P_802_3_MIN); } /** * eth_random_addr - Generate software assigned random Ethernet address * @addr: Pointer to a six-byte array containing the Ethernet address * * Generate a random Ethernet address (MAC) that is not multicast * and has the local assigned bit set. */ static inline void eth_random_addr(u8 *addr) { get_random_bytes(addr, ETH_ALEN); addr[0] &= 0xfe; /* clear multicast bit */ addr[0] |= 0x02; /* set local assignment bit (IEEE802) */ } /** * eth_broadcast_addr - Assign broadcast address * @addr: Pointer to a six-byte array containing the Ethernet address * * Assign the broadcast address to the given address array. */ static inline void eth_broadcast_addr(u8 *addr) { memset(addr, 0xff, ETH_ALEN); } /** * eth_zero_addr - Assign zero address * @addr: Pointer to a six-byte array containing the Ethernet address * * Assign the zero address to the given address array. */ static inline void eth_zero_addr(u8 *addr) { memset(addr, 0x00, ETH_ALEN); } /** * eth_hw_addr_random - Generate software assigned random Ethernet and * set device flag * @dev: pointer to net_device structure * * Generate a random Ethernet address (MAC) to be used by a net device * and set addr_assign_type so the state can be read by sysfs and be * used by userspace. */ static inline void eth_hw_addr_random(struct net_device *dev) { u8 addr[ETH_ALEN]; eth_random_addr(addr); __dev_addr_set(dev, addr, ETH_ALEN); dev->addr_assign_type = NET_ADDR_RANDOM; } /** * eth_hw_addr_crc - Calculate CRC from netdev_hw_addr * @ha: pointer to hardware address * * Calculate CRC from a hardware address as basis for filter hashes. */ static inline u32 eth_hw_addr_crc(struct netdev_hw_addr *ha) { return ether_crc(ETH_ALEN, ha->addr); } /** * ether_addr_copy - Copy an Ethernet address * @dst: Pointer to a six-byte array Ethernet address destination * @src: Pointer to a six-byte array Ethernet address source * * Please note: dst & src must both be aligned to u16. */ static inline void ether_addr_copy(u8 *dst, const u8 *src) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) *(u32 *)dst = *(const u32 *)src; *(u16 *)(dst + 4) = *(const u16 *)(src + 4); #else u16 *a = (u16 *)dst; const u16 *b = (const u16 *)src; a[0] = b[0]; a[1] = b[1]; a[2] = b[2]; #endif } /** * eth_hw_addr_set - Assign Ethernet address to a net_device * @dev: pointer to net_device structure * @addr: address to assign * * Assign given address to the net_device, addr_assign_type is not changed. */ static inline void eth_hw_addr_set(struct net_device *dev, const u8 *addr) { __dev_addr_set(dev, addr, ETH_ALEN); } /** * eth_hw_addr_inherit - Copy dev_addr from another net_device * @dst: pointer to net_device to copy dev_addr to * @src: pointer to net_device to copy dev_addr from * * Copy the Ethernet address from one net_device to another along with * the address attributes (addr_assign_type). */ static inline void eth_hw_addr_inherit(struct net_device *dst, struct net_device *src) { dst->addr_assign_type = src->addr_assign_type; eth_hw_addr_set(dst, src->dev_addr); } /** * ether_addr_equal - Compare two Ethernet addresses * @addr1: Pointer to a six-byte array containing the Ethernet address * @addr2: Pointer other six-byte array containing the Ethernet address * * Compare two Ethernet addresses, returns true if equal * * Please note: addr1 & addr2 must both be aligned to u16. */ static inline bool ether_addr_equal(const u8 *addr1, const u8 *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) u32 fold = ((*(const u32 *)addr1) ^ (*(const u32 *)addr2)) | ((*(const u16 *)(addr1 + 4)) ^ (*(const u16 *)(addr2 + 4))); return fold == 0; #else const u16 *a = (const u16 *)addr1; const u16 *b = (const u16 *)addr2; return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) == 0; #endif } /** * ether_addr_equal_64bits - Compare two Ethernet addresses * @addr1: Pointer to an array of 8 bytes * @addr2: Pointer to an other array of 8 bytes * * Compare two Ethernet addresses, returns true if equal, false otherwise. * * The function doesn't need any conditional branches and possibly uses * word memory accesses on CPU allowing cheap unaligned memory reads. * arrays = { byte1, byte2, byte3, byte4, byte5, byte6, pad1, pad2 } * * Please note that alignment of addr1 & addr2 are only guaranteed to be 16 bits. */ static inline bool ether_addr_equal_64bits(const u8 *addr1, const u8 *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 u64 fold = (*(const u64 *)addr1) ^ (*(const u64 *)addr2); #ifdef __BIG_ENDIAN return (fold >> 16) == 0; #else return (fold << 16) == 0; #endif #else return ether_addr_equal(addr1, addr2); #endif } /** * ether_addr_equal_unaligned - Compare two not u16 aligned Ethernet addresses * @addr1: Pointer to a six-byte array containing the Ethernet address * @addr2: Pointer other six-byte array containing the Ethernet address * * Compare two Ethernet addresses, returns true if equal * * Please note: Use only when any Ethernet address may not be u16 aligned. */ static inline bool ether_addr_equal_unaligned(const u8 *addr1, const u8 *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return ether_addr_equal(addr1, addr2); #else return memcmp(addr1, addr2, ETH_ALEN) == 0; #endif } /** * ether_addr_equal_masked - Compare two Ethernet addresses with a mask * @addr1: Pointer to a six-byte array containing the 1st Ethernet address * @addr2: Pointer to a six-byte array containing the 2nd Ethernet address * @mask: Pointer to a six-byte array containing the Ethernet address bitmask * * Compare two Ethernet addresses with a mask, returns true if for every bit * set in the bitmask the equivalent bits in the ethernet addresses are equal. * Using a mask with all bits set is a slower ether_addr_equal. */ static inline bool ether_addr_equal_masked(const u8 *addr1, const u8 *addr2, const u8 *mask) { int i; for (i = 0; i < ETH_ALEN; i++) { if ((addr1[i] ^ addr2[i]) & mask[i]) return false; } return true; } static inline bool ether_addr_is_ipv4_mcast(const u8 *addr) { u8 base[ETH_ALEN] = { 0x01, 0x00, 0x5e, 0x00, 0x00, 0x00 }; u8 mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0x80, 0x00, 0x00 }; return ether_addr_equal_masked(addr, base, mask); } static inline bool ether_addr_is_ipv6_mcast(const u8 *addr) { u8 base[ETH_ALEN] = { 0x33, 0x33, 0x00, 0x00, 0x00, 0x00 }; u8 mask[ETH_ALEN] = { 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 }; return ether_addr_equal_masked(addr, base, mask); } static inline bool ether_addr_is_ip_mcast(const u8 *addr) { return ether_addr_is_ipv4_mcast(addr) || ether_addr_is_ipv6_mcast(addr); } /** * ether_addr_to_u64 - Convert an Ethernet address into a u64 value. * @addr: Pointer to a six-byte array containing the Ethernet address * * Return a u64 value of the address */ static inline u64 ether_addr_to_u64(const u8 *addr) { u64 u = 0; int i; for (i = 0; i < ETH_ALEN; i++) u = u << 8 | addr[i]; return u; } /** * u64_to_ether_addr - Convert a u64 to an Ethernet address. * @u: u64 to convert to an Ethernet MAC address * @addr: Pointer to a six-byte array to contain the Ethernet address */ static inline void u64_to_ether_addr(u64 u, u8 *addr) { int i; for (i = ETH_ALEN - 1; i >= 0; i--) { addr[i] = u & 0xff; u = u >> 8; } } /** * eth_addr_dec - Decrement the given MAC address * * @addr: Pointer to a six-byte array containing Ethernet address to decrement */ static inline void eth_addr_dec(u8 *addr) { u64 u = ether_addr_to_u64(addr); u--; u64_to_ether_addr(u, addr); } /** * eth_addr_inc() - Increment the given MAC address. * @addr: Pointer to a six-byte array containing Ethernet address to increment. */ static inline void eth_addr_inc(u8 *addr) { u64 u = ether_addr_to_u64(addr); u++; u64_to_ether_addr(u, addr); } /** * is_etherdev_addr - Tell if given Ethernet address belongs to the device. * @dev: Pointer to a device structure * @addr: Pointer to a six-byte array containing the Ethernet address * * Compare passed address with all addresses of the device. Return true if the * address if one of the device addresses. * * Note that this function calls ether_addr_equal_64bits() so take care of * the right padding. */ static inline bool is_etherdev_addr(const struct net_device *dev, const u8 addr[6 + 2]) { struct netdev_hw_addr *ha; bool res = false; rcu_read_lock(); for_each_dev_addr(dev, ha) { res = ether_addr_equal_64bits(addr, ha->addr); if (res) break; } rcu_read_unlock(); return res; } #endif /* __KERNEL__ */ /** * compare_ether_header - Compare two Ethernet headers * @a: Pointer to Ethernet header * @b: Pointer to Ethernet header * * Compare two Ethernet headers, returns 0 if equal. * This assumes that the network header (i.e., IP header) is 4-byte * aligned OR the platform can handle unaligned access. This is the * case for all packets coming into netif_receive_skb or similar * entry points. */ static inline unsigned long compare_ether_header(const void *a, const void *b) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 unsigned long fold; /* * We want to compare 14 bytes: * [a0 ... a13] ^ [b0 ... b13] * Use two long XOR, ORed together, with an overlap of two bytes. * [a0 a1 a2 a3 a4 a5 a6 a7 ] ^ [b0 b1 b2 b3 b4 b5 b6 b7 ] | * [a6 a7 a8 a9 a10 a11 a12 a13] ^ [b6 b7 b8 b9 b10 b11 b12 b13] * This means the [a6 a7] ^ [b6 b7] part is done two times. */ fold = *(unsigned long *)a ^ *(unsigned long *)b; fold |= *(unsigned long *)(a + 6) ^ *(unsigned long *)(b + 6); return fold; #else u32 *a32 = (u32 *)((u8 *)a + 2); u32 *b32 = (u32 *)((u8 *)b + 2); return (*(u16 *)a ^ *(u16 *)b) | (a32[0] ^ b32[0]) | (a32[1] ^ b32[1]) | (a32[2] ^ b32[2]); #endif } /** * eth_hw_addr_gen - Generate and assign Ethernet address to a port * @dev: pointer to port's net_device structure * @base_addr: base Ethernet address * @id: offset to add to the base address * * Generate a MAC address using a base address and an offset and assign it * to a net_device. Commonly used by switch drivers which need to compute * addresses for all their ports. addr_assign_type is not changed. */ static inline void eth_hw_addr_gen(struct net_device *dev, const u8 *base_addr, unsigned int id) { u64 u = ether_addr_to_u64(base_addr); u8 addr[ETH_ALEN]; u += id; u64_to_ether_addr(u, addr); eth_hw_addr_set(dev, addr); } /** * eth_skb_pkt_type - Assign packet type if destination address does not match * @skb: Assigned a packet type if address does not match @dev address * @dev: Network device used to compare packet address against * * If the destination MAC address of the packet does not match the network * device address, assign an appropriate packet type. */ static inline void eth_skb_pkt_type(struct sk_buff *skb, const struct net_device *dev) { const struct ethhdr *eth = eth_hdr(skb); if (unlikely(!ether_addr_equal_64bits(eth->h_dest, dev->dev_addr))) { if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) { if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) skb->pkt_type = PACKET_BROADCAST; else skb->pkt_type = PACKET_MULTICAST; } else { skb->pkt_type = PACKET_OTHERHOST; } } } /** * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame * @skb: Buffer to pad * * An Ethernet frame should have a minimum size of 60 bytes. This function * takes short frames and pads them with zeros up to the 60 byte limit. */ static inline int eth_skb_pad(struct sk_buff *skb) { return skb_put_padto(skb, ETH_ZLEN); } #endif /* _LINUX_ETHERDEVICE_H */ |
| 270 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Queued spinlock * * A 'generic' spinlock implementation that is based on MCS locks. For an * architecture that's looking for a 'generic' spinlock, please first consider * ticket-lock.h and only come looking here when you've considered all the * constraints below and can show your hardware does actually perform better * with qspinlock. * * qspinlock relies on atomic_*_release()/atomic_*_acquire() to be RCsc (or no * weaker than RCtso if you're power), where regular code only expects atomic_t * to be RCpc. * * qspinlock relies on a far greater (compared to asm-generic/spinlock.h) set * of atomic operations to behave well together, please audit them carefully to * ensure they all have forward progress. Many atomic operations may default to * cmpxchg() loops which will not have good forward progress properties on * LL/SC architectures. * * One notable example is atomic_fetch_or_acquire(), which x86 cannot (cheaply) * do. Carefully read the patches that introduced * queued_fetch_set_pending_acquire(). * * qspinlock also heavily relies on mixed size atomic operations, in specific * it requires architectures to have xchg16; something which many LL/SC * architectures need to implement as a 32bit and+or in order to satisfy the * forward progress guarantees mentioned above. * * Further reading on mixed size atomics that might be relevant: * * http://www.cl.cam.ac.uk/~pes20/popl17/mixed-size.pdf * * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P. * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP * * Authors: Waiman Long <waiman.long@hpe.com> */ #ifndef __ASM_GENERIC_QSPINLOCK_H #define __ASM_GENERIC_QSPINLOCK_H #include <asm-generic/qspinlock_types.h> #include <linux/atomic.h> #ifndef queued_spin_is_locked /** * queued_spin_is_locked - is the spinlock locked? * @lock: Pointer to queued spinlock structure * Return: 1 if it is locked, 0 otherwise */ static __always_inline int queued_spin_is_locked(struct qspinlock *lock) { /* * Any !0 state indicates it is locked, even if _Q_LOCKED_VAL * isn't immediately observable. */ return atomic_read(&lock->val); } #endif /** * queued_spin_value_unlocked - is the spinlock structure unlocked? * @lock: queued spinlock structure * Return: 1 if it is unlocked, 0 otherwise * * N.B. Whenever there are tasks waiting for the lock, it is considered * locked wrt the lockref code to avoid lock stealing by the lockref * code and change things underneath the lock. This also allows some * optimizations to be applied without conflict with lockref. */ static __always_inline int queued_spin_value_unlocked(struct qspinlock lock) { return !lock.val.counter; } /** * queued_spin_is_contended - check if the lock is contended * @lock : Pointer to queued spinlock structure * Return: 1 if lock contended, 0 otherwise */ static __always_inline int queued_spin_is_contended(struct qspinlock *lock) { return atomic_read(&lock->val) & ~_Q_LOCKED_MASK; } /** * queued_spin_trylock - try to acquire the queued spinlock * @lock : Pointer to queued spinlock structure * Return: 1 if lock acquired, 0 if failed */ static __always_inline int queued_spin_trylock(struct qspinlock *lock) { int val = atomic_read(&lock->val); if (unlikely(val)) return 0; return likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL)); } extern void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); #ifndef queued_spin_lock /** * queued_spin_lock - acquire a queued spinlock * @lock: Pointer to queued spinlock structure */ static __always_inline void queued_spin_lock(struct qspinlock *lock) { int val = 0; if (likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL))) return; queued_spin_lock_slowpath(lock, val); } #endif #ifndef queued_spin_unlock /** * queued_spin_unlock - release a queued spinlock * @lock : Pointer to queued spinlock structure */ static __always_inline void queued_spin_unlock(struct qspinlock *lock) { /* * unlock() needs release semantics: */ smp_store_release(&lock->locked, 0); } #endif #ifndef virt_spin_lock static __always_inline bool virt_spin_lock(struct qspinlock *lock) { return false; } #endif /* * Remapping spinlock architecture specific functions to the corresponding * queued spinlock functions. */ #define arch_spin_is_locked(l) queued_spin_is_locked(l) #define arch_spin_is_contended(l) queued_spin_is_contended(l) #define arch_spin_value_unlocked(l) queued_spin_value_unlocked(l) #define arch_spin_lock(l) queued_spin_lock(l) #define arch_spin_trylock(l) queued_spin_trylock(l) #define arch_spin_unlock(l) queued_spin_unlock(l) #endif /* __ASM_GENERIC_QSPINLOCK_H */ |
| 47 47 47 1 47 47 9 47 8 16 40 40 5 7 7 43 23 44 57 37 44 66 66 48 5 2 4 64 2 48 3 20 17 37 37 1 44 44 44 44 44 19 29 28 20 4 51 3 1 29 29 19 3 3 2 3 37 11 26 9 28 32 5 37 30 6 1 16 674 37 66 40 73 46 1 2 4 1 3 38 2 39 41 38 6 1 6 1 44 3 3 3 44 674 1 673 674 674 674 674 1 673 674 674 674 674 21 653 637 637 695 695 695 695 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * GRE over IPv6 protocol decoder. * * Authors: Dmitry Kozlov (xeb@mail.ru) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/in6.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/netfilter_ipv4.h> #include <linux/etherdevice.h> #include <linux/if_ether.h> #include <linux/hash.h> #include <linux/if_tunnel.h> #include <linux/ip6_tunnel.h> #include <net/sock.h> #include <net/ip.h> #include <net/ip_tunnels.h> #include <net/icmp.h> #include <net/protocol.h> #include <net/addrconf.h> #include <net/arp.h> #include <net/checksum.h> #include <net/dsfield.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #include <net/ip6_tunnel.h> #include <net/gre.h> #include <net/erspan.h> #include <net/dst_metadata.h> static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); #define IP6_GRE_HASH_SIZE_SHIFT 5 #define IP6_GRE_HASH_SIZE (1 << IP6_GRE_HASH_SIZE_SHIFT) static unsigned int ip6gre_net_id __read_mostly; struct ip6gre_net { struct ip6_tnl __rcu *tunnels[4][IP6_GRE_HASH_SIZE]; struct ip6_tnl __rcu *collect_md_tun; struct ip6_tnl __rcu *collect_md_tun_erspan; struct net_device *fb_tunnel_dev; }; static struct rtnl_link_ops ip6gre_link_ops __read_mostly; static struct rtnl_link_ops ip6gre_tap_ops __read_mostly; static struct rtnl_link_ops ip6erspan_tap_ops __read_mostly; static int ip6gre_tunnel_init(struct net_device *dev); static void ip6gre_tunnel_setup(struct net_device *dev); static void ip6gre_tunnel_link(struct ip6gre_net *ign, struct ip6_tnl *t); static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu); static void ip6erspan_tnl_link_config(struct ip6_tnl *t, int set_mtu); /* Tunnel hash table */ /* 4 hash tables: 3: (remote,local) 2: (remote,*) 1: (*,local) 0: (*,*) We require exact key match i.e. if a key is present in packet it will match only tunnel with the same key; if it is not present, it will match only keyless tunnel. All keysless packets, if not matched configured keyless tunnels will match fallback tunnel. */ #define HASH_KEY(key) (((__force u32)key^((__force u32)key>>4))&(IP6_GRE_HASH_SIZE - 1)) static u32 HASH_ADDR(const struct in6_addr *addr) { u32 hash = ipv6_addr_hash(addr); return hash_32(hash, IP6_GRE_HASH_SIZE_SHIFT); } #define tunnels_r_l tunnels[3] #define tunnels_r tunnels[2] #define tunnels_l tunnels[1] #define tunnels_wc tunnels[0] /* Given src, dst and key, find appropriate for input tunnel. */ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, const struct in6_addr *remote, const struct in6_addr *local, __be32 key, __be16 gre_proto) { struct net *net = dev_net(dev); int link = dev->ifindex; unsigned int h0 = HASH_ADDR(remote); unsigned int h1 = HASH_KEY(key); struct ip6_tnl *t, *cand = NULL; struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); int dev_type = (gre_proto == htons(ETH_P_TEB) || gre_proto == htons(ETH_P_ERSPAN) || gre_proto == htons(ETH_P_ERSPAN2)) ? ARPHRD_ETHER : ARPHRD_IP6GRE; int score, cand_score = 4; struct net_device *ndev; for_each_ip_tunnel_rcu(t, ign->tunnels_r_l[h0 ^ h1]) { if (!ipv6_addr_equal(local, &t->parms.laddr) || !ipv6_addr_equal(remote, &t->parms.raddr) || key != t->parms.i_key || !(t->dev->flags & IFF_UP)) continue; if (t->dev->type != ARPHRD_IP6GRE && t->dev->type != dev_type) continue; score = 0; if (t->parms.link != link) score |= 1; if (t->dev->type != dev_type) score |= 2; if (score == 0) return t; if (score < cand_score) { cand = t; cand_score = score; } } for_each_ip_tunnel_rcu(t, ign->tunnels_r[h0 ^ h1]) { if (!ipv6_addr_equal(remote, &t->parms.raddr) || key != t->parms.i_key || !(t->dev->flags & IFF_UP)) continue; if (t->dev->type != ARPHRD_IP6GRE && t->dev->type != dev_type) continue; score = 0; if (t->parms.link != link) score |= 1; if (t->dev->type != dev_type) score |= 2; if (score == 0) return t; if (score < cand_score) { cand = t; cand_score = score; } } for_each_ip_tunnel_rcu(t, ign->tunnels_l[h1]) { if ((!ipv6_addr_equal(local, &t->parms.laddr) && (!ipv6_addr_equal(local, &t->parms.raddr) || !ipv6_addr_is_multicast(local))) || key != t->parms.i_key || !(t->dev->flags & IFF_UP)) continue; if (t->dev->type != ARPHRD_IP6GRE && t->dev->type != dev_type) continue; score = 0; if (t->parms.link != link) score |= 1; if (t->dev->type != dev_type) score |= 2; if (score == 0) return t; if (score < cand_score) { cand = t; cand_score = score; } } for_each_ip_tunnel_rcu(t, ign->tunnels_wc[h1]) { if (t->parms.i_key != key || !(t->dev->flags & IFF_UP)) continue; if (t->dev->type != ARPHRD_IP6GRE && t->dev->type != dev_type) continue; score = 0; if (t->parms.link != link) score |= 1; if (t->dev->type != dev_type) score |= 2; if (score == 0) return t; if (score < cand_score) { cand = t; cand_score = score; } } if (cand) return cand; if (gre_proto == htons(ETH_P_ERSPAN) || gre_proto == htons(ETH_P_ERSPAN2)) t = rcu_dereference(ign->collect_md_tun_erspan); else t = rcu_dereference(ign->collect_md_tun); if (t && t->dev->flags & IFF_UP) return t; ndev = READ_ONCE(ign->fb_tunnel_dev); if (ndev && ndev->flags & IFF_UP) return netdev_priv(ndev); return NULL; } static struct ip6_tnl __rcu **__ip6gre_bucket(struct ip6gre_net *ign, const struct __ip6_tnl_parm *p) { const struct in6_addr *remote = &p->raddr; const struct in6_addr *local = &p->laddr; unsigned int h = HASH_KEY(p->i_key); int prio = 0; if (!ipv6_addr_any(local)) prio |= 1; if (!ipv6_addr_any(remote) && !ipv6_addr_is_multicast(remote)) { prio |= 2; h ^= HASH_ADDR(remote); } return &ign->tunnels[prio][h]; } static void ip6gre_tunnel_link_md(struct ip6gre_net *ign, struct ip6_tnl *t) { if (t->parms.collect_md) rcu_assign_pointer(ign->collect_md_tun, t); } static void ip6erspan_tunnel_link_md(struct ip6gre_net *ign, struct ip6_tnl *t) { if (t->parms.collect_md) rcu_assign_pointer(ign->collect_md_tun_erspan, t); } static void ip6gre_tunnel_unlink_md(struct ip6gre_net *ign, struct ip6_tnl *t) { if (t->parms.collect_md) rcu_assign_pointer(ign->collect_md_tun, NULL); } static void ip6erspan_tunnel_unlink_md(struct ip6gre_net *ign, struct ip6_tnl *t) { if (t->parms.collect_md) rcu_assign_pointer(ign->collect_md_tun_erspan, NULL); } static inline struct ip6_tnl __rcu **ip6gre_bucket(struct ip6gre_net *ign, const struct ip6_tnl *t) { return __ip6gre_bucket(ign, &t->parms); } static void ip6gre_tunnel_link(struct ip6gre_net *ign, struct ip6_tnl *t) { struct ip6_tnl __rcu **tp = ip6gre_bucket(ign, t); rcu_assign_pointer(t->next, rtnl_dereference(*tp)); rcu_assign_pointer(*tp, t); } static void ip6gre_tunnel_unlink(struct ip6gre_net *ign, struct ip6_tnl *t) { struct ip6_tnl __rcu **tp; struct ip6_tnl *iter; for (tp = ip6gre_bucket(ign, t); (iter = rtnl_dereference(*tp)) != NULL; tp = &iter->next) { if (t == iter) { rcu_assign_pointer(*tp, t->next); break; } } } static struct ip6_tnl *ip6gre_tunnel_find(struct net *net, const struct __ip6_tnl_parm *parms, int type) { const struct in6_addr *remote = &parms->raddr; const struct in6_addr *local = &parms->laddr; __be32 key = parms->i_key; int link = parms->link; struct ip6_tnl *t; struct ip6_tnl __rcu **tp; struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); for (tp = __ip6gre_bucket(ign, parms); (t = rtnl_dereference(*tp)) != NULL; tp = &t->next) if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_equal(remote, &t->parms.raddr) && key == t->parms.i_key && link == t->parms.link && type == t->dev->type) break; return t; } static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net, const struct __ip6_tnl_parm *parms, int create) { struct ip6_tnl *t, *nt; struct net_device *dev; char name[IFNAMSIZ]; struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); t = ip6gre_tunnel_find(net, parms, ARPHRD_IP6GRE); if (t && create) return NULL; if (t || !create) return t; if (parms->name[0]) { if (!dev_valid_name(parms->name)) return NULL; strscpy(name, parms->name, IFNAMSIZ); } else { strcpy(name, "ip6gre%d"); } dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, ip6gre_tunnel_setup); if (!dev) return NULL; dev_net_set(dev, net); nt = netdev_priv(dev); nt->parms = *parms; dev->rtnl_link_ops = &ip6gre_link_ops; nt->dev = dev; nt->net = dev_net(dev); if (register_netdevice(dev) < 0) goto failed_free; ip6gre_tnl_link_config(nt, 1); ip6gre_tunnel_link(ign, nt); return nt; failed_free: free_netdev(dev); return NULL; } static void ip6erspan_tunnel_uninit(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id); ip6erspan_tunnel_unlink_md(ign, t); ip6gre_tunnel_unlink(ign, t); dst_cache_reset(&t->dst_cache); netdev_put(dev, &t->dev_tracker); } static void ip6gre_tunnel_uninit(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id); ip6gre_tunnel_unlink_md(ign, t); ip6gre_tunnel_unlink(ign, t); if (ign->fb_tunnel_dev == dev) WRITE_ONCE(ign->fb_tunnel_dev, NULL); dst_cache_reset(&t->dst_cache); netdev_put(dev, &t->dev_tracker); } static int ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct net *net = dev_net(skb->dev); const struct ipv6hdr *ipv6h; struct tnl_ptk_info tpi; struct ip6_tnl *t; if (gre_parse_header(skb, &tpi, NULL, htons(ETH_P_IPV6), offset) < 0) return -EINVAL; ipv6h = (const struct ipv6hdr *)skb->data; t = ip6gre_tunnel_lookup(skb->dev, &ipv6h->daddr, &ipv6h->saddr, tpi.key, tpi.proto); if (!t) return -ENOENT; switch (type) { case ICMPV6_DEST_UNREACH: net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n", t->parms.name); if (code != ICMPV6_PORT_UNREACH) break; return 0; case ICMPV6_TIME_EXCEED: if (code == ICMPV6_EXC_HOPLIMIT) { net_dbg_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n", t->parms.name); break; } return 0; case ICMPV6_PARAMPROB: { struct ipv6_tlv_tnl_enc_lim *tel; __u32 teli; teli = 0; if (code == ICMPV6_HDR_FIELD) teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data); if (teli && teli == be32_to_cpu(info) - 2) { tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli]; if (tel->encap_limit == 0) { net_dbg_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n", t->parms.name); } } else { net_dbg_ratelimited("%s: Recipient unable to parse tunneled packet!\n", t->parms.name); } return 0; } case ICMPV6_PKT_TOOBIG: ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL)); return 0; case NDISC_REDIRECT: ip6_redirect(skb, net, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); return 0; } if (time_before(jiffies, t->err_time + IP6TUNNEL_ERR_TIMEO)) t->err_count++; else t->err_count = 1; t->err_time = jiffies; return 0; } static int ip6gre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi) { const struct ipv6hdr *ipv6h; struct ip6_tnl *tunnel; ipv6h = ipv6_hdr(skb); tunnel = ip6gre_tunnel_lookup(skb->dev, &ipv6h->saddr, &ipv6h->daddr, tpi->key, tpi->proto); if (tunnel) { if (tunnel->parms.collect_md) { struct metadata_dst *tun_dst; __be64 tun_id; __be16 flags; flags = tpi->flags; tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ipv6_tun_rx_dst(skb, flags, tun_id, 0); if (!tun_dst) return PACKET_REJECT; ip6_tnl_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); } else { ip6_tnl_rcv(tunnel, skb, tpi, NULL, log_ecn_error); } return PACKET_RCVD; } return PACKET_REJECT; } static int ip6erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, int gre_hdr_len) { struct erspan_base_hdr *ershdr; const struct ipv6hdr *ipv6h; struct erspan_md2 *md2; struct ip6_tnl *tunnel; u8 ver; if (unlikely(!pskb_may_pull(skb, sizeof(*ershdr)))) return PACKET_REJECT; ipv6h = ipv6_hdr(skb); ershdr = (struct erspan_base_hdr *)skb->data; ver = ershdr->ver; tunnel = ip6gre_tunnel_lookup(skb->dev, &ipv6h->saddr, &ipv6h->daddr, tpi->key, tpi->proto); if (tunnel) { int len = erspan_hdr_len(ver); if (unlikely(!pskb_may_pull(skb, len))) return PACKET_REJECT; if (__iptunnel_pull_header(skb, len, htons(ETH_P_TEB), false, false) < 0) return PACKET_REJECT; if (tunnel->parms.collect_md) { struct erspan_metadata *pkt_md, *md; struct metadata_dst *tun_dst; struct ip_tunnel_info *info; unsigned char *gh; __be64 tun_id; __be16 flags; tpi->flags |= TUNNEL_KEY; flags = tpi->flags; tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ipv6_tun_rx_dst(skb, flags, tun_id, sizeof(*md)); if (!tun_dst) return PACKET_REJECT; /* skb can be uncloned in __iptunnel_pull_header, so * old pkt_md is no longer valid and we need to reset * it */ gh = skb_network_header(skb) + skb_network_header_len(skb); pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len + sizeof(*ershdr)); info = &tun_dst->u.tun_info; md = ip_tunnel_info_opts(info); md->version = ver; md2 = &md->u.md2; memcpy(md2, pkt_md, ver == 1 ? ERSPAN_V1_MDSIZE : ERSPAN_V2_MDSIZE); info->key.tun_flags |= TUNNEL_ERSPAN_OPT; info->options_len = sizeof(*md); ip6_tnl_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); } else { ip6_tnl_rcv(tunnel, skb, tpi, NULL, log_ecn_error); } return PACKET_RCVD; } return PACKET_REJECT; } static int gre_rcv(struct sk_buff *skb) { struct tnl_ptk_info tpi; bool csum_err = false; int hdr_len; hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IPV6), 0); if (hdr_len < 0) goto drop; if (iptunnel_pull_header(skb, hdr_len, tpi.proto, false)) goto drop; if (unlikely(tpi.proto == htons(ETH_P_ERSPAN) || tpi.proto == htons(ETH_P_ERSPAN2))) { if (ip6erspan_rcv(skb, &tpi, hdr_len) == PACKET_RCVD) return 0; goto out; } if (ip6gre_rcv(skb, &tpi) == PACKET_RCVD) return 0; out: icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); drop: kfree_skb(skb); return 0; } static int gre_handle_offloads(struct sk_buff *skb, bool csum) { return iptunnel_handle_offloads(skb, csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE); } static void prepare_ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev, struct flowi6 *fl6, __u8 *dsfield, int *encap_limit) { const struct iphdr *iph = ip_hdr(skb); struct ip6_tnl *t = netdev_priv(dev); if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) *encap_limit = t->parms.encap_limit; memcpy(fl6, &t->fl.u.ip6, sizeof(*fl6)); if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) *dsfield = ipv4_get_dsfield(iph); else *dsfield = ip6_tclass(t->parms.flowinfo); if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) fl6->flowi6_mark = skb->mark; else fl6->flowi6_mark = t->parms.fwmark; fl6->flowi6_uid = sock_net_uid(dev_net(dev), NULL); } static int prepare_ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev, struct flowi6 *fl6, __u8 *dsfield, int *encap_limit) { struct ipv6hdr *ipv6h; struct ip6_tnl *t = netdev_priv(dev); __u16 offset; offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb)); /* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */ ipv6h = ipv6_hdr(skb); if (offset > 0) { struct ipv6_tlv_tnl_enc_lim *tel; tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset]; if (tel->encap_limit == 0) { icmpv6_ndo_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD, offset + 2); return -1; } *encap_limit = tel->encap_limit - 1; } else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) { *encap_limit = t->parms.encap_limit; } memcpy(fl6, &t->fl.u.ip6, sizeof(*fl6)); if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) *dsfield = ipv6_get_dsfield(ipv6h); else *dsfield = ip6_tclass(t->parms.flowinfo); if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL) fl6->flowlabel |= ip6_flowlabel(ipv6h); if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) fl6->flowi6_mark = skb->mark; else fl6->flowi6_mark = t->parms.fwmark; fl6->flowi6_uid = sock_net_uid(dev_net(dev), NULL); return 0; } static int prepare_ip6gre_xmit_other(struct sk_buff *skb, struct net_device *dev, struct flowi6 *fl6, __u8 *dsfield, int *encap_limit) { struct ip6_tnl *t = netdev_priv(dev); if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) *encap_limit = t->parms.encap_limit; memcpy(fl6, &t->fl.u.ip6, sizeof(*fl6)); if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) *dsfield = 0; else *dsfield = ip6_tclass(t->parms.flowinfo); if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) fl6->flowi6_mark = skb->mark; else fl6->flowi6_mark = t->parms.fwmark; fl6->flowi6_uid = sock_net_uid(dev_net(dev), NULL); return 0; } static struct ip_tunnel_info *skb_tunnel_info_txcheck(struct sk_buff *skb) { struct ip_tunnel_info *tun_info; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX))) return ERR_PTR(-EINVAL); return tun_info; } static netdev_tx_t __gre6_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, struct flowi6 *fl6, int encap_limit, __u32 *pmtu, __be16 proto) { struct ip6_tnl *tunnel = netdev_priv(dev); __be16 protocol; __be16 flags; if (dev->type == ARPHRD_ETHER) IPCB(skb)->flags = 0; if (dev->header_ops && dev->type == ARPHRD_IP6GRE) fl6->daddr = ((struct ipv6hdr *)skb->data)->daddr; else fl6->daddr = tunnel->parms.raddr; /* Push GRE header. */ protocol = (dev->type == ARPHRD_ETHER) ? htons(ETH_P_TEB) : proto; if (tunnel->parms.collect_md) { struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; int tun_hlen; tun_info = skb_tunnel_info_txcheck(skb); if (IS_ERR(tun_info) || unlikely(ip_tunnel_info_af(tun_info) != AF_INET6)) return -EINVAL; key = &tun_info->key; memset(fl6, 0, sizeof(*fl6)); fl6->flowi6_proto = IPPROTO_GRE; fl6->daddr = key->u.ipv6.dst; fl6->flowlabel = key->label; fl6->flowi6_uid = sock_net_uid(dev_net(dev), NULL); fl6->fl6_gre_key = tunnel_id_to_key32(key->tun_id); dsfield = key->tos; flags = key->tun_flags & (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); tun_hlen = gre_calc_hlen(flags); if (skb_cow_head(skb, dev->needed_headroom ?: tun_hlen + tunnel->encap_hlen)) return -ENOMEM; gre_build_header(skb, tun_hlen, flags, protocol, tunnel_id_to_key32(tun_info->key.tun_id), (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); } else { if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen)) return -ENOMEM; flags = tunnel->parms.o_flags; gre_build_header(skb, tunnel->tun_hlen, flags, protocol, tunnel->parms.o_key, (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); } return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu, NEXTHDR_GRE); } static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); int encap_limit = -1; struct flowi6 fl6; __u8 dsfield = 0; __u32 mtu; int err; memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); if (!t->parms.collect_md) prepare_ip6gre_xmit_ipv4(skb, dev, &fl6, &dsfield, &encap_limit); err = gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM)); if (err) return -1; err = __gre6_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, skb->protocol); if (err != 0) { /* XXX: send ICMP error even if DF is not set. */ if (err == -EMSGSIZE) icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); return -1; } return 0; } static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct ipv6hdr *ipv6h = ipv6_hdr(skb); int encap_limit = -1; struct flowi6 fl6; __u8 dsfield = 0; __u32 mtu; int err; if (ipv6_addr_equal(&t->parms.raddr, &ipv6h->saddr)) return -1; if (!t->parms.collect_md && prepare_ip6gre_xmit_ipv6(skb, dev, &fl6, &dsfield, &encap_limit)) return -1; if (gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM))) return -1; err = __gre6_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, skb->protocol); if (err != 0) { if (err == -EMSGSIZE) icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); return -1; } return 0; } /** * ip6gre_tnl_addr_conflict - compare packet addresses to tunnel's own * @t: the outgoing tunnel device * @hdr: IPv6 header from the incoming packet * * Description: * Avoid trivial tunneling loop by checking that tunnel exit-point * doesn't match source of incoming packet. * * Return: * 1 if conflict, * 0 else **/ static inline bool ip6gre_tnl_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr) { return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr); } static int ip6gre_xmit_other(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); int encap_limit = -1; struct flowi6 fl6; __u8 dsfield = 0; __u32 mtu; int err; if (!t->parms.collect_md && prepare_ip6gre_xmit_other(skb, dev, &fl6, &dsfield, &encap_limit)) return -1; err = gre_handle_offloads(skb, !!(t->parms.o_flags & TUNNEL_CSUM)); if (err) return err; err = __gre6_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, skb->protocol); return err; } static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net_device_stats *stats = &t->dev->stats; __be16 payload_protocol; int ret; if (!pskb_inet_may_pull(skb)) goto tx_err; if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr)) goto tx_err; payload_protocol = skb_protocol(skb, true); switch (payload_protocol) { case htons(ETH_P_IP): ret = ip6gre_xmit_ipv4(skb, dev); break; case htons(ETH_P_IPV6): ret = ip6gre_xmit_ipv6(skb, dev); break; default: ret = ip6gre_xmit_other(skb, dev); break; } if (ret < 0) goto tx_err; return NETDEV_TX_OK; tx_err: if (!t->parms.collect_md || !IS_ERR(skb_tunnel_info_txcheck(skb))) stats->tx_errors++; stats->tx_dropped++; kfree_skb(skb); return NETDEV_TX_OK; } static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel_info *tun_info = NULL; struct ip6_tnl *t = netdev_priv(dev); struct dst_entry *dst = skb_dst(skb); struct net_device_stats *stats; bool truncate = false; int encap_limit = -1; __u8 dsfield = false; struct flowi6 fl6; int err = -EINVAL; __be16 proto; __u32 mtu; int nhoff; if (!pskb_inet_may_pull(skb)) goto tx_err; if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr)) goto tx_err; if (gre_handle_offloads(skb, false)) goto tx_err; if (skb->len > dev->mtu + dev->hard_header_len) { if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) goto tx_err; truncate = true; } nhoff = skb_network_offset(skb); if (skb->protocol == htons(ETH_P_IP) && (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff)) truncate = true; if (skb->protocol == htons(ETH_P_IPV6)) { int thoff; if (skb_transport_header_was_set(skb)) thoff = skb_transport_offset(skb); else thoff = nhoff + sizeof(struct ipv6hdr); if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff) truncate = true; } if (skb_cow_head(skb, dev->needed_headroom ?: t->hlen)) goto tx_err; t->parms.o_flags &= ~TUNNEL_KEY; IPCB(skb)->flags = 0; /* For collect_md mode, derive fl6 from the tunnel key, * for native mode, call prepare_ip6gre_xmit_{ipv4,ipv6}. */ if (t->parms.collect_md) { const struct ip_tunnel_key *key; struct erspan_metadata *md; __be32 tun_id; tun_info = skb_tunnel_info_txcheck(skb); if (IS_ERR(tun_info) || unlikely(ip_tunnel_info_af(tun_info) != AF_INET6)) goto tx_err; key = &tun_info->key; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_GRE; fl6.daddr = key->u.ipv6.dst; fl6.flowlabel = key->label; fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL); fl6.fl6_gre_key = tunnel_id_to_key32(key->tun_id); dsfield = key->tos; if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) goto tx_err; if (tun_info->options_len < sizeof(*md)) goto tx_err; md = ip_tunnel_info_opts(tun_info); tun_id = tunnel_id_to_key32(key->tun_id); if (md->version == 1) { erspan_build_header(skb, ntohl(tun_id), ntohl(md->u.index), truncate, false); proto = htons(ETH_P_ERSPAN); } else if (md->version == 2) { erspan_build_header_v2(skb, ntohl(tun_id), md->u.md2.dir, get_hwid(&md->u.md2), truncate, false); proto = htons(ETH_P_ERSPAN2); } else { goto tx_err; } } else { switch (skb->protocol) { case htons(ETH_P_IP): memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); prepare_ip6gre_xmit_ipv4(skb, dev, &fl6, &dsfield, &encap_limit); break; case htons(ETH_P_IPV6): if (ipv6_addr_equal(&t->parms.raddr, &ipv6_hdr(skb)->saddr)) goto tx_err; if (prepare_ip6gre_xmit_ipv6(skb, dev, &fl6, &dsfield, &encap_limit)) goto tx_err; break; default: memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); break; } if (t->parms.erspan_ver == 1) { erspan_build_header(skb, ntohl(t->parms.o_key), t->parms.index, truncate, false); proto = htons(ETH_P_ERSPAN); } else if (t->parms.erspan_ver == 2) { erspan_build_header_v2(skb, ntohl(t->parms.o_key), t->parms.dir, t->parms.hwid, truncate, false); proto = htons(ETH_P_ERSPAN2); } else { goto tx_err; } fl6.daddr = t->parms.raddr; } /* Push GRE header. */ gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(atomic_fetch_inc(&t->o_seqno))); /* TooBig packet may have updated dst->dev's mtu */ if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu) dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu, false); err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, NEXTHDR_GRE); if (err != 0) { /* XXX: send ICMP error even if DF is not set. */ if (err == -EMSGSIZE) { if (skb->protocol == htons(ETH_P_IP)) icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); else icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); } goto tx_err; } return NETDEV_TX_OK; tx_err: stats = &t->dev->stats; if (!IS_ERR(tun_info)) stats->tx_errors++; stats->tx_dropped++; kfree_skb(skb); return NETDEV_TX_OK; } static void ip6gre_tnl_link_config_common(struct ip6_tnl *t) { struct net_device *dev = t->dev; struct __ip6_tnl_parm *p = &t->parms; struct flowi6 *fl6 = &t->fl.u.ip6; if (dev->type != ARPHRD_ETHER) { __dev_addr_set(dev, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); } /* Set up flowi template */ fl6->saddr = p->laddr; fl6->daddr = p->raddr; fl6->flowi6_oif = p->link; fl6->flowlabel = 0; fl6->flowi6_proto = IPPROTO_GRE; fl6->fl6_gre_key = t->parms.o_key; if (!(p->flags&IP6_TNL_F_USE_ORIG_TCLASS)) fl6->flowlabel |= IPV6_TCLASS_MASK & p->flowinfo; if (!(p->flags&IP6_TNL_F_USE_ORIG_FLOWLABEL)) fl6->flowlabel |= IPV6_FLOWLABEL_MASK & p->flowinfo; p->flags &= ~(IP6_TNL_F_CAP_XMIT|IP6_TNL_F_CAP_RCV|IP6_TNL_F_CAP_PER_PACKET); p->flags |= ip6_tnl_get_cap(t, &p->laddr, &p->raddr); if (p->flags&IP6_TNL_F_CAP_XMIT && p->flags&IP6_TNL_F_CAP_RCV && dev->type != ARPHRD_ETHER) dev->flags |= IFF_POINTOPOINT; else dev->flags &= ~IFF_POINTOPOINT; } static void ip6gre_tnl_link_config_route(struct ip6_tnl *t, int set_mtu, int t_hlen) { const struct __ip6_tnl_parm *p = &t->parms; struct net_device *dev = t->dev; if (p->flags & IP6_TNL_F_CAP_XMIT) { int strict = (ipv6_addr_type(&p->raddr) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL)); struct rt6_info *rt = rt6_lookup(t->net, &p->raddr, &p->laddr, p->link, NULL, strict); if (!rt) return; if (rt->dst.dev) { unsigned short dst_len = rt->dst.dev->hard_header_len + t_hlen; if (t->dev->header_ops) dev->hard_header_len = dst_len; else dev->needed_headroom = dst_len; if (set_mtu) { int mtu = rt->dst.dev->mtu - t_hlen; if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) mtu -= 8; if (dev->type == ARPHRD_ETHER) mtu -= ETH_HLEN; if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; WRITE_ONCE(dev->mtu, mtu); } } ip6_rt_put(rt); } } static int ip6gre_calc_hlen(struct ip6_tnl *tunnel) { int t_hlen; tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; t_hlen = tunnel->hlen + sizeof(struct ipv6hdr); if (tunnel->dev->header_ops) tunnel->dev->hard_header_len = LL_MAX_HEADER + t_hlen; else tunnel->dev->needed_headroom = LL_MAX_HEADER + t_hlen; return t_hlen; } static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) { ip6gre_tnl_link_config_common(t); ip6gre_tnl_link_config_route(t, set_mtu, ip6gre_calc_hlen(t)); } static void ip6gre_tnl_copy_tnl_parm(struct ip6_tnl *t, const struct __ip6_tnl_parm *p) { t->parms.laddr = p->laddr; t->parms.raddr = p->raddr; t->parms.flags = p->flags; t->parms.hop_limit = p->hop_limit; t->parms.encap_limit = p->encap_limit; t->parms.flowinfo = p->flowinfo; t->parms.link = p->link; t->parms.proto = p->proto; t->parms.i_key = p->i_key; t->parms.o_key = p->o_key; t->parms.i_flags = p->i_flags; t->parms.o_flags = p->o_flags; t->parms.fwmark = p->fwmark; t->parms.erspan_ver = p->erspan_ver; t->parms.index = p->index; t->parms.dir = p->dir; t->parms.hwid = p->hwid; dst_cache_reset(&t->dst_cache); } static int ip6gre_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p, int set_mtu) { ip6gre_tnl_copy_tnl_parm(t, p); ip6gre_tnl_link_config(t, set_mtu); return 0; } static void ip6gre_tnl_parm_from_user(struct __ip6_tnl_parm *p, const struct ip6_tnl_parm2 *u) { p->laddr = u->laddr; p->raddr = u->raddr; p->flags = u->flags; p->hop_limit = u->hop_limit; p->encap_limit = u->encap_limit; p->flowinfo = u->flowinfo; p->link = u->link; p->i_key = u->i_key; p->o_key = u->o_key; p->i_flags = gre_flags_to_tnl_flags(u->i_flags); p->o_flags = gre_flags_to_tnl_flags(u->o_flags); memcpy(p->name, u->name, sizeof(u->name)); } static void ip6gre_tnl_parm_to_user(struct ip6_tnl_parm2 *u, const struct __ip6_tnl_parm *p) { u->proto = IPPROTO_GRE; u->laddr = p->laddr; u->raddr = p->raddr; u->flags = p->flags; u->hop_limit = p->hop_limit; u->encap_limit = p->encap_limit; u->flowinfo = p->flowinfo; u->link = p->link; u->i_key = p->i_key; u->o_key = p->o_key; u->i_flags = gre_tnl_flags_to_gre_flags(p->i_flags); u->o_flags = gre_tnl_flags_to_gre_flags(p->o_flags); memcpy(u->name, p->name, sizeof(u->name)); } static int ip6gre_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd) { int err = 0; struct ip6_tnl_parm2 p; struct __ip6_tnl_parm p1; struct ip6_tnl *t = netdev_priv(dev); struct net *net = t->net; struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); memset(&p1, 0, sizeof(p1)); switch (cmd) { case SIOCGETTUNNEL: if (dev == ign->fb_tunnel_dev) { if (copy_from_user(&p, data, sizeof(p))) { err = -EFAULT; break; } ip6gre_tnl_parm_from_user(&p1, &p); t = ip6gre_tunnel_locate(net, &p1, 0); if (!t) t = netdev_priv(dev); } memset(&p, 0, sizeof(p)); ip6gre_tnl_parm_to_user(&p, &t->parms); if (copy_to_user(data, &p, sizeof(p))) err = -EFAULT; break; case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; err = -EFAULT; if (copy_from_user(&p, data, sizeof(p))) goto done; err = -EINVAL; if ((p.i_flags|p.o_flags)&(GRE_VERSION|GRE_ROUTING)) goto done; if (!(p.i_flags&GRE_KEY)) p.i_key = 0; if (!(p.o_flags&GRE_KEY)) p.o_key = 0; ip6gre_tnl_parm_from_user(&p1, &p); t = ip6gre_tunnel_locate(net, &p1, cmd == SIOCADDTUNNEL); if (dev != ign->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) { if (t) { if (t->dev != dev) { err = -EEXIST; break; } } else { t = netdev_priv(dev); ip6gre_tunnel_unlink(ign, t); synchronize_net(); ip6gre_tnl_change(t, &p1, 1); ip6gre_tunnel_link(ign, t); netdev_state_change(dev); } } if (t) { err = 0; memset(&p, 0, sizeof(p)); ip6gre_tnl_parm_to_user(&p, &t->parms); if (copy_to_user(data, &p, sizeof(p))) err = -EFAULT; } else err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT); break; case SIOCDELTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto done; if (dev == ign->fb_tunnel_dev) { err = -EFAULT; if (copy_from_user(&p, data, sizeof(p))) goto done; err = -ENOENT; ip6gre_tnl_parm_from_user(&p1, &p); t = ip6gre_tunnel_locate(net, &p1, 0); if (!t) goto done; err = -EPERM; if (t == netdev_priv(ign->fb_tunnel_dev)) goto done; dev = t->dev; } unregister_netdevice(dev); err = 0; break; default: err = -EINVAL; } done: return err; } static int ip6gre_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { struct ip6_tnl *t = netdev_priv(dev); struct ipv6hdr *ipv6h; __be16 *p; ipv6h = skb_push(skb, t->hlen + sizeof(*ipv6h)); ip6_flow_hdr(ipv6h, 0, ip6_make_flowlabel(dev_net(dev), skb, t->fl.u.ip6.flowlabel, true, &t->fl.u.ip6)); ipv6h->hop_limit = t->parms.hop_limit; ipv6h->nexthdr = NEXTHDR_GRE; ipv6h->saddr = t->parms.laddr; ipv6h->daddr = t->parms.raddr; p = (__be16 *)(ipv6h + 1); p[0] = t->parms.o_flags; p[1] = htons(type); /* * Set the source hardware address. */ if (saddr) memcpy(&ipv6h->saddr, saddr, sizeof(struct in6_addr)); if (daddr) memcpy(&ipv6h->daddr, daddr, sizeof(struct in6_addr)); if (!ipv6_addr_any(&ipv6h->daddr)) return t->hlen; return -t->hlen; } static const struct header_ops ip6gre_header_ops = { .create = ip6gre_header, }; static const struct net_device_ops ip6gre_netdev_ops = { .ndo_init = ip6gre_tunnel_init, .ndo_uninit = ip6gre_tunnel_uninit, .ndo_start_xmit = ip6gre_tunnel_xmit, .ndo_siocdevprivate = ip6gre_tunnel_siocdevprivate, .ndo_change_mtu = ip6_tnl_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip6_tnl_get_iflink, }; static void ip6gre_dev_free(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); gro_cells_destroy(&t->gro_cells); dst_cache_destroy(&t->dst_cache); free_percpu(dev->tstats); } static void ip6gre_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ip6gre_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = ip6gre_dev_free; dev->type = ARPHRD_IP6GRE; dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); netif_keep_dst(dev); /* This perm addr will be used as interface identifier by IPv6 */ dev->addr_assign_type = NET_ADDR_RANDOM; eth_random_addr(dev->perm_addr); } #define GRE6_FEATURES (NETIF_F_SG | \ NETIF_F_FRAGLIST | \ NETIF_F_HIGHDMA | \ NETIF_F_HW_CSUM) static void ip6gre_tnl_init_features(struct net_device *dev) { struct ip6_tnl *nt = netdev_priv(dev); __be16 flags; dev->features |= GRE6_FEATURES | NETIF_F_LLTX; dev->hw_features |= GRE6_FEATURES; flags = nt->parms.o_flags; /* TCP offload with GRE SEQ is not supported, nor can we support 2 * levels of outer headers requiring an update. */ if (flags & TUNNEL_SEQ) return; if (flags & TUNNEL_CSUM && nt->encap.type != TUNNEL_ENCAP_NONE) return; dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_GSO_SOFTWARE; } static int ip6gre_tunnel_init_common(struct net_device *dev) { struct ip6_tnl *tunnel; int ret; int t_hlen; tunnel = netdev_priv(dev); tunnel->dev = dev; tunnel->net = dev_net(dev); strcpy(tunnel->parms.name, dev->name); dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; ret = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); if (ret) goto cleanup_alloc_pcpu_stats; ret = gro_cells_init(&tunnel->gro_cells, dev); if (ret) goto cleanup_dst_cache_init; t_hlen = ip6gre_calc_hlen(tunnel); dev->mtu = ETH_DATA_LEN - t_hlen; if (dev->type == ARPHRD_ETHER) dev->mtu -= ETH_HLEN; if (!(tunnel->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) dev->mtu -= 8; if (tunnel->parms.collect_md) { netif_keep_dst(dev); } ip6gre_tnl_init_features(dev); netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL); return 0; cleanup_dst_cache_init: dst_cache_destroy(&tunnel->dst_cache); cleanup_alloc_pcpu_stats: free_percpu(dev->tstats); dev->tstats = NULL; return ret; } static int ip6gre_tunnel_init(struct net_device *dev) { struct ip6_tnl *tunnel; int ret; ret = ip6gre_tunnel_init_common(dev); if (ret) return ret; tunnel = netdev_priv(dev); if (tunnel->parms.collect_md) return 0; __dev_addr_set(dev, &tunnel->parms.laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &tunnel->parms.raddr, sizeof(struct in6_addr)); if (ipv6_addr_any(&tunnel->parms.raddr)) dev->header_ops = &ip6gre_header_ops; return 0; } static void ip6gre_fb_tunnel_init(struct net_device *dev) { struct ip6_tnl *tunnel = netdev_priv(dev); tunnel->dev = dev; tunnel->net = dev_net(dev); strcpy(tunnel->parms.name, dev->name); tunnel->hlen = sizeof(struct ipv6hdr) + 4; } static struct inet6_protocol ip6gre_protocol __read_mostly = { .handler = gre_rcv, .err_handler = ip6gre_err, .flags = INET6_PROTO_FINAL, }; static void ip6gre_destroy_tunnels(struct net *net, struct list_head *head) { struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); struct net_device *dev, *aux; int prio; for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == &ip6gre_link_ops || dev->rtnl_link_ops == &ip6gre_tap_ops || dev->rtnl_link_ops == &ip6erspan_tap_ops) unregister_netdevice_queue(dev, head); for (prio = 0; prio < 4; prio++) { int h; for (h = 0; h < IP6_GRE_HASH_SIZE; h++) { struct ip6_tnl *t; t = rtnl_dereference(ign->tunnels[prio][h]); while (t) { /* If dev is in the same netns, it has already * been added to the list by the previous loop. */ if (!net_eq(dev_net(t->dev), net)) unregister_netdevice_queue(t->dev, head); t = rtnl_dereference(t->next); } } } } static int __net_init ip6gre_init_net(struct net *net) { struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); struct net_device *ndev; int err; if (!net_has_fallback_tunnels(net)) return 0; ndev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0", NET_NAME_UNKNOWN, ip6gre_tunnel_setup); if (!ndev) { err = -ENOMEM; goto err_alloc_dev; } ign->fb_tunnel_dev = ndev; dev_net_set(ign->fb_tunnel_dev, net); /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ ign->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; ip6gre_fb_tunnel_init(ign->fb_tunnel_dev); ign->fb_tunnel_dev->rtnl_link_ops = &ip6gre_link_ops; err = register_netdev(ign->fb_tunnel_dev); if (err) goto err_reg_dev; rcu_assign_pointer(ign->tunnels_wc[0], netdev_priv(ign->fb_tunnel_dev)); return 0; err_reg_dev: free_netdev(ndev); err_alloc_dev: return err; } static void __net_exit ip6gre_exit_batch_net(struct list_head *net_list) { struct net *net; LIST_HEAD(list); rtnl_lock(); list_for_each_entry(net, net_list, exit_list) ip6gre_destroy_tunnels(net, &list); unregister_netdevice_many(&list); rtnl_unlock(); } static struct pernet_operations ip6gre_net_ops = { .init = ip6gre_init_net, .exit_batch = ip6gre_exit_batch_net, .id = &ip6gre_net_id, .size = sizeof(struct ip6gre_net), }; static int ip6gre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { __be16 flags; if (!data) return 0; flags = 0; if (data[IFLA_GRE_IFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_IFLAGS]); if (data[IFLA_GRE_OFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_OFLAGS]); if (flags & (GRE_VERSION|GRE_ROUTING)) return -EINVAL; return 0; } static int ip6gre_tap_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct in6_addr daddr; if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } if (!data) goto out; if (data[IFLA_GRE_REMOTE]) { daddr = nla_get_in6_addr(data[IFLA_GRE_REMOTE]); if (ipv6_addr_any(&daddr)) return -EINVAL; } out: return ip6gre_tunnel_validate(tb, data, extack); } static int ip6erspan_tap_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { __be16 flags = 0; int ret, ver = 0; if (!data) return 0; ret = ip6gre_tap_validate(tb, data, extack); if (ret) return ret; /* ERSPAN should only have GRE sequence and key flag */ if (data[IFLA_GRE_OFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_OFLAGS]); if (data[IFLA_GRE_IFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_IFLAGS]); if (!data[IFLA_GRE_COLLECT_METADATA] && flags != (GRE_SEQ | GRE_KEY)) return -EINVAL; /* ERSPAN Session ID only has 10-bit. Since we reuse * 32-bit key field as ID, check it's range. */ if (data[IFLA_GRE_IKEY] && (ntohl(nla_get_be32(data[IFLA_GRE_IKEY])) & ~ID_MASK)) return -EINVAL; if (data[IFLA_GRE_OKEY] && (ntohl(nla_get_be32(data[IFLA_GRE_OKEY])) & ~ID_MASK)) return -EINVAL; if (data[IFLA_GRE_ERSPAN_VER]) { ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); if (ver != 1 && ver != 2) return -EINVAL; } if (ver == 1) { if (data[IFLA_GRE_ERSPAN_INDEX]) { u32 index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]); if (index & ~INDEX_MASK) return -EINVAL; } } else if (ver == 2) { if (data[IFLA_GRE_ERSPAN_DIR]) { u16 dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]); if (dir & ~(DIR_MASK >> DIR_OFFSET)) return -EINVAL; } if (data[IFLA_GRE_ERSPAN_HWID]) { u16 hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]); if (hwid & ~(HWID_MASK >> HWID_OFFSET)) return -EINVAL; } } return 0; } static void ip6erspan_set_version(struct nlattr *data[], struct __ip6_tnl_parm *parms) { if (!data) return; parms->erspan_ver = 1; if (data[IFLA_GRE_ERSPAN_VER]) parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); if (parms->erspan_ver == 1) { if (data[IFLA_GRE_ERSPAN_INDEX]) parms->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]); } else if (parms->erspan_ver == 2) { if (data[IFLA_GRE_ERSPAN_DIR]) parms->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]); if (data[IFLA_GRE_ERSPAN_HWID]) parms->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]); } } static void ip6gre_netlink_parms(struct nlattr *data[], struct __ip6_tnl_parm *parms) { memset(parms, 0, sizeof(*parms)); if (!data) return; if (data[IFLA_GRE_LINK]) parms->link = nla_get_u32(data[IFLA_GRE_LINK]); if (data[IFLA_GRE_IFLAGS]) parms->i_flags = gre_flags_to_tnl_flags( nla_get_be16(data[IFLA_GRE_IFLAGS])); if (data[IFLA_GRE_OFLAGS]) parms->o_flags = gre_flags_to_tnl_flags( nla_get_be16(data[IFLA_GRE_OFLAGS])); if (data[IFLA_GRE_IKEY]) parms->i_key = nla_get_be32(data[IFLA_GRE_IKEY]); if (data[IFLA_GRE_OKEY]) parms->o_key = nla_get_be32(data[IFLA_GRE_OKEY]); if (data[IFLA_GRE_LOCAL]) parms->laddr = nla_get_in6_addr(data[IFLA_GRE_LOCAL]); if (data[IFLA_GRE_REMOTE]) parms->raddr = nla_get_in6_addr(data[IFLA_GRE_REMOTE]); if (data[IFLA_GRE_TTL]) parms->hop_limit = nla_get_u8(data[IFLA_GRE_TTL]); if (data[IFLA_GRE_ENCAP_LIMIT]) parms->encap_limit = nla_get_u8(data[IFLA_GRE_ENCAP_LIMIT]); if (data[IFLA_GRE_FLOWINFO]) parms->flowinfo = nla_get_be32(data[IFLA_GRE_FLOWINFO]); if (data[IFLA_GRE_FLAGS]) parms->flags = nla_get_u32(data[IFLA_GRE_FLAGS]); if (data[IFLA_GRE_FWMARK]) parms->fwmark = nla_get_u32(data[IFLA_GRE_FWMARK]); if (data[IFLA_GRE_COLLECT_METADATA]) parms->collect_md = true; } static int ip6gre_tap_init(struct net_device *dev) { int ret; ret = ip6gre_tunnel_init_common(dev); if (ret) return ret; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; return 0; } static const struct net_device_ops ip6gre_tap_netdev_ops = { .ndo_init = ip6gre_tap_init, .ndo_uninit = ip6gre_tunnel_uninit, .ndo_start_xmit = ip6gre_tunnel_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ip6_tnl_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip6_tnl_get_iflink, }; static int ip6erspan_calc_hlen(struct ip6_tnl *tunnel) { int t_hlen; tunnel->tun_hlen = 8; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen + erspan_hdr_len(tunnel->parms.erspan_ver); t_hlen = tunnel->hlen + sizeof(struct ipv6hdr); tunnel->dev->needed_headroom = LL_MAX_HEADER + t_hlen; return t_hlen; } static int ip6erspan_tap_init(struct net_device *dev) { struct ip6_tnl *tunnel; int t_hlen; int ret; tunnel = netdev_priv(dev); tunnel->dev = dev; tunnel->net = dev_net(dev); strcpy(tunnel->parms.name, dev->name); dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; ret = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); if (ret) goto cleanup_alloc_pcpu_stats; ret = gro_cells_init(&tunnel->gro_cells, dev); if (ret) goto cleanup_dst_cache_init; t_hlen = ip6erspan_calc_hlen(tunnel); dev->mtu = ETH_DATA_LEN - t_hlen; if (dev->type == ARPHRD_ETHER) dev->mtu -= ETH_HLEN; if (!(tunnel->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) dev->mtu -= 8; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip6erspan_tnl_link_config(tunnel, 1); netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL); return 0; cleanup_dst_cache_init: dst_cache_destroy(&tunnel->dst_cache); cleanup_alloc_pcpu_stats: free_percpu(dev->tstats); dev->tstats = NULL; return ret; } static const struct net_device_ops ip6erspan_netdev_ops = { .ndo_init = ip6erspan_tap_init, .ndo_uninit = ip6erspan_tunnel_uninit, .ndo_start_xmit = ip6erspan_tunnel_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ip6_tnl_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip6_tnl_get_iflink, }; static void ip6gre_tap_setup(struct net_device *dev) { ether_setup(dev); dev->max_mtu = 0; dev->netdev_ops = &ip6gre_tap_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = ip6gre_dev_free; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); } static bool ip6gre_netlink_encap_parms(struct nlattr *data[], struct ip_tunnel_encap *ipencap) { bool ret = false; memset(ipencap, 0, sizeof(*ipencap)); if (!data) return ret; if (data[IFLA_GRE_ENCAP_TYPE]) { ret = true; ipencap->type = nla_get_u16(data[IFLA_GRE_ENCAP_TYPE]); } if (data[IFLA_GRE_ENCAP_FLAGS]) { ret = true; ipencap->flags = nla_get_u16(data[IFLA_GRE_ENCAP_FLAGS]); } if (data[IFLA_GRE_ENCAP_SPORT]) { ret = true; ipencap->sport = nla_get_be16(data[IFLA_GRE_ENCAP_SPORT]); } if (data[IFLA_GRE_ENCAP_DPORT]) { ret = true; ipencap->dport = nla_get_be16(data[IFLA_GRE_ENCAP_DPORT]); } return ret; } static int ip6gre_newlink_common(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip6_tnl *nt; struct ip_tunnel_encap ipencap; int err; nt = netdev_priv(dev); if (ip6gre_netlink_encap_parms(data, &ipencap)) { int err = ip6_tnl_encap_setup(nt, &ipencap); if (err < 0) return err; } if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS]) eth_hw_addr_random(dev); nt->dev = dev; nt->net = dev_net(dev); err = register_netdevice(dev); if (err) goto out; if (tb[IFLA_MTU]) ip6_tnl_change_mtu(dev, nla_get_u32(tb[IFLA_MTU])); out: return err; } static int ip6gre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip6_tnl *nt = netdev_priv(dev); struct net *net = dev_net(dev); struct ip6gre_net *ign; int err; ip6gre_netlink_parms(data, &nt->parms); ign = net_generic(net, ip6gre_net_id); if (nt->parms.collect_md) { if (rtnl_dereference(ign->collect_md_tun)) return -EEXIST; } else { if (ip6gre_tunnel_find(net, &nt->parms, dev->type)) return -EEXIST; } err = ip6gre_newlink_common(src_net, dev, tb, data, extack); if (!err) { ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]); ip6gre_tunnel_link_md(ign, nt); ip6gre_tunnel_link(net_generic(net, ip6gre_net_id), nt); } return err; } static struct ip6_tnl * ip6gre_changelink_common(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct __ip6_tnl_parm *p_p, struct netlink_ext_ack *extack) { struct ip6_tnl *t, *nt = netdev_priv(dev); struct net *net = nt->net; struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); struct ip_tunnel_encap ipencap; if (dev == ign->fb_tunnel_dev) return ERR_PTR(-EINVAL); if (ip6gre_netlink_encap_parms(data, &ipencap)) { int err = ip6_tnl_encap_setup(nt, &ipencap); if (err < 0) return ERR_PTR(err); } ip6gre_netlink_parms(data, p_p); t = ip6gre_tunnel_locate(net, p_p, 0); if (t) { if (t->dev != dev) return ERR_PTR(-EEXIST); } else { t = nt; } return t; } static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip6_tnl *t = netdev_priv(dev); struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id); struct __ip6_tnl_parm p; t = ip6gre_changelink_common(dev, tb, data, &p, extack); if (IS_ERR(t)) return PTR_ERR(t); ip6gre_tunnel_unlink_md(ign, t); ip6gre_tunnel_unlink(ign, t); ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]); ip6gre_tunnel_link_md(ign, t); ip6gre_tunnel_link(ign, t); return 0; } static void ip6gre_dellink(struct net_device *dev, struct list_head *head) { struct net *net = dev_net(dev); struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); if (dev != ign->fb_tunnel_dev) unregister_netdevice_queue(dev, head); } static size_t ip6gre_get_size(const struct net_device *dev) { return /* IFLA_GRE_LINK */ nla_total_size(4) + /* IFLA_GRE_IFLAGS */ nla_total_size(2) + /* IFLA_GRE_OFLAGS */ nla_total_size(2) + /* IFLA_GRE_IKEY */ nla_total_size(4) + /* IFLA_GRE_OKEY */ nla_total_size(4) + /* IFLA_GRE_LOCAL */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GRE_REMOTE */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GRE_TTL */ nla_total_size(1) + /* IFLA_GRE_ENCAP_LIMIT */ nla_total_size(1) + /* IFLA_GRE_FLOWINFO */ nla_total_size(4) + /* IFLA_GRE_FLAGS */ nla_total_size(4) + /* IFLA_GRE_ENCAP_TYPE */ nla_total_size(2) + /* IFLA_GRE_ENCAP_FLAGS */ nla_total_size(2) + /* IFLA_GRE_ENCAP_SPORT */ nla_total_size(2) + /* IFLA_GRE_ENCAP_DPORT */ nla_total_size(2) + /* IFLA_GRE_COLLECT_METADATA */ nla_total_size(0) + /* IFLA_GRE_FWMARK */ nla_total_size(4) + /* IFLA_GRE_ERSPAN_INDEX */ nla_total_size(4) + 0; } static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct __ip6_tnl_parm *p = &t->parms; __be16 o_flags = p->o_flags; if (p->erspan_ver == 1 || p->erspan_ver == 2) { if (!p->collect_md) o_flags |= TUNNEL_KEY; if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, p->erspan_ver)) goto nla_put_failure; if (p->erspan_ver == 1) { if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index)) goto nla_put_failure; } else { if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, p->dir)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, p->hwid)) goto nla_put_failure; } } if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, gre_tnl_flags_to_gre_flags(p->i_flags)) || nla_put_be16(skb, IFLA_GRE_OFLAGS, gre_tnl_flags_to_gre_flags(o_flags)) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || nla_put_in6_addr(skb, IFLA_GRE_LOCAL, &p->laddr) || nla_put_in6_addr(skb, IFLA_GRE_REMOTE, &p->raddr) || nla_put_u8(skb, IFLA_GRE_TTL, p->hop_limit) || nla_put_u8(skb, IFLA_GRE_ENCAP_LIMIT, p->encap_limit) || nla_put_be32(skb, IFLA_GRE_FLOWINFO, p->flowinfo) || nla_put_u32(skb, IFLA_GRE_FLAGS, p->flags) || nla_put_u32(skb, IFLA_GRE_FWMARK, p->fwmark)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_GRE_ENCAP_TYPE, t->encap.type) || nla_put_be16(skb, IFLA_GRE_ENCAP_SPORT, t->encap.sport) || nla_put_be16(skb, IFLA_GRE_ENCAP_DPORT, t->encap.dport) || nla_put_u16(skb, IFLA_GRE_ENCAP_FLAGS, t->encap.flags)) goto nla_put_failure; if (p->collect_md) { if (nla_put_flag(skb, IFLA_GRE_COLLECT_METADATA)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static const struct nla_policy ip6gre_policy[IFLA_GRE_MAX + 1] = { [IFLA_GRE_LINK] = { .type = NLA_U32 }, [IFLA_GRE_IFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_OFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_IKEY] = { .type = NLA_U32 }, [IFLA_GRE_OKEY] = { .type = NLA_U32 }, [IFLA_GRE_LOCAL] = { .len = sizeof_field(struct ipv6hdr, saddr) }, [IFLA_GRE_REMOTE] = { .len = sizeof_field(struct ipv6hdr, daddr) }, [IFLA_GRE_TTL] = { .type = NLA_U8 }, [IFLA_GRE_ENCAP_LIMIT] = { .type = NLA_U8 }, [IFLA_GRE_FLOWINFO] = { .type = NLA_U32 }, [IFLA_GRE_FLAGS] = { .type = NLA_U32 }, [IFLA_GRE_ENCAP_TYPE] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_FLAGS] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_SPORT] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_DPORT] = { .type = NLA_U16 }, [IFLA_GRE_COLLECT_METADATA] = { .type = NLA_FLAG }, [IFLA_GRE_FWMARK] = { .type = NLA_U32 }, [IFLA_GRE_ERSPAN_INDEX] = { .type = NLA_U32 }, [IFLA_GRE_ERSPAN_VER] = { .type = NLA_U8 }, [IFLA_GRE_ERSPAN_DIR] = { .type = NLA_U8 }, [IFLA_GRE_ERSPAN_HWID] = { .type = NLA_U16 }, }; static void ip6erspan_tap_setup(struct net_device *dev) { ether_setup(dev); dev->max_mtu = 0; dev->netdev_ops = &ip6erspan_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = ip6gre_dev_free; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); } static int ip6erspan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip6_tnl *nt = netdev_priv(dev); struct net *net = dev_net(dev); struct ip6gre_net *ign; int err; ip6gre_netlink_parms(data, &nt->parms); ip6erspan_set_version(data, &nt->parms); ign = net_generic(net, ip6gre_net_id); if (nt->parms.collect_md) { if (rtnl_dereference(ign->collect_md_tun_erspan)) return -EEXIST; } else { if (ip6gre_tunnel_find(net, &nt->parms, dev->type)) return -EEXIST; } err = ip6gre_newlink_common(src_net, dev, tb, data, extack); if (!err) { ip6erspan_tnl_link_config(nt, !tb[IFLA_MTU]); ip6erspan_tunnel_link_md(ign, nt); ip6gre_tunnel_link(net_generic(net, ip6gre_net_id), nt); } return err; } static void ip6erspan_tnl_link_config(struct ip6_tnl *t, int set_mtu) { ip6gre_tnl_link_config_common(t); ip6gre_tnl_link_config_route(t, set_mtu, ip6erspan_calc_hlen(t)); } static int ip6erspan_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p, int set_mtu) { ip6gre_tnl_copy_tnl_parm(t, p); ip6erspan_tnl_link_config(t, set_mtu); return 0; } static int ip6erspan_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip6gre_net *ign = net_generic(dev_net(dev), ip6gre_net_id); struct __ip6_tnl_parm p; struct ip6_tnl *t; t = ip6gre_changelink_common(dev, tb, data, &p, extack); if (IS_ERR(t)) return PTR_ERR(t); ip6erspan_set_version(data, &p); ip6gre_tunnel_unlink_md(ign, t); ip6gre_tunnel_unlink(ign, t); ip6erspan_tnl_change(t, &p, !tb[IFLA_MTU]); ip6erspan_tunnel_link_md(ign, t); ip6gre_tunnel_link(ign, t); return 0; } static struct rtnl_link_ops ip6gre_link_ops __read_mostly = { .kind = "ip6gre", .maxtype = IFLA_GRE_MAX, .policy = ip6gre_policy, .priv_size = sizeof(struct ip6_tnl), .setup = ip6gre_tunnel_setup, .validate = ip6gre_tunnel_validate, .newlink = ip6gre_newlink, .changelink = ip6gre_changelink, .dellink = ip6gre_dellink, .get_size = ip6gre_get_size, .fill_info = ip6gre_fill_info, .get_link_net = ip6_tnl_get_link_net, }; static struct rtnl_link_ops ip6gre_tap_ops __read_mostly = { .kind = "ip6gretap", .maxtype = IFLA_GRE_MAX, .policy = ip6gre_policy, .priv_size = sizeof(struct ip6_tnl), .setup = ip6gre_tap_setup, .validate = ip6gre_tap_validate, .newlink = ip6gre_newlink, .changelink = ip6gre_changelink, .get_size = ip6gre_get_size, .fill_info = ip6gre_fill_info, .get_link_net = ip6_tnl_get_link_net, }; static struct rtnl_link_ops ip6erspan_tap_ops __read_mostly = { .kind = "ip6erspan", .maxtype = IFLA_GRE_MAX, .policy = ip6gre_policy, .priv_size = sizeof(struct ip6_tnl), .setup = ip6erspan_tap_setup, .validate = ip6erspan_tap_validate, .newlink = ip6erspan_newlink, .changelink = ip6erspan_changelink, .get_size = ip6gre_get_size, .fill_info = ip6gre_fill_info, .get_link_net = ip6_tnl_get_link_net, }; /* * And now the modules code and kernel interface. */ static int __init ip6gre_init(void) { int err; pr_info("GRE over IPv6 tunneling driver\n"); err = register_pernet_device(&ip6gre_net_ops); if (err < 0) return err; err = inet6_add_protocol(&ip6gre_protocol, IPPROTO_GRE); if (err < 0) { pr_info("%s: can't add protocol\n", __func__); goto add_proto_failed; } err = rtnl_link_register(&ip6gre_link_ops); if (err < 0) goto rtnl_link_failed; err = rtnl_link_register(&ip6gre_tap_ops); if (err < 0) goto tap_ops_failed; err = rtnl_link_register(&ip6erspan_tap_ops); if (err < 0) goto erspan_link_failed; out: return err; erspan_link_failed: rtnl_link_unregister(&ip6gre_tap_ops); tap_ops_failed: rtnl_link_unregister(&ip6gre_link_ops); rtnl_link_failed: inet6_del_protocol(&ip6gre_protocol, IPPROTO_GRE); add_proto_failed: unregister_pernet_device(&ip6gre_net_ops); goto out; } static void __exit ip6gre_fini(void) { rtnl_link_unregister(&ip6gre_tap_ops); rtnl_link_unregister(&ip6gre_link_ops); rtnl_link_unregister(&ip6erspan_tap_ops); inet6_del_protocol(&ip6gre_protocol, IPPROTO_GRE); unregister_pernet_device(&ip6gre_net_ops); } module_init(ip6gre_init); module_exit(ip6gre_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("D. Kozlov (xeb@mail.ru)"); MODULE_DESCRIPTION("GRE over IPv6 tunneling device"); MODULE_ALIAS_RTNL_LINK("ip6gre"); MODULE_ALIAS_RTNL_LINK("ip6gretap"); MODULE_ALIAS_RTNL_LINK("ip6erspan"); MODULE_ALIAS_NETDEV("ip6gre0"); |
| 1410 1410 1410 1410 1409 1418 455 1410 1410 1410 1409 1409 1418 1418 4 4 16 16 2241 2243 2208 2227 1841 1841 1841 1841 1840 1809 641 607 566 566 566 647 628 629 629 2 2 2252 2293 2017 2015 631 627 521 631 631 112 18 96 1832 1832 1833 1831 1832 1832 1833 1832 1832 1833 8 175 1678 2196 2193 2126 2193 1911 1910 1801 1800 710 123 2 703 705 295 295 146 222 139 2 137 2109 2106 2109 2106 208 208 1843 59 1831 1833 1843 1844 1843 629 629 629 629 629 629 629 629 628 590 591 476 478 476 651 537 628 16 16 16 16 16 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/kernfs/dir.c - kernfs directory implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org> */ #include <linux/sched.h> #include <linux/fs.h> #include <linux/namei.h> #include <linux/idr.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/hash.h> #include "kernfs-internal.h" static DEFINE_SPINLOCK(kernfs_rename_lock); /* kn->parent and ->name */ /* * Don't use rename_lock to piggy back on pr_cont_buf. We don't want to * call pr_cont() while holding rename_lock. Because sometimes pr_cont() * will perform wakeups when releasing console_sem. Holding rename_lock * will introduce deadlock if the scheduler reads the kernfs_name in the * wakeup path. */ static DEFINE_SPINLOCK(kernfs_pr_cont_lock); static char kernfs_pr_cont_buf[PATH_MAX]; /* protected by pr_cont_lock */ static DEFINE_SPINLOCK(kernfs_idr_lock); /* root->ino_idr */ #define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb) static bool __kernfs_active(struct kernfs_node *kn) { return atomic_read(&kn->active) >= 0; } static bool kernfs_active(struct kernfs_node *kn) { lockdep_assert_held(&kernfs_root(kn)->kernfs_rwsem); return __kernfs_active(kn); } static bool kernfs_lockdep(struct kernfs_node *kn) { #ifdef CONFIG_DEBUG_LOCK_ALLOC return kn->flags & KERNFS_LOCKDEP; #else return false; #endif } static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen) { if (!kn) return strlcpy(buf, "(null)", buflen); return strlcpy(buf, kn->parent ? kn->name : "/", buflen); } /* kernfs_node_depth - compute depth from @from to @to */ static size_t kernfs_depth(struct kernfs_node *from, struct kernfs_node *to) { size_t depth = 0; while (to->parent && to != from) { depth++; to = to->parent; } return depth; } static struct kernfs_node *kernfs_common_ancestor(struct kernfs_node *a, struct kernfs_node *b) { size_t da, db; struct kernfs_root *ra = kernfs_root(a), *rb = kernfs_root(b); if (ra != rb) return NULL; da = kernfs_depth(ra->kn, a); db = kernfs_depth(rb->kn, b); while (da > db) { a = a->parent; da--; } while (db > da) { b = b->parent; db--; } /* worst case b and a will be the same at root */ while (b != a) { b = b->parent; a = a->parent; } return a; } /** * kernfs_path_from_node_locked - find a pseudo-absolute path to @kn_to, * where kn_from is treated as root of the path. * @kn_from: kernfs node which should be treated as root for the path * @kn_to: kernfs node to which path is needed * @buf: buffer to copy the path into * @buflen: size of @buf * * We need to handle couple of scenarios here: * [1] when @kn_from is an ancestor of @kn_to at some level * kn_from: /n1/n2/n3 * kn_to: /n1/n2/n3/n4/n5 * result: /n4/n5 * * [2] when @kn_from is on a different hierarchy and we need to find common * ancestor between @kn_from and @kn_to. * kn_from: /n1/n2/n3/n4 * kn_to: /n1/n2/n5 * result: /../../n5 * OR * kn_from: /n1/n2/n3/n4/n5 [depth=5] * kn_to: /n1/n2/n3 [depth=3] * result: /../.. * * [3] when @kn_to is %NULL result will be "(null)" * * Return: the length of the constructed path. If the path would have been * greater than @buflen, @buf contains the truncated path with the trailing * '\0'. On error, -errno is returned. */ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to, struct kernfs_node *kn_from, char *buf, size_t buflen) { struct kernfs_node *kn, *common; const char parent_str[] = "/.."; size_t depth_from, depth_to, len = 0; ssize_t copied; int i, j; if (!kn_to) return strscpy(buf, "(null)", buflen); if (!kn_from) kn_from = kernfs_root(kn_to)->kn; if (kn_from == kn_to) return strscpy(buf, "/", buflen); if (!buf) return -EINVAL; common = kernfs_common_ancestor(kn_from, kn_to); if (WARN_ON(!common)) return -EINVAL; depth_to = kernfs_depth(common, kn_to); depth_from = kernfs_depth(common, kn_from); buf[0] = '\0'; for (i = 0; i < depth_from; i++) { copied = strscpy(buf + len, parent_str, buflen - len); if (copied < 0) return copied; len += copied; } /* Calculate how many bytes we need for the rest */ for (i = depth_to - 1; i >= 0; i--) { for (kn = kn_to, j = 0; j < i; j++) kn = kn->parent; len += scnprintf(buf + len, buflen - len, "/%s", kn->name); } return len; } /** * kernfs_name - obtain the name of a given node * @kn: kernfs_node of interest * @buf: buffer to copy @kn's name into * @buflen: size of @buf * * Copies the name of @kn into @buf of @buflen bytes. The behavior is * similar to strlcpy(). * * Fills buffer with "(null)" if @kn is %NULL. * * Return: the length of @kn's name and if @buf isn't long enough, * it's filled up to @buflen-1 and nul terminated. * * This function can be called from any context. */ int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen) { unsigned long flags; int ret; spin_lock_irqsave(&kernfs_rename_lock, flags); ret = kernfs_name_locked(kn, buf, buflen); spin_unlock_irqrestore(&kernfs_rename_lock, flags); return ret; } /** * kernfs_path_from_node - build path of node @to relative to @from. * @from: parent kernfs_node relative to which we need to build the path * @to: kernfs_node of interest * @buf: buffer to copy @to's path into * @buflen: size of @buf * * Builds @to's path relative to @from in @buf. @from and @to must * be on the same kernfs-root. If @from is not parent of @to, then a relative * path (which includes '..'s) as needed to reach from @from to @to is * returned. * * Return: the length of the constructed path. If the path would have been * greater than @buflen, @buf contains the truncated path with the trailing * '\0'. On error, -errno is returned. */ int kernfs_path_from_node(struct kernfs_node *to, struct kernfs_node *from, char *buf, size_t buflen) { unsigned long flags; int ret; spin_lock_irqsave(&kernfs_rename_lock, flags); ret = kernfs_path_from_node_locked(to, from, buf, buflen); spin_unlock_irqrestore(&kernfs_rename_lock, flags); return ret; } EXPORT_SYMBOL_GPL(kernfs_path_from_node); /** * pr_cont_kernfs_name - pr_cont name of a kernfs_node * @kn: kernfs_node of interest * * This function can be called from any context. */ void pr_cont_kernfs_name(struct kernfs_node *kn) { unsigned long flags; spin_lock_irqsave(&kernfs_pr_cont_lock, flags); kernfs_name(kn, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf)); pr_cont("%s", kernfs_pr_cont_buf); spin_unlock_irqrestore(&kernfs_pr_cont_lock, flags); } /** * pr_cont_kernfs_path - pr_cont path of a kernfs_node * @kn: kernfs_node of interest * * This function can be called from any context. */ void pr_cont_kernfs_path(struct kernfs_node *kn) { unsigned long flags; int sz; spin_lock_irqsave(&kernfs_pr_cont_lock, flags); sz = kernfs_path_from_node(kn, NULL, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf)); if (sz < 0) { if (sz == -E2BIG) pr_cont("(name too long)"); else pr_cont("(error)"); goto out; } pr_cont("%s", kernfs_pr_cont_buf); out: spin_unlock_irqrestore(&kernfs_pr_cont_lock, flags); } /** * kernfs_get_parent - determine the parent node and pin it * @kn: kernfs_node of interest * * Determines @kn's parent, pins and returns it. This function can be * called from any context. * * Return: parent node of @kn */ struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn) { struct kernfs_node *parent; unsigned long flags; spin_lock_irqsave(&kernfs_rename_lock, flags); parent = kn->parent; kernfs_get(parent); spin_unlock_irqrestore(&kernfs_rename_lock, flags); return parent; } /** * kernfs_name_hash - calculate hash of @ns + @name * @name: Null terminated string to hash * @ns: Namespace tag to hash * * Return: 31-bit hash of ns + name (so it fits in an off_t) */ static unsigned int kernfs_name_hash(const char *name, const void *ns) { unsigned long hash = init_name_hash(ns); unsigned int len = strlen(name); while (len--) hash = partial_name_hash(*name++, hash); hash = end_name_hash(hash); hash &= 0x7fffffffU; /* Reserve hash numbers 0, 1 and INT_MAX for magic directory entries */ if (hash < 2) hash += 2; if (hash >= INT_MAX) hash = INT_MAX - 1; return hash; } static int kernfs_name_compare(unsigned int hash, const char *name, const void *ns, const struct kernfs_node *kn) { if (hash < kn->hash) return -1; if (hash > kn->hash) return 1; if (ns < kn->ns) return -1; if (ns > kn->ns) return 1; return strcmp(name, kn->name); } static int kernfs_sd_compare(const struct kernfs_node *left, const struct kernfs_node *right) { return kernfs_name_compare(left->hash, left->name, left->ns, right); } /** * kernfs_link_sibling - link kernfs_node into sibling rbtree * @kn: kernfs_node of interest * * Link @kn into its sibling rbtree which starts from * @kn->parent->dir.children. * * Locking: * kernfs_rwsem held exclusive * * Return: * %0 on success, -EEXIST on failure. */ static int kernfs_link_sibling(struct kernfs_node *kn) { struct rb_node **node = &kn->parent->dir.children.rb_node; struct rb_node *parent = NULL; while (*node) { struct kernfs_node *pos; int result; pos = rb_to_kn(*node); parent = *node; result = kernfs_sd_compare(kn, pos); if (result < 0) node = &pos->rb.rb_left; else if (result > 0) node = &pos->rb.rb_right; else return -EEXIST; } /* add new node and rebalance the tree */ rb_link_node(&kn->rb, parent, node); rb_insert_color(&kn->rb, &kn->parent->dir.children); /* successfully added, account subdir number */ if (kernfs_type(kn) == KERNFS_DIR) kn->parent->dir.subdirs++; kernfs_inc_rev(kn->parent); return 0; } /** * kernfs_unlink_sibling - unlink kernfs_node from sibling rbtree * @kn: kernfs_node of interest * * Try to unlink @kn from its sibling rbtree which starts from * kn->parent->dir.children. * * Return: %true if @kn was actually removed, * %false if @kn wasn't on the rbtree. * * Locking: * kernfs_rwsem held exclusive */ static bool kernfs_unlink_sibling(struct kernfs_node *kn) { if (RB_EMPTY_NODE(&kn->rb)) return false; if (kernfs_type(kn) == KERNFS_DIR) kn->parent->dir.subdirs--; kernfs_inc_rev(kn->parent); rb_erase(&kn->rb, &kn->parent->dir.children); RB_CLEAR_NODE(&kn->rb); return true; } /** * kernfs_get_active - get an active reference to kernfs_node * @kn: kernfs_node to get an active reference to * * Get an active reference of @kn. This function is noop if @kn * is %NULL. * * Return: * Pointer to @kn on success, %NULL on failure. */ struct kernfs_node *kernfs_get_active(struct kernfs_node *kn) { if (unlikely(!kn)) return NULL; if (!atomic_inc_unless_negative(&kn->active)) return NULL; if (kernfs_lockdep(kn)) rwsem_acquire_read(&kn->dep_map, 0, 1, _RET_IP_); return kn; } /** * kernfs_put_active - put an active reference to kernfs_node * @kn: kernfs_node to put an active reference to * * Put an active reference to @kn. This function is noop if @kn * is %NULL. */ void kernfs_put_active(struct kernfs_node *kn) { int v; if (unlikely(!kn)) return; if (kernfs_lockdep(kn)) rwsem_release(&kn->dep_map, _RET_IP_); v = atomic_dec_return(&kn->active); if (likely(v != KN_DEACTIVATED_BIAS)) return; wake_up_all(&kernfs_root(kn)->deactivate_waitq); } /** * kernfs_drain - drain kernfs_node * @kn: kernfs_node to drain * * Drain existing usages and nuke all existing mmaps of @kn. Multiple * removers may invoke this function concurrently on @kn and all will * return after draining is complete. */ static void kernfs_drain(struct kernfs_node *kn) __releases(&kernfs_root(kn)->kernfs_rwsem) __acquires(&kernfs_root(kn)->kernfs_rwsem) { struct kernfs_root *root = kernfs_root(kn); lockdep_assert_held_write(&root->kernfs_rwsem); WARN_ON_ONCE(kernfs_active(kn)); /* * Skip draining if already fully drained. This avoids draining and its * lockdep annotations for nodes which have never been activated * allowing embedding kernfs_remove() in create error paths without * worrying about draining. */ if (atomic_read(&kn->active) == KN_DEACTIVATED_BIAS && !kernfs_should_drain_open_files(kn)) return; up_write(&root->kernfs_rwsem); if (kernfs_lockdep(kn)) { rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_); if (atomic_read(&kn->active) != KN_DEACTIVATED_BIAS) lock_contended(&kn->dep_map, _RET_IP_); } wait_event(root->deactivate_waitq, atomic_read(&kn->active) == KN_DEACTIVATED_BIAS); if (kernfs_lockdep(kn)) { lock_acquired(&kn->dep_map, _RET_IP_); rwsem_release(&kn->dep_map, _RET_IP_); } if (kernfs_should_drain_open_files(kn)) kernfs_drain_open_files(kn); down_write(&root->kernfs_rwsem); } /** * kernfs_get - get a reference count on a kernfs_node * @kn: the target kernfs_node */ void kernfs_get(struct kernfs_node *kn) { if (kn) { WARN_ON(!atomic_read(&kn->count)); atomic_inc(&kn->count); } } EXPORT_SYMBOL_GPL(kernfs_get); /** * kernfs_put - put a reference count on a kernfs_node * @kn: the target kernfs_node * * Put a reference count of @kn and destroy it if it reached zero. */ void kernfs_put(struct kernfs_node *kn) { struct kernfs_node *parent; struct kernfs_root *root; if (!kn || !atomic_dec_and_test(&kn->count)) return; root = kernfs_root(kn); repeat: /* * Moving/renaming is always done while holding reference. * kn->parent won't change beneath us. */ parent = kn->parent; WARN_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS, "kernfs_put: %s/%s: released with incorrect active_ref %d\n", parent ? parent->name : "", kn->name, atomic_read(&kn->active)); if (kernfs_type(kn) == KERNFS_LINK) kernfs_put(kn->symlink.target_kn); kfree_const(kn->name); if (kn->iattr) { simple_xattrs_free(&kn->iattr->xattrs); kmem_cache_free(kernfs_iattrs_cache, kn->iattr); } spin_lock(&kernfs_idr_lock); idr_remove(&root->ino_idr, (u32)kernfs_ino(kn)); spin_unlock(&kernfs_idr_lock); kmem_cache_free(kernfs_node_cache, kn); kn = parent; if (kn) { if (atomic_dec_and_test(&kn->count)) goto repeat; } else { /* just released the root kn, free @root too */ idr_destroy(&root->ino_idr); kfree(root); } } EXPORT_SYMBOL_GPL(kernfs_put); /** * kernfs_node_from_dentry - determine kernfs_node associated with a dentry * @dentry: the dentry in question * * Return: the kernfs_node associated with @dentry. If @dentry is not a * kernfs one, %NULL is returned. * * While the returned kernfs_node will stay accessible as long as @dentry * is accessible, the returned node can be in any state and the caller is * fully responsible for determining what's accessible. */ struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry) { if (dentry->d_sb->s_op == &kernfs_sops) return kernfs_dentry_node(dentry); return NULL; } static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, unsigned flags) { struct kernfs_node *kn; u32 id_highbits; int ret; name = kstrdup_const(name, GFP_KERNEL); if (!name) return NULL; kn = kmem_cache_zalloc(kernfs_node_cache, GFP_KERNEL); if (!kn) goto err_out1; idr_preload(GFP_KERNEL); spin_lock(&kernfs_idr_lock); ret = idr_alloc_cyclic(&root->ino_idr, kn, 1, 0, GFP_ATOMIC); if (ret >= 0 && ret < root->last_id_lowbits) root->id_highbits++; id_highbits = root->id_highbits; root->last_id_lowbits = ret; spin_unlock(&kernfs_idr_lock); idr_preload_end(); if (ret < 0) goto err_out2; kn->id = (u64)id_highbits << 32 | ret; atomic_set(&kn->count, 1); atomic_set(&kn->active, KN_DEACTIVATED_BIAS); RB_CLEAR_NODE(&kn->rb); kn->name = name; kn->mode = mode; kn->flags = flags; if (!uid_eq(uid, GLOBAL_ROOT_UID) || !gid_eq(gid, GLOBAL_ROOT_GID)) { struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID, .ia_uid = uid, .ia_gid = gid, }; ret = __kernfs_setattr(kn, &iattr); if (ret < 0) goto err_out3; } if (parent) { ret = security_kernfs_init_security(parent, kn); if (ret) goto err_out3; } return kn; err_out3: spin_lock(&kernfs_idr_lock); idr_remove(&root->ino_idr, (u32)kernfs_ino(kn)); spin_unlock(&kernfs_idr_lock); err_out2: kmem_cache_free(kernfs_node_cache, kn); err_out1: kfree_const(name); return NULL; } struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, unsigned flags) { struct kernfs_node *kn; if (parent->mode & S_ISGID) { /* this code block imitates inode_init_owner() for * kernfs */ if (parent->iattr) gid = parent->iattr->ia_gid; if (flags & KERNFS_DIR) mode |= S_ISGID; } kn = __kernfs_new_node(kernfs_root(parent), parent, name, mode, uid, gid, flags); if (kn) { kernfs_get(parent); kn->parent = parent; } return kn; } /* * kernfs_find_and_get_node_by_id - get kernfs_node from node id * @root: the kernfs root * @id: the target node id * * @id's lower 32bits encode ino and upper gen. If the gen portion is * zero, all generations are matched. * * Return: %NULL on failure, * otherwise a kernfs node with reference counter incremented. */ struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root, u64 id) { struct kernfs_node *kn; ino_t ino = kernfs_id_ino(id); u32 gen = kernfs_id_gen(id); spin_lock(&kernfs_idr_lock); kn = idr_find(&root->ino_idr, (u32)ino); if (!kn) goto err_unlock; if (sizeof(ino_t) >= sizeof(u64)) { /* we looked up with the low 32bits, compare the whole */ if (kernfs_ino(kn) != ino) goto err_unlock; } else { /* 0 matches all generations */ if (unlikely(gen && kernfs_gen(kn) != gen)) goto err_unlock; } /* * We should fail if @kn has never been activated and guarantee success * if the caller knows that @kn is active. Both can be achieved by * __kernfs_active() which tests @kn->active without kernfs_rwsem. */ if (unlikely(!__kernfs_active(kn) || !atomic_inc_not_zero(&kn->count))) goto err_unlock; spin_unlock(&kernfs_idr_lock); return kn; err_unlock: spin_unlock(&kernfs_idr_lock); return NULL; } /** * kernfs_add_one - add kernfs_node to parent without warning * @kn: kernfs_node to be added * * The caller must already have initialized @kn->parent. This * function increments nlink of the parent's inode if @kn is a * directory and link into the children list of the parent. * * Return: * %0 on success, -EEXIST if entry with the given name already * exists. */ int kernfs_add_one(struct kernfs_node *kn) { struct kernfs_node *parent = kn->parent; struct kernfs_root *root = kernfs_root(parent); struct kernfs_iattrs *ps_iattr; bool has_ns; int ret; down_write(&root->kernfs_rwsem); ret = -EINVAL; has_ns = kernfs_ns_enabled(parent); if (WARN(has_ns != (bool)kn->ns, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n", has_ns ? "required" : "invalid", parent->name, kn->name)) goto out_unlock; if (kernfs_type(parent) != KERNFS_DIR) goto out_unlock; ret = -ENOENT; if (parent->flags & (KERNFS_REMOVING | KERNFS_EMPTY_DIR)) goto out_unlock; kn->hash = kernfs_name_hash(kn->name, kn->ns); ret = kernfs_link_sibling(kn); if (ret) goto out_unlock; /* Update timestamps on the parent */ ps_iattr = parent->iattr; if (ps_iattr) { ktime_get_real_ts64(&ps_iattr->ia_ctime); ps_iattr->ia_mtime = ps_iattr->ia_ctime; } up_write(&root->kernfs_rwsem); /* * Activate the new node unless CREATE_DEACTIVATED is requested. * If not activated here, the kernfs user is responsible for * activating the node with kernfs_activate(). A node which hasn't * been activated is not visible to userland and its removal won't * trigger deactivation. */ if (!(kernfs_root(kn)->flags & KERNFS_ROOT_CREATE_DEACTIVATED)) kernfs_activate(kn); return 0; out_unlock: up_write(&root->kernfs_rwsem); return ret; } /** * kernfs_find_ns - find kernfs_node with the given name * @parent: kernfs_node to search under * @name: name to look for * @ns: the namespace tag to use * * Look for kernfs_node with name @name under @parent. * * Return: pointer to the found kernfs_node on success, %NULL on failure. */ static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent, const unsigned char *name, const void *ns) { struct rb_node *node = parent->dir.children.rb_node; bool has_ns = kernfs_ns_enabled(parent); unsigned int hash; lockdep_assert_held(&kernfs_root(parent)->kernfs_rwsem); if (has_ns != (bool)ns) { WARN(1, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n", has_ns ? "required" : "invalid", parent->name, name); return NULL; } hash = kernfs_name_hash(name, ns); while (node) { struct kernfs_node *kn; int result; kn = rb_to_kn(node); result = kernfs_name_compare(hash, name, ns, kn); if (result < 0) node = node->rb_left; else if (result > 0) node = node->rb_right; else return kn; } return NULL; } static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent, const unsigned char *path, const void *ns) { size_t len; char *p, *name; lockdep_assert_held_read(&kernfs_root(parent)->kernfs_rwsem); spin_lock_irq(&kernfs_pr_cont_lock); len = strlcpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf)); if (len >= sizeof(kernfs_pr_cont_buf)) { spin_unlock_irq(&kernfs_pr_cont_lock); return NULL; } p = kernfs_pr_cont_buf; while ((name = strsep(&p, "/")) && parent) { if (*name == '\0') continue; parent = kernfs_find_ns(parent, name, ns); } spin_unlock_irq(&kernfs_pr_cont_lock); return parent; } /** * kernfs_find_and_get_ns - find and get kernfs_node with the given name * @parent: kernfs_node to search under * @name: name to look for * @ns: the namespace tag to use * * Look for kernfs_node with name @name under @parent and get a reference * if found. This function may sleep. * * Return: pointer to the found kernfs_node on success, %NULL on failure. */ struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name, const void *ns) { struct kernfs_node *kn; struct kernfs_root *root = kernfs_root(parent); down_read(&root->kernfs_rwsem); kn = kernfs_find_ns(parent, name, ns); kernfs_get(kn); up_read(&root->kernfs_rwsem); return kn; } EXPORT_SYMBOL_GPL(kernfs_find_and_get_ns); /** * kernfs_walk_and_get_ns - find and get kernfs_node with the given path * @parent: kernfs_node to search under * @path: path to look for * @ns: the namespace tag to use * * Look for kernfs_node with path @path under @parent and get a reference * if found. This function may sleep. * * Return: pointer to the found kernfs_node on success, %NULL on failure. */ struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent, const char *path, const void *ns) { struct kernfs_node *kn; struct kernfs_root *root = kernfs_root(parent); down_read(&root->kernfs_rwsem); kn = kernfs_walk_ns(parent, path, ns); kernfs_get(kn); up_read(&root->kernfs_rwsem); return kn; } /** * kernfs_create_root - create a new kernfs hierarchy * @scops: optional syscall operations for the hierarchy * @flags: KERNFS_ROOT_* flags * @priv: opaque data associated with the new directory * * Return: the root of the new hierarchy on success, ERR_PTR() value on * failure. */ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv) { struct kernfs_root *root; struct kernfs_node *kn; root = kzalloc(sizeof(*root), GFP_KERNEL); if (!root) return ERR_PTR(-ENOMEM); idr_init(&root->ino_idr); init_rwsem(&root->kernfs_rwsem); INIT_LIST_HEAD(&root->supers); /* * On 64bit ino setups, id is ino. On 32bit, low 32bits are ino. * High bits generation. The starting value for both ino and * genenration is 1. Initialize upper 32bit allocation * accordingly. */ if (sizeof(ino_t) >= sizeof(u64)) root->id_highbits = 0; else root->id_highbits = 1; kn = __kernfs_new_node(root, NULL, "", S_IFDIR | S_IRUGO | S_IXUGO, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, KERNFS_DIR); if (!kn) { idr_destroy(&root->ino_idr); kfree(root); return ERR_PTR(-ENOMEM); } kn->priv = priv; kn->dir.root = root; root->syscall_ops = scops; root->flags = flags; root->kn = kn; init_waitqueue_head(&root->deactivate_waitq); if (!(root->flags & KERNFS_ROOT_CREATE_DEACTIVATED)) kernfs_activate(kn); return root; } /** * kernfs_destroy_root - destroy a kernfs hierarchy * @root: root of the hierarchy to destroy * * Destroy the hierarchy anchored at @root by removing all existing * directories and destroying @root. */ void kernfs_destroy_root(struct kernfs_root *root) { /* * kernfs_remove holds kernfs_rwsem from the root so the root * shouldn't be freed during the operation. */ kernfs_get(root->kn); kernfs_remove(root->kn); kernfs_put(root->kn); /* will also free @root */ } /** * kernfs_root_to_node - return the kernfs_node associated with a kernfs_root * @root: root to use to lookup * * Return: @root's kernfs_node */ struct kernfs_node *kernfs_root_to_node(struct kernfs_root *root) { return root->kn; } /** * kernfs_create_dir_ns - create a directory * @parent: parent in which to create a new directory * @name: name of the new directory * @mode: mode of the new directory * @uid: uid of the new directory * @gid: gid of the new directory * @priv: opaque data associated with the new directory * @ns: optional namespace tag of the directory * * Return: the created node on success, ERR_PTR() value on failure. */ struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, void *priv, const void *ns) { struct kernfs_node *kn; int rc; /* allocate */ kn = kernfs_new_node(parent, name, mode | S_IFDIR, uid, gid, KERNFS_DIR); if (!kn) return ERR_PTR(-ENOMEM); kn->dir.root = parent->dir.root; kn->ns = ns; kn->priv = priv; /* link in */ rc = kernfs_add_one(kn); if (!rc) return kn; kernfs_put(kn); return ERR_PTR(rc); } /** * kernfs_create_empty_dir - create an always empty directory * @parent: parent in which to create a new directory * @name: name of the new directory * * Return: the created node on success, ERR_PTR() value on failure. */ struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent, const char *name) { struct kernfs_node *kn; int rc; /* allocate */ kn = kernfs_new_node(parent, name, S_IRUGO|S_IXUGO|S_IFDIR, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, KERNFS_DIR); if (!kn) return ERR_PTR(-ENOMEM); kn->flags |= KERNFS_EMPTY_DIR; kn->dir.root = parent->dir.root; kn->ns = NULL; kn->priv = NULL; /* link in */ rc = kernfs_add_one(kn); if (!rc) return kn; kernfs_put(kn); return ERR_PTR(rc); } static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) { struct kernfs_node *kn; struct kernfs_root *root; if (flags & LOOKUP_RCU) return -ECHILD; /* Negative hashed dentry? */ if (d_really_is_negative(dentry)) { struct kernfs_node *parent; /* If the kernfs parent node has changed discard and * proceed to ->lookup. */ spin_lock(&dentry->d_lock); parent = kernfs_dentry_node(dentry->d_parent); if (parent) { spin_unlock(&dentry->d_lock); root = kernfs_root(parent); down_read(&root->kernfs_rwsem); if (kernfs_dir_changed(parent, dentry)) { up_read(&root->kernfs_rwsem); return 0; } up_read(&root->kernfs_rwsem); } else spin_unlock(&dentry->d_lock); /* The kernfs parent node hasn't changed, leave the * dentry negative and return success. */ return 1; } kn = kernfs_dentry_node(dentry); root = kernfs_root(kn); down_read(&root->kernfs_rwsem); /* The kernfs node has been deactivated */ if (!kernfs_active(kn)) goto out_bad; /* The kernfs node has been moved? */ if (kernfs_dentry_node(dentry->d_parent) != kn->parent) goto out_bad; /* The kernfs node has been renamed */ if (strcmp(dentry->d_name.name, kn->name) != 0) goto out_bad; /* The kernfs node has been moved to a different namespace */ if (kn->parent && kernfs_ns_enabled(kn->parent) && kernfs_info(dentry->d_sb)->ns != kn->ns) goto out_bad; up_read(&root->kernfs_rwsem); return 1; out_bad: up_read(&root->kernfs_rwsem); return 0; } const struct dentry_operations kernfs_dops = { .d_revalidate = kernfs_dop_revalidate, }; static struct dentry *kernfs_iop_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct kernfs_node *parent = dir->i_private; struct kernfs_node *kn; struct kernfs_root *root; struct inode *inode = NULL; const void *ns = NULL; root = kernfs_root(parent); down_read(&root->kernfs_rwsem); if (kernfs_ns_enabled(parent)) ns = kernfs_info(dir->i_sb)->ns; kn = kernfs_find_ns(parent, dentry->d_name.name, ns); /* attach dentry and inode */ if (kn) { /* Inactive nodes are invisible to the VFS so don't * create a negative. */ if (!kernfs_active(kn)) { up_read(&root->kernfs_rwsem); return NULL; } inode = kernfs_get_inode(dir->i_sb, kn); if (!inode) inode = ERR_PTR(-ENOMEM); } /* * Needed for negative dentry validation. * The negative dentry can be created in kernfs_iop_lookup() * or transforms from positive dentry in dentry_unlink_inode() * called from vfs_rmdir(). */ if (!IS_ERR(inode)) kernfs_set_rev(parent, dentry); up_read(&root->kernfs_rwsem); /* instantiate and hash (possibly negative) dentry */ return d_splice_alias(inode, dentry); } static int kernfs_iop_mkdir(struct user_namespace *mnt_userns, struct inode *dir, struct dentry *dentry, umode_t mode) { struct kernfs_node *parent = dir->i_private; struct kernfs_syscall_ops *scops = kernfs_root(parent)->syscall_ops; int ret; if (!scops || !scops->mkdir) return -EPERM; if (!kernfs_get_active(parent)) return -ENODEV; ret = scops->mkdir(parent, dentry->d_name.name, mode); kernfs_put_active(parent); return ret; } static int kernfs_iop_rmdir(struct inode *dir, struct dentry *dentry) { struct kernfs_node *kn = kernfs_dentry_node(dentry); struct kernfs_syscall_ops *scops = kernfs_root(kn)->syscall_ops; int ret; if (!scops || !scops->rmdir) return -EPERM; if (!kernfs_get_active(kn)) return -ENODEV; ret = scops->rmdir(kn); kernfs_put_active(kn); return ret; } static int kernfs_iop_rename(struct user_namespace *mnt_userns, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { struct kernfs_node *kn = kernfs_dentry_node(old_dentry); struct kernfs_node *new_parent = new_dir->i_private; struct kernfs_syscall_ops *scops = kernfs_root(kn)->syscall_ops; int ret; if (flags) return -EINVAL; if (!scops || !scops->rename) return -EPERM; if (!kernfs_get_active(kn)) return -ENODEV; if (!kernfs_get_active(new_parent)) { kernfs_put_active(kn); return -ENODEV; } ret = scops->rename(kn, new_parent, new_dentry->d_name.name); kernfs_put_active(new_parent); kernfs_put_active(kn); return ret; } const struct inode_operations kernfs_dir_iops = { .lookup = kernfs_iop_lookup, .permission = kernfs_iop_permission, .setattr = kernfs_iop_setattr, .getattr = kernfs_iop_getattr, .listxattr = kernfs_iop_listxattr, .mkdir = kernfs_iop_mkdir, .rmdir = kernfs_iop_rmdir, .rename = kernfs_iop_rename, }; static struct kernfs_node *kernfs_leftmost_descendant(struct kernfs_node *pos) { struct kernfs_node *last; while (true) { struct rb_node *rbn; last = pos; if (kernfs_type(pos) != KERNFS_DIR) break; rbn = rb_first(&pos->dir.children); if (!rbn) break; pos = rb_to_kn(rbn); } return last; } /** * kernfs_next_descendant_post - find the next descendant for post-order walk * @pos: the current position (%NULL to initiate traversal) * @root: kernfs_node whose descendants to walk * * Find the next descendant to visit for post-order traversal of @root's * descendants. @root is included in the iteration and the last node to be * visited. * * Return: the next descendant to visit or %NULL when done. */ static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos, struct kernfs_node *root) { struct rb_node *rbn; lockdep_assert_held_write(&kernfs_root(root)->kernfs_rwsem); /* if first iteration, visit leftmost descendant which may be root */ if (!pos) return kernfs_leftmost_descendant(root); /* if we visited @root, we're done */ if (pos == root) return NULL; /* if there's an unvisited sibling, visit its leftmost descendant */ rbn = rb_next(&pos->rb); if (rbn) return kernfs_leftmost_descendant(rb_to_kn(rbn)); /* no sibling left, visit parent */ return pos->parent; } static void kernfs_activate_one(struct kernfs_node *kn) { lockdep_assert_held_write(&kernfs_root(kn)->kernfs_rwsem); kn->flags |= KERNFS_ACTIVATED; if (kernfs_active(kn) || (kn->flags & (KERNFS_HIDDEN | KERNFS_REMOVING))) return; WARN_ON_ONCE(kn->parent && RB_EMPTY_NODE(&kn->rb)); WARN_ON_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS); atomic_sub(KN_DEACTIVATED_BIAS, &kn->active); } /** * kernfs_activate - activate a node which started deactivated * @kn: kernfs_node whose subtree is to be activated * * If the root has KERNFS_ROOT_CREATE_DEACTIVATED set, a newly created node * needs to be explicitly activated. A node which hasn't been activated * isn't visible to userland and deactivation is skipped during its * removal. This is useful to construct atomic init sequences where * creation of multiple nodes should either succeed or fail atomically. * * The caller is responsible for ensuring that this function is not called * after kernfs_remove*() is invoked on @kn. */ void kernfs_activate(struct kernfs_node *kn) { struct kernfs_node *pos; struct kernfs_root *root = kernfs_root(kn); down_write(&root->kernfs_rwsem); pos = NULL; while ((pos = kernfs_next_descendant_post(pos, kn))) kernfs_activate_one(pos); up_write(&root->kernfs_rwsem); } /** * kernfs_show - show or hide a node * @kn: kernfs_node to show or hide * @show: whether to show or hide * * If @show is %false, @kn is marked hidden and deactivated. A hidden node is * ignored in future activaitons. If %true, the mark is removed and activation * state is restored. This function won't implicitly activate a new node in a * %KERNFS_ROOT_CREATE_DEACTIVATED root which hasn't been activated yet. * * To avoid recursion complexities, directories aren't supported for now. */ void kernfs_show(struct kernfs_node *kn, bool show) { struct kernfs_root *root = kernfs_root(kn); if (WARN_ON_ONCE(kernfs_type(kn) == KERNFS_DIR)) return; down_write(&root->kernfs_rwsem); if (show) { kn->flags &= ~KERNFS_HIDDEN; if (kn->flags & KERNFS_ACTIVATED) kernfs_activate_one(kn); } else { kn->flags |= KERNFS_HIDDEN; if (kernfs_active(kn)) atomic_add(KN_DEACTIVATED_BIAS, &kn->active); kernfs_drain(kn); } up_write(&root->kernfs_rwsem); } static void __kernfs_remove(struct kernfs_node *kn) { struct kernfs_node *pos; /* Short-circuit if non-root @kn has already finished removal. */ if (!kn) return; lockdep_assert_held_write(&kernfs_root(kn)->kernfs_rwsem); /* * This is for kernfs_remove_self() which plays with active ref * after removal. */ if (kn->parent && RB_EMPTY_NODE(&kn->rb)) return; pr_debug("kernfs %s: removing\n", kn->name); /* prevent new usage by marking all nodes removing and deactivating */ pos = NULL; while ((pos = kernfs_next_descendant_post(pos, kn))) { pos->flags |= KERNFS_REMOVING; if (kernfs_active(pos)) atomic_add(KN_DEACTIVATED_BIAS, &pos->active); } /* deactivate and unlink the subtree node-by-node */ do { pos = kernfs_leftmost_descendant(kn); /* * kernfs_drain() may drop kernfs_rwsem temporarily and @pos's * base ref could have been put by someone else by the time * the function returns. Make sure it doesn't go away * underneath us. */ kernfs_get(pos); kernfs_drain(pos); /* * kernfs_unlink_sibling() succeeds once per node. Use it * to decide who's responsible for cleanups. */ if (!pos->parent || kernfs_unlink_sibling(pos)) { struct kernfs_iattrs *ps_iattr = pos->parent ? pos->parent->iattr : NULL; /* update timestamps on the parent */ if (ps_iattr) { ktime_get_real_ts64(&ps_iattr->ia_ctime); ps_iattr->ia_mtime = ps_iattr->ia_ctime; } kernfs_put(pos); } kernfs_put(pos); } while (pos != kn); } /** * kernfs_remove - remove a kernfs_node recursively * @kn: the kernfs_node to remove * * Remove @kn along with all its subdirectories and files. */ void kernfs_remove(struct kernfs_node *kn) { struct kernfs_root *root; if (!kn) return; root = kernfs_root(kn); down_write(&root->kernfs_rwsem); __kernfs_remove(kn); up_write(&root->kernfs_rwsem); } /** * kernfs_break_active_protection - break out of active protection * @kn: the self kernfs_node * * The caller must be running off of a kernfs operation which is invoked * with an active reference - e.g. one of kernfs_ops. Each invocation of * this function must also be matched with an invocation of * kernfs_unbreak_active_protection(). * * This function releases the active reference of @kn the caller is * holding. Once this function is called, @kn may be removed at any point * and the caller is solely responsible for ensuring that the objects it * dereferences are accessible. */ void kernfs_break_active_protection(struct kernfs_node *kn) { /* * Take out ourself out of the active ref dependency chain. If * we're called without an active ref, lockdep will complain. */ kernfs_put_active(kn); } /** * kernfs_unbreak_active_protection - undo kernfs_break_active_protection() * @kn: the self kernfs_node * * If kernfs_break_active_protection() was called, this function must be * invoked before finishing the kernfs operation. Note that while this * function restores the active reference, it doesn't and can't actually * restore the active protection - @kn may already or be in the process of * being removed. Once kernfs_break_active_protection() is invoked, that * protection is irreversibly gone for the kernfs operation instance. * * While this function may be called at any point after * kernfs_break_active_protection() is invoked, its most useful location * would be right before the enclosing kernfs operation returns. */ void kernfs_unbreak_active_protection(struct kernfs_node *kn) { /* * @kn->active could be in any state; however, the increment we do * here will be undone as soon as the enclosing kernfs operation * finishes and this temporary bump can't break anything. If @kn * is alive, nothing changes. If @kn is being deactivated, the * soon-to-follow put will either finish deactivation or restore * deactivated state. If @kn is already removed, the temporary * bump is guaranteed to be gone before @kn is released. */ atomic_inc(&kn->active); if (kernfs_lockdep(kn)) rwsem_acquire(&kn->dep_map, 0, 1, _RET_IP_); } /** * kernfs_remove_self - remove a kernfs_node from its own method * @kn: the self kernfs_node to remove * * The caller must be running off of a kernfs operation which is invoked * with an active reference - e.g. one of kernfs_ops. This can be used to * implement a file operation which deletes itself. * * For example, the "delete" file for a sysfs device directory can be * implemented by invoking kernfs_remove_self() on the "delete" file * itself. This function breaks the circular dependency of trying to * deactivate self while holding an active ref itself. It isn't necessary * to modify the usual removal path to use kernfs_remove_self(). The * "delete" implementation can simply invoke kernfs_remove_self() on self * before proceeding with the usual removal path. kernfs will ignore later * kernfs_remove() on self. * * kernfs_remove_self() can be called multiple times concurrently on the * same kernfs_node. Only the first one actually performs removal and * returns %true. All others will wait until the kernfs operation which * won self-removal finishes and return %false. Note that the losers wait * for the completion of not only the winning kernfs_remove_self() but also * the whole kernfs_ops which won the arbitration. This can be used to * guarantee, for example, all concurrent writes to a "delete" file to * finish only after the whole operation is complete. * * Return: %true if @kn is removed by this call, otherwise %false. */ bool kernfs_remove_self(struct kernfs_node *kn) { bool ret; struct kernfs_root *root = kernfs_root(kn); down_write(&root->kernfs_rwsem); kernfs_break_active_protection(kn); /* * SUICIDAL is used to arbitrate among competing invocations. Only * the first one will actually perform removal. When the removal * is complete, SUICIDED is set and the active ref is restored * while kernfs_rwsem for held exclusive. The ones which lost * arbitration waits for SUICIDED && drained which can happen only * after the enclosing kernfs operation which executed the winning * instance of kernfs_remove_self() finished. */ if (!(kn->flags & KERNFS_SUICIDAL)) { kn->flags |= KERNFS_SUICIDAL; __kernfs_remove(kn); kn->flags |= KERNFS_SUICIDED; ret = true; } else { wait_queue_head_t *waitq = &kernfs_root(kn)->deactivate_waitq; DEFINE_WAIT(wait); while (true) { prepare_to_wait(waitq, &wait, TASK_UNINTERRUPTIBLE); if ((kn->flags & KERNFS_SUICIDED) && atomic_read(&kn->active) == KN_DEACTIVATED_BIAS) break; up_write(&root->kernfs_rwsem); schedule(); down_write(&root->kernfs_rwsem); } finish_wait(waitq, &wait); WARN_ON_ONCE(!RB_EMPTY_NODE(&kn->rb)); ret = false; } /* * This must be done while kernfs_rwsem held exclusive; otherwise, * waiting for SUICIDED && deactivated could finish prematurely. */ kernfs_unbreak_active_protection(kn); up_write(&root->kernfs_rwsem); return ret; } /** * kernfs_remove_by_name_ns - find a kernfs_node by name and remove it * @parent: parent of the target * @name: name of the kernfs_node to remove * @ns: namespace tag of the kernfs_node to remove * * Look for the kernfs_node with @name and @ns under @parent and remove it. * * Return: %0 on success, -ENOENT if such entry doesn't exist. */ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, const void *ns) { struct kernfs_node *kn; struct kernfs_root *root; if (!parent) { WARN(1, KERN_WARNING "kernfs: can not remove '%s', no directory\n", name); return -ENOENT; } root = kernfs_root(parent); down_write(&root->kernfs_rwsem); kn = kernfs_find_ns(parent, name, ns); if (kn) { kernfs_get(kn); __kernfs_remove(kn); kernfs_put(kn); } up_write(&root->kernfs_rwsem); if (kn) return 0; else return -ENOENT; } /** * kernfs_rename_ns - move and rename a kernfs_node * @kn: target node * @new_parent: new parent to put @sd under * @new_name: new name * @new_ns: new namespace tag * * Return: %0 on success, -errno on failure. */ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name, const void *new_ns) { struct kernfs_node *old_parent; struct kernfs_root *root; const char *old_name = NULL; int error; /* can't move or rename root */ if (!kn->parent) return -EINVAL; root = kernfs_root(kn); down_write(&root->kernfs_rwsem); error = -ENOENT; if (!kernfs_active(kn) || !kernfs_active(new_parent) || (new_parent->flags & KERNFS_EMPTY_DIR)) goto out; error = 0; if ((kn->parent == new_parent) && (kn->ns == new_ns) && (strcmp(kn->name, new_name) == 0)) goto out; /* nothing to rename */ error = -EEXIST; if (kernfs_find_ns(new_parent, new_name, new_ns)) goto out; /* rename kernfs_node */ if (strcmp(kn->name, new_name) != 0) { error = -ENOMEM; new_name = kstrdup_const(new_name, GFP_KERNEL); if (!new_name) goto out; } else { new_name = NULL; } /* * Move to the appropriate place in the appropriate directories rbtree. */ kernfs_unlink_sibling(kn); kernfs_get(new_parent); /* rename_lock protects ->parent and ->name accessors */ spin_lock_irq(&kernfs_rename_lock); old_parent = kn->parent; kn->parent = new_parent; kn->ns = new_ns; if (new_name) { old_name = kn->name; kn->name = new_name; } spin_unlock_irq(&kernfs_rename_lock); kn->hash = kernfs_name_hash(kn->name, kn->ns); kernfs_link_sibling(kn); kernfs_put(old_parent); kfree_const(old_name); error = 0; out: up_write(&root->kernfs_rwsem); return error; } /* Relationship between mode and the DT_xxx types */ static inline unsigned char dt_type(struct kernfs_node *kn) { return (kn->mode >> 12) & 15; } static int kernfs_dir_fop_release(struct inode *inode, struct file *filp) { kernfs_put(filp->private_data); return 0; } static struct kernfs_node *kernfs_dir_pos(const void *ns, struct kernfs_node *parent, loff_t hash, struct kernfs_node *pos) { if (pos) { int valid = kernfs_active(pos) && pos->parent == parent && hash == pos->hash; kernfs_put(pos); if (!valid) pos = NULL; } if (!pos && (hash > 1) && (hash < INT_MAX)) { struct rb_node *node = parent->dir.children.rb_node; while (node) { pos = rb_to_kn(node); if (hash < pos->hash) node = node->rb_left; else if (hash > pos->hash) node = node->rb_right; else break; } } /* Skip over entries which are dying/dead or in the wrong namespace */ while (pos && (!kernfs_active(pos) || pos->ns != ns)) { struct rb_node *node = rb_next(&pos->rb); if (!node) pos = NULL; else pos = rb_to_kn(node); } return pos; } static struct kernfs_node *kernfs_dir_next_pos(const void *ns, struct kernfs_node *parent, ino_t ino, struct kernfs_node *pos) { pos = kernfs_dir_pos(ns, parent, ino, pos); if (pos) { do { struct rb_node *node = rb_next(&pos->rb); if (!node) pos = NULL; else pos = rb_to_kn(node); } while (pos && (!kernfs_active(pos) || pos->ns != ns)); } return pos; } static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file->f_path.dentry; struct kernfs_node *parent = kernfs_dentry_node(dentry); struct kernfs_node *pos = file->private_data; struct kernfs_root *root; const void *ns = NULL; if (!dir_emit_dots(file, ctx)) return 0; root = kernfs_root(parent); down_read(&root->kernfs_rwsem); if (kernfs_ns_enabled(parent)) ns = kernfs_info(dentry->d_sb)->ns; for (pos = kernfs_dir_pos(ns, parent, ctx->pos, pos); pos; pos = kernfs_dir_next_pos(ns, parent, ctx->pos, pos)) { const char *name = pos->name; unsigned int type = dt_type(pos); int len = strlen(name); ino_t ino = kernfs_ino(pos); ctx->pos = pos->hash; file->private_data = pos; kernfs_get(pos); up_read(&root->kernfs_rwsem); if (!dir_emit(ctx, name, len, ino, type)) return 0; down_read(&root->kernfs_rwsem); } up_read(&root->kernfs_rwsem); file->private_data = NULL; ctx->pos = INT_MAX; return 0; } const struct file_operations kernfs_dir_fops = { .read = generic_read_dir, .iterate_shared = kernfs_fop_readdir, .release = kernfs_dir_fop_release, .llseek = generic_file_llseek, }; |
| 32 32 32 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 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 | /* SPDX-License-Identifier: GPL-2.0 * * IO cost model based controller. * * Copyright (C) 2019 Tejun Heo <tj@kernel.org> * Copyright (C) 2019 Andy Newell <newella@fb.com> * Copyright (C) 2019 Facebook * * One challenge of controlling IO resources is the lack of trivially * observable cost metric. This is distinguished from CPU and memory where * wallclock time and the number of bytes can serve as accurate enough * approximations. * * Bandwidth and iops are the most commonly used metrics for IO devices but * depending on the type and specifics of the device, different IO patterns * easily lead to multiple orders of magnitude variations rendering them * useless for the purpose of IO capacity distribution. While on-device * time, with a lot of clutches, could serve as a useful approximation for * non-queued rotational devices, this is no longer viable with modern * devices, even the rotational ones. * * While there is no cost metric we can trivially observe, it isn't a * complete mystery. For example, on a rotational device, seek cost * dominates while a contiguous transfer contributes a smaller amount * proportional to the size. If we can characterize at least the relative * costs of these different types of IOs, it should be possible to * implement a reasonable work-conserving proportional IO resource * distribution. * * 1. IO Cost Model * * IO cost model estimates the cost of an IO given its basic parameters and * history (e.g. the end sector of the last IO). The cost is measured in * device time. If a given IO is estimated to cost 10ms, the device should * be able to process ~100 of those IOs in a second. * * Currently, there's only one builtin cost model - linear. Each IO is * classified as sequential or random and given a base cost accordingly. * On top of that, a size cost proportional to the length of the IO is * added. While simple, this model captures the operational * characteristics of a wide varienty of devices well enough. Default * parameters for several different classes of devices are provided and the * parameters can be configured from userspace via * /sys/fs/cgroup/io.cost.model. * * If needed, tools/cgroup/iocost_coef_gen.py can be used to generate * device-specific coefficients. * * 2. Control Strategy * * The device virtual time (vtime) is used as the primary control metric. * The control strategy is composed of the following three parts. * * 2-1. Vtime Distribution * * When a cgroup becomes active in terms of IOs, its hierarchical share is * calculated. Please consider the following hierarchy where the numbers * inside parentheses denote the configured weights. * * root * / \ * A (w:100) B (w:300) * / \ * A0 (w:100) A1 (w:100) * * If B is idle and only A0 and A1 are actively issuing IOs, as the two are * of equal weight, each gets 50% share. If then B starts issuing IOs, B * gets 300/(100+300) or 75% share, and A0 and A1 equally splits the rest, * 12.5% each. The distribution mechanism only cares about these flattened * shares. They're called hweights (hierarchical weights) and always add * upto 1 (WEIGHT_ONE). * * A given cgroup's vtime runs slower in inverse proportion to its hweight. * For example, with 12.5% weight, A0's time runs 8 times slower (100/12.5) * against the device vtime - an IO which takes 10ms on the underlying * device is considered to take 80ms on A0. * * This constitutes the basis of IO capacity distribution. Each cgroup's * vtime is running at a rate determined by its hweight. A cgroup tracks * the vtime consumed by past IOs and can issue a new IO if doing so * wouldn't outrun the current device vtime. Otherwise, the IO is * suspended until the vtime has progressed enough to cover it. * * 2-2. Vrate Adjustment * * It's unrealistic to expect the cost model to be perfect. There are too * many devices and even on the same device the overall performance * fluctuates depending on numerous factors such as IO mixture and device * internal garbage collection. The controller needs to adapt dynamically. * * This is achieved by adjusting the overall IO rate according to how busy * the device is. If the device becomes overloaded, we're sending down too * many IOs and should generally slow down. If there are waiting issuers * but the device isn't saturated, we're issuing too few and should * generally speed up. * * To slow down, we lower the vrate - the rate at which the device vtime * passes compared to the wall clock. For example, if the vtime is running * at the vrate of 75%, all cgroups added up would only be able to issue * 750ms worth of IOs per second, and vice-versa for speeding up. * * Device business is determined using two criteria - rq wait and * completion latencies. * * When a device gets saturated, the on-device and then the request queues * fill up and a bio which is ready to be issued has to wait for a request * to become available. When this delay becomes noticeable, it's a clear * indication that the device is saturated and we lower the vrate. This * saturation signal is fairly conservative as it only triggers when both * hardware and software queues are filled up, and is used as the default * busy signal. * * As devices can have deep queues and be unfair in how the queued commands * are executed, soley depending on rq wait may not result in satisfactory * control quality. For a better control quality, completion latency QoS * parameters can be configured so that the device is considered saturated * if N'th percentile completion latency rises above the set point. * * The completion latency requirements are a function of both the * underlying device characteristics and the desired IO latency quality of * service. There is an inherent trade-off - the tighter the latency QoS, * the higher the bandwidth lossage. Latency QoS is disabled by default * and can be set through /sys/fs/cgroup/io.cost.qos. * * 2-3. Work Conservation * * Imagine two cgroups A and B with equal weights. A is issuing a small IO * periodically while B is sending out enough parallel IOs to saturate the * device on its own. Let's say A's usage amounts to 100ms worth of IO * cost per second, i.e., 10% of the device capacity. The naive * distribution of half and half would lead to 60% utilization of the * device, a significant reduction in the total amount of work done * compared to free-for-all competition. This is too high a cost to pay * for IO control. * * To conserve the total amount of work done, we keep track of how much * each active cgroup is actually using and yield part of its weight if * there are other cgroups which can make use of it. In the above case, * A's weight will be lowered so that it hovers above the actual usage and * B would be able to use the rest. * * As we don't want to penalize a cgroup for donating its weight, the * surplus weight adjustment factors in a margin and has an immediate * snapback mechanism in case the cgroup needs more IO vtime for itself. * * Note that adjusting down surplus weights has the same effects as * accelerating vtime for other cgroups and work conservation can also be * implemented by adjusting vrate dynamically. However, squaring who can * donate and should take back how much requires hweight propagations * anyway making it easier to implement and understand as a separate * mechanism. * * 3. Monitoring * * Instead of debugfs or other clumsy monitoring mechanisms, this * controller uses a drgn based monitoring script - * tools/cgroup/iocost_monitor.py. For details on drgn, please see * https://github.com/osandov/drgn. The output looks like the following. * * sdb RUN per=300ms cur_per=234.218:v203.695 busy= +1 vrate= 62.12% * active weight hweight% inflt% dbt delay usages% * test/a * 50/ 50 33.33/ 33.33 27.65 2 0*041 033:033:033 * test/b * 100/ 100 66.67/ 66.67 17.56 0 0*000 066:079:077 * * - per : Timer period * - cur_per : Internal wall and device vtime clock * - vrate : Device virtual time rate against wall clock * - weight : Surplus-adjusted and configured weights * - hweight : Surplus-adjusted and configured hierarchical weights * - inflt : The percentage of in-flight IO cost at the end of last period * - del_ms : Deferred issuer delay induction level and duration * - usages : Usage history */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/timer.h> #include <linux/time64.h> #include <linux/parser.h> #include <linux/sched/signal.h> #include <asm/local.h> #include <asm/local64.h> #include "blk-rq-qos.h" #include "blk-stat.h" #include "blk-wbt.h" #include "blk-cgroup.h" #ifdef CONFIG_TRACEPOINTS /* copied from TRACE_CGROUP_PATH, see cgroup-internal.h */ #define TRACE_IOCG_PATH_LEN 1024 static DEFINE_SPINLOCK(trace_iocg_path_lock); static char trace_iocg_path[TRACE_IOCG_PATH_LEN]; #define TRACE_IOCG_PATH(type, iocg, ...) \ do { \ unsigned long flags; \ if (trace_iocost_##type##_enabled()) { \ spin_lock_irqsave(&trace_iocg_path_lock, flags); \ cgroup_path(iocg_to_blkg(iocg)->blkcg->css.cgroup, \ trace_iocg_path, TRACE_IOCG_PATH_LEN); \ trace_iocost_##type(iocg, trace_iocg_path, \ ##__VA_ARGS__); \ spin_unlock_irqrestore(&trace_iocg_path_lock, flags); \ } \ } while (0) #else /* CONFIG_TRACE_POINTS */ #define TRACE_IOCG_PATH(type, iocg, ...) do { } while (0) #endif /* CONFIG_TRACE_POINTS */ enum { MILLION = 1000000, /* timer period is calculated from latency requirements, bound it */ MIN_PERIOD = USEC_PER_MSEC, MAX_PERIOD = USEC_PER_SEC, /* * iocg->vtime is targeted at 50% behind the device vtime, which * serves as its IO credit buffer. Surplus weight adjustment is * immediately canceled if the vtime margin runs below 10%. */ MARGIN_MIN_PCT = 10, MARGIN_LOW_PCT = 20, MARGIN_TARGET_PCT = 50, INUSE_ADJ_STEP_PCT = 25, /* Have some play in timer operations */ TIMER_SLACK_PCT = 1, /* 1/64k is granular enough and can easily be handled w/ u32 */ WEIGHT_ONE = 1 << 16, }; enum { /* * As vtime is used to calculate the cost of each IO, it needs to * be fairly high precision. For example, it should be able to * represent the cost of a single page worth of discard with * suffificient accuracy. At the same time, it should be able to * represent reasonably long enough durations to be useful and * convenient during operation. * * 1s worth of vtime is 2^37. This gives us both sub-nanosecond * granularity and days of wrap-around time even at extreme vrates. */ VTIME_PER_SEC_SHIFT = 37, VTIME_PER_SEC = 1LLU << VTIME_PER_SEC_SHIFT, VTIME_PER_USEC = VTIME_PER_SEC / USEC_PER_SEC, VTIME_PER_NSEC = VTIME_PER_SEC / NSEC_PER_SEC, /* bound vrate adjustments within two orders of magnitude */ VRATE_MIN_PPM = 10000, /* 1% */ VRATE_MAX_PPM = 100000000, /* 10000% */ VRATE_MIN = VTIME_PER_USEC * VRATE_MIN_PPM / MILLION, VRATE_CLAMP_ADJ_PCT = 4, /* switch iff the conditions are met for longer than this */ AUTOP_CYCLE_NSEC = 10LLU * NSEC_PER_SEC, }; enum { /* if IOs end up waiting for requests, issue less */ RQ_WAIT_BUSY_PCT = 5, /* unbusy hysterisis */ UNBUSY_THR_PCT = 75, /* * The effect of delay is indirect and non-linear and a huge amount of * future debt can accumulate abruptly while unthrottled. Linearly scale * up delay as debt is going up and then let it decay exponentially. * This gives us quick ramp ups while delay is accumulating and long * tails which can help reducing the frequency of debt explosions on * unthrottle. The parameters are experimentally determined. * * The delay mechanism provides adequate protection and behavior in many * cases. However, this is far from ideal and falls shorts on both * fronts. The debtors are often throttled too harshly costing a * significant level of fairness and possibly total work while the * protection against their impacts on the system can be choppy and * unreliable. * * The shortcoming primarily stems from the fact that, unlike for page * cache, the kernel doesn't have well-defined back-pressure propagation * mechanism and policies for anonymous memory. Fully addressing this * issue will likely require substantial improvements in the area. */ MIN_DELAY_THR_PCT = 500, MAX_DELAY_THR_PCT = 25000, MIN_DELAY = 250, MAX_DELAY = 250 * USEC_PER_MSEC, /* halve debts if avg usage over 100ms is under 50% */ DFGV_USAGE_PCT = 50, DFGV_PERIOD = 100 * USEC_PER_MSEC, /* don't let cmds which take a very long time pin lagging for too long */ MAX_LAGGING_PERIODS = 10, /* * Count IO size in 4k pages. The 12bit shift helps keeping * size-proportional components of cost calculation in closer * numbers of digits to per-IO cost components. */ IOC_PAGE_SHIFT = 12, IOC_PAGE_SIZE = 1 << IOC_PAGE_SHIFT, IOC_SECT_TO_PAGE_SHIFT = IOC_PAGE_SHIFT - SECTOR_SHIFT, /* if apart further than 16M, consider randio for linear model */ LCOEF_RANDIO_PAGES = 4096, }; enum ioc_running { IOC_IDLE, IOC_RUNNING, IOC_STOP, }; /* io.cost.qos controls including per-dev enable of the whole controller */ enum { QOS_ENABLE, QOS_CTRL, NR_QOS_CTRL_PARAMS, }; /* io.cost.qos params */ enum { QOS_RPPM, QOS_RLAT, QOS_WPPM, QOS_WLAT, QOS_MIN, QOS_MAX, NR_QOS_PARAMS, }; /* io.cost.model controls */ enum { COST_CTRL, COST_MODEL, NR_COST_CTRL_PARAMS, }; /* builtin linear cost model coefficients */ enum { I_LCOEF_RBPS, I_LCOEF_RSEQIOPS, I_LCOEF_RRANDIOPS, I_LCOEF_WBPS, I_LCOEF_WSEQIOPS, I_LCOEF_WRANDIOPS, NR_I_LCOEFS, }; enum { LCOEF_RPAGE, LCOEF_RSEQIO, LCOEF_RRANDIO, LCOEF_WPAGE, LCOEF_WSEQIO, LCOEF_WRANDIO, NR_LCOEFS, }; enum { AUTOP_INVALID, AUTOP_HDD, AUTOP_SSD_QD1, AUTOP_SSD_DFL, AUTOP_SSD_FAST, }; struct ioc_params { u32 qos[NR_QOS_PARAMS]; u64 i_lcoefs[NR_I_LCOEFS]; u64 lcoefs[NR_LCOEFS]; u32 too_fast_vrate_pct; u32 too_slow_vrate_pct; }; struct ioc_margins { s64 min; s64 low; s64 target; }; struct ioc_missed { local_t nr_met; local_t nr_missed; u32 last_met; u32 last_missed; }; struct ioc_pcpu_stat { struct ioc_missed missed[2]; local64_t rq_wait_ns; u64 last_rq_wait_ns; }; /* per device */ struct ioc { struct rq_qos rqos; bool enabled; struct ioc_params params; struct ioc_margins margins; u32 period_us; u32 timer_slack_ns; u64 vrate_min; u64 vrate_max; spinlock_t lock; struct timer_list timer; struct list_head active_iocgs; /* active cgroups */ struct ioc_pcpu_stat __percpu *pcpu_stat; enum ioc_running running; atomic64_t vtime_rate; u64 vtime_base_rate; s64 vtime_err; seqcount_spinlock_t period_seqcount; u64 period_at; /* wallclock starttime */ u64 period_at_vtime; /* vtime starttime */ atomic64_t cur_period; /* inc'd each period */ int busy_level; /* saturation history */ bool weights_updated; atomic_t hweight_gen; /* for lazy hweights */ /* debt forgivness */ u64 dfgv_period_at; u64 dfgv_period_rem; u64 dfgv_usage_us_sum; u64 autop_too_fast_at; u64 autop_too_slow_at; int autop_idx; bool user_qos_params:1; bool user_cost_model:1; }; struct iocg_pcpu_stat { local64_t abs_vusage; }; struct iocg_stat { u64 usage_us; u64 wait_us; u64 indebt_us; u64 indelay_us; }; /* per device-cgroup pair */ struct ioc_gq { struct blkg_policy_data pd; struct ioc *ioc; /* * A iocg can get its weight from two sources - an explicit * per-device-cgroup configuration or the default weight of the * cgroup. `cfg_weight` is the explicit per-device-cgroup * configuration. `weight` is the effective considering both * sources. * * When an idle cgroup becomes active its `active` goes from 0 to * `weight`. `inuse` is the surplus adjusted active weight. * `active` and `inuse` are used to calculate `hweight_active` and * `hweight_inuse`. * * `last_inuse` remembers `inuse` while an iocg is idle to persist * surplus adjustments. * * `inuse` may be adjusted dynamically during period. `saved_*` are used * to determine and track adjustments. */ u32 cfg_weight; u32 weight; u32 active; u32 inuse; u32 last_inuse; s64 saved_margin; sector_t cursor; /* to detect randio */ /* * `vtime` is this iocg's vtime cursor which progresses as IOs are * issued. If lagging behind device vtime, the delta represents * the currently available IO budget. If running ahead, the * overage. * * `vtime_done` is the same but progressed on completion rather * than issue. The delta behind `vtime` represents the cost of * currently in-flight IOs. */ atomic64_t vtime; atomic64_t done_vtime; u64 abs_vdebt; /* current delay in effect and when it started */ u64 delay; u64 delay_at; /* * The period this iocg was last active in. Used for deactivation * and invalidating `vtime`. */ atomic64_t active_period; struct list_head active_list; /* see __propagate_weights() and current_hweight() for details */ u64 child_active_sum; u64 child_inuse_sum; u64 child_adjusted_sum; int hweight_gen; u32 hweight_active; u32 hweight_inuse; u32 hweight_donating; u32 hweight_after_donation; struct list_head walk_list; struct list_head surplus_list; struct wait_queue_head waitq; struct hrtimer waitq_timer; /* timestamp at the latest activation */ u64 activated_at; /* statistics */ struct iocg_pcpu_stat __percpu *pcpu_stat; struct iocg_stat stat; struct iocg_stat last_stat; u64 last_stat_abs_vusage; u64 usage_delta_us; u64 wait_since; u64 indebt_since; u64 indelay_since; /* this iocg's depth in the hierarchy and ancestors including self */ int level; struct ioc_gq *ancestors[]; }; /* per cgroup */ struct ioc_cgrp { struct blkcg_policy_data cpd; unsigned int dfl_weight; }; struct ioc_now { u64 now_ns; u64 now; u64 vnow; u64 vrate; }; struct iocg_wait { struct wait_queue_entry wait; struct bio *bio; u64 abs_cost; bool committed; }; struct iocg_wake_ctx { struct ioc_gq *iocg; u32 hw_inuse; s64 vbudget; }; static const struct ioc_params autop[] = { [AUTOP_HDD] = { .qos = { [QOS_RLAT] = 250000, /* 250ms */ [QOS_WLAT] = 250000, [QOS_MIN] = VRATE_MIN_PPM, [QOS_MAX] = VRATE_MAX_PPM, }, .i_lcoefs = { [I_LCOEF_RBPS] = 174019176, [I_LCOEF_RSEQIOPS] = 41708, [I_LCOEF_RRANDIOPS] = 370, [I_LCOEF_WBPS] = 178075866, [I_LCOEF_WSEQIOPS] = 42705, [I_LCOEF_WRANDIOPS] = 378, }, }, [AUTOP_SSD_QD1] = { .qos = { [QOS_RLAT] = 25000, /* 25ms */ [QOS_WLAT] = 25000, [QOS_MIN] = VRATE_MIN_PPM, [QOS_MAX] = VRATE_MAX_PPM, }, .i_lcoefs = { [I_LCOEF_RBPS] = 245855193, [I_LCOEF_RSEQIOPS] = 61575, [I_LCOEF_RRANDIOPS] = 6946, [I_LCOEF_WBPS] = 141365009, [I_LCOEF_WSEQIOPS] = 33716, [I_LCOEF_WRANDIOPS] = 26796, }, }, [AUTOP_SSD_DFL] = { .qos = { [QOS_RLAT] = 25000, /* 25ms */ [QOS_WLAT] = 25000, [QOS_MIN] = VRATE_MIN_PPM, [QOS_MAX] = VRATE_MAX_PPM, }, .i_lcoefs = { [I_LCOEF_RBPS] = 488636629, [I_LCOEF_RSEQIOPS] = 8932, [I_LCOEF_RRANDIOPS] = 8518, [I_LCOEF_WBPS] = 427891549, [I_LCOEF_WSEQIOPS] = 28755, [I_LCOEF_WRANDIOPS] = 21940, }, .too_fast_vrate_pct = 500, }, [AUTOP_SSD_FAST] = { .qos = { [QOS_RLAT] = 5000, /* 5ms */ [QOS_WLAT] = 5000, [QOS_MIN] = VRATE_MIN_PPM, [QOS_MAX] = VRATE_MAX_PPM, }, .i_lcoefs = { [I_LCOEF_RBPS] = 3102524156LLU, [I_LCOEF_RSEQIOPS] = 724816, [I_LCOEF_RRANDIOPS] = 778122, [I_LCOEF_WBPS] = 1742780862LLU, [I_LCOEF_WSEQIOPS] = 425702, [I_LCOEF_WRANDIOPS] = 443193, }, .too_slow_vrate_pct = 10, }, }; /* * vrate adjust percentages indexed by ioc->busy_level. We adjust up on * vtime credit shortage and down on device saturation. */ static u32 vrate_adj_pct[] = { 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 4, 4, 4, 4, 4, 4, 8, 8, 8, 8, 8, 8, 8, 8, 16 }; static struct blkcg_policy blkcg_policy_iocost; /* accessors and helpers */ static struct ioc *rqos_to_ioc(struct rq_qos *rqos) { return container_of(rqos, struct ioc, rqos); } static struct ioc *q_to_ioc(struct request_queue *q) { return rqos_to_ioc(rq_qos_id(q, RQ_QOS_COST)); } static const char __maybe_unused *ioc_name(struct ioc *ioc) { struct gendisk *disk = ioc->rqos.q->disk; if (!disk) return "<unknown>"; return disk->disk_name; } static struct ioc_gq *pd_to_iocg(struct blkg_policy_data *pd) { return pd ? container_of(pd, struct ioc_gq, pd) : NULL; } static struct ioc_gq *blkg_to_iocg(struct blkcg_gq *blkg) { return pd_to_iocg(blkg_to_pd(blkg, &blkcg_policy_iocost)); } static struct blkcg_gq *iocg_to_blkg(struct ioc_gq *iocg) { return pd_to_blkg(&iocg->pd); } static struct ioc_cgrp *blkcg_to_iocc(struct blkcg *blkcg) { return container_of(blkcg_to_cpd(blkcg, &blkcg_policy_iocost), struct ioc_cgrp, cpd); } /* * Scale @abs_cost to the inverse of @hw_inuse. The lower the hierarchical * weight, the more expensive each IO. Must round up. */ static u64 abs_cost_to_cost(u64 abs_cost, u32 hw_inuse) { return DIV64_U64_ROUND_UP(abs_cost * WEIGHT_ONE, hw_inuse); } /* * The inverse of abs_cost_to_cost(). Must round up. */ static u64 cost_to_abs_cost(u64 cost, u32 hw_inuse) { return DIV64_U64_ROUND_UP(cost * hw_inuse, WEIGHT_ONE); } static void iocg_commit_bio(struct ioc_gq *iocg, struct bio *bio, u64 abs_cost, u64 cost) { struct iocg_pcpu_stat *gcs; bio->bi_iocost_cost = cost; atomic64_add(cost, &iocg->vtime); gcs = get_cpu_ptr(iocg->pcpu_stat); local64_add(abs_cost, &gcs->abs_vusage); put_cpu_ptr(gcs); } static void iocg_lock(struct ioc_gq *iocg, bool lock_ioc, unsigned long *flags) { if (lock_ioc) { spin_lock_irqsave(&iocg->ioc->lock, *flags); spin_lock(&iocg->waitq.lock); } else { spin_lock_irqsave(&iocg->waitq.lock, *flags); } } static void iocg_unlock(struct ioc_gq *iocg, bool unlock_ioc, unsigned long *flags) { if (unlock_ioc) { spin_unlock(&iocg->waitq.lock); spin_unlock_irqrestore(&iocg->ioc->lock, *flags); } else { spin_unlock_irqrestore(&iocg->waitq.lock, *flags); } } #define CREATE_TRACE_POINTS #include <trace/events/iocost.h> static void ioc_refresh_margins(struct ioc *ioc) { struct ioc_margins *margins = &ioc->margins; u32 period_us = ioc->period_us; u64 vrate = ioc->vtime_base_rate; margins->min = (period_us * MARGIN_MIN_PCT / 100) * vrate; margins->low = (period_us * MARGIN_LOW_PCT / 100) * vrate; margins->target = (period_us * MARGIN_TARGET_PCT / 100) * vrate; } /* latency Qos params changed, update period_us and all the dependent params */ static void ioc_refresh_period_us(struct ioc *ioc) { u32 ppm, lat, multi, period_us; lockdep_assert_held(&ioc->lock); /* pick the higher latency target */ if (ioc->params.qos[QOS_RLAT] >= ioc->params.qos[QOS_WLAT]) { ppm = ioc->params.qos[QOS_RPPM]; lat = ioc->params.qos[QOS_RLAT]; } else { ppm = ioc->params.qos[QOS_WPPM]; lat = ioc->params.qos[QOS_WLAT]; } /* * We want the period to be long enough to contain a healthy number * of IOs while short enough for granular control. Define it as a * multiple of the latency target. Ideally, the multiplier should * be scaled according to the percentile so that it would nominally * contain a certain number of requests. Let's be simpler and * scale it linearly so that it's 2x >= pct(90) and 10x at pct(50). */ if (ppm) multi = max_t(u32, (MILLION - ppm) / 50000, 2); else multi = 2; period_us = multi * lat; period_us = clamp_t(u32, period_us, MIN_PERIOD, MAX_PERIOD); /* calculate dependent params */ ioc->period_us = period_us; ioc->timer_slack_ns = div64_u64( (u64)period_us * NSEC_PER_USEC * TIMER_SLACK_PCT, 100); ioc_refresh_margins(ioc); } static int ioc_autop_idx(struct ioc *ioc) { int idx = ioc->autop_idx; const struct ioc_params *p = &autop[idx]; u32 vrate_pct; u64 now_ns; /* rotational? */ if (!blk_queue_nonrot(ioc->rqos.q)) return AUTOP_HDD; /* handle SATA SSDs w/ broken NCQ */ if (blk_queue_depth(ioc->rqos.q) == 1) return AUTOP_SSD_QD1; /* use one of the normal ssd sets */ if (idx < AUTOP_SSD_DFL) return AUTOP_SSD_DFL; /* if user is overriding anything, maintain what was there */ if (ioc->user_qos_params || ioc->user_cost_model) return idx; /* step up/down based on the vrate */ vrate_pct = div64_u64(ioc->vtime_base_rate * 100, VTIME_PER_USEC); now_ns = ktime_get_ns(); if (p->too_fast_vrate_pct && p->too_fast_vrate_pct <= vrate_pct) { if (!ioc->autop_too_fast_at) ioc->autop_too_fast_at = now_ns; if (now_ns - ioc->autop_too_fast_at >= AUTOP_CYCLE_NSEC) return idx + 1; } else { ioc->autop_too_fast_at = 0; } if (p->too_slow_vrate_pct && p->too_slow_vrate_pct >= vrate_pct) { if (!ioc->autop_too_slow_at) ioc->autop_too_slow_at = now_ns; if (now_ns - ioc->autop_too_slow_at >= AUTOP_CYCLE_NSEC) return idx - 1; } else { ioc->autop_too_slow_at = 0; } return idx; } /* * Take the followings as input * * @bps maximum sequential throughput * @seqiops maximum sequential 4k iops * @randiops maximum random 4k iops * * and calculate the linear model cost coefficients. * * *@page per-page cost 1s / (@bps / 4096) * *@seqio base cost of a seq IO max((1s / @seqiops) - *@page, 0) * @randiops base cost of a rand IO max((1s / @randiops) - *@page, 0) */ static void calc_lcoefs(u64 bps, u64 seqiops, u64 randiops, u64 *page, u64 *seqio, u64 *randio) { u64 v; *page = *seqio = *randio = 0; if (bps) { u64 bps_pages = DIV_ROUND_UP_ULL(bps, IOC_PAGE_SIZE); if (bps_pages) *page = DIV64_U64_ROUND_UP(VTIME_PER_SEC, bps_pages); else *page = 1; } if (seqiops) { v = DIV64_U64_ROUND_UP(VTIME_PER_SEC, seqiops); if (v > *page) *seqio = v - *page; } if (randiops) { v = DIV64_U64_ROUND_UP(VTIME_PER_SEC, randiops); if (v > *page) *randio = v - *page; } } static void ioc_refresh_lcoefs(struct ioc *ioc) { u64 *u = ioc->params.i_lcoefs; u64 *c = ioc->params.lcoefs; calc_lcoefs(u[I_LCOEF_RBPS], u[I_LCOEF_RSEQIOPS], u[I_LCOEF_RRANDIOPS], &c[LCOEF_RPAGE], &c[LCOEF_RSEQIO], &c[LCOEF_RRANDIO]); calc_lcoefs(u[I_LCOEF_WBPS], u[I_LCOEF_WSEQIOPS], u[I_LCOEF_WRANDIOPS], &c[LCOEF_WPAGE], &c[LCOEF_WSEQIO], &c[LCOEF_WRANDIO]); } static bool ioc_refresh_params(struct ioc *ioc, bool force) { const struct ioc_params *p; int idx; lockdep_assert_held(&ioc->lock); idx = ioc_autop_idx(ioc); p = &autop[idx]; if (idx == ioc->autop_idx && !force) return false; if (idx != ioc->autop_idx) atomic64_set(&ioc->vtime_rate, VTIME_PER_USEC); ioc->autop_idx = idx; ioc->autop_too_fast_at = 0; ioc->autop_too_slow_at = 0; if (!ioc->user_qos_params) memcpy(ioc->params.qos, p->qos, sizeof(p->qos)); if (!ioc->user_cost_model) memcpy(ioc->params.i_lcoefs, p->i_lcoefs, sizeof(p->i_lcoefs)); ioc_refresh_period_us(ioc); ioc_refresh_lcoefs(ioc); ioc->vrate_min = DIV64_U64_ROUND_UP((u64)ioc->params.qos[QOS_MIN] * VTIME_PER_USEC, MILLION); ioc->vrate_max = div64_u64((u64)ioc->params.qos[QOS_MAX] * VTIME_PER_USEC, MILLION); return true; } /* * When an iocg accumulates too much vtime or gets deactivated, we throw away * some vtime, which lowers the overall device utilization. As the exact amount * which is being thrown away is known, we can compensate by accelerating the * vrate accordingly so that the extra vtime generated in the current period * matches what got lost. */ static void ioc_refresh_vrate(struct ioc *ioc, struct ioc_now *now) { s64 pleft = ioc->period_at + ioc->period_us - now->now; s64 vperiod = ioc->period_us * ioc->vtime_base_rate; s64 vcomp, vcomp_min, vcomp_max; lockdep_assert_held(&ioc->lock); /* we need some time left in this period */ if (pleft <= 0) goto done; /* * Calculate how much vrate should be adjusted to offset the error. * Limit the amount of adjustment and deduct the adjusted amount from * the error. */ vcomp = -div64_s64(ioc->vtime_err, pleft); vcomp_min = -(ioc->vtime_base_rate >> 1); vcomp_max = ioc->vtime_base_rate; vcomp = clamp(vcomp, vcomp_min, vcomp_max); ioc->vtime_err += vcomp * pleft; atomic64_set(&ioc->vtime_rate, ioc->vtime_base_rate + vcomp); done: /* bound how much error can accumulate */ ioc->vtime_err = clamp(ioc->vtime_err, -vperiod, vperiod); } static void ioc_adjust_base_vrate(struct ioc *ioc, u32 rq_wait_pct, int nr_lagging, int nr_shortages, int prev_busy_level, u32 *missed_ppm) { u64 vrate = ioc->vtime_base_rate; u64 vrate_min = ioc->vrate_min, vrate_max = ioc->vrate_max; if (!ioc->busy_level || (ioc->busy_level < 0 && nr_lagging)) { if (ioc->busy_level != prev_busy_level || nr_lagging) trace_iocost_ioc_vrate_adj(ioc, atomic64_read(&ioc->vtime_rate), missed_ppm, rq_wait_pct, nr_lagging, nr_shortages); return; } /* * If vrate is out of bounds, apply clamp gradually as the * bounds can change abruptly. Otherwise, apply busy_level * based adjustment. */ if (vrate < vrate_min) { vrate = div64_u64(vrate * (100 + VRATE_CLAMP_ADJ_PCT), 100); vrate = min(vrate, vrate_min); } else if (vrate > vrate_max) { vrate = div64_u64(vrate * (100 - VRATE_CLAMP_ADJ_PCT), 100); vrate = max(vrate, vrate_max); } else { int idx = min_t(int, abs(ioc->busy_level), ARRAY_SIZE(vrate_adj_pct) - 1); u32 adj_pct = vrate_adj_pct[idx]; if (ioc->busy_level > 0) adj_pct = 100 - adj_pct; else adj_pct = 100 + adj_pct; vrate = clamp(DIV64_U64_ROUND_UP(vrate * adj_pct, 100), vrate_min, vrate_max); } trace_iocost_ioc_vrate_adj(ioc, vrate, missed_ppm, rq_wait_pct, nr_lagging, nr_shortages); ioc->vtime_base_rate = vrate; ioc_refresh_margins(ioc); } /* take a snapshot of the current [v]time and vrate */ static void ioc_now(struct ioc *ioc, struct ioc_now *now) { unsigned seq; now->now_ns = ktime_get(); now->now = ktime_to_us(now->now_ns); now->vrate = atomic64_read(&ioc->vtime_rate); /* * The current vtime is * * vtime at period start + (wallclock time since the start) * vrate * * As a consistent snapshot of `period_at_vtime` and `period_at` is * needed, they're seqcount protected. */ do { seq = read_seqcount_begin(&ioc->period_seqcount); now->vnow = ioc->period_at_vtime + (now->now - ioc->period_at) * now->vrate; } while (read_seqcount_retry(&ioc->period_seqcount, seq)); } static void ioc_start_period(struct ioc *ioc, struct ioc_now *now) { WARN_ON_ONCE(ioc->running != IOC_RUNNING); write_seqcount_begin(&ioc->period_seqcount); ioc->period_at = now->now; ioc->period_at_vtime = now->vnow; write_seqcount_end(&ioc->period_seqcount); ioc->timer.expires = jiffies + usecs_to_jiffies(ioc->period_us); add_timer(&ioc->timer); } /* * Update @iocg's `active` and `inuse` to @active and @inuse, update level * weight sums and propagate upwards accordingly. If @save, the current margin * is saved to be used as reference for later inuse in-period adjustments. */ static void __propagate_weights(struct ioc_gq *iocg, u32 active, u32 inuse, bool save, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; int lvl; lockdep_assert_held(&ioc->lock); /* * For an active leaf node, its inuse shouldn't be zero or exceed * @active. An active internal node's inuse is solely determined by the * inuse to active ratio of its children regardless of @inuse. */ if (list_empty(&iocg->active_list) && iocg->child_active_sum) { inuse = DIV64_U64_ROUND_UP(active * iocg->child_inuse_sum, iocg->child_active_sum); } else { /* * It may be tempting to turn this into a clamp expression with * a lower limit of 1 but active may be 0, which cannot be used * as an upper limit in that situation. This expression allows * active to clamp inuse unless it is 0, in which case inuse * becomes 1. */ inuse = min(inuse, active) ?: 1; } iocg->last_inuse = iocg->inuse; if (save) iocg->saved_margin = now->vnow - atomic64_read(&iocg->vtime); if (active == iocg->active && inuse == iocg->inuse) return; for (lvl = iocg->level - 1; lvl >= 0; lvl--) { struct ioc_gq *parent = iocg->ancestors[lvl]; struct ioc_gq *child = iocg->ancestors[lvl + 1]; u32 parent_active = 0, parent_inuse = 0; /* update the level sums */ parent->child_active_sum += (s32)(active - child->active); parent->child_inuse_sum += (s32)(inuse - child->inuse); /* apply the updates */ child->active = active; child->inuse = inuse; /* * The delta between inuse and active sums indicates that * much of weight is being given away. Parent's inuse * and active should reflect the ratio. */ if (parent->child_active_sum) { parent_active = parent->weight; parent_inuse = DIV64_U64_ROUND_UP( parent_active * parent->child_inuse_sum, parent->child_active_sum); } /* do we need to keep walking up? */ if (parent_active == parent->active && parent_inuse == parent->inuse) break; active = parent_active; inuse = parent_inuse; } ioc->weights_updated = true; } static void commit_weights(struct ioc *ioc) { lockdep_assert_held(&ioc->lock); if (ioc->weights_updated) { /* paired with rmb in current_hweight(), see there */ smp_wmb(); atomic_inc(&ioc->hweight_gen); ioc->weights_updated = false; } } static void propagate_weights(struct ioc_gq *iocg, u32 active, u32 inuse, bool save, struct ioc_now *now) { __propagate_weights(iocg, active, inuse, save, now); commit_weights(iocg->ioc); } static void current_hweight(struct ioc_gq *iocg, u32 *hw_activep, u32 *hw_inusep) { struct ioc *ioc = iocg->ioc; int lvl; u32 hwa, hwi; int ioc_gen; /* hot path - if uptodate, use cached */ ioc_gen = atomic_read(&ioc->hweight_gen); if (ioc_gen == iocg->hweight_gen) goto out; /* * Paired with wmb in commit_weights(). If we saw the updated * hweight_gen, all the weight updates from __propagate_weights() are * visible too. * * We can race with weight updates during calculation and get it * wrong. However, hweight_gen would have changed and a future * reader will recalculate and we're guaranteed to discard the * wrong result soon. */ smp_rmb(); hwa = hwi = WEIGHT_ONE; for (lvl = 0; lvl <= iocg->level - 1; lvl++) { struct ioc_gq *parent = iocg->ancestors[lvl]; struct ioc_gq *child = iocg->ancestors[lvl + 1]; u64 active_sum = READ_ONCE(parent->child_active_sum); u64 inuse_sum = READ_ONCE(parent->child_inuse_sum); u32 active = READ_ONCE(child->active); u32 inuse = READ_ONCE(child->inuse); /* we can race with deactivations and either may read as zero */ if (!active_sum || !inuse_sum) continue; active_sum = max_t(u64, active, active_sum); hwa = div64_u64((u64)hwa * active, active_sum); inuse_sum = max_t(u64, inuse, inuse_sum); hwi = div64_u64((u64)hwi * inuse, inuse_sum); } iocg->hweight_active = max_t(u32, hwa, 1); iocg->hweight_inuse = max_t(u32, hwi, 1); iocg->hweight_gen = ioc_gen; out: if (hw_activep) *hw_activep = iocg->hweight_active; if (hw_inusep) *hw_inusep = iocg->hweight_inuse; } /* * Calculate the hweight_inuse @iocg would get with max @inuse assuming all the * other weights stay unchanged. */ static u32 current_hweight_max(struct ioc_gq *iocg) { u32 hwm = WEIGHT_ONE; u32 inuse = iocg->active; u64 child_inuse_sum; int lvl; lockdep_assert_held(&iocg->ioc->lock); for (lvl = iocg->level - 1; lvl >= 0; lvl--) { struct ioc_gq *parent = iocg->ancestors[lvl]; struct ioc_gq *child = iocg->ancestors[lvl + 1]; child_inuse_sum = parent->child_inuse_sum + inuse - child->inuse; hwm = div64_u64((u64)hwm * inuse, child_inuse_sum); inuse = DIV64_U64_ROUND_UP(parent->active * child_inuse_sum, parent->child_active_sum); } return max_t(u32, hwm, 1); } static void weight_updated(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; struct blkcg_gq *blkg = iocg_to_blkg(iocg); struct ioc_cgrp *iocc = blkcg_to_iocc(blkg->blkcg); u32 weight; lockdep_assert_held(&ioc->lock); weight = iocg->cfg_weight ?: iocc->dfl_weight; if (weight != iocg->weight && iocg->active) propagate_weights(iocg, weight, iocg->inuse, true, now); iocg->weight = weight; } static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; u64 last_period, cur_period; u64 vtime, vtarget; int i; /* * If seem to be already active, just update the stamp to tell the * timer that we're still active. We don't mind occassional races. */ if (!list_empty(&iocg->active_list)) { ioc_now(ioc, now); cur_period = atomic64_read(&ioc->cur_period); if (atomic64_read(&iocg->active_period) != cur_period) atomic64_set(&iocg->active_period, cur_period); return true; } /* racy check on internal node IOs, treat as root level IOs */ if (iocg->child_active_sum) return false; spin_lock_irq(&ioc->lock); ioc_now(ioc, now); /* update period */ cur_period = atomic64_read(&ioc->cur_period); last_period = atomic64_read(&iocg->active_period); atomic64_set(&iocg->active_period, cur_period); /* already activated or breaking leaf-only constraint? */ if (!list_empty(&iocg->active_list)) goto succeed_unlock; for (i = iocg->level - 1; i > 0; i--) if (!list_empty(&iocg->ancestors[i]->active_list)) goto fail_unlock; if (iocg->child_active_sum) goto fail_unlock; /* * Always start with the target budget. On deactivation, we throw away * anything above it. */ vtarget = now->vnow - ioc->margins.target; vtime = atomic64_read(&iocg->vtime); atomic64_add(vtarget - vtime, &iocg->vtime); atomic64_add(vtarget - vtime, &iocg->done_vtime); vtime = vtarget; /* * Activate, propagate weight and start period timer if not * running. Reset hweight_gen to avoid accidental match from * wrapping. */ iocg->hweight_gen = atomic_read(&ioc->hweight_gen) - 1; list_add(&iocg->active_list, &ioc->active_iocgs); propagate_weights(iocg, iocg->weight, iocg->last_inuse ?: iocg->weight, true, now); TRACE_IOCG_PATH(iocg_activate, iocg, now, last_period, cur_period, vtime); iocg->activated_at = now->now; if (ioc->running == IOC_IDLE) { ioc->running = IOC_RUNNING; ioc->dfgv_period_at = now->now; ioc->dfgv_period_rem = 0; ioc_start_period(ioc, now); } succeed_unlock: spin_unlock_irq(&ioc->lock); return true; fail_unlock: spin_unlock_irq(&ioc->lock); return false; } static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; struct blkcg_gq *blkg = iocg_to_blkg(iocg); u64 tdelta, delay, new_delay, shift; s64 vover, vover_pct; u32 hwa; lockdep_assert_held(&iocg->waitq.lock); /* * If the delay is set by another CPU, we may be in the past. No need to * change anything if so. This avoids decay calculation underflow. */ if (time_before64(now->now, iocg->delay_at)) return false; /* calculate the current delay in effect - 1/2 every second */ tdelta = now->now - iocg->delay_at; shift = div64_u64(tdelta, USEC_PER_SEC); if (iocg->delay && shift < BITS_PER_LONG) delay = iocg->delay >> shift; else delay = 0; /* calculate the new delay from the debt amount */ current_hweight(iocg, &hwa, NULL); vover = atomic64_read(&iocg->vtime) + abs_cost_to_cost(iocg->abs_vdebt, hwa) - now->vnow; vover_pct = div64_s64(100 * vover, ioc->period_us * ioc->vtime_base_rate); if (vover_pct <= MIN_DELAY_THR_PCT) new_delay = 0; else if (vover_pct >= MAX_DELAY_THR_PCT) new_delay = MAX_DELAY; else new_delay = MIN_DELAY + div_u64((MAX_DELAY - MIN_DELAY) * (vover_pct - MIN_DELAY_THR_PCT), MAX_DELAY_THR_PCT - MIN_DELAY_THR_PCT); /* pick the higher one and apply */ if (new_delay > delay) { iocg->delay = new_delay; iocg->delay_at = now->now; delay = new_delay; } if (delay >= MIN_DELAY) { if (!iocg->indelay_since) iocg->indelay_since = now->now; blkcg_set_delay(blkg, delay * NSEC_PER_USEC); return true; } else { if (iocg->indelay_since) { iocg->stat.indelay_us += now->now - iocg->indelay_since; iocg->indelay_since = 0; } iocg->delay = 0; blkcg_clear_delay(blkg); return false; } } static void iocg_incur_debt(struct ioc_gq *iocg, u64 abs_cost, struct ioc_now *now) { struct iocg_pcpu_stat *gcs; lockdep_assert_held(&iocg->ioc->lock); lockdep_assert_held(&iocg->waitq.lock); WARN_ON_ONCE(list_empty(&iocg->active_list)); /* * Once in debt, debt handling owns inuse. @iocg stays at the minimum * inuse donating all of it share to others until its debt is paid off. */ if (!iocg->abs_vdebt && abs_cost) { iocg->indebt_since = now->now; propagate_weights(iocg, iocg->active, 0, false, now); } iocg->abs_vdebt += abs_cost; gcs = get_cpu_ptr(iocg->pcpu_stat); local64_add(abs_cost, &gcs->abs_vusage); put_cpu_ptr(gcs); } static void iocg_pay_debt(struct ioc_gq *iocg, u64 abs_vpay, struct ioc_now *now) { lockdep_assert_held(&iocg->ioc->lock); lockdep_assert_held(&iocg->waitq.lock); /* make sure that nobody messed with @iocg */ WARN_ON_ONCE(list_empty(&iocg->active_list)); WARN_ON_ONCE(iocg->inuse > 1); iocg->abs_vdebt -= min(abs_vpay, iocg->abs_vdebt); /* if debt is paid in full, restore inuse */ if (!iocg->abs_vdebt) { iocg->stat.indebt_us += now->now - iocg->indebt_since; iocg->indebt_since = 0; propagate_weights(iocg, iocg->active, iocg->last_inuse, false, now); } } static int iocg_wake_fn(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key) { struct iocg_wait *wait = container_of(wq_entry, struct iocg_wait, wait); struct iocg_wake_ctx *ctx = key; u64 cost = abs_cost_to_cost(wait->abs_cost, ctx->hw_inuse); ctx->vbudget -= cost; if (ctx->vbudget < 0) return -1; iocg_commit_bio(ctx->iocg, wait->bio, wait->abs_cost, cost); wait->committed = true; /* * autoremove_wake_function() removes the wait entry only when it * actually changed the task state. We want the wait always removed. * Remove explicitly and use default_wake_function(). Note that the * order of operations is important as finish_wait() tests whether * @wq_entry is removed without grabbing the lock. */ default_wake_function(wq_entry, mode, flags, key); list_del_init_careful(&wq_entry->entry); return 0; } /* * Calculate the accumulated budget, pay debt if @pay_debt and wake up waiters * accordingly. When @pay_debt is %true, the caller must be holding ioc->lock in * addition to iocg->waitq.lock. */ static void iocg_kick_waitq(struct ioc_gq *iocg, bool pay_debt, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; struct iocg_wake_ctx ctx = { .iocg = iocg }; u64 vshortage, expires, oexpires; s64 vbudget; u32 hwa; lockdep_assert_held(&iocg->waitq.lock); current_hweight(iocg, &hwa, NULL); vbudget = now->vnow - atomic64_read(&iocg->vtime); /* pay off debt */ if (pay_debt && iocg->abs_vdebt && vbudget > 0) { u64 abs_vbudget = cost_to_abs_cost(vbudget, hwa); u64 abs_vpay = min_t(u64, abs_vbudget, iocg->abs_vdebt); u64 vpay = abs_cost_to_cost(abs_vpay, hwa); lockdep_assert_held(&ioc->lock); atomic64_add(vpay, &iocg->vtime); atomic64_add(vpay, &iocg->done_vtime); iocg_pay_debt(iocg, abs_vpay, now); vbudget -= vpay; } if (iocg->abs_vdebt || iocg->delay) iocg_kick_delay(iocg, now); /* * Debt can still be outstanding if we haven't paid all yet or the * caller raced and called without @pay_debt. Shouldn't wake up waiters * under debt. Make sure @vbudget reflects the outstanding amount and is * not positive. */ if (iocg->abs_vdebt) { s64 vdebt = abs_cost_to_cost(iocg->abs_vdebt, hwa); vbudget = min_t(s64, 0, vbudget - vdebt); } /* * Wake up the ones which are due and see how much vtime we'll need for * the next one. As paying off debt restores hw_inuse, it must be read * after the above debt payment. */ ctx.vbudget = vbudget; current_hweight(iocg, NULL, &ctx.hw_inuse); __wake_up_locked_key(&iocg->waitq, TASK_NORMAL, &ctx); if (!waitqueue_active(&iocg->waitq)) { if (iocg->wait_since) { iocg->stat.wait_us += now->now - iocg->wait_since; iocg->wait_since = 0; } return; } if (!iocg->wait_since) iocg->wait_since = now->now; if (WARN_ON_ONCE(ctx.vbudget >= 0)) return; /* determine next wakeup, add a timer margin to guarantee chunking */ vshortage = -ctx.vbudget; expires = now->now_ns + DIV64_U64_ROUND_UP(vshortage, ioc->vtime_base_rate) * NSEC_PER_USEC; expires += ioc->timer_slack_ns; /* if already active and close enough, don't bother */ oexpires = ktime_to_ns(hrtimer_get_softexpires(&iocg->waitq_timer)); if (hrtimer_is_queued(&iocg->waitq_timer) && abs(oexpires - expires) <= ioc->timer_slack_ns) return; hrtimer_start_range_ns(&iocg->waitq_timer, ns_to_ktime(expires), ioc->timer_slack_ns, HRTIMER_MODE_ABS); } static enum hrtimer_restart iocg_waitq_timer_fn(struct hrtimer *timer) { struct ioc_gq *iocg = container_of(timer, struct ioc_gq, waitq_timer); bool pay_debt = READ_ONCE(iocg->abs_vdebt); struct ioc_now now; unsigned long flags; ioc_now(iocg->ioc, &now); iocg_lock(iocg, pay_debt, &flags); iocg_kick_waitq(iocg, pay_debt, &now); iocg_unlock(iocg, pay_debt, &flags); return HRTIMER_NORESTART; } static void ioc_lat_stat(struct ioc *ioc, u32 *missed_ppm_ar, u32 *rq_wait_pct_p) { u32 nr_met[2] = { }; u32 nr_missed[2] = { }; u64 rq_wait_ns = 0; int cpu, rw; for_each_online_cpu(cpu) { struct ioc_pcpu_stat *stat = per_cpu_ptr(ioc->pcpu_stat, cpu); u64 this_rq_wait_ns; for (rw = READ; rw <= WRITE; rw++) { u32 this_met = local_read(&stat->missed[rw].nr_met); u32 this_missed = local_read(&stat->missed[rw].nr_missed); nr_met[rw] += this_met - stat->missed[rw].last_met; nr_missed[rw] += this_missed - stat->missed[rw].last_missed; stat->missed[rw].last_met = this_met; stat->missed[rw].last_missed = this_missed; } this_rq_wait_ns = local64_read(&stat->rq_wait_ns); rq_wait_ns += this_rq_wait_ns - stat->last_rq_wait_ns; stat->last_rq_wait_ns = this_rq_wait_ns; } for (rw = READ; rw <= WRITE; rw++) { if (nr_met[rw] + nr_missed[rw]) missed_ppm_ar[rw] = DIV64_U64_ROUND_UP((u64)nr_missed[rw] * MILLION, nr_met[rw] + nr_missed[rw]); else missed_ppm_ar[rw] = 0; } *rq_wait_pct_p = div64_u64(rq_wait_ns * 100, ioc->period_us * NSEC_PER_USEC); } /* was iocg idle this period? */ static bool iocg_is_idle(struct ioc_gq *iocg) { struct ioc *ioc = iocg->ioc; /* did something get issued this period? */ if (atomic64_read(&iocg->active_period) == atomic64_read(&ioc->cur_period)) return false; /* is something in flight? */ if (atomic64_read(&iocg->done_vtime) != atomic64_read(&iocg->vtime)) return false; return true; } /* * Call this function on the target leaf @iocg's to build pre-order traversal * list of all the ancestors in @inner_walk. The inner nodes are linked through * ->walk_list and the caller is responsible for dissolving the list after use. */ static void iocg_build_inner_walk(struct ioc_gq *iocg, struct list_head *inner_walk) { int lvl; WARN_ON_ONCE(!list_empty(&iocg->walk_list)); /* find the first ancestor which hasn't been visited yet */ for (lvl = iocg->level - 1; lvl >= 0; lvl--) { if (!list_empty(&iocg->ancestors[lvl]->walk_list)) break; } /* walk down and visit the inner nodes to get pre-order traversal */ while (++lvl <= iocg->level - 1) { struct ioc_gq *inner = iocg->ancestors[lvl]; /* record traversal order */ list_add_tail(&inner->walk_list, inner_walk); } } /* propagate the deltas to the parent */ static void iocg_flush_stat_upward(struct ioc_gq *iocg) { if (iocg->level > 0) { struct iocg_stat *parent_stat = &iocg->ancestors[iocg->level - 1]->stat; parent_stat->usage_us += iocg->stat.usage_us - iocg->last_stat.usage_us; parent_stat->wait_us += iocg->stat.wait_us - iocg->last_stat.wait_us; parent_stat->indebt_us += iocg->stat.indebt_us - iocg->last_stat.indebt_us; parent_stat->indelay_us += iocg->stat.indelay_us - iocg->last_stat.indelay_us; } iocg->last_stat = iocg->stat; } /* collect per-cpu counters and propagate the deltas to the parent */ static void iocg_flush_stat_leaf(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; u64 abs_vusage = 0; u64 vusage_delta; int cpu; lockdep_assert_held(&iocg->ioc->lock); /* collect per-cpu counters */ for_each_possible_cpu(cpu) { abs_vusage += local64_read( per_cpu_ptr(&iocg->pcpu_stat->abs_vusage, cpu)); } vusage_delta = abs_vusage - iocg->last_stat_abs_vusage; iocg->last_stat_abs_vusage = abs_vusage; iocg->usage_delta_us = div64_u64(vusage_delta, ioc->vtime_base_rate); iocg->stat.usage_us += iocg->usage_delta_us; iocg_flush_stat_upward(iocg); } /* get stat counters ready for reading on all active iocgs */ static void iocg_flush_stat(struct list_head *target_iocgs, struct ioc_now *now) { LIST_HEAD(inner_walk); struct ioc_gq *iocg, *tiocg; /* flush leaves and build inner node walk list */ list_for_each_entry(iocg, target_iocgs, active_list) { iocg_flush_stat_leaf(iocg, now); iocg_build_inner_walk(iocg, &inner_walk); } /* keep flushing upwards by walking the inner list backwards */ list_for_each_entry_safe_reverse(iocg, tiocg, &inner_walk, walk_list) { iocg_flush_stat_upward(iocg); list_del_init(&iocg->walk_list); } } /* * Determine what @iocg's hweight_inuse should be after donating unused * capacity. @hwm is the upper bound and used to signal no donation. This * function also throws away @iocg's excess budget. */ static u32 hweight_after_donation(struct ioc_gq *iocg, u32 old_hwi, u32 hwm, u32 usage, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; u64 vtime = atomic64_read(&iocg->vtime); s64 excess, delta, target, new_hwi; /* debt handling owns inuse for debtors */ if (iocg->abs_vdebt) return 1; /* see whether minimum margin requirement is met */ if (waitqueue_active(&iocg->waitq) || time_after64(vtime, now->vnow - ioc->margins.min)) return hwm; /* throw away excess above target */ excess = now->vnow - vtime - ioc->margins.target; if (excess > 0) { atomic64_add(excess, &iocg->vtime); atomic64_add(excess, &iocg->done_vtime); vtime += excess; ioc->vtime_err -= div64_u64(excess * old_hwi, WEIGHT_ONE); } /* * Let's say the distance between iocg's and device's vtimes as a * fraction of period duration is delta. Assuming that the iocg will * consume the usage determined above, we want to determine new_hwi so * that delta equals MARGIN_TARGET at the end of the next period. * * We need to execute usage worth of IOs while spending the sum of the * new budget (1 - MARGIN_TARGET) and the leftover from the last period * (delta): * * usage = (1 - MARGIN_TARGET + delta) * new_hwi * * Therefore, the new_hwi is: * * new_hwi = usage / (1 - MARGIN_TARGET + delta) */ delta = div64_s64(WEIGHT_ONE * (now->vnow - vtime), now->vnow - ioc->period_at_vtime); target = WEIGHT_ONE * MARGIN_TARGET_PCT / 100; new_hwi = div64_s64(WEIGHT_ONE * usage, WEIGHT_ONE - target + delta); return clamp_t(s64, new_hwi, 1, hwm); } /* * For work-conservation, an iocg which isn't using all of its share should * donate the leftover to other iocgs. There are two ways to achieve this - 1. * bumping up vrate accordingly 2. lowering the donating iocg's inuse weight. * * #1 is mathematically simpler but has the drawback of requiring synchronous * global hweight_inuse updates when idle iocg's get activated or inuse weights * change due to donation snapbacks as it has the possibility of grossly * overshooting what's allowed by the model and vrate. * * #2 is inherently safe with local operations. The donating iocg can easily * snap back to higher weights when needed without worrying about impacts on * other nodes as the impacts will be inherently correct. This also makes idle * iocg activations safe. The only effect activations have is decreasing * hweight_inuse of others, the right solution to which is for those iocgs to * snap back to higher weights. * * So, we go with #2. The challenge is calculating how each donating iocg's * inuse should be adjusted to achieve the target donation amounts. This is done * using Andy's method described in the following pdf. * * https://drive.google.com/file/d/1PsJwxPFtjUnwOY1QJ5AeICCcsL7BM3bo * * Given the weights and target after-donation hweight_inuse values, Andy's * method determines how the proportional distribution should look like at each * sibling level to maintain the relative relationship between all non-donating * pairs. To roughly summarize, it divides the tree into donating and * non-donating parts, calculates global donation rate which is used to * determine the target hweight_inuse for each node, and then derives per-level * proportions. * * The following pdf shows that global distribution calculated this way can be * achieved by scaling inuse weights of donating leaves and propagating the * adjustments upwards proportionally. * * https://drive.google.com/file/d/1vONz1-fzVO7oY5DXXsLjSxEtYYQbOvsE * * Combining the above two, we can determine how each leaf iocg's inuse should * be adjusted to achieve the target donation. * * https://drive.google.com/file/d/1WcrltBOSPN0qXVdBgnKm4mdp9FhuEFQN * * The inline comments use symbols from the last pdf. * * b is the sum of the absolute budgets in the subtree. 1 for the root node. * f is the sum of the absolute budgets of non-donating nodes in the subtree. * t is the sum of the absolute budgets of donating nodes in the subtree. * w is the weight of the node. w = w_f + w_t * w_f is the non-donating portion of w. w_f = w * f / b * w_b is the donating portion of w. w_t = w * t / b * s is the sum of all sibling weights. s = Sum(w) for siblings * s_f and s_t are the non-donating and donating portions of s. * * Subscript p denotes the parent's counterpart and ' the adjusted value - e.g. * w_pt is the donating portion of the parent's weight and w'_pt the same value * after adjustments. Subscript r denotes the root node's values. */ static void transfer_surpluses(struct list_head *surpluses, struct ioc_now *now) { LIST_HEAD(over_hwa); LIST_HEAD(inner_walk); struct ioc_gq *iocg, *tiocg, *root_iocg; u32 after_sum, over_sum, over_target, gamma; /* * It's pretty unlikely but possible for the total sum of * hweight_after_donation's to be higher than WEIGHT_ONE, which will * confuse the following calculations. If such condition is detected, * scale down everyone over its full share equally to keep the sum below * WEIGHT_ONE. */ after_sum = 0; over_sum = 0; list_for_each_entry(iocg, surpluses, surplus_list) { u32 hwa; current_hweight(iocg, &hwa, NULL); after_sum += iocg->hweight_after_donation; if (iocg->hweight_after_donation > hwa) { over_sum += iocg->hweight_after_donation; list_add(&iocg->walk_list, &over_hwa); } } if (after_sum >= WEIGHT_ONE) { /* * The delta should be deducted from the over_sum, calculate * target over_sum value. */ u32 over_delta = after_sum - (WEIGHT_ONE - 1); WARN_ON_ONCE(over_sum <= over_delta); over_target = over_sum - over_delta; } else { over_target = 0; } list_for_each_entry_safe(iocg, tiocg, &over_hwa, walk_list) { if (over_target) iocg->hweight_after_donation = div_u64((u64)iocg->hweight_after_donation * over_target, over_sum); list_del_init(&iocg->walk_list); } /* * Build pre-order inner node walk list and prepare for donation * adjustment calculations. */ list_for_each_entry(iocg, surpluses, surplus_list) { iocg_build_inner_walk(iocg, &inner_walk); } root_iocg = list_first_entry(&inner_walk, struct ioc_gq, walk_list); WARN_ON_ONCE(root_iocg->level > 0); list_for_each_entry(iocg, &inner_walk, walk_list) { iocg->child_adjusted_sum = 0; iocg->hweight_donating = 0; iocg->hweight_after_donation = 0; } /* * Propagate the donating budget (b_t) and after donation budget (b'_t) * up the hierarchy. */ list_for_each_entry(iocg, surpluses, surplus_list) { struct ioc_gq *parent = iocg->ancestors[iocg->level - 1]; parent->hweight_donating += iocg->hweight_donating; parent->hweight_after_donation += iocg->hweight_after_donation; } list_for_each_entry_reverse(iocg, &inner_walk, walk_list) { if (iocg->level > 0) { struct ioc_gq *parent = iocg->ancestors[iocg->level - 1]; parent->hweight_donating += iocg->hweight_donating; parent->hweight_after_donation += iocg->hweight_after_donation; } } /* * Calculate inner hwa's (b) and make sure the donation values are * within the accepted ranges as we're doing low res calculations with * roundups. */ list_for_each_entry(iocg, &inner_walk, walk_list) { if (iocg->level) { struct ioc_gq *parent = iocg->ancestors[iocg->level - 1]; iocg->hweight_active = DIV64_U64_ROUND_UP( (u64)parent->hweight_active * iocg->active, parent->child_active_sum); } iocg->hweight_donating = min(iocg->hweight_donating, iocg->hweight_active); iocg->hweight_after_donation = min(iocg->hweight_after_donation, iocg->hweight_donating - 1); if (WARN_ON_ONCE(iocg->hweight_active <= 1 || iocg->hweight_donating <= 1 || iocg->hweight_after_donation == 0)) { pr_warn("iocg: invalid donation weights in "); pr_cont_cgroup_path(iocg_to_blkg(iocg)->blkcg->css.cgroup); pr_cont(": active=%u donating=%u after=%u\n", iocg->hweight_active, iocg->hweight_donating, iocg->hweight_after_donation); } } /* * Calculate the global donation rate (gamma) - the rate to adjust * non-donating budgets by. * * No need to use 64bit multiplication here as the first operand is * guaranteed to be smaller than WEIGHT_ONE (1<<16). * * We know that there are beneficiary nodes and the sum of the donating * hweights can't be whole; however, due to the round-ups during hweight * calculations, root_iocg->hweight_donating might still end up equal to * or greater than whole. Limit the range when calculating the divider. * * gamma = (1 - t_r') / (1 - t_r) */ gamma = DIV_ROUND_UP( (WEIGHT_ONE - root_iocg->hweight_after_donation) * WEIGHT_ONE, WEIGHT_ONE - min_t(u32, root_iocg->hweight_donating, WEIGHT_ONE - 1)); /* * Calculate adjusted hwi, child_adjusted_sum and inuse for the inner * nodes. */ list_for_each_entry(iocg, &inner_walk, walk_list) { struct ioc_gq *parent; u32 inuse, wpt, wptp; u64 st, sf; if (iocg->level == 0) { /* adjusted weight sum for 1st level: s' = s * b_pf / b'_pf */ iocg->child_adjusted_sum = DIV64_U64_ROUND_UP( iocg->child_active_sum * (WEIGHT_ONE - iocg->hweight_donating), WEIGHT_ONE - iocg->hweight_after_donation); continue; } parent = iocg->ancestors[iocg->level - 1]; /* b' = gamma * b_f + b_t' */ iocg->hweight_inuse = DIV64_U64_ROUND_UP( (u64)gamma * (iocg->hweight_active - iocg->hweight_donating), WEIGHT_ONE) + iocg->hweight_after_donation; /* w' = s' * b' / b'_p */ inuse = DIV64_U64_ROUND_UP( (u64)parent->child_adjusted_sum * iocg->hweight_inuse, parent->hweight_inuse); /* adjusted weight sum for children: s' = s_f + s_t * w'_pt / w_pt */ st = DIV64_U64_ROUND_UP( iocg->child_active_sum * iocg->hweight_donating, iocg->hweight_active); sf = iocg->child_active_sum - st; wpt = DIV64_U64_ROUND_UP( (u64)iocg->active * iocg->hweight_donating, iocg->hweight_active); wptp = DIV64_U64_ROUND_UP( (u64)inuse * iocg->hweight_after_donation, iocg->hweight_inuse); iocg->child_adjusted_sum = sf + DIV64_U64_ROUND_UP(st * wptp, wpt); } /* * All inner nodes now have ->hweight_inuse and ->child_adjusted_sum and * we can finally determine leaf adjustments. */ list_for_each_entry(iocg, surpluses, surplus_list) { struct ioc_gq *parent = iocg->ancestors[iocg->level - 1]; u32 inuse; /* * In-debt iocgs participated in the donation calculation with * the minimum target hweight_inuse. Configuring inuse * accordingly would work fine but debt handling expects * @iocg->inuse stay at the minimum and we don't wanna * interfere. */ if (iocg->abs_vdebt) { WARN_ON_ONCE(iocg->inuse > 1); continue; } /* w' = s' * b' / b'_p, note that b' == b'_t for donating leaves */ inuse = DIV64_U64_ROUND_UP( parent->child_adjusted_sum * iocg->hweight_after_donation, parent->hweight_inuse); TRACE_IOCG_PATH(inuse_transfer, iocg, now, iocg->inuse, inuse, iocg->hweight_inuse, iocg->hweight_after_donation); __propagate_weights(iocg, iocg->active, inuse, true, now); } /* walk list should be dissolved after use */ list_for_each_entry_safe(iocg, tiocg, &inner_walk, walk_list) list_del_init(&iocg->walk_list); } /* * A low weight iocg can amass a large amount of debt, for example, when * anonymous memory gets reclaimed aggressively. If the system has a lot of * memory paired with a slow IO device, the debt can span multiple seconds or * more. If there are no other subsequent IO issuers, the in-debt iocg may end * up blocked paying its debt while the IO device is idle. * * The following protects against such cases. If the device has been * sufficiently idle for a while, the debts are halved and delays are * recalculated. */ static void ioc_forgive_debts(struct ioc *ioc, u64 usage_us_sum, int nr_debtors, struct ioc_now *now) { struct ioc_gq *iocg; u64 dur, usage_pct, nr_cycles, nr_cycles_shift; /* if no debtor, reset the cycle */ if (!nr_debtors) { ioc->dfgv_period_at = now->now; ioc->dfgv_period_rem = 0; ioc->dfgv_usage_us_sum = 0; return; } /* * Debtors can pass through a lot of writes choking the device and we * don't want to be forgiving debts while the device is struggling from * write bursts. If we're missing latency targets, consider the device * fully utilized. */ if (ioc->busy_level > 0) usage_us_sum = max_t(u64, usage_us_sum, ioc->period_us); ioc->dfgv_usage_us_sum += usage_us_sum; if (time_before64(now->now, ioc->dfgv_period_at + DFGV_PERIOD)) return; /* * At least DFGV_PERIOD has passed since the last period. Calculate the * average usage and reset the period counters. */ dur = now->now - ioc->dfgv_period_at; usage_pct = div64_u64(100 * ioc->dfgv_usage_us_sum, dur); ioc->dfgv_period_at = now->now; ioc->dfgv_usage_us_sum = 0; /* if was too busy, reset everything */ if (usage_pct > DFGV_USAGE_PCT) { ioc->dfgv_period_rem = 0; return; } /* * Usage is lower than threshold. Let's forgive some debts. Debt * forgiveness runs off of the usual ioc timer but its period usually * doesn't match ioc's. Compensate the difference by performing the * reduction as many times as would fit in the duration since the last * run and carrying over the left-over duration in @ioc->dfgv_period_rem * - if ioc period is 75% of DFGV_PERIOD, one out of three consecutive * reductions is doubled. */ nr_cycles = dur + ioc->dfgv_period_rem; ioc->dfgv_period_rem = do_div(nr_cycles, DFGV_PERIOD); list_for_each_entry(iocg, &ioc->active_iocgs, active_list) { u64 __maybe_unused old_debt, __maybe_unused old_delay; if (!iocg->abs_vdebt && !iocg->delay) continue; spin_lock(&iocg->waitq.lock); old_debt = iocg->abs_vdebt; old_delay = iocg->delay; nr_cycles_shift = min_t(u64, nr_cycles, BITS_PER_LONG - 1); if (iocg->abs_vdebt) iocg->abs_vdebt = iocg->abs_vdebt >> nr_cycles_shift ?: 1; if (iocg->delay) iocg->delay = iocg->delay >> nr_cycles_shift ?: 1; iocg_kick_waitq(iocg, true, now); TRACE_IOCG_PATH(iocg_forgive_debt, iocg, now, usage_pct, old_debt, iocg->abs_vdebt, old_delay, iocg->delay); spin_unlock(&iocg->waitq.lock); } } /* * Check the active iocgs' state to avoid oversleeping and deactive * idle iocgs. * * Since waiters determine the sleep durations based on the vrate * they saw at the time of sleep, if vrate has increased, some * waiters could be sleeping for too long. Wake up tardy waiters * which should have woken up in the last period and expire idle * iocgs. */ static int ioc_check_iocgs(struct ioc *ioc, struct ioc_now *now) { int nr_debtors = 0; struct ioc_gq *iocg, *tiocg; list_for_each_entry_safe(iocg, tiocg, &ioc->active_iocgs, active_list) { if (!waitqueue_active(&iocg->waitq) && !iocg->abs_vdebt && !iocg->delay && !iocg_is_idle(iocg)) continue; spin_lock(&iocg->waitq.lock); /* flush wait and indebt stat deltas */ if (iocg->wait_since) { iocg->stat.wait_us += now->now - iocg->wait_since; iocg->wait_since = now->now; } if (iocg->indebt_since) { iocg->stat.indebt_us += now->now - iocg->indebt_since; iocg->indebt_since = now->now; } if (iocg->indelay_since) { iocg->stat.indelay_us += now->now - iocg->indelay_since; iocg->indelay_since = now->now; } if (waitqueue_active(&iocg->waitq) || iocg->abs_vdebt || iocg->delay) { /* might be oversleeping vtime / hweight changes, kick */ iocg_kick_waitq(iocg, true, now); if (iocg->abs_vdebt || iocg->delay) nr_debtors++; } else if (iocg_is_idle(iocg)) { /* no waiter and idle, deactivate */ u64 vtime = atomic64_read(&iocg->vtime); s64 excess; /* * @iocg has been inactive for a full duration and will * have a high budget. Account anything above target as * error and throw away. On reactivation, it'll start * with the target budget. */ excess = now->vnow - vtime - ioc->margins.target; if (excess > 0) { u32 old_hwi; current_hweight(iocg, NULL, &old_hwi); ioc->vtime_err -= div64_u64(excess * old_hwi, WEIGHT_ONE); } TRACE_IOCG_PATH(iocg_idle, iocg, now, atomic64_read(&iocg->active_period), atomic64_read(&ioc->cur_period), vtime); __propagate_weights(iocg, 0, 0, false, now); list_del_init(&iocg->active_list); } spin_unlock(&iocg->waitq.lock); } commit_weights(ioc); return nr_debtors; } static void ioc_timer_fn(struct timer_list *timer) { struct ioc *ioc = container_of(timer, struct ioc, timer); struct ioc_gq *iocg, *tiocg; struct ioc_now now; LIST_HEAD(surpluses); int nr_debtors, nr_shortages = 0, nr_lagging = 0; u64 usage_us_sum = 0; u32 ppm_rthr = MILLION - ioc->params.qos[QOS_RPPM]; u32 ppm_wthr = MILLION - ioc->params.qos[QOS_WPPM]; u32 missed_ppm[2], rq_wait_pct; u64 period_vtime; int prev_busy_level; /* how were the latencies during the period? */ ioc_lat_stat(ioc, missed_ppm, &rq_wait_pct); /* take care of active iocgs */ spin_lock_irq(&ioc->lock); ioc_now(ioc, &now); period_vtime = now.vnow - ioc->period_at_vtime; if (WARN_ON_ONCE(!period_vtime)) { spin_unlock_irq(&ioc->lock); return; } nr_debtors = ioc_check_iocgs(ioc, &now); /* * Wait and indebt stat are flushed above and the donation calculation * below needs updated usage stat. Let's bring stat up-to-date. */ iocg_flush_stat(&ioc->active_iocgs, &now); /* calc usage and see whether some weights need to be moved around */ list_for_each_entry(iocg, &ioc->active_iocgs, active_list) { u64 vdone, vtime, usage_us; u32 hw_active, hw_inuse; /* * Collect unused and wind vtime closer to vnow to prevent * iocgs from accumulating a large amount of budget. */ vdone = atomic64_read(&iocg->done_vtime); vtime = atomic64_read(&iocg->vtime); current_hweight(iocg, &hw_active, &hw_inuse); /* * Latency QoS detection doesn't account for IOs which are * in-flight for longer than a period. Detect them by * comparing vdone against period start. If lagging behind * IOs from past periods, don't increase vrate. */ if ((ppm_rthr != MILLION || ppm_wthr != MILLION) && !atomic_read(&iocg_to_blkg(iocg)->use_delay) && time_after64(vtime, vdone) && time_after64(vtime, now.vnow - MAX_LAGGING_PERIODS * period_vtime) && time_before64(vdone, now.vnow - period_vtime)) nr_lagging++; /* * Determine absolute usage factoring in in-flight IOs to avoid * high-latency completions appearing as idle. */ usage_us = iocg->usage_delta_us; usage_us_sum += usage_us; /* see whether there's surplus vtime */ WARN_ON_ONCE(!list_empty(&iocg->surplus_list)); if (hw_inuse < hw_active || (!waitqueue_active(&iocg->waitq) && time_before64(vtime, now.vnow - ioc->margins.low))) { u32 hwa, old_hwi, hwm, new_hwi, usage; u64 usage_dur; if (vdone != vtime) { u64 inflight_us = DIV64_U64_ROUND_UP( cost_to_abs_cost(vtime - vdone, hw_inuse), ioc->vtime_base_rate); usage_us = max(usage_us, inflight_us); } /* convert to hweight based usage ratio */ if (time_after64(iocg->activated_at, ioc->period_at)) usage_dur = max_t(u64, now.now - iocg->activated_at, 1); else usage_dur = max_t(u64, now.now - ioc->period_at, 1); usage = clamp_t(u32, DIV64_U64_ROUND_UP(usage_us * WEIGHT_ONE, usage_dur), 1, WEIGHT_ONE); /* * Already donating or accumulated enough to start. * Determine the donation amount. */ current_hweight(iocg, &hwa, &old_hwi); hwm = current_hweight_max(iocg); new_hwi = hweight_after_donation(iocg, old_hwi, hwm, usage, &now); /* * Donation calculation assumes hweight_after_donation * to be positive, a condition that a donor w/ hwa < 2 * can't meet. Don't bother with donation if hwa is * below 2. It's not gonna make a meaningful difference * anyway. */ if (new_hwi < hwm && hwa >= 2) { iocg->hweight_donating = hwa; iocg->hweight_after_donation = new_hwi; list_add(&iocg->surplus_list, &surpluses); } else if (!iocg->abs_vdebt) { /* * @iocg doesn't have enough to donate. Reset * its inuse to active. * * Don't reset debtors as their inuse's are * owned by debt handling. This shouldn't affect * donation calculuation in any meaningful way * as @iocg doesn't have a meaningful amount of * share anyway. */ TRACE_IOCG_PATH(inuse_shortage, iocg, &now, iocg->inuse, iocg->active, iocg->hweight_inuse, new_hwi); __propagate_weights(iocg, iocg->active, iocg->active, true, &now); nr_shortages++; } } else { /* genuinely short on vtime */ nr_shortages++; } } if (!list_empty(&surpluses) && nr_shortages) transfer_surpluses(&surpluses, &now); commit_weights(ioc); /* surplus list should be dissolved after use */ list_for_each_entry_safe(iocg, tiocg, &surpluses, surplus_list) list_del_init(&iocg->surplus_list); /* * If q is getting clogged or we're missing too much, we're issuing * too much IO and should lower vtime rate. If we're not missing * and experiencing shortages but not surpluses, we're too stingy * and should increase vtime rate. */ prev_busy_level = ioc->busy_level; if (rq_wait_pct > RQ_WAIT_BUSY_PCT || missed_ppm[READ] > ppm_rthr || missed_ppm[WRITE] > ppm_wthr) { /* clearly missing QoS targets, slow down vrate */ ioc->busy_level = max(ioc->busy_level, 0); ioc->busy_level++; } else if (rq_wait_pct <= RQ_WAIT_BUSY_PCT * UNBUSY_THR_PCT / 100 && missed_ppm[READ] <= ppm_rthr * UNBUSY_THR_PCT / 100 && missed_ppm[WRITE] <= ppm_wthr * UNBUSY_THR_PCT / 100) { /* QoS targets are being met with >25% margin */ if (nr_shortages) { /* * We're throttling while the device has spare * capacity. If vrate was being slowed down, stop. */ ioc->busy_level = min(ioc->busy_level, 0); /* * If there are IOs spanning multiple periods, wait * them out before pushing the device harder. */ if (!nr_lagging) ioc->busy_level--; } else { /* * Nobody is being throttled and the users aren't * issuing enough IOs to saturate the device. We * simply don't know how close the device is to * saturation. Coast. */ ioc->busy_level = 0; } } else { /* inside the hysterisis margin, we're good */ ioc->busy_level = 0; } ioc->busy_level = clamp(ioc->busy_level, -1000, 1000); ioc_adjust_base_vrate(ioc, rq_wait_pct, nr_lagging, nr_shortages, prev_busy_level, missed_ppm); ioc_refresh_params(ioc, false); ioc_forgive_debts(ioc, usage_us_sum, nr_debtors, &now); /* * This period is done. Move onto the next one. If nothing's * going on with the device, stop the timer. */ atomic64_inc(&ioc->cur_period); if (ioc->running != IOC_STOP) { if (!list_empty(&ioc->active_iocgs)) { ioc_start_period(ioc, &now); } else { ioc->busy_level = 0; ioc->vtime_err = 0; ioc->running = IOC_IDLE; } ioc_refresh_vrate(ioc, &now); } spin_unlock_irq(&ioc->lock); } static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime, u64 abs_cost, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; struct ioc_margins *margins = &ioc->margins; u32 __maybe_unused old_inuse = iocg->inuse, __maybe_unused old_hwi; u32 hwi, adj_step; s64 margin; u64 cost, new_inuse; unsigned long flags; current_hweight(iocg, NULL, &hwi); old_hwi = hwi; cost = abs_cost_to_cost(abs_cost, hwi); margin = now->vnow - vtime - cost; /* debt handling owns inuse for debtors */ if (iocg->abs_vdebt) return cost; /* * We only increase inuse during period and do so if the margin has * deteriorated since the previous adjustment. */ if (margin >= iocg->saved_margin || margin >= margins->low || iocg->inuse == iocg->active) return cost; spin_lock_irqsave(&ioc->lock, flags); /* we own inuse only when @iocg is in the normal active state */ if (iocg->abs_vdebt || list_empty(&iocg->active_list)) { spin_unlock_irqrestore(&ioc->lock, flags); return cost; } /* * Bump up inuse till @abs_cost fits in the existing budget. * adj_step must be determined after acquiring ioc->lock - we might * have raced and lost to another thread for activation and could * be reading 0 iocg->active before ioc->lock which will lead to * infinite loop. */ new_inuse = iocg->inuse; adj_step = DIV_ROUND_UP(iocg->active * INUSE_ADJ_STEP_PCT, 100); do { new_inuse = new_inuse + adj_step; propagate_weights(iocg, iocg->active, new_inuse, true, now); current_hweight(iocg, NULL, &hwi); cost = abs_cost_to_cost(abs_cost, hwi); } while (time_after64(vtime + cost, now->vnow) && iocg->inuse != iocg->active); spin_unlock_irqrestore(&ioc->lock, flags); TRACE_IOCG_PATH(inuse_adjust, iocg, now, old_inuse, iocg->inuse, old_hwi, hwi); return cost; } static void calc_vtime_cost_builtin(struct bio *bio, struct ioc_gq *iocg, bool is_merge, u64 *costp) { struct ioc *ioc = iocg->ioc; u64 coef_seqio, coef_randio, coef_page; u64 pages = max_t(u64, bio_sectors(bio) >> IOC_SECT_TO_PAGE_SHIFT, 1); u64 seek_pages = 0; u64 cost = 0; switch (bio_op(bio)) { case REQ_OP_READ: coef_seqio = ioc->params.lcoefs[LCOEF_RSEQIO]; coef_randio = ioc->params.lcoefs[LCOEF_RRANDIO]; coef_page = ioc->params.lcoefs[LCOEF_RPAGE]; break; case REQ_OP_WRITE: coef_seqio = ioc->params.lcoefs[LCOEF_WSEQIO]; coef_randio = ioc->params.lcoefs[LCOEF_WRANDIO]; coef_page = ioc->params.lcoefs[LCOEF_WPAGE]; break; default: goto out; } if (iocg->cursor) { seek_pages = abs(bio->bi_iter.bi_sector - iocg->cursor); seek_pages >>= IOC_SECT_TO_PAGE_SHIFT; } if (!is_merge) { if (seek_pages > LCOEF_RANDIO_PAGES) { cost += coef_randio; } else { cost += coef_seqio; } } cost += pages * coef_page; out: *costp = cost; } static u64 calc_vtime_cost(struct bio *bio, struct ioc_gq *iocg, bool is_merge) { u64 cost; calc_vtime_cost_builtin(bio, iocg, is_merge, &cost); return cost; } static void calc_size_vtime_cost_builtin(struct request *rq, struct ioc *ioc, u64 *costp) { unsigned int pages = blk_rq_stats_sectors(rq) >> IOC_SECT_TO_PAGE_SHIFT; switch (req_op(rq)) { case REQ_OP_READ: *costp = pages * ioc->params.lcoefs[LCOEF_RPAGE]; break; case REQ_OP_WRITE: *costp = pages * ioc->params.lcoefs[LCOEF_WPAGE]; break; default: *costp = 0; } } static u64 calc_size_vtime_cost(struct request *rq, struct ioc *ioc) { u64 cost; calc_size_vtime_cost_builtin(rq, ioc, &cost); return cost; } static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio) { struct blkcg_gq *blkg = bio->bi_blkg; struct ioc *ioc = rqos_to_ioc(rqos); struct ioc_gq *iocg = blkg_to_iocg(blkg); struct ioc_now now; struct iocg_wait wait; u64 abs_cost, cost, vtime; bool use_debt, ioc_locked; unsigned long flags; /* bypass IOs if disabled, still initializing, or for root cgroup */ if (!ioc->enabled || !iocg || !iocg->level) return; /* calculate the absolute vtime cost */ abs_cost = calc_vtime_cost(bio, iocg, false); if (!abs_cost) return; if (!iocg_activate(iocg, &now)) return; iocg->cursor = bio_end_sector(bio); vtime = atomic64_read(&iocg->vtime); cost = adjust_inuse_and_calc_cost(iocg, vtime, abs_cost, &now); /* * If no one's waiting and within budget, issue right away. The * tests are racy but the races aren't systemic - we only miss once * in a while which is fine. */ if (!waitqueue_active(&iocg->waitq) && !iocg->abs_vdebt && time_before_eq64(vtime + cost, now.vnow)) { iocg_commit_bio(iocg, bio, abs_cost, cost); return; } /* * We're over budget. This can be handled in two ways. IOs which may * cause priority inversions are punted to @ioc->aux_iocg and charged as * debt. Otherwise, the issuer is blocked on @iocg->waitq. Debt handling * requires @ioc->lock, waitq handling @iocg->waitq.lock. Determine * whether debt handling is needed and acquire locks accordingly. */ use_debt = bio_issue_as_root_blkg(bio) || fatal_signal_pending(current); ioc_locked = use_debt || READ_ONCE(iocg->abs_vdebt); retry_lock: iocg_lock(iocg, ioc_locked, &flags); /* * @iocg must stay activated for debt and waitq handling. Deactivation * is synchronized against both ioc->lock and waitq.lock and we won't * get deactivated as long as we're waiting or has debt, so we're good * if we're activated here. In the unlikely cases that we aren't, just * issue the IO. */ if (unlikely(list_empty(&iocg->active_list))) { iocg_unlock(iocg, ioc_locked, &flags); iocg_commit_bio(iocg, bio, abs_cost, cost); return; } /* * We're over budget. If @bio has to be issued regardless, remember * the abs_cost instead of advancing vtime. iocg_kick_waitq() will pay * off the debt before waking more IOs. * * This way, the debt is continuously paid off each period with the * actual budget available to the cgroup. If we just wound vtime, we * would incorrectly use the current hw_inuse for the entire amount * which, for example, can lead to the cgroup staying blocked for a * long time even with substantially raised hw_inuse. * * An iocg with vdebt should stay online so that the timer can keep * deducting its vdebt and [de]activate use_delay mechanism * accordingly. We don't want to race against the timer trying to * clear them and leave @iocg inactive w/ dangling use_delay heavily * penalizing the cgroup and its descendants. */ if (use_debt) { iocg_incur_debt(iocg, abs_cost, &now); if (iocg_kick_delay(iocg, &now)) blkcg_schedule_throttle(rqos->q->disk, (bio->bi_opf & REQ_SWAP) == REQ_SWAP); iocg_unlock(iocg, ioc_locked, &flags); return; } /* guarantee that iocgs w/ waiters have maximum inuse */ if (!iocg->abs_vdebt && iocg->inuse != iocg->active) { if (!ioc_locked) { iocg_unlock(iocg, false, &flags); ioc_locked = true; goto retry_lock; } propagate_weights(iocg, iocg->active, iocg->active, true, &now); } /* * Append self to the waitq and schedule the wakeup timer if we're * the first waiter. The timer duration is calculated based on the * current vrate. vtime and hweight changes can make it too short * or too long. Each wait entry records the absolute cost it's * waiting for to allow re-evaluation using a custom wait entry. * * If too short, the timer simply reschedules itself. If too long, * the period timer will notice and trigger wakeups. * * All waiters are on iocg->waitq and the wait states are * synchronized using waitq.lock. */ init_waitqueue_func_entry(&wait.wait, iocg_wake_fn); wait.wait.private = current; wait.bio = bio; wait.abs_cost = abs_cost; wait.committed = false; /* will be set true by waker */ __add_wait_queue_entry_tail(&iocg->waitq, &wait.wait); iocg_kick_waitq(iocg, ioc_locked, &now); iocg_unlock(iocg, ioc_locked, &flags); while (true) { set_current_state(TASK_UNINTERRUPTIBLE); if (wait.committed) break; io_schedule(); } /* waker already committed us, proceed */ finish_wait(&iocg->waitq, &wait.wait); } static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq, struct bio *bio) { struct ioc_gq *iocg = blkg_to_iocg(bio->bi_blkg); struct ioc *ioc = rqos_to_ioc(rqos); sector_t bio_end = bio_end_sector(bio); struct ioc_now now; u64 vtime, abs_cost, cost; unsigned long flags; /* bypass if disabled, still initializing, or for root cgroup */ if (!ioc->enabled || !iocg || !iocg->level) return; abs_cost = calc_vtime_cost(bio, iocg, true); if (!abs_cost) return; ioc_now(ioc, &now); vtime = atomic64_read(&iocg->vtime); cost = adjust_inuse_and_calc_cost(iocg, vtime, abs_cost, &now); /* update cursor if backmerging into the request at the cursor */ if (blk_rq_pos(rq) < bio_end && blk_rq_pos(rq) + blk_rq_sectors(rq) == iocg->cursor) iocg->cursor = bio_end; /* * Charge if there's enough vtime budget and the existing request has * cost assigned. */ if (rq->bio && rq->bio->bi_iocost_cost && time_before_eq64(atomic64_read(&iocg->vtime) + cost, now.vnow)) { iocg_commit_bio(iocg, bio, abs_cost, cost); return; } /* * Otherwise, account it as debt if @iocg is online, which it should * be for the vast majority of cases. See debt handling in * ioc_rqos_throttle() for details. */ spin_lock_irqsave(&ioc->lock, flags); spin_lock(&iocg->waitq.lock); if (likely(!list_empty(&iocg->active_list))) { iocg_incur_debt(iocg, abs_cost, &now); if (iocg_kick_delay(iocg, &now)) blkcg_schedule_throttle(rqos->q->disk, (bio->bi_opf & REQ_SWAP) == REQ_SWAP); } else { iocg_commit_bio(iocg, bio, abs_cost, cost); } spin_unlock(&iocg->waitq.lock); spin_unlock_irqrestore(&ioc->lock, flags); } static void ioc_rqos_done_bio(struct rq_qos *rqos, struct bio *bio) { struct ioc_gq *iocg = blkg_to_iocg(bio->bi_blkg); if (iocg && bio->bi_iocost_cost) atomic64_add(bio->bi_iocost_cost, &iocg->done_vtime); } static void ioc_rqos_done(struct rq_qos *rqos, struct request *rq) { struct ioc *ioc = rqos_to_ioc(rqos); struct ioc_pcpu_stat *ccs; u64 on_q_ns, rq_wait_ns, size_nsec; int pidx, rw; if (!ioc->enabled || !rq->alloc_time_ns || !rq->start_time_ns) return; switch (req_op(rq)) { case REQ_OP_READ: pidx = QOS_RLAT; rw = READ; break; case REQ_OP_WRITE: pidx = QOS_WLAT; rw = WRITE; break; default: return; } on_q_ns = ktime_get_ns() - rq->alloc_time_ns; rq_wait_ns = rq->start_time_ns - rq->alloc_time_ns; size_nsec = div64_u64(calc_size_vtime_cost(rq, ioc), VTIME_PER_NSEC); ccs = get_cpu_ptr(ioc->pcpu_stat); if (on_q_ns <= size_nsec || on_q_ns - size_nsec <= ioc->params.qos[pidx] * NSEC_PER_USEC) local_inc(&ccs->missed[rw].nr_met); else local_inc(&ccs->missed[rw].nr_missed); local64_add(rq_wait_ns, &ccs->rq_wait_ns); put_cpu_ptr(ccs); } static void ioc_rqos_queue_depth_changed(struct rq_qos *rqos) { struct ioc *ioc = rqos_to_ioc(rqos); spin_lock_irq(&ioc->lock); ioc_refresh_params(ioc, false); spin_unlock_irq(&ioc->lock); } static void ioc_rqos_exit(struct rq_qos *rqos) { struct ioc *ioc = rqos_to_ioc(rqos); blkcg_deactivate_policy(rqos->q, &blkcg_policy_iocost); spin_lock_irq(&ioc->lock); ioc->running = IOC_STOP; spin_unlock_irq(&ioc->lock); del_timer_sync(&ioc->timer); free_percpu(ioc->pcpu_stat); kfree(ioc); } static struct rq_qos_ops ioc_rqos_ops = { .throttle = ioc_rqos_throttle, .merge = ioc_rqos_merge, .done_bio = ioc_rqos_done_bio, .done = ioc_rqos_done, .queue_depth_changed = ioc_rqos_queue_depth_changed, .exit = ioc_rqos_exit, }; static int blk_iocost_init(struct gendisk *disk) { struct request_queue *q = disk->queue; struct ioc *ioc; struct rq_qos *rqos; int i, cpu, ret; ioc = kzalloc(sizeof(*ioc), GFP_KERNEL); if (!ioc) return -ENOMEM; ioc->pcpu_stat = alloc_percpu(struct ioc_pcpu_stat); if (!ioc->pcpu_stat) { kfree(ioc); return -ENOMEM; } for_each_possible_cpu(cpu) { struct ioc_pcpu_stat *ccs = per_cpu_ptr(ioc->pcpu_stat, cpu); for (i = 0; i < ARRAY_SIZE(ccs->missed); i++) { local_set(&ccs->missed[i].nr_met, 0); local_set(&ccs->missed[i].nr_missed, 0); } local64_set(&ccs->rq_wait_ns, 0); } rqos = &ioc->rqos; rqos->id = RQ_QOS_COST; rqos->ops = &ioc_rqos_ops; rqos->q = q; spin_lock_init(&ioc->lock); timer_setup(&ioc->timer, ioc_timer_fn, 0); INIT_LIST_HEAD(&ioc->active_iocgs); ioc->running = IOC_IDLE; ioc->vtime_base_rate = VTIME_PER_USEC; atomic64_set(&ioc->vtime_rate, VTIME_PER_USEC); seqcount_spinlock_init(&ioc->period_seqcount, &ioc->lock); ioc->period_at = ktime_to_us(ktime_get()); atomic64_set(&ioc->cur_period, 0); atomic_set(&ioc->hweight_gen, 0); spin_lock_irq(&ioc->lock); ioc->autop_idx = AUTOP_INVALID; ioc_refresh_params(ioc, true); spin_unlock_irq(&ioc->lock); /* * rqos must be added before activation to allow iocg_pd_init() to * lookup the ioc from q. This means that the rqos methods may get * called before policy activation completion, can't assume that the * target bio has an iocg associated and need to test for NULL iocg. */ ret = rq_qos_add(q, rqos); if (ret) goto err_free_ioc; ret = blkcg_activate_policy(q, &blkcg_policy_iocost); if (ret) goto err_del_qos; return 0; err_del_qos: rq_qos_del(q, rqos); err_free_ioc: free_percpu(ioc->pcpu_stat); kfree(ioc); return ret; } static struct blkcg_policy_data *ioc_cpd_alloc(gfp_t gfp) { struct ioc_cgrp *iocc; iocc = kzalloc(sizeof(struct ioc_cgrp), gfp); if (!iocc) return NULL; iocc->dfl_weight = CGROUP_WEIGHT_DFL * WEIGHT_ONE; return &iocc->cpd; } static void ioc_cpd_free(struct blkcg_policy_data *cpd) { kfree(container_of(cpd, struct ioc_cgrp, cpd)); } static struct blkg_policy_data *ioc_pd_alloc(gfp_t gfp, struct request_queue *q, struct blkcg *blkcg) { int levels = blkcg->css.cgroup->level + 1; struct ioc_gq *iocg; iocg = kzalloc_node(struct_size(iocg, ancestors, levels), gfp, q->node); if (!iocg) return NULL; iocg->pcpu_stat = alloc_percpu_gfp(struct iocg_pcpu_stat, gfp); if (!iocg->pcpu_stat) { kfree(iocg); return NULL; } return &iocg->pd; } static void ioc_pd_init(struct blkg_policy_data *pd) { struct ioc_gq *iocg = pd_to_iocg(pd); struct blkcg_gq *blkg = pd_to_blkg(&iocg->pd); struct ioc *ioc = q_to_ioc(blkg->q); struct ioc_now now; struct blkcg_gq *tblkg; unsigned long flags; ioc_now(ioc, &now); iocg->ioc = ioc; atomic64_set(&iocg->vtime, now.vnow); atomic64_set(&iocg->done_vtime, now.vnow); atomic64_set(&iocg->active_period, atomic64_read(&ioc->cur_period)); INIT_LIST_HEAD(&iocg->active_list); INIT_LIST_HEAD(&iocg->walk_list); INIT_LIST_HEAD(&iocg->surplus_list); iocg->hweight_active = WEIGHT_ONE; iocg->hweight_inuse = WEIGHT_ONE; init_waitqueue_head(&iocg->waitq); hrtimer_init(&iocg->waitq_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); iocg->waitq_timer.function = iocg_waitq_timer_fn; iocg->level = blkg->blkcg->css.cgroup->level; for (tblkg = blkg; tblkg; tblkg = tblkg->parent) { struct ioc_gq *tiocg = blkg_to_iocg(tblkg); iocg->ancestors[tiocg->level] = tiocg; } spin_lock_irqsave(&ioc->lock, flags); weight_updated(iocg, &now); spin_unlock_irqrestore(&ioc->lock, flags); } static void ioc_pd_free(struct blkg_policy_data *pd) { struct ioc_gq *iocg = pd_to_iocg(pd); struct ioc *ioc = iocg->ioc; unsigned long flags; if (ioc) { spin_lock_irqsave(&ioc->lock, flags); if (!list_empty(&iocg->active_list)) { struct ioc_now now; ioc_now(ioc, &now); propagate_weights(iocg, 0, 0, false, &now); list_del_init(&iocg->active_list); } WARN_ON_ONCE(!list_empty(&iocg->walk_list)); WARN_ON_ONCE(!list_empty(&iocg->surplus_list)); spin_unlock_irqrestore(&ioc->lock, flags); hrtimer_cancel(&iocg->waitq_timer); } free_percpu(iocg->pcpu_stat); kfree(iocg); } static void ioc_pd_stat(struct blkg_policy_data *pd, struct seq_file *s) { struct ioc_gq *iocg = pd_to_iocg(pd); struct ioc *ioc = iocg->ioc; if (!ioc->enabled) return; if (iocg->level == 0) { unsigned vp10k = DIV64_U64_ROUND_CLOSEST( ioc->vtime_base_rate * 10000, VTIME_PER_USEC); seq_printf(s, " cost.vrate=%u.%02u", vp10k / 100, vp10k % 100); } seq_printf(s, " cost.usage=%llu", iocg->last_stat.usage_us); if (blkcg_debug_stats) seq_printf(s, " cost.wait=%llu cost.indebt=%llu cost.indelay=%llu", iocg->last_stat.wait_us, iocg->last_stat.indebt_us, iocg->last_stat.indelay_us); } static u64 ioc_weight_prfill(struct seq_file *sf, struct blkg_policy_data *pd, int off) { const char *dname = blkg_dev_name(pd->blkg); struct ioc_gq *iocg = pd_to_iocg(pd); if (dname && iocg->cfg_weight) seq_printf(sf, "%s %u\n", dname, iocg->cfg_weight / WEIGHT_ONE); return 0; } static int ioc_weight_show(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); struct ioc_cgrp *iocc = blkcg_to_iocc(blkcg); seq_printf(sf, "default %u\n", iocc->dfl_weight / WEIGHT_ONE); blkcg_print_blkgs(sf, blkcg, ioc_weight_prfill, &blkcg_policy_iocost, seq_cft(sf)->private, false); return 0; } static ssize_t ioc_weight_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct blkcg *blkcg = css_to_blkcg(of_css(of)); struct ioc_cgrp *iocc = blkcg_to_iocc(blkcg); struct blkg_conf_ctx ctx; struct ioc_now now; struct ioc_gq *iocg; u32 v; int ret; if (!strchr(buf, ':')) { struct blkcg_gq *blkg; if (!sscanf(buf, "default %u", &v) && !sscanf(buf, "%u", &v)) return -EINVAL; if (v < CGROUP_WEIGHT_MIN || v > CGROUP_WEIGHT_MAX) return -EINVAL; spin_lock_irq(&blkcg->lock); iocc->dfl_weight = v * WEIGHT_ONE; hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { struct ioc_gq *iocg = blkg_to_iocg(blkg); if (iocg) { spin_lock(&iocg->ioc->lock); ioc_now(iocg->ioc, &now); weight_updated(iocg, &now); spin_unlock(&iocg->ioc->lock); } } spin_unlock_irq(&blkcg->lock); return nbytes; } ret = blkg_conf_prep(blkcg, &blkcg_policy_iocost, buf, &ctx); if (ret) return ret; iocg = blkg_to_iocg(ctx.blkg); if (!strncmp(ctx.body, "default", 7)) { v = 0; } else { if (!sscanf(ctx.body, "%u", &v)) goto einval; if (v < CGROUP_WEIGHT_MIN || v > CGROUP_WEIGHT_MAX) goto einval; } spin_lock(&iocg->ioc->lock); iocg->cfg_weight = v * WEIGHT_ONE; ioc_now(iocg->ioc, &now); weight_updated(iocg, &now); spin_unlock(&iocg->ioc->lock); blkg_conf_finish(&ctx); return nbytes; einval: blkg_conf_finish(&ctx); return -EINVAL; } static u64 ioc_qos_prfill(struct seq_file *sf, struct blkg_policy_data *pd, int off) { const char *dname = blkg_dev_name(pd->blkg); struct ioc *ioc = pd_to_iocg(pd)->ioc; if (!dname) return 0; seq_printf(sf, "%s enable=%d ctrl=%s rpct=%u.%02u rlat=%u wpct=%u.%02u wlat=%u min=%u.%02u max=%u.%02u\n", dname, ioc->enabled, ioc->user_qos_params ? "user" : "auto", ioc->params.qos[QOS_RPPM] / 10000, ioc->params.qos[QOS_RPPM] % 10000 / 100, ioc->params.qos[QOS_RLAT], ioc->params.qos[QOS_WPPM] / 10000, ioc->params.qos[QOS_WPPM] % 10000 / 100, ioc->params.qos[QOS_WLAT], ioc->params.qos[QOS_MIN] / 10000, ioc->params.qos[QOS_MIN] % 10000 / 100, ioc->params.qos[QOS_MAX] / 10000, ioc->params.qos[QOS_MAX] % 10000 / 100); return 0; } static int ioc_qos_show(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); blkcg_print_blkgs(sf, blkcg, ioc_qos_prfill, &blkcg_policy_iocost, seq_cft(sf)->private, false); return 0; } static const match_table_t qos_ctrl_tokens = { { QOS_ENABLE, "enable=%u" }, { QOS_CTRL, "ctrl=%s" }, { NR_QOS_CTRL_PARAMS, NULL }, }; static const match_table_t qos_tokens = { { QOS_RPPM, "rpct=%s" }, { QOS_RLAT, "rlat=%u" }, { QOS_WPPM, "wpct=%s" }, { QOS_WLAT, "wlat=%u" }, { QOS_MIN, "min=%s" }, { QOS_MAX, "max=%s" }, { NR_QOS_PARAMS, NULL }, }; static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input, size_t nbytes, loff_t off) { struct block_device *bdev; struct gendisk *disk; struct ioc *ioc; u32 qos[NR_QOS_PARAMS]; bool enable, user; char *p; int ret; bdev = blkcg_conf_open_bdev(&input); if (IS_ERR(bdev)) return PTR_ERR(bdev); disk = bdev->bd_disk; ioc = q_to_ioc(disk->queue); if (!ioc) { ret = blk_iocost_init(disk); if (ret) goto err; ioc = q_to_ioc(disk->queue); } spin_lock_irq(&ioc->lock); memcpy(qos, ioc->params.qos, sizeof(qos)); enable = ioc->enabled; user = ioc->user_qos_params; spin_unlock_irq(&ioc->lock); while ((p = strsep(&input, " \t\n"))) { substring_t args[MAX_OPT_ARGS]; char buf[32]; int tok; s64 v; if (!*p) continue; switch (match_token(p, qos_ctrl_tokens, args)) { case QOS_ENABLE: match_u64(&args[0], &v); enable = v; continue; case QOS_CTRL: match_strlcpy(buf, &args[0], sizeof(buf)); if (!strcmp(buf, "auto")) user = false; else if (!strcmp(buf, "user")) user = true; else goto einval; continue; } tok = match_token(p, qos_tokens, args); switch (tok) { case QOS_RPPM: case QOS_WPPM: if (match_strlcpy(buf, &args[0], sizeof(buf)) >= sizeof(buf)) goto einval; if (cgroup_parse_float(buf, 2, &v)) goto einval; if (v < 0 || v > 10000) goto einval; qos[tok] = v * 100; break; case QOS_RLAT: case QOS_WLAT: if (match_u64(&args[0], &v)) goto einval; qos[tok] = v; break; case QOS_MIN: case QOS_MAX: if (match_strlcpy(buf, &args[0], sizeof(buf)) >= sizeof(buf)) goto einval; if (cgroup_parse_float(buf, 2, &v)) goto einval; if (v < 0) goto einval; qos[tok] = clamp_t(s64, v * 100, VRATE_MIN_PPM, VRATE_MAX_PPM); break; default: goto einval; } user = true; } if (qos[QOS_MIN] > qos[QOS_MAX]) goto einval; spin_lock_irq(&ioc->lock); if (enable) { blk_stat_enable_accounting(disk->queue); blk_queue_flag_set(QUEUE_FLAG_RQ_ALLOC_TIME, disk->queue); ioc->enabled = true; } else { blk_queue_flag_clear(QUEUE_FLAG_RQ_ALLOC_TIME, disk->queue); ioc->enabled = false; } if (user) { memcpy(ioc->params.qos, qos, sizeof(qos)); ioc->user_qos_params = true; } else { ioc->user_qos_params = false; } ioc_refresh_params(ioc, true); spin_unlock_irq(&ioc->lock); blkdev_put_no_open(bdev); return nbytes; einval: ret = -EINVAL; err: blkdev_put_no_open(bdev); return ret; } static u64 ioc_cost_model_prfill(struct seq_file *sf, struct blkg_policy_data *pd, int off) { const char *dname = blkg_dev_name(pd->blkg); struct ioc *ioc = pd_to_iocg(pd)->ioc; u64 *u = ioc->params.i_lcoefs; if (!dname) return 0; seq_printf(sf, "%s ctrl=%s model=linear " "rbps=%llu rseqiops=%llu rrandiops=%llu " "wbps=%llu wseqiops=%llu wrandiops=%llu\n", dname, ioc->user_cost_model ? "user" : "auto", u[I_LCOEF_RBPS], u[I_LCOEF_RSEQIOPS], u[I_LCOEF_RRANDIOPS], u[I_LCOEF_WBPS], u[I_LCOEF_WSEQIOPS], u[I_LCOEF_WRANDIOPS]); return 0; } static int ioc_cost_model_show(struct seq_file *sf, void *v) { struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); blkcg_print_blkgs(sf, blkcg, ioc_cost_model_prfill, &blkcg_policy_iocost, seq_cft(sf)->private, false); return 0; } static const match_table_t cost_ctrl_tokens = { { COST_CTRL, "ctrl=%s" }, { COST_MODEL, "model=%s" }, { NR_COST_CTRL_PARAMS, NULL }, }; static const match_table_t i_lcoef_tokens = { { I_LCOEF_RBPS, "rbps=%u" }, { I_LCOEF_RSEQIOPS, "rseqiops=%u" }, { I_LCOEF_RRANDIOPS, "rrandiops=%u" }, { I_LCOEF_WBPS, "wbps=%u" }, { I_LCOEF_WSEQIOPS, "wseqiops=%u" }, { I_LCOEF_WRANDIOPS, "wrandiops=%u" }, { NR_I_LCOEFS, NULL }, }; static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input, size_t nbytes, loff_t off) { struct block_device *bdev; struct ioc *ioc; u64 u[NR_I_LCOEFS]; bool user; char *p; int ret; bdev = blkcg_conf_open_bdev(&input); if (IS_ERR(bdev)) return PTR_ERR(bdev); ioc = q_to_ioc(bdev_get_queue(bdev)); if (!ioc) { ret = blk_iocost_init(bdev->bd_disk); if (ret) goto err; ioc = q_to_ioc(bdev_get_queue(bdev)); } spin_lock_irq(&ioc->lock); memcpy(u, ioc->params.i_lcoefs, sizeof(u)); user = ioc->user_cost_model; spin_unlock_irq(&ioc->lock); while ((p = strsep(&input, " \t\n"))) { substring_t args[MAX_OPT_ARGS]; char buf[32]; int tok; u64 v; if (!*p) continue; switch (match_token(p, cost_ctrl_tokens, args)) { case COST_CTRL: match_strlcpy(buf, &args[0], sizeof(buf)); if (!strcmp(buf, "auto")) user = false; else if (!strcmp(buf, "user")) user = true; else goto einval; continue; case COST_MODEL: match_strlcpy(buf, &args[0], sizeof(buf)); if (strcmp(buf, "linear")) goto einval; continue; } tok = match_token(p, i_lcoef_tokens, args); if (tok == NR_I_LCOEFS) goto einval; if (match_u64(&args[0], &v)) goto einval; u[tok] = v; user = true; } spin_lock_irq(&ioc->lock); if (user) { memcpy(ioc->params.i_lcoefs, u, sizeof(u)); ioc->user_cost_model = true; } else { ioc->user_cost_model = false; } ioc_refresh_params(ioc, true); spin_unlock_irq(&ioc->lock); blkdev_put_no_open(bdev); return nbytes; einval: ret = -EINVAL; err: blkdev_put_no_open(bdev); return ret; } static struct cftype ioc_files[] = { { .name = "weight", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = ioc_weight_show, .write = ioc_weight_write, }, { .name = "cost.qos", .flags = CFTYPE_ONLY_ON_ROOT, .seq_show = ioc_qos_show, .write = ioc_qos_write, }, { .name = "cost.model", .flags = CFTYPE_ONLY_ON_ROOT, .seq_show = ioc_cost_model_show, .write = ioc_cost_model_write, }, {} }; static struct blkcg_policy blkcg_policy_iocost = { .dfl_cftypes = ioc_files, .cpd_alloc_fn = ioc_cpd_alloc, .cpd_free_fn = ioc_cpd_free, .pd_alloc_fn = ioc_pd_alloc, .pd_init_fn = ioc_pd_init, .pd_free_fn = ioc_pd_free, .pd_stat_fn = ioc_pd_stat, }; static int __init ioc_init(void) { return blkcg_policy_register(&blkcg_policy_iocost); } static void __exit ioc_exit(void) { blkcg_policy_unregister(&blkcg_policy_iocost); } module_init(ioc_init); module_exit(ioc_exit); |
| 2557 1799 1396 1569 2182 547 1396 1158 2582 2585 190 204 3 225 180 3 185 190 126 19 18 1 74 18 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 | /* * Implementation of the access vector table type. * * Author : Stephen Smalley, <sds@tycho.nsa.gov> */ /* Updated: Frank Mayer <mayerf@tresys.com> and Karl MacMillan <kmacmillan@tresys.com> * * Added conditional policy language extensions * * Copyright (C) 2003 Tresys Technology, LLC * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation, version 2. * * Updated: Yuichi Nakamura <ynakam@hitachisoft.jp> * Tuned number of hash slots for avtab to reduce memory usage */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/errno.h> #include "avtab.h" #include "policydb.h" static struct kmem_cache *avtab_node_cachep __ro_after_init; static struct kmem_cache *avtab_xperms_cachep __ro_after_init; /* Based on MurmurHash3, written by Austin Appleby and placed in the * public domain. */ static inline int avtab_hash(const struct avtab_key *keyp, u32 mask) { static const u32 c1 = 0xcc9e2d51; static const u32 c2 = 0x1b873593; static const u32 r1 = 15; static const u32 r2 = 13; static const u32 m = 5; static const u32 n = 0xe6546b64; u32 hash = 0; #define mix(input) do { \ u32 v = input; \ v *= c1; \ v = (v << r1) | (v >> (32 - r1)); \ v *= c2; \ hash ^= v; \ hash = (hash << r2) | (hash >> (32 - r2)); \ hash = hash * m + n; \ } while (0) mix(keyp->target_class); mix(keyp->target_type); mix(keyp->source_type); #undef mix hash ^= hash >> 16; hash *= 0x85ebca6b; hash ^= hash >> 13; hash *= 0xc2b2ae35; hash ^= hash >> 16; return hash & mask; } static struct avtab_node* avtab_insert_node(struct avtab *h, int hvalue, struct avtab_node *prev, const struct avtab_key *key, const struct avtab_datum *datum) { struct avtab_node *newnode; struct avtab_extended_perms *xperms; newnode = kmem_cache_zalloc(avtab_node_cachep, GFP_KERNEL); if (newnode == NULL) return NULL; newnode->key = *key; if (key->specified & AVTAB_XPERMS) { xperms = kmem_cache_zalloc(avtab_xperms_cachep, GFP_KERNEL); if (xperms == NULL) { kmem_cache_free(avtab_node_cachep, newnode); return NULL; } *xperms = *(datum->u.xperms); newnode->datum.u.xperms = xperms; } else { newnode->datum.u.data = datum->u.data; } if (prev) { newnode->next = prev->next; prev->next = newnode; } else { struct avtab_node **n = &h->htable[hvalue]; newnode->next = *n; *n = newnode; } h->nel++; return newnode; } static int avtab_insert(struct avtab *h, const struct avtab_key *key, const struct avtab_datum *datum) { int hvalue; struct avtab_node *prev, *cur, *newnode; u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD); if (!h || !h->nslot) return -EINVAL; hvalue = avtab_hash(key, h->mask); for (prev = NULL, cur = h->htable[hvalue]; cur; prev = cur, cur = cur->next) { if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class == cur->key.target_class && (specified & cur->key.specified)) { /* extended perms may not be unique */ if (specified & AVTAB_XPERMS) break; return -EEXIST; } if (key->source_type < cur->key.source_type) break; if (key->source_type == cur->key.source_type && key->target_type < cur->key.target_type) break; if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class < cur->key.target_class) break; } newnode = avtab_insert_node(h, hvalue, prev, key, datum); if (!newnode) return -ENOMEM; return 0; } /* Unlike avtab_insert(), this function allow multiple insertions of the same * key/specified mask into the table, as needed by the conditional avtab. * It also returns a pointer to the node inserted. */ struct avtab_node *avtab_insert_nonunique(struct avtab *h, const struct avtab_key *key, const struct avtab_datum *datum) { int hvalue; struct avtab_node *prev, *cur; u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD); if (!h || !h->nslot) return NULL; hvalue = avtab_hash(key, h->mask); for (prev = NULL, cur = h->htable[hvalue]; cur; prev = cur, cur = cur->next) { if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class == cur->key.target_class && (specified & cur->key.specified)) break; if (key->source_type < cur->key.source_type) break; if (key->source_type == cur->key.source_type && key->target_type < cur->key.target_type) break; if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class < cur->key.target_class) break; } return avtab_insert_node(h, hvalue, prev, key, datum); } struct avtab_datum *avtab_search(struct avtab *h, const struct avtab_key *key) { int hvalue; struct avtab_node *cur; u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD); if (!h || !h->nslot) return NULL; hvalue = avtab_hash(key, h->mask); for (cur = h->htable[hvalue]; cur; cur = cur->next) { if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class == cur->key.target_class && (specified & cur->key.specified)) return &cur->datum; if (key->source_type < cur->key.source_type) break; if (key->source_type == cur->key.source_type && key->target_type < cur->key.target_type) break; if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class < cur->key.target_class) break; } return NULL; } /* This search function returns a node pointer, and can be used in * conjunction with avtab_search_next_node() */ struct avtab_node *avtab_search_node(struct avtab *h, const struct avtab_key *key) { int hvalue; struct avtab_node *cur; u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD); if (!h || !h->nslot) return NULL; hvalue = avtab_hash(key, h->mask); for (cur = h->htable[hvalue]; cur; cur = cur->next) { if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class == cur->key.target_class && (specified & cur->key.specified)) return cur; if (key->source_type < cur->key.source_type) break; if (key->source_type == cur->key.source_type && key->target_type < cur->key.target_type) break; if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class < cur->key.target_class) break; } return NULL; } struct avtab_node* avtab_search_node_next(struct avtab_node *node, int specified) { struct avtab_node *cur; if (!node) return NULL; specified &= ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD); for (cur = node->next; cur; cur = cur->next) { if (node->key.source_type == cur->key.source_type && node->key.target_type == cur->key.target_type && node->key.target_class == cur->key.target_class && (specified & cur->key.specified)) return cur; if (node->key.source_type < cur->key.source_type) break; if (node->key.source_type == cur->key.source_type && node->key.target_type < cur->key.target_type) break; if (node->key.source_type == cur->key.source_type && node->key.target_type == cur->key.target_type && node->key.target_class < cur->key.target_class) break; } return NULL; } void avtab_destroy(struct avtab *h) { int i; struct avtab_node *cur, *temp; if (!h) return; for (i = 0; i < h->nslot; i++) { cur = h->htable[i]; while (cur) { temp = cur; cur = cur->next; if (temp->key.specified & AVTAB_XPERMS) kmem_cache_free(avtab_xperms_cachep, temp->datum.u.xperms); kmem_cache_free(avtab_node_cachep, temp); } } kvfree(h->htable); h->htable = NULL; h->nel = 0; h->nslot = 0; h->mask = 0; } void avtab_init(struct avtab *h) { h->htable = NULL; h->nel = 0; h->nslot = 0; h->mask = 0; } static int avtab_alloc_common(struct avtab *h, u32 nslot) { if (!nslot) return 0; h->htable = kvcalloc(nslot, sizeof(void *), GFP_KERNEL); if (!h->htable) return -ENOMEM; h->nslot = nslot; h->mask = nslot - 1; return 0; } int avtab_alloc(struct avtab *h, u32 nrules) { int rc; u32 nslot = 0; if (nrules != 0) { u32 shift = 1; u32 work = nrules >> 3; while (work) { work >>= 1; shift++; } nslot = 1 << shift; if (nslot > MAX_AVTAB_HASH_BUCKETS) nslot = MAX_AVTAB_HASH_BUCKETS; rc = avtab_alloc_common(h, nslot); if (rc) return rc; } pr_debug("SELinux: %d avtab hash slots, %d rules.\n", nslot, nrules); return 0; } int avtab_alloc_dup(struct avtab *new, const struct avtab *orig) { return avtab_alloc_common(new, orig->nslot); } void avtab_hash_eval(struct avtab *h, char *tag) { int i, chain_len, slots_used, max_chain_len; unsigned long long chain2_len_sum; struct avtab_node *cur; slots_used = 0; max_chain_len = 0; chain2_len_sum = 0; for (i = 0; i < h->nslot; i++) { cur = h->htable[i]; if (cur) { slots_used++; chain_len = 0; while (cur) { chain_len++; cur = cur->next; } if (chain_len > max_chain_len) max_chain_len = chain_len; chain2_len_sum += chain_len * chain_len; } } pr_debug("SELinux: %s: %d entries and %d/%d buckets used, " "longest chain length %d sum of chain length^2 %llu\n", tag, h->nel, slots_used, h->nslot, max_chain_len, chain2_len_sum); } static const uint16_t spec_order[] = { AVTAB_ALLOWED, AVTAB_AUDITDENY, AVTAB_AUDITALLOW, AVTAB_TRANSITION, AVTAB_CHANGE, AVTAB_MEMBER, AVTAB_XPERMS_ALLOWED, AVTAB_XPERMS_AUDITALLOW, AVTAB_XPERMS_DONTAUDIT }; int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol, int (*insertf)(struct avtab *a, const struct avtab_key *k, const struct avtab_datum *d, void *p), void *p) { __le16 buf16[4]; u16 enabled; u32 items, items2, val, vers = pol->policyvers; struct avtab_key key; struct avtab_datum datum; struct avtab_extended_perms xperms; __le32 buf32[ARRAY_SIZE(xperms.perms.p)]; int i, rc; unsigned set; memset(&key, 0, sizeof(struct avtab_key)); memset(&datum, 0, sizeof(struct avtab_datum)); if (vers < POLICYDB_VERSION_AVTAB) { rc = next_entry(buf32, fp, sizeof(u32)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } items2 = le32_to_cpu(buf32[0]); if (items2 > ARRAY_SIZE(buf32)) { pr_err("SELinux: avtab: entry overflow\n"); return -EINVAL; } rc = next_entry(buf32, fp, sizeof(u32)*items2); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } items = 0; val = le32_to_cpu(buf32[items++]); key.source_type = (u16)val; if (key.source_type != val) { pr_err("SELinux: avtab: truncated source type\n"); return -EINVAL; } val = le32_to_cpu(buf32[items++]); key.target_type = (u16)val; if (key.target_type != val) { pr_err("SELinux: avtab: truncated target type\n"); return -EINVAL; } val = le32_to_cpu(buf32[items++]); key.target_class = (u16)val; if (key.target_class != val) { pr_err("SELinux: avtab: truncated target class\n"); return -EINVAL; } val = le32_to_cpu(buf32[items++]); enabled = (val & AVTAB_ENABLED_OLD) ? AVTAB_ENABLED : 0; if (!(val & (AVTAB_AV | AVTAB_TYPE))) { pr_err("SELinux: avtab: null entry\n"); return -EINVAL; } if ((val & AVTAB_AV) && (val & AVTAB_TYPE)) { pr_err("SELinux: avtab: entry has both access vectors and types\n"); return -EINVAL; } if (val & AVTAB_XPERMS) { pr_err("SELinux: avtab: entry has extended permissions\n"); return -EINVAL; } for (i = 0; i < ARRAY_SIZE(spec_order); i++) { if (val & spec_order[i]) { key.specified = spec_order[i] | enabled; datum.u.data = le32_to_cpu(buf32[items++]); rc = insertf(a, &key, &datum, p); if (rc) return rc; } } if (items != items2) { pr_err("SELinux: avtab: entry only had %d items, expected %d\n", items2, items); return -EINVAL; } return 0; } rc = next_entry(buf16, fp, sizeof(u16)*4); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } items = 0; key.source_type = le16_to_cpu(buf16[items++]); key.target_type = le16_to_cpu(buf16[items++]); key.target_class = le16_to_cpu(buf16[items++]); key.specified = le16_to_cpu(buf16[items++]); if (!policydb_type_isvalid(pol, key.source_type) || !policydb_type_isvalid(pol, key.target_type) || !policydb_class_isvalid(pol, key.target_class)) { pr_err("SELinux: avtab: invalid type or class\n"); return -EINVAL; } set = 0; for (i = 0; i < ARRAY_SIZE(spec_order); i++) { if (key.specified & spec_order[i]) set++; } if (!set || set > 1) { pr_err("SELinux: avtab: more than one specifier\n"); return -EINVAL; } if ((vers < POLICYDB_VERSION_XPERMS_IOCTL) && (key.specified & AVTAB_XPERMS)) { pr_err("SELinux: avtab: policy version %u does not " "support extended permissions rules and one " "was specified\n", vers); return -EINVAL; } else if (key.specified & AVTAB_XPERMS) { memset(&xperms, 0, sizeof(struct avtab_extended_perms)); rc = next_entry(&xperms.specified, fp, sizeof(u8)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } rc = next_entry(&xperms.driver, fp, sizeof(u8)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } rc = next_entry(buf32, fp, sizeof(u32)*ARRAY_SIZE(xperms.perms.p)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } for (i = 0; i < ARRAY_SIZE(xperms.perms.p); i++) xperms.perms.p[i] = le32_to_cpu(buf32[i]); datum.u.xperms = &xperms; } else { rc = next_entry(buf32, fp, sizeof(u32)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } datum.u.data = le32_to_cpu(*buf32); } if ((key.specified & AVTAB_TYPE) && !policydb_type_isvalid(pol, datum.u.data)) { pr_err("SELinux: avtab: invalid type\n"); return -EINVAL; } return insertf(a, &key, &datum, p); } static int avtab_insertf(struct avtab *a, const struct avtab_key *k, const struct avtab_datum *d, void *p) { return avtab_insert(a, k, d); } int avtab_read(struct avtab *a, void *fp, struct policydb *pol) { int rc; __le32 buf[1]; u32 nel, i; rc = next_entry(buf, fp, sizeof(u32)); if (rc < 0) { pr_err("SELinux: avtab: truncated table\n"); goto bad; } nel = le32_to_cpu(buf[0]); if (!nel) { pr_err("SELinux: avtab: table is empty\n"); rc = -EINVAL; goto bad; } rc = avtab_alloc(a, nel); if (rc) goto bad; for (i = 0; i < nel; i++) { rc = avtab_read_item(a, fp, pol, avtab_insertf, NULL); if (rc) { if (rc == -ENOMEM) pr_err("SELinux: avtab: out of memory\n"); else if (rc == -EEXIST) pr_err("SELinux: avtab: duplicate entry\n"); goto bad; } } rc = 0; out: return rc; bad: avtab_destroy(a); goto out; } int avtab_write_item(struct policydb *p, const struct avtab_node *cur, void *fp) { __le16 buf16[4]; __le32 buf32[ARRAY_SIZE(cur->datum.u.xperms->perms.p)]; int rc; unsigned int i; buf16[0] = cpu_to_le16(cur->key.source_type); buf16[1] = cpu_to_le16(cur->key.target_type); buf16[2] = cpu_to_le16(cur->key.target_class); buf16[3] = cpu_to_le16(cur->key.specified); rc = put_entry(buf16, sizeof(u16), 4, fp); if (rc) return rc; if (cur->key.specified & AVTAB_XPERMS) { rc = put_entry(&cur->datum.u.xperms->specified, sizeof(u8), 1, fp); if (rc) return rc; rc = put_entry(&cur->datum.u.xperms->driver, sizeof(u8), 1, fp); if (rc) return rc; for (i = 0; i < ARRAY_SIZE(cur->datum.u.xperms->perms.p); i++) buf32[i] = cpu_to_le32(cur->datum.u.xperms->perms.p[i]); rc = put_entry(buf32, sizeof(u32), ARRAY_SIZE(cur->datum.u.xperms->perms.p), fp); } else { buf32[0] = cpu_to_le32(cur->datum.u.data); rc = put_entry(buf32, sizeof(u32), 1, fp); } if (rc) return rc; return 0; } int avtab_write(struct policydb *p, struct avtab *a, void *fp) { unsigned int i; int rc = 0; struct avtab_node *cur; __le32 buf[1]; buf[0] = cpu_to_le32(a->nel); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; for (i = 0; i < a->nslot; i++) { for (cur = a->htable[i]; cur; cur = cur->next) { rc = avtab_write_item(p, cur, fp); if (rc) return rc; } } return rc; } void __init avtab_cache_init(void) { avtab_node_cachep = kmem_cache_create("avtab_node", sizeof(struct avtab_node), 0, SLAB_PANIC, NULL); avtab_xperms_cachep = kmem_cache_create("avtab_extended_perms", sizeof(struct avtab_extended_perms), 0, SLAB_PANIC, NULL); } |
| 2174 1639 536 536 536 536 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MNT_IDMAPPING_H #define _LINUX_MNT_IDMAPPING_H #include <linux/types.h> #include <linux/uidgid.h> struct user_namespace; /* * Carries the initial idmapping of 0:0:4294967295 which is an identity * mapping. This means that {g,u}id 0 is mapped to {g,u}id 0, {g,u}id 1 is * mapped to {g,u}id 1, [...], {g,u}id 1000 to {g,u}id 1000, [...]. */ extern struct user_namespace init_user_ns; typedef struct { uid_t val; } vfsuid_t; typedef struct { gid_t val; } vfsgid_t; static_assert(sizeof(vfsuid_t) == sizeof(kuid_t)); static_assert(sizeof(vfsgid_t) == sizeof(kgid_t)); static_assert(offsetof(vfsuid_t, val) == offsetof(kuid_t, val)); static_assert(offsetof(vfsgid_t, val) == offsetof(kgid_t, val)); #ifdef CONFIG_MULTIUSER static inline uid_t __vfsuid_val(vfsuid_t uid) { return uid.val; } static inline gid_t __vfsgid_val(vfsgid_t gid) { return gid.val; } #else static inline uid_t __vfsuid_val(vfsuid_t uid) { return 0; } static inline gid_t __vfsgid_val(vfsgid_t gid) { return 0; } #endif static inline bool vfsuid_valid(vfsuid_t uid) { return __vfsuid_val(uid) != (uid_t)-1; } static inline bool vfsgid_valid(vfsgid_t gid) { return __vfsgid_val(gid) != (gid_t)-1; } static inline bool vfsuid_eq(vfsuid_t left, vfsuid_t right) { return vfsuid_valid(left) && __vfsuid_val(left) == __vfsuid_val(right); } static inline bool vfsgid_eq(vfsgid_t left, vfsgid_t right) { return vfsgid_valid(left) && __vfsgid_val(left) == __vfsgid_val(right); } /** * vfsuid_eq_kuid - check whether kuid and vfsuid have the same value * @vfsuid: the vfsuid to compare * @kuid: the kuid to compare * * Check whether @vfsuid and @kuid have the same values. * * Return: true if @vfsuid and @kuid have the same value, false if not. * Comparison between two invalid uids returns false. */ static inline bool vfsuid_eq_kuid(vfsuid_t vfsuid, kuid_t kuid) { return vfsuid_valid(vfsuid) && __vfsuid_val(vfsuid) == __kuid_val(kuid); } /** * vfsgid_eq_kgid - check whether kgid and vfsgid have the same value * @vfsgid: the vfsgid to compare * @kgid: the kgid to compare * * Check whether @vfsgid and @kgid have the same values. * * Return: true if @vfsgid and @kgid have the same value, false if not. * Comparison between two invalid gids returns false. */ static inline bool vfsgid_eq_kgid(vfsgid_t vfsgid, kgid_t kgid) { return vfsgid_valid(vfsgid) && __vfsgid_val(vfsgid) == __kgid_val(kgid); } /* * vfs{g,u}ids are created from k{g,u}ids. * We don't allow them to be created from regular {u,g}id. */ #define VFSUIDT_INIT(val) (vfsuid_t){ __kuid_val(val) } #define VFSGIDT_INIT(val) (vfsgid_t){ __kgid_val(val) } #define INVALID_VFSUID VFSUIDT_INIT(INVALID_UID) #define INVALID_VFSGID VFSGIDT_INIT(INVALID_GID) /* * Allow a vfs{g,u}id to be used as a k{g,u}id where we want to compare * whether the mapped value is identical to value of a k{g,u}id. */ #define AS_KUIDT(val) (kuid_t){ __vfsuid_val(val) } #define AS_KGIDT(val) (kgid_t){ __vfsgid_val(val) } #ifdef CONFIG_MULTIUSER /** * vfsgid_in_group_p() - check whether a vfsuid matches the caller's groups * @vfsgid: the mnt gid to match * * This function can be used to determine whether @vfsuid matches any of the * caller's groups. * * Return: 1 if vfsuid matches caller's groups, 0 if not. */ static inline int vfsgid_in_group_p(vfsgid_t vfsgid) { return in_group_p(AS_KGIDT(vfsgid)); } #else static inline int vfsgid_in_group_p(vfsgid_t vfsgid) { return 1; } #endif /** * initial_idmapping - check whether this is the initial mapping * @ns: idmapping to check * * Check whether this is the initial mapping, mapping 0 to 0, 1 to 1, * [...], 1000 to 1000 [...]. * * Return: true if this is the initial mapping, false if not. */ static inline bool initial_idmapping(const struct user_namespace *ns) { return ns == &init_user_ns; } /** * no_idmapping - check whether we can skip remapping a kuid/gid * @mnt_userns: the mount's idmapping * @fs_userns: the filesystem's idmapping * * This function can be used to check whether a remapping between two * idmappings is required. * An idmapped mount is a mount that has an idmapping attached to it that * is different from the filsystem's idmapping and the initial idmapping. * If the initial mapping is used or the idmapping of the mount and the * filesystem are identical no remapping is required. * * Return: true if remapping can be skipped, false if not. */ static inline bool no_idmapping(const struct user_namespace *mnt_userns, const struct user_namespace *fs_userns) { return initial_idmapping(mnt_userns) || mnt_userns == fs_userns; } /** * make_vfsuid - map a filesystem kuid into a mnt_userns * @mnt_userns: the mount's idmapping * @fs_userns: the filesystem's idmapping * @kuid : kuid to be mapped * * Take a @kuid and remap it from @fs_userns into @mnt_userns. Use this * function when preparing a @kuid to be reported to userspace. * * If no_idmapping() determines that this is not an idmapped mount we can * simply return @kuid unchanged. * If initial_idmapping() tells us that the filesystem is not mounted with an * idmapping we know the value of @kuid won't change when calling * from_kuid() so we can simply retrieve the value via __kuid_val() * directly. * * Return: @kuid mapped according to @mnt_userns. * If @kuid has no mapping in either @mnt_userns or @fs_userns INVALID_UID is * returned. */ static inline vfsuid_t make_vfsuid(struct user_namespace *mnt_userns, struct user_namespace *fs_userns, kuid_t kuid) { uid_t uid; if (no_idmapping(mnt_userns, fs_userns)) return VFSUIDT_INIT(kuid); if (initial_idmapping(fs_userns)) uid = __kuid_val(kuid); else uid = from_kuid(fs_userns, kuid); if (uid == (uid_t)-1) return INVALID_VFSUID; return VFSUIDT_INIT(make_kuid(mnt_userns, uid)); } static inline kuid_t mapped_kuid_fs(struct user_namespace *mnt_userns, struct user_namespace *fs_userns, kuid_t kuid) { return AS_KUIDT(make_vfsuid(mnt_userns, fs_userns, kuid)); } /** * make_vfsgid - map a filesystem kgid into a mnt_userns * @mnt_userns: the mount's idmapping * @fs_userns: the filesystem's idmapping * @kgid : kgid to be mapped * * Take a @kgid and remap it from @fs_userns into @mnt_userns. Use this * function when preparing a @kgid to be reported to userspace. * * If no_idmapping() determines that this is not an idmapped mount we can * simply return @kgid unchanged. * If initial_idmapping() tells us that the filesystem is not mounted with an * idmapping we know the value of @kgid won't change when calling * from_kgid() so we can simply retrieve the value via __kgid_val() * directly. * * Return: @kgid mapped according to @mnt_userns. * If @kgid has no mapping in either @mnt_userns or @fs_userns INVALID_GID is * returned. */ static inline vfsgid_t make_vfsgid(struct user_namespace *mnt_userns, struct user_namespace *fs_userns, kgid_t kgid) { gid_t gid; if (no_idmapping(mnt_userns, fs_userns)) return VFSGIDT_INIT(kgid); if (initial_idmapping(fs_userns)) gid = __kgid_val(kgid); else gid = from_kgid(fs_userns, kgid); if (gid == (gid_t)-1) return INVALID_VFSGID; return VFSGIDT_INIT(make_kgid(mnt_userns, gid)); } static inline kgid_t mapped_kgid_fs(struct user_namespace *mnt_userns, struct user_namespace *fs_userns, kgid_t kgid) { return AS_KGIDT(make_vfsgid(mnt_userns, fs_userns, kgid)); } /** * from_vfsuid - map a vfsuid into the filesystem idmapping * @mnt_userns: the mount's idmapping * @fs_userns: the filesystem's idmapping * @vfsuid : vfsuid to be mapped * * Map @vfsuid into the filesystem idmapping. This function has to be used in * order to e.g. write @vfsuid to inode->i_uid. * * Return: @vfsuid mapped into the filesystem idmapping */ static inline kuid_t from_vfsuid(struct user_namespace *mnt_userns, struct user_namespace *fs_userns, vfsuid_t vfsuid) { uid_t uid; if (no_idmapping(mnt_userns, fs_userns)) return AS_KUIDT(vfsuid); uid = from_kuid(mnt_userns, AS_KUIDT(vfsuid)); if (uid == (uid_t)-1) return INVALID_UID; if (initial_idmapping(fs_userns)) return KUIDT_INIT(uid); return make_kuid(fs_userns, uid); } /** * mapped_kuid_user - map a user kuid into a mnt_userns * @mnt_userns: the mount's idmapping * @fs_userns: the filesystem's idmapping * @kuid : kuid to be mapped * * Use the idmapping of @mnt_userns to remap a @kuid into @fs_userns. Use this * function when preparing a @kuid to be written to disk or inode. * * If no_idmapping() determines that this is not an idmapped mount we can * simply return @kuid unchanged. * If initial_idmapping() tells us that the filesystem is not mounted with an * idmapping we know the value of @kuid won't change when calling * make_kuid() so we can simply retrieve the value via KUIDT_INIT() * directly. * * Return: @kuid mapped according to @mnt_userns. * If @kuid has no mapping in either @mnt_userns or @fs_userns INVALID_UID is * returned. */ static inline kuid_t mapped_kuid_user(struct user_namespace *mnt_userns, struct user_namespace *fs_userns, kuid_t kuid) { return from_vfsuid(mnt_userns, fs_userns, VFSUIDT_INIT(kuid)); } /** * vfsuid_has_fsmapping - check whether a vfsuid maps into the filesystem * @mnt_userns: the mount's idmapping * @fs_userns: the filesystem's idmapping * @vfsuid: vfsuid to be mapped * * Check whether @vfsuid has a mapping in the filesystem idmapping. Use this * function to check whether the filesystem idmapping has a mapping for * @vfsuid. * * Return: true if @vfsuid has a mapping in the filesystem, false if not. */ static inline bool vfsuid_has_fsmapping(struct user_namespace *mnt_userns, struct user_namespace *fs_userns, vfsuid_t vfsuid) { return uid_valid(from_vfsuid(mnt_userns, fs_userns, vfsuid)); } /** * vfsuid_into_kuid - convert vfsuid into kuid * @vfsuid: the vfsuid to convert * * This can be used when a vfsuid is committed as a kuid. * * Return: a kuid with the value of @vfsuid */ static inline kuid_t vfsuid_into_kuid(vfsuid_t vfsuid) { return AS_KUIDT(vfsuid); } /** * from_vfsgid - map a vfsgid into the filesystem idmapping * @mnt_userns: the mount's idmapping * @fs_userns: the filesystem's idmapping * @vfsgid : vfsgid to be mapped * * Map @vfsgid into the filesystem idmapping. This function has to be used in * order to e.g. write @vfsgid to inode->i_gid. * * Return: @vfsgid mapped into the filesystem idmapping */ static inline kgid_t from_vfsgid(struct user_namespace *mnt_userns, struct user_namespace *fs_userns, vfsgid_t vfsgid) { gid_t gid; if (no_idmapping(mnt_userns, fs_userns)) return AS_KGIDT(vfsgid); gid = from_kgid(mnt_userns, AS_KGIDT(vfsgid)); if (gid == (gid_t)-1) return INVALID_GID; if (initial_idmapping(fs_userns)) return KGIDT_INIT(gid); return make_kgid(fs_userns, gid); } /** * mapped_kgid_user - map a user kgid into a mnt_userns * @mnt_userns: the mount's idmapping * @fs_userns: the filesystem's idmapping * @kgid : kgid to be mapped * * Use the idmapping of @mnt_userns to remap a @kgid into @fs_userns. Use this * function when preparing a @kgid to be written to disk or inode. * * If no_idmapping() determines that this is not an idmapped mount we can * simply return @kgid unchanged. * If initial_idmapping() tells us that the filesystem is not mounted with an * idmapping we know the value of @kgid won't change when calling * make_kgid() so we can simply retrieve the value via KGIDT_INIT() * directly. * * Return: @kgid mapped according to @mnt_userns. * If @kgid has no mapping in either @mnt_userns or @fs_userns INVALID_GID is * returned. */ static inline kgid_t mapped_kgid_user(struct user_namespace *mnt_userns, struct user_namespace *fs_userns, kgid_t kgid) { return from_vfsgid(mnt_userns, fs_userns, VFSGIDT_INIT(kgid)); } /** * vfsgid_has_fsmapping - check whether a vfsgid maps into the filesystem * @mnt_userns: the mount's idmapping * @fs_userns: the filesystem's idmapping * @vfsgid: vfsgid to be mapped * * Check whether @vfsgid has a mapping in the filesystem idmapping. Use this * function to check whether the filesystem idmapping has a mapping for * @vfsgid. * * Return: true if @vfsgid has a mapping in the filesystem, false if not. */ static inline bool vfsgid_has_fsmapping(struct user_namespace *mnt_userns, struct user_namespace *fs_userns, vfsgid_t vfsgid) { return gid_valid(from_vfsgid(mnt_userns, fs_userns, vfsgid)); } /** * vfsgid_into_kgid - convert vfsgid into kgid * @vfsgid: the vfsgid to convert * * This can be used when a vfsgid is committed as a kgid. * * Return: a kgid with the value of @vfsgid */ static inline kgid_t vfsgid_into_kgid(vfsgid_t vfsgid) { return AS_KGIDT(vfsgid); } /** * mapped_fsuid - return caller's fsuid mapped up into a mnt_userns * @mnt_userns: the mount's idmapping * @fs_userns: the filesystem's idmapping * * Use this helper to initialize a new vfs or filesystem object based on * the caller's fsuid. A common example is initializing the i_uid field of * a newly allocated inode triggered by a creation event such as mkdir or * O_CREAT. Other examples include the allocation of quotas for a specific * user. * * Return: the caller's current fsuid mapped up according to @mnt_userns. */ static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns, struct user_namespace *fs_userns) { return from_vfsuid(mnt_userns, fs_userns, VFSUIDT_INIT(current_fsuid())); } /** * mapped_fsgid - return caller's fsgid mapped up into a mnt_userns * @mnt_userns: the mount's idmapping * @fs_userns: the filesystem's idmapping * * Use this helper to initialize a new vfs or filesystem object based on * the caller's fsgid. A common example is initializing the i_gid field of * a newly allocated inode triggered by a creation event such as mkdir or * O_CREAT. Other examples include the allocation of quotas for a specific * user. * * Return: the caller's current fsgid mapped up according to @mnt_userns. */ static inline kgid_t mapped_fsgid(struct user_namespace *mnt_userns, struct user_namespace *fs_userns) { return from_vfsgid(mnt_userns, fs_userns, VFSGIDT_INIT(current_fsgid())); } #endif /* _LINUX_MNT_IDMAPPING_H */ |
| 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/stat.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/blkdev.h> #include <linux/export.h> #include <linux/mm.h> #include <linux/errno.h> #include <linux/file.h> #include <linux/highuid.h> #include <linux/fs.h> #include <linux/namei.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/syscalls.h> #include <linux/pagemap.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include "internal.h" #include "mount.h" /** * generic_fillattr - Fill in the basic attributes from the inode struct * @mnt_userns: user namespace of the mount the inode was found from * @inode: Inode to use as the source * @stat: Where to fill in the attributes * * Fill in the basic attributes in the kstat structure from data that's to be * found on the VFS inode structure. This is the default if no getattr inode * operation is supplied. * * If the inode has been found through an idmapped mount the user namespace of * the vfsmount must be passed through @mnt_userns. This function will then * take care to map the inode according to @mnt_userns before filling in the * uid and gid filds. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply passs init_user_ns. */ void generic_fillattr(struct user_namespace *mnt_userns, struct inode *inode, struct kstat *stat) { stat->dev = inode->i_sb->s_dev; stat->ino = inode->i_ino; stat->mode = inode->i_mode; stat->nlink = inode->i_nlink; stat->uid = i_uid_into_mnt(mnt_userns, inode); stat->gid = i_gid_into_mnt(mnt_userns, inode); stat->rdev = inode->i_rdev; stat->size = i_size_read(inode); stat->atime = inode->i_atime; stat->mtime = inode->i_mtime; stat->ctime = inode->i_ctime; stat->blksize = i_blocksize(inode); stat->blocks = inode->i_blocks; } EXPORT_SYMBOL(generic_fillattr); /** * generic_fill_statx_attr - Fill in the statx attributes from the inode flags * @inode: Inode to use as the source * @stat: Where to fill in the attribute flags * * Fill in the STATX_ATTR_* flags in the kstat structure for properties of the * inode that are published on i_flags and enforced by the VFS. */ void generic_fill_statx_attr(struct inode *inode, struct kstat *stat) { if (inode->i_flags & S_IMMUTABLE) stat->attributes |= STATX_ATTR_IMMUTABLE; if (inode->i_flags & S_APPEND) stat->attributes |= STATX_ATTR_APPEND; stat->attributes_mask |= KSTAT_ATTR_VFS_FLAGS; } EXPORT_SYMBOL(generic_fill_statx_attr); /** * vfs_getattr_nosec - getattr without security checks * @path: file to get attributes from * @stat: structure to return attributes in * @request_mask: STATX_xxx flags indicating what the caller wants * @query_flags: Query mode (AT_STATX_SYNC_TYPE) * * Get attributes without calling security_inode_getattr. * * Currently the only caller other than vfs_getattr is internal to the * filehandle lookup code, which uses only the inode number and returns no * attributes to any user. Any other code probably wants vfs_getattr. */ int vfs_getattr_nosec(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct user_namespace *mnt_userns; struct inode *inode = d_backing_inode(path->dentry); memset(stat, 0, sizeof(*stat)); stat->result_mask |= STATX_BASIC_STATS; query_flags &= AT_STATX_SYNC_TYPE; /* allow the fs to override these if it really wants to */ /* SB_NOATIME means filesystem supplies dummy atime value */ if (inode->i_sb->s_flags & SB_NOATIME) stat->result_mask &= ~STATX_ATIME; /* * Note: If you add another clause to set an attribute flag, please * update attributes_mask below. */ if (IS_AUTOMOUNT(inode)) stat->attributes |= STATX_ATTR_AUTOMOUNT; if (IS_DAX(inode)) stat->attributes |= STATX_ATTR_DAX; stat->attributes_mask |= (STATX_ATTR_AUTOMOUNT | STATX_ATTR_DAX); mnt_userns = mnt_user_ns(path->mnt); if (inode->i_op->getattr) return inode->i_op->getattr(mnt_userns, path, stat, request_mask, query_flags); generic_fillattr(mnt_userns, inode, stat); return 0; } EXPORT_SYMBOL(vfs_getattr_nosec); /* * vfs_getattr - Get the enhanced basic attributes of a file * @path: The file of interest * @stat: Where to return the statistics * @request_mask: STATX_xxx flags indicating what the caller wants * @query_flags: Query mode (AT_STATX_SYNC_TYPE) * * Ask the filesystem for a file's attributes. The caller must indicate in * request_mask and query_flags to indicate what they want. * * If the file is remote, the filesystem can be forced to update the attributes * from the backing store by passing AT_STATX_FORCE_SYNC in query_flags or can * suppress the update by passing AT_STATX_DONT_SYNC. * * Bits must have been set in request_mask to indicate which attributes the * caller wants retrieving. Any such attribute not requested may be returned * anyway, but the value may be approximate, and, if remote, may not have been * synchronised with the server. * * 0 will be returned on success, and a -ve error code if unsuccessful. */ int vfs_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { int retval; retval = security_inode_getattr(path); if (retval) return retval; return vfs_getattr_nosec(path, stat, request_mask, query_flags); } EXPORT_SYMBOL(vfs_getattr); /** * vfs_fstat - Get the basic attributes by file descriptor * @fd: The file descriptor referring to the file of interest * @stat: The result structure to fill in. * * This function is a wrapper around vfs_getattr(). The main difference is * that it uses a file descriptor to determine the file location. * * 0 will be returned on success, and a -ve error code if unsuccessful. */ int vfs_fstat(int fd, struct kstat *stat) { struct fd f; int error; f = fdget_raw(fd); if (!f.file) return -EBADF; error = vfs_getattr(&f.file->f_path, stat, STATX_BASIC_STATS, 0); fdput(f); return error; } int getname_statx_lookup_flags(int flags) { int lookup_flags = 0; if (!(flags & AT_SYMLINK_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; if (!(flags & AT_NO_AUTOMOUNT)) lookup_flags |= LOOKUP_AUTOMOUNT; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; return lookup_flags; } /** * vfs_statx - Get basic and extra attributes by filename * @dfd: A file descriptor representing the base dir for a relative filename * @filename: The name of the file of interest * @flags: Flags to control the query * @stat: The result structure to fill in. * @request_mask: STATX_xxx flags indicating what the caller wants * * This function is a wrapper around vfs_getattr(). The main difference is * that it uses a filename and base directory to determine the file location. * Additionally, the use of AT_SYMLINK_NOFOLLOW in flags will prevent a symlink * at the given name from being referenced. * * 0 will be returned on success, and a -ve error code if unsuccessful. */ static int vfs_statx(int dfd, struct filename *filename, int flags, struct kstat *stat, u32 request_mask) { struct path path; unsigned int lookup_flags = getname_statx_lookup_flags(flags); int error; if (flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT | AT_EMPTY_PATH | AT_STATX_SYNC_TYPE)) return -EINVAL; retry: error = filename_lookup(dfd, filename, lookup_flags, &path, NULL); if (error) goto out; error = vfs_getattr(&path, stat, request_mask, flags); stat->mnt_id = real_mount(path.mnt)->mnt_id; stat->result_mask |= STATX_MNT_ID; if (path.mnt->mnt_root == path.dentry) stat->attributes |= STATX_ATTR_MOUNT_ROOT; stat->attributes_mask |= STATX_ATTR_MOUNT_ROOT; /* Handle STATX_DIOALIGN for block devices. */ if (request_mask & STATX_DIOALIGN) { struct inode *inode = d_backing_inode(path.dentry); if (S_ISBLK(inode->i_mode)) bdev_statx_dioalign(inode, stat); } path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: return error; } int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, int flags) { int ret; int statx_flags = flags | AT_NO_AUTOMOUNT; struct filename *name; name = getname_flags(filename, getname_statx_lookup_flags(statx_flags), NULL); ret = vfs_statx(dfd, name, statx_flags, stat, STATX_BASIC_STATS); putname(name); return ret; } #ifdef __ARCH_WANT_OLD_STAT /* * For backward compatibility? Maybe this should be moved * into arch/i386 instead? */ static int cp_old_stat(struct kstat *stat, struct __old_kernel_stat __user * statbuf) { static int warncount = 5; struct __old_kernel_stat tmp; if (warncount > 0) { warncount--; printk(KERN_WARNING "VFS: Warning: %s using old stat() call. Recompile your binary.\n", current->comm); } else if (warncount < 0) { /* it's laughable, but... */ warncount = 0; } memset(&tmp, 0, sizeof(struct __old_kernel_stat)); tmp.st_dev = old_encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; tmp.st_mode = stat->mode; tmp.st_nlink = stat->nlink; if (tmp.st_nlink != stat->nlink) return -EOVERFLOW; SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); tmp.st_rdev = old_encode_dev(stat->rdev); #if BITS_PER_LONG == 32 if (stat->size > MAX_NON_LFS) return -EOVERFLOW; #endif tmp.st_size = stat->size; tmp.st_atime = stat->atime.tv_sec; tmp.st_mtime = stat->mtime.tv_sec; tmp.st_ctime = stat->ctime.tv_sec; return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0; } SYSCALL_DEFINE2(stat, const char __user *, filename, struct __old_kernel_stat __user *, statbuf) { struct kstat stat; int error; error = vfs_stat(filename, &stat); if (error) return error; return cp_old_stat(&stat, statbuf); } SYSCALL_DEFINE2(lstat, const char __user *, filename, struct __old_kernel_stat __user *, statbuf) { struct kstat stat; int error; error = vfs_lstat(filename, &stat); if (error) return error; return cp_old_stat(&stat, statbuf); } SYSCALL_DEFINE2(fstat, unsigned int, fd, struct __old_kernel_stat __user *, statbuf) { struct kstat stat; int error = vfs_fstat(fd, &stat); if (!error) error = cp_old_stat(&stat, statbuf); return error; } #endif /* __ARCH_WANT_OLD_STAT */ #ifdef __ARCH_WANT_NEW_STAT #if BITS_PER_LONG == 32 # define choose_32_64(a,b) a #else # define choose_32_64(a,b) b #endif #ifndef INIT_STRUCT_STAT_PADDING # define INIT_STRUCT_STAT_PADDING(st) memset(&st, 0, sizeof(st)) #endif static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) { struct stat tmp; if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev)) return -EOVERFLOW; if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev)) return -EOVERFLOW; #if BITS_PER_LONG == 32 if (stat->size > MAX_NON_LFS) return -EOVERFLOW; #endif INIT_STRUCT_STAT_PADDING(tmp); tmp.st_dev = new_encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; tmp.st_mode = stat->mode; tmp.st_nlink = stat->nlink; if (tmp.st_nlink != stat->nlink) return -EOVERFLOW; SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); tmp.st_rdev = new_encode_dev(stat->rdev); tmp.st_size = stat->size; tmp.st_atime = stat->atime.tv_sec; tmp.st_mtime = stat->mtime.tv_sec; tmp.st_ctime = stat->ctime.tv_sec; #ifdef STAT_HAVE_NSEC tmp.st_atime_nsec = stat->atime.tv_nsec; tmp.st_mtime_nsec = stat->mtime.tv_nsec; tmp.st_ctime_nsec = stat->ctime.tv_nsec; #endif tmp.st_blocks = stat->blocks; tmp.st_blksize = stat->blksize; return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0; } SYSCALL_DEFINE2(newstat, const char __user *, filename, struct stat __user *, statbuf) { struct kstat stat; int error = vfs_stat(filename, &stat); if (error) return error; return cp_new_stat(&stat, statbuf); } SYSCALL_DEFINE2(newlstat, const char __user *, filename, struct stat __user *, statbuf) { struct kstat stat; int error; error = vfs_lstat(filename, &stat); if (error) return error; return cp_new_stat(&stat, statbuf); } #if !defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_SYS_NEWFSTATAT) SYSCALL_DEFINE4(newfstatat, int, dfd, const char __user *, filename, struct stat __user *, statbuf, int, flag) { struct kstat stat; int error; error = vfs_fstatat(dfd, filename, &stat, flag); if (error) return error; return cp_new_stat(&stat, statbuf); } #endif SYSCALL_DEFINE2(newfstat, unsigned int, fd, struct stat __user *, statbuf) { struct kstat stat; int error = vfs_fstat(fd, &stat); if (!error) error = cp_new_stat(&stat, statbuf); return error; } #endif static int do_readlinkat(int dfd, const char __user *pathname, char __user *buf, int bufsiz) { struct path path; int error; int empty = 0; unsigned int lookup_flags = LOOKUP_EMPTY; if (bufsiz <= 0) return -EINVAL; retry: error = user_path_at_empty(dfd, pathname, lookup_flags, &path, &empty); if (!error) { struct inode *inode = d_backing_inode(path.dentry); error = empty ? -ENOENT : -EINVAL; /* * AFS mountpoints allow readlink(2) but are not symlinks */ if (d_is_symlink(path.dentry) || inode->i_op->readlink) { error = security_inode_readlink(path.dentry); if (!error) { touch_atime(&path); error = vfs_readlink(path.dentry, buf, bufsiz); } } path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } } return error; } SYSCALL_DEFINE4(readlinkat, int, dfd, const char __user *, pathname, char __user *, buf, int, bufsiz) { return do_readlinkat(dfd, pathname, buf, bufsiz); } SYSCALL_DEFINE3(readlink, const char __user *, path, char __user *, buf, int, bufsiz) { return do_readlinkat(AT_FDCWD, path, buf, bufsiz); } /* ---------- LFS-64 ----------- */ #if defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_COMPAT_STAT64) #ifndef INIT_STRUCT_STAT64_PADDING # define INIT_STRUCT_STAT64_PADDING(st) memset(&st, 0, sizeof(st)) #endif static long cp_new_stat64(struct kstat *stat, struct stat64 __user *statbuf) { struct stat64 tmp; INIT_STRUCT_STAT64_PADDING(tmp); #ifdef CONFIG_MIPS /* mips has weird padding, so we don't get 64 bits there */ tmp.st_dev = new_encode_dev(stat->dev); tmp.st_rdev = new_encode_dev(stat->rdev); #else tmp.st_dev = huge_encode_dev(stat->dev); tmp.st_rdev = huge_encode_dev(stat->rdev); #endif tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; #ifdef STAT64_HAS_BROKEN_ST_INO tmp.__st_ino = stat->ino; #endif tmp.st_mode = stat->mode; tmp.st_nlink = stat->nlink; tmp.st_uid = from_kuid_munged(current_user_ns(), stat->uid); tmp.st_gid = from_kgid_munged(current_user_ns(), stat->gid); tmp.st_atime = stat->atime.tv_sec; tmp.st_atime_nsec = stat->atime.tv_nsec; tmp.st_mtime = stat->mtime.tv_sec; tmp.st_mtime_nsec = stat->mtime.tv_nsec; tmp.st_ctime = stat->ctime.tv_sec; tmp.st_ctime_nsec = stat->ctime.tv_nsec; tmp.st_size = stat->size; tmp.st_blocks = stat->blocks; tmp.st_blksize = stat->blksize; return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0; } SYSCALL_DEFINE2(stat64, const char __user *, filename, struct stat64 __user *, statbuf) { struct kstat stat; int error = vfs_stat(filename, &stat); if (!error) error = cp_new_stat64(&stat, statbuf); return error; } SYSCALL_DEFINE2(lstat64, const char __user *, filename, struct stat64 __user *, statbuf) { struct kstat stat; int error = vfs_lstat(filename, &stat); if (!error) error = cp_new_stat64(&stat, statbuf); return error; } SYSCALL_DEFINE2(fstat64, unsigned long, fd, struct stat64 __user *, statbuf) { struct kstat stat; int error = vfs_fstat(fd, &stat); if (!error) error = cp_new_stat64(&stat, statbuf); return error; } SYSCALL_DEFINE4(fstatat64, int, dfd, const char __user *, filename, struct stat64 __user *, statbuf, int, flag) { struct kstat stat; int error; error = vfs_fstatat(dfd, filename, &stat, flag); if (error) return error; return cp_new_stat64(&stat, statbuf); } #endif /* __ARCH_WANT_STAT64 || __ARCH_WANT_COMPAT_STAT64 */ static noinline_for_stack int cp_statx(const struct kstat *stat, struct statx __user *buffer) { struct statx tmp; memset(&tmp, 0, sizeof(tmp)); tmp.stx_mask = stat->result_mask; tmp.stx_blksize = stat->blksize; tmp.stx_attributes = stat->attributes; tmp.stx_nlink = stat->nlink; tmp.stx_uid = from_kuid_munged(current_user_ns(), stat->uid); tmp.stx_gid = from_kgid_munged(current_user_ns(), stat->gid); tmp.stx_mode = stat->mode; tmp.stx_ino = stat->ino; tmp.stx_size = stat->size; tmp.stx_blocks = stat->blocks; tmp.stx_attributes_mask = stat->attributes_mask; tmp.stx_atime.tv_sec = stat->atime.tv_sec; tmp.stx_atime.tv_nsec = stat->atime.tv_nsec; tmp.stx_btime.tv_sec = stat->btime.tv_sec; tmp.stx_btime.tv_nsec = stat->btime.tv_nsec; tmp.stx_ctime.tv_sec = stat->ctime.tv_sec; tmp.stx_ctime.tv_nsec = stat->ctime.tv_nsec; tmp.stx_mtime.tv_sec = stat->mtime.tv_sec; tmp.stx_mtime.tv_nsec = stat->mtime.tv_nsec; tmp.stx_rdev_major = MAJOR(stat->rdev); tmp.stx_rdev_minor = MINOR(stat->rdev); tmp.stx_dev_major = MAJOR(stat->dev); tmp.stx_dev_minor = MINOR(stat->dev); tmp.stx_mnt_id = stat->mnt_id; tmp.stx_dio_mem_align = stat->dio_mem_align; tmp.stx_dio_offset_align = stat->dio_offset_align; return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0; } int do_statx(int dfd, struct filename *filename, unsigned int flags, unsigned int mask, struct statx __user *buffer) { struct kstat stat; int error; if (mask & STATX__RESERVED) return -EINVAL; if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE) return -EINVAL; error = vfs_statx(dfd, filename, flags, &stat, mask); if (error) return error; return cp_statx(&stat, buffer); } /** * sys_statx - System call to get enhanced stats * @dfd: Base directory to pathwalk from *or* fd to stat. * @filename: File to stat or "" with AT_EMPTY_PATH * @flags: AT_* flags to control pathwalk. * @mask: Parts of statx struct actually required. * @buffer: Result buffer. * * Note that fstat() can be emulated by setting dfd to the fd of interest, * supplying "" as the filename and setting AT_EMPTY_PATH in the flags. */ SYSCALL_DEFINE5(statx, int, dfd, const char __user *, filename, unsigned, flags, unsigned int, mask, struct statx __user *, buffer) { int ret; struct filename *name; name = getname_flags(filename, getname_statx_lookup_flags(flags), NULL); ret = do_statx(dfd, name, flags, mask, buffer); putname(name); return ret; } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_STAT) static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) { struct compat_stat tmp; if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev)) return -EOVERFLOW; if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev)) return -EOVERFLOW; memset(&tmp, 0, sizeof(tmp)); tmp.st_dev = new_encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; tmp.st_mode = stat->mode; tmp.st_nlink = stat->nlink; if (tmp.st_nlink != stat->nlink) return -EOVERFLOW; SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); tmp.st_rdev = new_encode_dev(stat->rdev); if ((u64) stat->size > MAX_NON_LFS) return -EOVERFLOW; tmp.st_size = stat->size; tmp.st_atime = stat->atime.tv_sec; tmp.st_atime_nsec = stat->atime.tv_nsec; tmp.st_mtime = stat->mtime.tv_sec; tmp.st_mtime_nsec = stat->mtime.tv_nsec; tmp.st_ctime = stat->ctime.tv_sec; tmp.st_ctime_nsec = stat->ctime.tv_nsec; tmp.st_blocks = stat->blocks; tmp.st_blksize = stat->blksize; return copy_to_user(ubuf, &tmp, sizeof(tmp)) ? -EFAULT : 0; } COMPAT_SYSCALL_DEFINE2(newstat, const char __user *, filename, struct compat_stat __user *, statbuf) { struct kstat stat; int error; error = vfs_stat(filename, &stat); if (error) return error; return cp_compat_stat(&stat, statbuf); } COMPAT_SYSCALL_DEFINE2(newlstat, const char __user *, filename, struct compat_stat __user *, statbuf) { struct kstat stat; int error; error = vfs_lstat(filename, &stat); if (error) return error; return cp_compat_stat(&stat, statbuf); } #ifndef __ARCH_WANT_STAT64 COMPAT_SYSCALL_DEFINE4(newfstatat, unsigned int, dfd, const char __user *, filename, struct compat_stat __user *, statbuf, int, flag) { struct kstat stat; int error; error = vfs_fstatat(dfd, filename, &stat, flag); if (error) return error; return cp_compat_stat(&stat, statbuf); } #endif COMPAT_SYSCALL_DEFINE2(newfstat, unsigned int, fd, struct compat_stat __user *, statbuf) { struct kstat stat; int error = vfs_fstat(fd, &stat); if (!error) error = cp_compat_stat(&stat, statbuf); return error; } #endif /* Caller is here responsible for sufficient locking (ie. inode->i_lock) */ void __inode_add_bytes(struct inode *inode, loff_t bytes) { inode->i_blocks += bytes >> 9; bytes &= 511; inode->i_bytes += bytes; if (inode->i_bytes >= 512) { inode->i_blocks++; inode->i_bytes -= 512; } } EXPORT_SYMBOL(__inode_add_bytes); void inode_add_bytes(struct inode *inode, loff_t bytes) { spin_lock(&inode->i_lock); __inode_add_bytes(inode, bytes); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(inode_add_bytes); void __inode_sub_bytes(struct inode *inode, loff_t bytes) { inode->i_blocks -= bytes >> 9; bytes &= 511; if (inode->i_bytes < bytes) { inode->i_blocks--; inode->i_bytes += 512; } inode->i_bytes -= bytes; } EXPORT_SYMBOL(__inode_sub_bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes) { spin_lock(&inode->i_lock); __inode_sub_bytes(inode, bytes); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(inode_sub_bytes); loff_t inode_get_bytes(struct inode *inode) { loff_t ret; spin_lock(&inode->i_lock); ret = __inode_get_bytes(inode); spin_unlock(&inode->i_lock); return ret; } EXPORT_SYMBOL(inode_get_bytes); void inode_set_bytes(struct inode *inode, loff_t bytes) { /* Caller is here responsible for sufficient locking * (ie. inode->i_lock) */ inode->i_blocks = bytes >> 9; inode->i_bytes = bytes & 511; } EXPORT_SYMBOL(inode_set_bytes); |
| 1434 1433 1434 587 587 587 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Generic Timer-queue * * Manages a simple queue of timers, ordered by expiration time. * Uses rbtrees for quick list adds and expiration. * * NOTE: All of the following functions need to be serialized * to avoid races. No locking is done by this library code. */ #include <linux/bug.h> #include <linux/timerqueue.h> #include <linux/rbtree.h> #include <linux/export.h> #define __node_2_tq(_n) \ rb_entry((_n), struct timerqueue_node, node) static inline bool __timerqueue_less(struct rb_node *a, const struct rb_node *b) { return __node_2_tq(a)->expires < __node_2_tq(b)->expires; } /** * timerqueue_add - Adds timer to timerqueue. * * @head: head of timerqueue * @node: timer node to be added * * Adds the timer node to the timerqueue, sorted by the node's expires * value. Returns true if the newly added timer is the first expiring timer in * the queue. */ bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node) { /* Make sure we don't add nodes that are already added */ WARN_ON_ONCE(!RB_EMPTY_NODE(&node->node)); return rb_add_cached(&node->node, &head->rb_root, __timerqueue_less); } EXPORT_SYMBOL_GPL(timerqueue_add); /** * timerqueue_del - Removes a timer from the timerqueue. * * @head: head of timerqueue * @node: timer node to be removed * * Removes the timer node from the timerqueue. Returns true if the queue is * not empty after the remove. */ bool timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node) { WARN_ON_ONCE(RB_EMPTY_NODE(&node->node)); rb_erase_cached(&node->node, &head->rb_root); RB_CLEAR_NODE(&node->node); return !RB_EMPTY_ROOT(&head->rb_root.rb_root); } EXPORT_SYMBOL_GPL(timerqueue_del); /** * timerqueue_iterate_next - Returns the timer after the provided timer * * @node: Pointer to a timer. * * Provides the timer that is after the given node. This is used, when * necessary, to iterate through the list of timers in a timer list * without modifying the list. */ struct timerqueue_node *timerqueue_iterate_next(struct timerqueue_node *node) { struct rb_node *next; if (!node) return NULL; next = rb_next(&node->node); if (!next) return NULL; return container_of(next, struct timerqueue_node, node); } EXPORT_SYMBOL_GPL(timerqueue_iterate_next); |
| 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs */ #ifndef _ASM_X86_STACKTRACE_H #define _ASM_X86_STACKTRACE_H #include <linux/uaccess.h> #include <linux/ptrace.h> #include <asm/cpu_entry_area.h> #include <asm/switch_to.h> enum stack_type { STACK_TYPE_UNKNOWN, STACK_TYPE_TASK, STACK_TYPE_IRQ, STACK_TYPE_SOFTIRQ, STACK_TYPE_ENTRY, STACK_TYPE_EXCEPTION, STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1, }; struct stack_info { enum stack_type type; unsigned long *begin, *end, *next_sp; }; bool in_task_stack(unsigned long *stack, struct task_struct *task, struct stack_info *info); bool in_entry_stack(unsigned long *stack, struct stack_info *info); int get_stack_info(unsigned long *stack, struct task_struct *task, struct stack_info *info, unsigned long *visit_mask); bool get_stack_info_noinstr(unsigned long *stack, struct task_struct *task, struct stack_info *info); static __always_inline bool get_stack_guard_info(unsigned long *stack, struct stack_info *info) { /* make sure it's not in the stack proper */ if (get_stack_info_noinstr(stack, current, info)) return false; /* but if it is in the page below it, we hit a guard */ return get_stack_info_noinstr((void *)stack + PAGE_SIZE, current, info); } const char *stack_type_name(enum stack_type type); static inline bool on_stack(struct stack_info *info, void *addr, size_t len) { void *begin = info->begin; void *end = info->end; return (info->type != STACK_TYPE_UNKNOWN && addr >= begin && addr < end && addr + len > begin && addr + len <= end); } #ifdef CONFIG_X86_32 #define STACKSLOTS_PER_LINE 8 #else #define STACKSLOTS_PER_LINE 4 #endif #ifdef CONFIG_FRAME_POINTER static inline unsigned long * get_frame_pointer(struct task_struct *task, struct pt_regs *regs) { if (regs) return (unsigned long *)regs->bp; if (task == current) return __builtin_frame_address(0); return &((struct inactive_task_frame *)task->thread.sp)->bp; } #else static inline unsigned long * get_frame_pointer(struct task_struct *task, struct pt_regs *regs) { return NULL; } #endif /* CONFIG_FRAME_POINTER */ static inline unsigned long * get_stack_pointer(struct task_struct *task, struct pt_regs *regs) { if (regs) return (unsigned long *)regs->sp; if (task == current) return __builtin_frame_address(0); return (unsigned long *)task->thread.sp; } /* The form of the top of the frame on the stack */ struct stack_frame { struct stack_frame *next_frame; unsigned long return_address; }; struct stack_frame_ia32 { u32 next_frame; u32 return_address; }; void show_opcodes(struct pt_regs *regs, const char *loglvl); void show_ip(struct pt_regs *regs, const char *loglvl); #endif /* _ASM_X86_STACKTRACE_H */ |
| 255 253 253 253 254 255 253 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 | // SPDX-License-Identifier: GPL-2.0-only /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> */ #include <linux/types.h> #include <linux/export.h> #include <linux/init.h> #include <linux/udp.h> #include <linux/tcp.h> #include <linux/icmp.h> #include <linux/icmpv6.h> #include <linux/dccp.h> #include <linux/sctp.h> #include <net/sctp/checksum.h> #include <linux/netfilter.h> #include <net/netfilter/nf_nat.h> #include <linux/ipv6.h> #include <linux/netfilter_ipv6.h> #include <net/checksum.h> #include <net/ip6_checksum.h> #include <net/ip6_route.h> #include <net/xfrm.h> #include <net/ipv6.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack.h> #include <linux/netfilter/nfnetlink_conntrack.h> static void nf_csum_update(struct sk_buff *skb, unsigned int iphdroff, __sum16 *check, const struct nf_conntrack_tuple *t, enum nf_nat_manip_type maniptype); static void __udp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, struct udphdr *hdr, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype, bool do_csum) { __be16 *portptr, newport; if (maniptype == NF_NAT_MANIP_SRC) { /* Get rid of src port */ newport = tuple->src.u.udp.port; portptr = &hdr->source; } else { /* Get rid of dst port */ newport = tuple->dst.u.udp.port; portptr = &hdr->dest; } if (do_csum) { nf_csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport, false); if (!hdr->check) hdr->check = CSUM_MANGLED_0; } *portptr = newport; } static bool udp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { struct udphdr *hdr; if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct udphdr *)(skb->data + hdroff); __udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, !!hdr->check); return true; } static bool udplite_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { #ifdef CONFIG_NF_CT_PROTO_UDPLITE struct udphdr *hdr; if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct udphdr *)(skb->data + hdroff); __udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, true); #endif return true; } static bool sctp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { #ifdef CONFIG_NF_CT_PROTO_SCTP struct sctphdr *hdr; int hdrsize = 8; /* This could be an inner header returned in imcp packet; in such * cases we cannot update the checksum field since it is outside * of the 8 bytes of transport layer headers we are guaranteed. */ if (skb->len >= hdroff + sizeof(*hdr)) hdrsize = sizeof(*hdr); if (skb_ensure_writable(skb, hdroff + hdrsize)) return false; hdr = (struct sctphdr *)(skb->data + hdroff); if (maniptype == NF_NAT_MANIP_SRC) { /* Get rid of src port */ hdr->source = tuple->src.u.sctp.port; } else { /* Get rid of dst port */ hdr->dest = tuple->dst.u.sctp.port; } if (hdrsize < sizeof(*hdr)) return true; if (skb->ip_summed != CHECKSUM_PARTIAL) { hdr->checksum = sctp_compute_cksum(skb, hdroff); skb->ip_summed = CHECKSUM_NONE; } #endif return true; } static bool tcp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { struct tcphdr *hdr; __be16 *portptr, newport, oldport; int hdrsize = 8; /* TCP connection tracking guarantees this much */ /* this could be a inner header returned in icmp packet; in such cases we cannot update the checksum field since it is outside of the 8 bytes of transport layer headers we are guaranteed */ if (skb->len >= hdroff + sizeof(struct tcphdr)) hdrsize = sizeof(struct tcphdr); if (skb_ensure_writable(skb, hdroff + hdrsize)) return false; hdr = (struct tcphdr *)(skb->data + hdroff); if (maniptype == NF_NAT_MANIP_SRC) { /* Get rid of src port */ newport = tuple->src.u.tcp.port; portptr = &hdr->source; } else { /* Get rid of dst port */ newport = tuple->dst.u.tcp.port; portptr = &hdr->dest; } oldport = *portptr; *portptr = newport; if (hdrsize < sizeof(*hdr)) return true; nf_csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); inet_proto_csum_replace2(&hdr->check, skb, oldport, newport, false); return true; } static bool dccp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { #ifdef CONFIG_NF_CT_PROTO_DCCP struct dccp_hdr *hdr; __be16 *portptr, oldport, newport; int hdrsize = 8; /* DCCP connection tracking guarantees this much */ if (skb->len >= hdroff + sizeof(struct dccp_hdr)) hdrsize = sizeof(struct dccp_hdr); if (skb_ensure_writable(skb, hdroff + hdrsize)) return false; hdr = (struct dccp_hdr *)(skb->data + hdroff); if (maniptype == NF_NAT_MANIP_SRC) { newport = tuple->src.u.dccp.port; portptr = &hdr->dccph_sport; } else { newport = tuple->dst.u.dccp.port; portptr = &hdr->dccph_dport; } oldport = *portptr; *portptr = newport; if (hdrsize < sizeof(*hdr)) return true; nf_csum_update(skb, iphdroff, &hdr->dccph_checksum, tuple, maniptype); inet_proto_csum_replace2(&hdr->dccph_checksum, skb, oldport, newport, false); #endif return true; } static bool icmp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { struct icmphdr *hdr; if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct icmphdr *)(skb->data + hdroff); switch (hdr->type) { case ICMP_ECHO: case ICMP_ECHOREPLY: case ICMP_TIMESTAMP: case ICMP_TIMESTAMPREPLY: case ICMP_INFO_REQUEST: case ICMP_INFO_REPLY: case ICMP_ADDRESS: case ICMP_ADDRESSREPLY: break; default: return true; } inet_proto_csum_replace2(&hdr->checksum, skb, hdr->un.echo.id, tuple->src.u.icmp.id, false); hdr->un.echo.id = tuple->src.u.icmp.id; return true; } static bool icmpv6_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { struct icmp6hdr *hdr; if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct icmp6hdr *)(skb->data + hdroff); nf_csum_update(skb, iphdroff, &hdr->icmp6_cksum, tuple, maniptype); if (hdr->icmp6_type == ICMPV6_ECHO_REQUEST || hdr->icmp6_type == ICMPV6_ECHO_REPLY) { inet_proto_csum_replace2(&hdr->icmp6_cksum, skb, hdr->icmp6_identifier, tuple->src.u.icmp.id, false); hdr->icmp6_identifier = tuple->src.u.icmp.id; } return true; } /* manipulate a GRE packet according to maniptype */ static bool gre_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { #if IS_ENABLED(CONFIG_NF_CT_PROTO_GRE) const struct gre_base_hdr *greh; struct pptp_gre_header *pgreh; /* pgreh includes two optional 32bit fields which are not required * to be there. That's where the magic '8' comes from */ if (skb_ensure_writable(skb, hdroff + sizeof(*pgreh) - 8)) return false; greh = (void *)skb->data + hdroff; pgreh = (struct pptp_gre_header *)greh; /* we only have destination manip of a packet, since 'source key' * is not present in the packet itself */ if (maniptype != NF_NAT_MANIP_DST) return true; switch (greh->flags & GRE_VERSION) { case GRE_VERSION_0: /* We do not currently NAT any GREv0 packets. * Try to behave like "nf_nat_proto_unknown" */ break; case GRE_VERSION_1: pr_debug("call_id -> 0x%04x\n", ntohs(tuple->dst.u.gre.key)); pgreh->call_id = tuple->dst.u.gre.key; break; default: pr_debug("can't nat unknown GRE version\n"); return false; } #endif return true; } static bool l4proto_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { switch (tuple->dst.protonum) { case IPPROTO_TCP: return tcp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_UDP: return udp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_UDPLITE: return udplite_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_SCTP: return sctp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_ICMP: return icmp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_ICMPV6: return icmpv6_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_DCCP: return dccp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_GRE: return gre_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); } /* If we don't know protocol -- no error, pass it unmodified. */ return true; } static bool nf_nat_ipv4_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, const struct nf_conntrack_tuple *target, enum nf_nat_manip_type maniptype) { struct iphdr *iph; unsigned int hdroff; if (skb_ensure_writable(skb, iphdroff + sizeof(*iph))) return false; iph = (void *)skb->data + iphdroff; hdroff = iphdroff + iph->ihl * 4; if (!l4proto_manip_pkt(skb, iphdroff, hdroff, target, maniptype)) return false; iph = (void *)skb->data + iphdroff; if (maniptype == NF_NAT_MANIP_SRC) { csum_replace4(&iph->check, iph->saddr, target->src.u3.ip); iph->saddr = target->src.u3.ip; } else { csum_replace4(&iph->check, iph->daddr, target->dst.u3.ip); iph->daddr = target->dst.u3.ip; } return true; } static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, const struct nf_conntrack_tuple *target, enum nf_nat_manip_type maniptype) { #if IS_ENABLED(CONFIG_IPV6) struct ipv6hdr *ipv6h; __be16 frag_off; int hdroff; u8 nexthdr; if (skb_ensure_writable(skb, iphdroff + sizeof(*ipv6h))) return false; ipv6h = (void *)skb->data + iphdroff; nexthdr = ipv6h->nexthdr; hdroff = ipv6_skip_exthdr(skb, iphdroff + sizeof(*ipv6h), &nexthdr, &frag_off); if (hdroff < 0) goto manip_addr; if ((frag_off & htons(~0x7)) == 0 && !l4proto_manip_pkt(skb, iphdroff, hdroff, target, maniptype)) return false; /* must reload, offset might have changed */ ipv6h = (void *)skb->data + iphdroff; manip_addr: if (maniptype == NF_NAT_MANIP_SRC) ipv6h->saddr = target->src.u3.in6; else ipv6h->daddr = target->dst.u3.in6; #endif return true; } unsigned int nf_nat_manip_pkt(struct sk_buff *skb, struct nf_conn *ct, enum nf_nat_manip_type mtype, enum ip_conntrack_dir dir) { struct nf_conntrack_tuple target; /* We are aiming to look like inverse of other direction. */ nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); switch (target.src.l3num) { case NFPROTO_IPV6: if (nf_nat_ipv6_manip_pkt(skb, 0, &target, mtype)) return NF_ACCEPT; break; case NFPROTO_IPV4: if (nf_nat_ipv4_manip_pkt(skb, 0, &target, mtype)) return NF_ACCEPT; break; default: WARN_ON_ONCE(1); break; } return NF_DROP; } static void nf_nat_ipv4_csum_update(struct sk_buff *skb, unsigned int iphdroff, __sum16 *check, const struct nf_conntrack_tuple *t, enum nf_nat_manip_type maniptype) { struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff); __be32 oldip, newip; if (maniptype == NF_NAT_MANIP_SRC) { oldip = iph->saddr; newip = t->src.u3.ip; } else { oldip = iph->daddr; newip = t->dst.u3.ip; } inet_proto_csum_replace4(check, skb, oldip, newip, true); } static void nf_nat_ipv6_csum_update(struct sk_buff *skb, unsigned int iphdroff, __sum16 *check, const struct nf_conntrack_tuple *t, enum nf_nat_manip_type maniptype) { #if IS_ENABLED(CONFIG_IPV6) const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + iphdroff); const struct in6_addr *oldip, *newip; if (maniptype == NF_NAT_MANIP_SRC) { oldip = &ipv6h->saddr; newip = &t->src.u3.in6; } else { oldip = &ipv6h->daddr; newip = &t->dst.u3.in6; } inet_proto_csum_replace16(check, skb, oldip->s6_addr32, newip->s6_addr32, true); #endif } static void nf_csum_update(struct sk_buff *skb, unsigned int iphdroff, __sum16 *check, const struct nf_conntrack_tuple *t, enum nf_nat_manip_type maniptype) { switch (t->src.l3num) { case NFPROTO_IPV4: nf_nat_ipv4_csum_update(skb, iphdroff, check, t, maniptype); return; case NFPROTO_IPV6: nf_nat_ipv6_csum_update(skb, iphdroff, check, t, maniptype); return; } } static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb, u8 proto, void *data, __sum16 *check, int datalen, int oldlen) { if (skb->ip_summed != CHECKSUM_PARTIAL) { const struct iphdr *iph = ip_hdr(skb); skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) + ip_hdrlen(skb); skb->csum_offset = (void *)check - data; *check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, datalen, proto, 0); } else { inet_proto_csum_replace2(check, skb, htons(oldlen), htons(datalen), true); } } #if IS_ENABLED(CONFIG_IPV6) static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb, u8 proto, void *data, __sum16 *check, int datalen, int oldlen) { if (skb->ip_summed != CHECKSUM_PARTIAL) { const struct ipv6hdr *ipv6h = ipv6_hdr(skb); skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) + (data - (void *)skb->data); skb->csum_offset = (void *)check - data; *check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, datalen, proto, 0); } else { inet_proto_csum_replace2(check, skb, htons(oldlen), htons(datalen), true); } } #endif void nf_nat_csum_recalc(struct sk_buff *skb, u8 nfproto, u8 proto, void *data, __sum16 *check, int datalen, int oldlen) { switch (nfproto) { case NFPROTO_IPV4: nf_nat_ipv4_csum_recalc(skb, proto, data, check, datalen, oldlen); return; #if IS_ENABLED(CONFIG_IPV6) case NFPROTO_IPV6: nf_nat_ipv6_csum_recalc(skb, proto, data, check, datalen, oldlen); return; #endif } WARN_ON_ONCE(1); } int nf_nat_icmp_reply_translation(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum) { struct { struct icmphdr icmp; struct iphdr ip; } *inside; enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); enum nf_nat_manip_type manip = HOOK2MANIP(hooknum); unsigned int hdrlen = ip_hdrlen(skb); struct nf_conntrack_tuple target; unsigned long statusbit; WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY); if (skb_ensure_writable(skb, hdrlen + sizeof(*inside))) return 0; if (nf_ip_checksum(skb, hooknum, hdrlen, IPPROTO_ICMP)) return 0; inside = (void *)skb->data + hdrlen; if (inside->icmp.type == ICMP_REDIRECT) { if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK) return 0; if (ct->status & IPS_NAT_MASK) return 0; } if (manip == NF_NAT_MANIP_SRC) statusbit = IPS_SRC_NAT; else statusbit = IPS_DST_NAT; /* Invert if this is reply direction */ if (dir == IP_CT_DIR_REPLY) statusbit ^= IPS_NAT_MASK; if (!(ct->status & statusbit)) return 1; if (!nf_nat_ipv4_manip_pkt(skb, hdrlen + sizeof(inside->icmp), &ct->tuplehash[!dir].tuple, !manip)) return 0; if (skb->ip_summed != CHECKSUM_PARTIAL) { /* Reloading "inside" here since manip_pkt may reallocate */ inside = (void *)skb->data + hdrlen; inside->icmp.checksum = 0; inside->icmp.checksum = csum_fold(skb_checksum(skb, hdrlen, skb->len - hdrlen, 0)); } /* Change outer to look like the reply to an incoming packet */ nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); target.dst.protonum = IPPROTO_ICMP; if (!nf_nat_ipv4_manip_pkt(skb, 0, &target, manip)) return 0; return 1; } EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation); static unsigned int nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; ct = nf_ct_get(skb, &ctinfo); if (!ct) return NF_ACCEPT; if (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY) { if (ip_hdr(skb)->protocol == IPPROTO_ICMP) { if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, state->hook)) return NF_DROP; else return NF_ACCEPT; } } return nf_nat_inet_fn(priv, skb, state); } static unsigned int nf_nat_ipv4_pre_routing(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { unsigned int ret; __be32 daddr = ip_hdr(skb)->daddr; ret = nf_nat_ipv4_fn(priv, skb, state); if (ret == NF_ACCEPT && daddr != ip_hdr(skb)->daddr) skb_dst_drop(skb); return ret; } #ifdef CONFIG_XFRM static int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family) { struct sock *sk = skb->sk; struct dst_entry *dst; unsigned int hh_len; struct flowi fl; int err; err = xfrm_decode_session(skb, &fl, family); if (err < 0) return err; dst = skb_dst(skb); if (dst->xfrm) dst = ((struct xfrm_dst *)dst)->route; if (!dst_hold_safe(dst)) return -EHOSTUNREACH; if (sk && !net_eq(net, sock_net(sk))) sk = NULL; dst = xfrm_lookup(net, dst, &fl, sk, 0); if (IS_ERR(dst)) return PTR_ERR(dst); skb_dst_drop(skb); skb_dst_set(skb, dst); /* Change in oif may mean change in hh_len. */ hh_len = skb_dst(skb)->dev->hard_header_len; if (skb_headroom(skb) < hh_len && pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC)) return -ENOMEM; return 0; } #endif static unsigned int nf_nat_ipv4_local_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { __be32 saddr = ip_hdr(skb)->saddr; struct sock *sk = skb->sk; unsigned int ret; ret = nf_nat_ipv4_fn(priv, skb, state); if (ret == NF_ACCEPT && sk && saddr != ip_hdr(skb)->saddr && !inet_sk_transparent(sk)) skb_orphan(skb); /* TCP edemux obtained wrong socket */ return ret; } static unsigned int nf_nat_ipv4_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { #ifdef CONFIG_XFRM const struct nf_conn *ct; enum ip_conntrack_info ctinfo; int err; #endif unsigned int ret; ret = nf_nat_ipv4_fn(priv, skb, state); #ifdef CONFIG_XFRM if (ret != NF_ACCEPT) return ret; if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) return ret; ct = nf_ct_get(skb, &ctinfo); if (ct) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (ct->tuplehash[dir].tuple.src.u3.ip != ct->tuplehash[!dir].tuple.dst.u3.ip || (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all)) { err = nf_xfrm_me_harder(state->net, skb, AF_INET); if (err < 0) ret = NF_DROP_ERR(err); } } #endif return ret; } static unsigned int nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { const struct nf_conn *ct; enum ip_conntrack_info ctinfo; unsigned int ret; int err; ret = nf_nat_ipv4_fn(priv, skb, state); if (ret != NF_ACCEPT) return ret; ct = nf_ct_get(skb, &ctinfo); if (ct) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (ct->tuplehash[dir].tuple.dst.u3.ip != ct->tuplehash[!dir].tuple.src.u3.ip) { err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } #ifdef CONFIG_XFRM else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && ct->tuplehash[dir].tuple.dst.u.all != ct->tuplehash[!dir].tuple.src.u.all) { err = nf_xfrm_me_harder(state->net, skb, AF_INET); if (err < 0) ret = NF_DROP_ERR(err); } #endif } return ret; } static const struct nf_hook_ops nf_nat_ipv4_ops[] = { /* Before packet filtering, change destination */ { .hook = nf_nat_ipv4_pre_routing, .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_NAT_DST, }, /* After packet filtering, change source */ { .hook = nf_nat_ipv4_out, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_NAT_SRC, }, /* Before packet filtering, change destination */ { .hook = nf_nat_ipv4_local_fn, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST, }, /* After packet filtering, change source */ { .hook = nf_nat_ipv4_local_in, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC, }, }; int nf_nat_ipv4_register_fn(struct net *net, const struct nf_hook_ops *ops) { return nf_nat_register_fn(net, ops->pf, ops, nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops)); } EXPORT_SYMBOL_GPL(nf_nat_ipv4_register_fn); void nf_nat_ipv4_unregister_fn(struct net *net, const struct nf_hook_ops *ops) { nf_nat_unregister_fn(net, ops->pf, ops, ARRAY_SIZE(nf_nat_ipv4_ops)); } EXPORT_SYMBOL_GPL(nf_nat_ipv4_unregister_fn); #if IS_ENABLED(CONFIG_IPV6) int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum, unsigned int hdrlen) { struct { struct icmp6hdr icmp6; struct ipv6hdr ip6; } *inside; enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); enum nf_nat_manip_type manip = HOOK2MANIP(hooknum); struct nf_conntrack_tuple target; unsigned long statusbit; WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY); if (skb_ensure_writable(skb, hdrlen + sizeof(*inside))) return 0; if (nf_ip6_checksum(skb, hooknum, hdrlen, IPPROTO_ICMPV6)) return 0; inside = (void *)skb->data + hdrlen; if (inside->icmp6.icmp6_type == NDISC_REDIRECT) { if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK) return 0; if (ct->status & IPS_NAT_MASK) return 0; } if (manip == NF_NAT_MANIP_SRC) statusbit = IPS_SRC_NAT; else statusbit = IPS_DST_NAT; /* Invert if this is reply direction */ if (dir == IP_CT_DIR_REPLY) statusbit ^= IPS_NAT_MASK; if (!(ct->status & statusbit)) return 1; if (!nf_nat_ipv6_manip_pkt(skb, hdrlen + sizeof(inside->icmp6), &ct->tuplehash[!dir].tuple, !manip)) return 0; if (skb->ip_summed != CHECKSUM_PARTIAL) { struct ipv6hdr *ipv6h = ipv6_hdr(skb); inside = (void *)skb->data + hdrlen; inside->icmp6.icmp6_cksum = 0; inside->icmp6.icmp6_cksum = csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len - hdrlen, IPPROTO_ICMPV6, skb_checksum(skb, hdrlen, skb->len - hdrlen, 0)); } nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); target.dst.protonum = IPPROTO_ICMPV6; if (!nf_nat_ipv6_manip_pkt(skb, 0, &target, manip)) return 0; return 1; } EXPORT_SYMBOL_GPL(nf_nat_icmpv6_reply_translation); static unsigned int nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; __be16 frag_off; int hdrlen; u8 nexthdr; ct = nf_ct_get(skb, &ctinfo); /* Can't track? It's not due to stress, or conntrack would * have dropped it. Hence it's the user's responsibilty to * packet filter it out, or implement conntrack/NAT for that * protocol. 8) --RR */ if (!ct) return NF_ACCEPT; if (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY) { nexthdr = ipv6_hdr(skb)->nexthdr; hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off); if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo, state->hook, hdrlen)) return NF_DROP; else return NF_ACCEPT; } } return nf_nat_inet_fn(priv, skb, state); } static unsigned int nf_nat_ipv6_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { unsigned int ret; struct in6_addr daddr = ipv6_hdr(skb)->daddr; ret = nf_nat_ipv6_fn(priv, skb, state); if (ret != NF_DROP && ret != NF_STOLEN && ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr)) skb_dst_drop(skb); return ret; } static unsigned int nf_nat_ipv6_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { #ifdef CONFIG_XFRM const struct nf_conn *ct; enum ip_conntrack_info ctinfo; int err; #endif unsigned int ret; ret = nf_nat_ipv6_fn(priv, skb, state); #ifdef CONFIG_XFRM if (ret != NF_ACCEPT) return ret; if (IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) return ret; ct = nf_ct_get(skb, &ctinfo); if (ct) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, &ct->tuplehash[!dir].tuple.dst.u3) || (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all)) { err = nf_xfrm_me_harder(state->net, skb, AF_INET6); if (err < 0) ret = NF_DROP_ERR(err); } } #endif return ret; } static unsigned int nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { const struct nf_conn *ct; enum ip_conntrack_info ctinfo; unsigned int ret; int err; ret = nf_nat_ipv6_fn(priv, skb, state); if (ret != NF_ACCEPT) return ret; ct = nf_ct_get(skb, &ctinfo); if (ct) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, &ct->tuplehash[!dir].tuple.src.u3)) { err = nf_ip6_route_me_harder(state->net, state->sk, skb); if (err < 0) ret = NF_DROP_ERR(err); } #ifdef CONFIG_XFRM else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && ct->tuplehash[dir].tuple.dst.u.all != ct->tuplehash[!dir].tuple.src.u.all) { err = nf_xfrm_me_harder(state->net, skb, AF_INET6); if (err < 0) ret = NF_DROP_ERR(err); } #endif } return ret; } static const struct nf_hook_ops nf_nat_ipv6_ops[] = { /* Before packet filtering, change destination */ { .hook = nf_nat_ipv6_in, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_NAT_DST, }, /* After packet filtering, change source */ { .hook = nf_nat_ipv6_out, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_NAT_SRC, }, /* Before packet filtering, change destination */ { .hook = nf_nat_ipv6_local_fn, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST, }, /* After packet filtering, change source */ { .hook = nf_nat_ipv6_fn, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC, }, }; int nf_nat_ipv6_register_fn(struct net *net, const struct nf_hook_ops *ops) { return nf_nat_register_fn(net, ops->pf, ops, nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops)); } EXPORT_SYMBOL_GPL(nf_nat_ipv6_register_fn); void nf_nat_ipv6_unregister_fn(struct net *net, const struct nf_hook_ops *ops) { nf_nat_unregister_fn(net, ops->pf, ops, ARRAY_SIZE(nf_nat_ipv6_ops)); } EXPORT_SYMBOL_GPL(nf_nat_ipv6_unregister_fn); #endif /* CONFIG_IPV6 */ #if defined(CONFIG_NF_TABLES_INET) && IS_ENABLED(CONFIG_NFT_NAT) int nf_nat_inet_register_fn(struct net *net, const struct nf_hook_ops *ops) { int ret; if (WARN_ON_ONCE(ops->pf != NFPROTO_INET)) return -EINVAL; ret = nf_nat_register_fn(net, NFPROTO_IPV6, ops, nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops)); if (ret) return ret; ret = nf_nat_register_fn(net, NFPROTO_IPV4, ops, nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops)); if (ret) nf_nat_unregister_fn(net, NFPROTO_IPV6, ops, ARRAY_SIZE(nf_nat_ipv6_ops)); return ret; } EXPORT_SYMBOL_GPL(nf_nat_inet_register_fn); void nf_nat_inet_unregister_fn(struct net *net, const struct nf_hook_ops *ops) { nf_nat_unregister_fn(net, NFPROTO_IPV4, ops, ARRAY_SIZE(nf_nat_ipv4_ops)); nf_nat_unregister_fn(net, NFPROTO_IPV6, ops, ARRAY_SIZE(nf_nat_ipv6_ops)); } EXPORT_SYMBOL_GPL(nf_nat_inet_unregister_fn); #endif /* NFT INET NAT */ |
| 10 150 10 150 150 4 3 1 4 644 643 1 640 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * RAW sockets for IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Adapted from linux/net/ipv4/raw.c * * Fixes: * Hideaki YOSHIFUJI : sin6_scope_id support * YOSHIFUJI,H.@USAGI : raw checksum (RFC2292(bis) compliance) * Kazunori MIYAZAWA @USAGI: change process style to use ip6_append_data */ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/slab.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/icmpv6.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <linux/skbuff.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/ndisc.h> #include <net/protocol.h> #include <net/ip6_route.h> #include <net/ip6_checksum.h> #include <net/addrconf.h> #include <net/transp_v6.h> #include <net/udp.h> #include <net/inet_common.h> #include <net/tcp_states.h> #if IS_ENABLED(CONFIG_IPV6_MIP6) #include <net/mip6.h> #endif #include <linux/mroute6.h> #include <net/raw.h> #include <net/rawv6.h> #include <net/xfrm.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/export.h> #define ICMPV6_HDRLEN 4 /* ICMPv6 header, RFC 4443 Section 2.1 */ struct raw_hashinfo raw_v6_hashinfo; EXPORT_SYMBOL_GPL(raw_v6_hashinfo); bool raw_v6_match(struct net *net, struct sock *sk, unsigned short num, const struct in6_addr *loc_addr, const struct in6_addr *rmt_addr, int dif, int sdif) { if (inet_sk(sk)->inet_num != num || !net_eq(sock_net(sk), net) || (!ipv6_addr_any(&sk->sk_v6_daddr) && !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) || !raw_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif)) return false; if (ipv6_addr_any(&sk->sk_v6_rcv_saddr) || ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr) || (ipv6_addr_is_multicast(loc_addr) && inet6_mc_check(sk, loc_addr, rmt_addr))) return true; return false; } EXPORT_SYMBOL_GPL(raw_v6_match); /* * 0 - deliver * 1 - block */ static int icmpv6_filter(const struct sock *sk, const struct sk_buff *skb) { struct icmp6hdr _hdr; const struct icmp6hdr *hdr; /* We require only the four bytes of the ICMPv6 header, not any * additional bytes of message body in "struct icmp6hdr". */ hdr = skb_header_pointer(skb, skb_transport_offset(skb), ICMPV6_HDRLEN, &_hdr); if (hdr) { const __u32 *data = &raw6_sk(sk)->filter.data[0]; unsigned int type = hdr->icmp6_type; return (data[type >> 5] & (1U << (type & 31))) != 0; } return 1; } #if IS_ENABLED(CONFIG_IPV6_MIP6) typedef int mh_filter_t(struct sock *sock, struct sk_buff *skb); static mh_filter_t __rcu *mh_filter __read_mostly; int rawv6_mh_filter_register(mh_filter_t filter) { rcu_assign_pointer(mh_filter, filter); return 0; } EXPORT_SYMBOL(rawv6_mh_filter_register); int rawv6_mh_filter_unregister(mh_filter_t filter) { RCU_INIT_POINTER(mh_filter, NULL); synchronize_rcu(); return 0; } EXPORT_SYMBOL(rawv6_mh_filter_unregister); #endif /* * demultiplex raw sockets. * (should consider queueing the skb in the sock receive_queue * without calling rawv6.c) * * Caller owns SKB so we must make clones. */ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) { struct net *net = dev_net(skb->dev); const struct in6_addr *saddr; const struct in6_addr *daddr; struct hlist_head *hlist; struct sock *sk; bool delivered = false; __u8 hash; saddr = &ipv6_hdr(skb)->saddr; daddr = saddr + 1; hash = raw_hashfunc(net, nexthdr); hlist = &raw_v6_hashinfo.ht[hash]; rcu_read_lock(); sk_for_each_rcu(sk, hlist) { int filtered; if (!raw_v6_match(net, sk, nexthdr, daddr, saddr, inet6_iif(skb), inet6_sdif(skb))) continue; delivered = true; switch (nexthdr) { case IPPROTO_ICMPV6: filtered = icmpv6_filter(sk, skb); break; #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPPROTO_MH: { /* XXX: To validate MH only once for each packet, * this is placed here. It should be after checking * xfrm policy, however it doesn't. The checking xfrm * policy is placed in rawv6_rcv() because it is * required for each socket. */ mh_filter_t *filter; filter = rcu_dereference(mh_filter); filtered = filter ? (*filter)(sk, skb) : 0; break; } #endif default: filtered = 0; break; } if (filtered < 0) break; if (filtered == 0) { struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC); /* Not releasing hash table! */ if (clone) rawv6_rcv(sk, clone); } } rcu_read_unlock(); return delivered; } bool raw6_local_deliver(struct sk_buff *skb, int nexthdr) { return ipv6_raw_deliver(skb, nexthdr); } /* This cleans up af_inet6 a bit. -DaveM */ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct sockaddr_in6 *addr = (struct sockaddr_in6 *) uaddr; __be32 v4addr = 0; int addr_type; int err; if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (addr->sin6_family != AF_INET6) return -EINVAL; addr_type = ipv6_addr_type(&addr->sin6_addr); /* Raw sockets are IPv6 only */ if (addr_type == IPV6_ADDR_MAPPED) return -EADDRNOTAVAIL; lock_sock(sk); err = -EINVAL; if (sk->sk_state != TCP_CLOSE) goto out; rcu_read_lock(); /* Check if the address belongs to the host. */ if (addr_type != IPV6_ADDR_ANY) { struct net_device *dev = NULL; if (__ipv6_addr_needs_scope_id(addr_type)) { if (addr_len >= sizeof(struct sockaddr_in6) && addr->sin6_scope_id) { /* Override any existing binding, if another * one is supplied by user. */ sk->sk_bound_dev_if = addr->sin6_scope_id; } /* Binding to link-local address requires an interface */ if (!sk->sk_bound_dev_if) goto out_unlock; } if (sk->sk_bound_dev_if) { err = -ENODEV; dev = dev_get_by_index_rcu(sock_net(sk), sk->sk_bound_dev_if); if (!dev) goto out_unlock; } /* ipv4 addr of the socket is invalid. Only the * unspecified and mapped address have a v4 equivalent. */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST) && !ipv6_can_nonlocal_bind(sock_net(sk), inet)) { err = -EADDRNOTAVAIL; if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr, dev, 0)) { goto out_unlock; } } } inet->inet_rcv_saddr = inet->inet_saddr = v4addr; sk->sk_v6_rcv_saddr = addr->sin6_addr; if (!(addr_type & IPV6_ADDR_MULTICAST)) np->saddr = addr->sin6_addr; err = 0; out_unlock: rcu_read_unlock(); out: release_sock(sk); return err; } static void rawv6_err(struct sock *sk, struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); int err; int harderr; /* Report error on raw socket, if: 1. User requested recverr. 2. Socket is connected (otherwise the error indication is useless without recverr and error is hard. */ if (!np->recverr && sk->sk_state != TCP_ESTABLISHED) return; harderr = icmpv6_err_convert(type, code, &err); if (type == ICMPV6_PKT_TOOBIG) { ip6_sk_update_pmtu(skb, sk, info); harderr = (np->pmtudisc == IPV6_PMTUDISC_DO); } if (type == NDISC_REDIRECT) { ip6_sk_redirect(skb, sk); return; } if (np->recverr) { u8 *payload = skb->data; if (!inet->hdrincl) payload += offset; ipv6_icmp_error(sk, skb, err, 0, ntohl(info), payload); } if (np->recverr || harderr) { sk->sk_err = err; sk_error_report(sk); } } void raw6_icmp_error(struct sk_buff *skb, int nexthdr, u8 type, u8 code, int inner_offset, __be32 info) { struct net *net = dev_net(skb->dev); struct hlist_head *hlist; struct sock *sk; int hash; hash = raw_hashfunc(net, nexthdr); hlist = &raw_v6_hashinfo.ht[hash]; rcu_read_lock(); sk_for_each_rcu(sk, hlist) { /* Note: ipv6_hdr(skb) != skb->data */ const struct ipv6hdr *ip6h = (const struct ipv6hdr *)skb->data; if (!raw_v6_match(net, sk, nexthdr, &ip6h->saddr, &ip6h->daddr, inet6_iif(skb), inet6_iif(skb))) continue; rawv6_err(sk, skb, NULL, type, code, inner_offset, info); } rcu_read_unlock(); } static inline int rawv6_rcv_skb(struct sock *sk, struct sk_buff *skb) { if ((raw6_sk(sk)->checksum || rcu_access_pointer(sk->sk_filter)) && skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); kfree_skb(skb); return NET_RX_DROP; } /* Charge it to the socket. */ skb_dst_drop(skb); if (sock_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); return NET_RX_DROP; } return 0; } /* * This is next to useless... * if we demultiplex in network layer we don't need the extra call * just to queue the skb... * maybe we could have the network decide upon a hint if it * should call raw_rcv for demultiplexing */ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) { struct inet_sock *inet = inet_sk(sk); struct raw6_sock *rp = raw6_sk(sk); if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { atomic_inc(&sk->sk_drops); kfree_skb(skb); return NET_RX_DROP; } nf_reset_ct(skb); if (!rp->checksum) skb->ip_summed = CHECKSUM_UNNECESSARY; if (skb->ip_summed == CHECKSUM_COMPLETE) { skb_postpull_rcsum(skb, skb_network_header(skb), skb_network_header_len(skb)); if (!csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len, inet->inet_num, skb->csum)) skb->ip_summed = CHECKSUM_UNNECESSARY; } if (!skb_csum_unnecessary(skb)) skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len, inet->inet_num, 0)); if (inet->hdrincl) { if (skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); kfree_skb(skb); return NET_RX_DROP; } } rawv6_rcv_skb(sk, skb); return 0; } /* * This should be easy, if there is something there * we return it, otherwise we block. */ static int rawv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct sk_buff *skb; size_t copied; int err; if (flags & MSG_OOB) return -EOPNOTSUPP; if (flags & MSG_ERRQUEUE) return ipv6_recv_error(sk, msg, len, addr_len); if (np->rxpmtu && np->rxopt.bits.rxpmtu) return ipv6_recv_rxpmtu(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, &err); if (!skb) goto out; copied = skb->len; if (copied > len) { copied = len; msg->msg_flags |= MSG_TRUNC; } if (skb_csum_unnecessary(skb)) { err = skb_copy_datagram_msg(skb, 0, msg, copied); } else if (msg->msg_flags&MSG_TRUNC) { if (__skb_checksum_complete(skb)) goto csum_copy_err; err = skb_copy_datagram_msg(skb, 0, msg, copied); } else { err = skb_copy_and_csum_datagram_msg(skb, 0, msg); if (err == -EINVAL) goto csum_copy_err; } if (err) goto out_free; /* Copy the address. */ if (sin6) { sin6->sin6_family = AF_INET6; sin6->sin6_port = 0; sin6->sin6_addr = ipv6_hdr(skb)->saddr; sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, inet6_iif(skb)); *addr_len = sizeof(*sin6); } sock_recv_cmsgs(msg, sk, skb); if (np->rxopt.all) ip6_datagram_recv_ctl(sk, msg, skb); err = copied; if (flags & MSG_TRUNC) err = skb->len; out_free: skb_free_datagram(sk, skb); out: return err; csum_copy_err: skb_kill_datagram(sk, skb, flags); /* Error for blocking case is chosen to masquerade as some normal condition. */ err = (flags&MSG_DONTWAIT) ? -EAGAIN : -EHOSTUNREACH; goto out; } static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct raw6_sock *rp) { struct ipv6_txoptions *opt; struct sk_buff *skb; int err = 0; int offset; int len; int total_len; __wsum tmp_csum; __sum16 csum; if (!rp->checksum) goto send; skb = skb_peek(&sk->sk_write_queue); if (!skb) goto out; offset = rp->offset; total_len = inet_sk(sk)->cork.base.length; opt = inet6_sk(sk)->cork.opt; total_len -= opt ? opt->opt_flen : 0; if (offset >= total_len - 1) { err = -EINVAL; ip6_flush_pending_frames(sk); goto out; } /* should be check HW csum miyazawa */ if (skb_queue_len(&sk->sk_write_queue) == 1) { /* * Only one fragment on the socket. */ tmp_csum = skb->csum; } else { struct sk_buff *csum_skb = NULL; tmp_csum = 0; skb_queue_walk(&sk->sk_write_queue, skb) { tmp_csum = csum_add(tmp_csum, skb->csum); if (csum_skb) continue; len = skb->len - skb_transport_offset(skb); if (offset >= len) { offset -= len; continue; } csum_skb = skb; } skb = csum_skb; } offset += skb_transport_offset(skb); err = skb_copy_bits(skb, offset, &csum, 2); if (err < 0) { ip6_flush_pending_frames(sk); goto out; } /* in case cksum was not initialized */ if (unlikely(csum)) tmp_csum = csum_sub(tmp_csum, csum_unfold(csum)); csum = csum_ipv6_magic(&fl6->saddr, &fl6->daddr, total_len, fl6->flowi6_proto, tmp_csum); if (csum == 0 && fl6->flowi6_proto == IPPROTO_UDP) csum = CSUM_MANGLED_0; BUG_ON(skb_store_bits(skb, offset, &csum, 2)); send: err = ip6_push_pending_frames(sk); out: return err; } static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, struct flowi6 *fl6, struct dst_entry **dstp, unsigned int flags, const struct sockcm_cookie *sockc) { struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); struct ipv6hdr *iph; struct sk_buff *skb; int err; struct rt6_info *rt = (struct rt6_info *)*dstp; int hlen = LL_RESERVED_SPACE(rt->dst.dev); int tlen = rt->dst.dev->needed_tailroom; if (length > rt->dst.dev->mtu) { ipv6_local_error(sk, EMSGSIZE, fl6, rt->dst.dev->mtu); return -EMSGSIZE; } if (length < sizeof(struct ipv6hdr)) return -EINVAL; if (flags&MSG_PROBE) goto out; skb = sock_alloc_send_skb(sk, length + hlen + tlen + 15, flags & MSG_DONTWAIT, &err); if (!skb) goto error; skb_reserve(skb, hlen); skb->protocol = htons(ETH_P_IPV6); skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; skb_put(skb, length); skb_reset_network_header(skb); iph = ipv6_hdr(skb); skb->ip_summed = CHECKSUM_NONE; skb_setup_tx_timestamp(skb, sockc->tsflags); if (flags & MSG_CONFIRM) skb_set_dst_pending_confirm(skb, 1); skb->transport_header = skb->network_header; err = memcpy_from_msg(iph, msg, length); if (err) { err = -EFAULT; kfree_skb(skb); goto error; } skb_dst_set(skb, &rt->dst); *dstp = NULL; /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip6_out(sk, skb); if (unlikely(!skb)) return 0; /* Acquire rcu_read_lock() in case we need to use rt->rt6i_idev * in the error path. Since skb has been freed, the dst could * have been queued for deletion. */ rcu_read_lock(); IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, rt->dst.dev, dst_output); if (err > 0) err = net_xmit_errno(err); if (err) { IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); goto error_check; } rcu_read_unlock(); out: return 0; error: IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); error_check: if (err == -ENOBUFS && !np->recverr) err = 0; return err; } struct raw6_frag_vec { struct msghdr *msg; int hlen; char c[4]; }; static int rawv6_probe_proto_opt(struct raw6_frag_vec *rfv, struct flowi6 *fl6) { int err = 0; switch (fl6->flowi6_proto) { case IPPROTO_ICMPV6: rfv->hlen = 2; err = memcpy_from_msg(rfv->c, rfv->msg, rfv->hlen); if (!err) { fl6->fl6_icmp_type = rfv->c[0]; fl6->fl6_icmp_code = rfv->c[1]; } break; case IPPROTO_MH: rfv->hlen = 4; err = memcpy_from_msg(rfv->c, rfv->msg, rfv->hlen); if (!err) fl6->fl6_mh_type = rfv->c[2]; } return err; } static int raw6_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct raw6_frag_vec *rfv = from; if (offset < rfv->hlen) { int copy = min(rfv->hlen - offset, len); if (skb->ip_summed == CHECKSUM_PARTIAL) memcpy(to, rfv->c + offset, copy); else skb->csum = csum_block_add( skb->csum, csum_partial_copy_nocheck(rfv->c + offset, to, copy), odd); odd = 0; offset += copy; to += copy; len -= copy; if (!len) return 0; } offset -= rfv->hlen; return ip_generic_getfrag(rfv->msg, to, offset, len, odd, skb); } static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct ipv6_txoptions *opt_to_free = NULL; struct ipv6_txoptions opt_space; DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct in6_addr *daddr, *final_p, final; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct raw6_sock *rp = raw6_sk(sk); struct ipv6_txoptions *opt = NULL; struct ip6_flowlabel *flowlabel = NULL; struct dst_entry *dst = NULL; struct raw6_frag_vec rfv; struct flowi6 fl6; struct ipcm6_cookie ipc6; int addr_len = msg->msg_namelen; int hdrincl; u16 proto; int err; /* Rough check on arithmetic overflow, better check is made in ip6_append_data(). */ if (len > INT_MAX) return -EMSGSIZE; /* Mirror BSD error message compatibility */ if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; /* hdrincl should be READ_ONCE(inet->hdrincl) * but READ_ONCE() doesn't work with bit fields. * Doing this indirectly yields the same result. */ hdrincl = inet->hdrincl; hdrincl = READ_ONCE(hdrincl); /* * Get and verify the address. */ memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_mark = READ_ONCE(sk->sk_mark); fl6.flowi6_uid = sk->sk_uid; ipcm6_init(&ipc6); ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags); ipc6.sockc.mark = fl6.flowi6_mark; if (sin6) { if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (sin6->sin6_family && sin6->sin6_family != AF_INET6) return -EAFNOSUPPORT; /* port is the proto value [0..255] carried in nexthdr */ proto = ntohs(sin6->sin6_port); if (!proto) proto = inet->inet_num; else if (proto != inet->inet_num && inet->inet_num != IPPROTO_RAW) return -EINVAL; if (proto > 255) return -EINVAL; daddr = &sin6->sin6_addr; if (np->sndflow) { fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; } } /* * Otherwise it will be difficult to maintain * sk->sk_dst_cache. */ if (sk->sk_state == TCP_ESTABLISHED && ipv6_addr_equal(daddr, &sk->sk_v6_daddr)) daddr = &sk->sk_v6_daddr; if (addr_len >= sizeof(struct sockaddr_in6) && sin6->sin6_scope_id && __ipv6_addr_needs_scope_id(__ipv6_addr_type(daddr))) fl6.flowi6_oif = sin6->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; proto = inet->inet_num; daddr = &sk->sk_v6_daddr; fl6.flowlabel = np->flow_label; } if (fl6.flowi6_oif == 0) fl6.flowi6_oif = sk->sk_bound_dev_if; if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); ipc6.opt = opt; err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6); if (err < 0) { fl6_sock_release(flowlabel); return err; } if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; } if (!(opt->opt_nflen|opt->opt_flen)) opt = NULL; } if (!opt) { opt = txopt_get(np); opt_to_free = opt; } if (flowlabel) opt = fl6_merge_options(&opt_space, flowlabel, opt); opt = ipv6_fixup_options(&opt_space, opt); fl6.flowi6_proto = proto; fl6.flowi6_mark = ipc6.sockc.mark; if (!hdrincl) { rfv.msg = msg; rfv.hlen = 0; err = rawv6_probe_proto_opt(&rfv, &fl6); if (err) goto out; } if (!ipv6_addr_any(daddr)) fl6.daddr = *daddr; else fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) fl6.saddr = np->saddr; final_p = fl6_update_dst(&fl6, opt, &final); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = np->mcast_oif; else if (!fl6.flowi6_oif) fl6.flowi6_oif = np->ucast_oif; security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); if (hdrincl) fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH; if (ipc6.tclass < 0) ipc6.tclass = np->tclass; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; } if (ipc6.hlimit < 0) ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); if (ipc6.dontfrag < 0) ipc6.dontfrag = np->dontfrag; if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; back_from_confirm: if (hdrincl) err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst, msg->msg_flags, &ipc6.sockc); else { ipc6.opt = opt; lock_sock(sk); err = ip6_append_data(sk, raw6_getfrag, &rfv, len, 0, &ipc6, &fl6, (struct rt6_info *)dst, msg->msg_flags); if (err) ip6_flush_pending_frames(sk); else if (!(msg->msg_flags & MSG_MORE)) err = rawv6_push_pending_frames(sk, &fl6, rp); release_sock(sk); } done: dst_release(dst); out: fl6_sock_release(flowlabel); txopt_put(opt_to_free); return err < 0 ? err : len; do_confirm: if (msg->msg_flags & MSG_PROBE) dst_confirm_neigh(dst, &fl6.daddr); if (!(msg->msg_flags & MSG_PROBE) || len) goto back_from_confirm; err = 0; goto done; } static int rawv6_seticmpfilter(struct sock *sk, int level, int optname, sockptr_t optval, int optlen) { switch (optname) { case ICMPV6_FILTER: if (optlen > sizeof(struct icmp6_filter)) optlen = sizeof(struct icmp6_filter); if (copy_from_sockptr(&raw6_sk(sk)->filter, optval, optlen)) return -EFAULT; return 0; default: return -ENOPROTOOPT; } return 0; } static int rawv6_geticmpfilter(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { int len; switch (optname) { case ICMPV6_FILTER: if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; if (len > sizeof(struct icmp6_filter)) len = sizeof(struct icmp6_filter); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &raw6_sk(sk)->filter, len)) return -EFAULT; return 0; default: return -ENOPROTOOPT; } return 0; } static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct raw6_sock *rp = raw6_sk(sk); int val; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; switch (optname) { case IPV6_HDRINCL: if (sk->sk_type != SOCK_RAW) return -EINVAL; inet_sk(sk)->hdrincl = !!val; return 0; case IPV6_CHECKSUM: if (inet_sk(sk)->inet_num == IPPROTO_ICMPV6 && level == IPPROTO_IPV6) { /* * RFC3542 tells that IPV6_CHECKSUM socket * option in the IPPROTO_IPV6 level is not * allowed on ICMPv6 sockets. * If you want to set it, use IPPROTO_RAW * level IPV6_CHECKSUM socket option * (Linux extension). */ return -EINVAL; } /* You may get strange result with a positive odd offset; RFC2292bis agrees with me. */ if (val > 0 && (val&1)) return -EINVAL; if (val < 0) { rp->checksum = 0; } else { rp->checksum = 1; rp->offset = val; } return 0; default: return -ENOPROTOOPT; } } static int rawv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { switch (level) { case SOL_RAW: break; case SOL_ICMPV6: if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_seticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; fallthrough; default: return ipv6_setsockopt(sk, level, optname, optval, optlen); } return do_rawv6_setsockopt(sk, level, optname, optval, optlen); } static int do_rawv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct raw6_sock *rp = raw6_sk(sk); int val, len; if (get_user(len, optlen)) return -EFAULT; switch (optname) { case IPV6_HDRINCL: val = inet_sk(sk)->hdrincl; break; case IPV6_CHECKSUM: /* * We allow getsockopt() for IPPROTO_IPV6-level * IPV6_CHECKSUM socket option on ICMPv6 sockets * since RFC3542 is silent about it. */ if (rp->checksum == 0) val = -1; else val = rp->offset; break; default: return -ENOPROTOOPT; } len = min_t(unsigned int, sizeof(int), len); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } static int rawv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { switch (level) { case SOL_RAW: break; case SOL_ICMPV6: if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_geticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; fallthrough; default: return ipv6_getsockopt(sk, level, optname, optval, optlen); } return do_rawv6_getsockopt(sk, level, optname, optval, optlen); } static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) { switch (cmd) { case SIOCOUTQ: { int amount = sk_wmem_alloc_get(sk); return put_user(amount, (int __user *)arg); } case SIOCINQ: { struct sk_buff *skb; int amount = 0; spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb) amount = skb->len; spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); } default: #ifdef CONFIG_IPV6_MROUTE return ip6mr_ioctl(sk, cmd, (void __user *)arg); #else return -ENOIOCTLCMD; #endif } } #ifdef CONFIG_COMPAT static int compat_rawv6_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg) { switch (cmd) { case SIOCOUTQ: case SIOCINQ: return -ENOIOCTLCMD; default: #ifdef CONFIG_IPV6_MROUTE return ip6mr_compat_ioctl(sk, cmd, compat_ptr(arg)); #else return -ENOIOCTLCMD; #endif } } #endif static void rawv6_close(struct sock *sk, long timeout) { if (inet_sk(sk)->inet_num == IPPROTO_RAW) ip6_ra_control(sk, -1); ip6mr_sk_done(sk); sk_common_release(sk); } static void raw6_destroy(struct sock *sk) { lock_sock(sk); ip6_flush_pending_frames(sk); release_sock(sk); } static int rawv6_init_sk(struct sock *sk) { struct raw6_sock *rp = raw6_sk(sk); switch (inet_sk(sk)->inet_num) { case IPPROTO_ICMPV6: rp->checksum = 1; rp->offset = 2; break; case IPPROTO_MH: rp->checksum = 1; rp->offset = 4; break; default: break; } return 0; } struct proto rawv6_prot = { .name = "RAWv6", .owner = THIS_MODULE, .close = rawv6_close, .destroy = raw6_destroy, .connect = ip6_datagram_connect_v6_only, .disconnect = __udp_disconnect, .ioctl = rawv6_ioctl, .init = rawv6_init_sk, .setsockopt = rawv6_setsockopt, .getsockopt = rawv6_getsockopt, .sendmsg = rawv6_sendmsg, .recvmsg = rawv6_recvmsg, .bind = rawv6_bind, .backlog_rcv = rawv6_rcv_skb, .hash = raw_hash_sk, .unhash = raw_unhash_sk, .obj_size = sizeof(struct raw6_sock), .useroffset = offsetof(struct raw6_sock, filter), .usersize = sizeof_field(struct raw6_sock, filter), .h.raw_hash = &raw_v6_hashinfo, #ifdef CONFIG_COMPAT .compat_ioctl = compat_rawv6_ioctl, #endif .diag_destroy = raw_abort, }; #ifdef CONFIG_PROC_FS static int raw6_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); } else { struct sock *sp = v; __u16 srcp = inet_sk(sp)->inet_num; ip6_dgram_sock_seq_show(seq, v, srcp, 0, raw_seq_private(seq)->bucket); } return 0; } static const struct seq_operations raw6_seq_ops = { .start = raw_seq_start, .next = raw_seq_next, .stop = raw_seq_stop, .show = raw6_seq_show, }; static int __net_init raw6_init_net(struct net *net) { if (!proc_create_net_data("raw6", 0444, net->proc_net, &raw6_seq_ops, sizeof(struct raw_iter_state), &raw_v6_hashinfo)) return -ENOMEM; return 0; } static void __net_exit raw6_exit_net(struct net *net) { remove_proc_entry("raw6", net->proc_net); } static struct pernet_operations raw6_net_ops = { .init = raw6_init_net, .exit = raw6_exit_net, }; int __init raw6_proc_init(void) { return register_pernet_subsys(&raw6_net_ops); } void raw6_proc_exit(void) { unregister_pernet_subsys(&raw6_net_ops); } #endif /* CONFIG_PROC_FS */ /* Same as inet6_dgram_ops, sans udp_poll. */ const struct proto_ops inet6_sockraw_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, .bind = inet6_bind, .connect = inet_dgram_connect, /* ok */ .socketpair = sock_no_socketpair, /* a do nothing */ .accept = sock_no_accept, /* a do nothing */ .getname = inet6_getname, .poll = datagram_poll, /* ok */ .ioctl = inet6_ioctl, /* must change */ .gettstamp = sock_gettstamp, .listen = sock_no_listen, /* ok */ .shutdown = inet_shutdown, /* ok */ .setsockopt = sock_common_setsockopt, /* ok */ .getsockopt = sock_common_getsockopt, /* ok */ .sendmsg = inet_sendmsg, /* ok */ .recvmsg = sock_common_recvmsg, /* ok */ .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif }; static struct inet_protosw rawv6_protosw = { .type = SOCK_RAW, .protocol = IPPROTO_IP, /* wild card */ .prot = &rawv6_prot, .ops = &inet6_sockraw_ops, .flags = INET_PROTOSW_REUSE, }; int __init rawv6_init(void) { return inet6_register_protosw(&rawv6_protosw); } void rawv6_exit(void) { inet6_unregister_protosw(&rawv6_protosw); } |
| 2 2 2 2 1 1 2 2 2 640 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * "Ping" sockets * * Based on ipv4/udp.c code. * * Authors: Vasiliy Kulikov / Openwall (for Linux 2.6), * Pavel Kankovsky (for Linux 2.4.32) * * Pavel gave all rights to bugs to Vasiliy, * none of the bugs are Pavel's now. */ #include <linux/uaccess.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/errno.h> #include <linux/timer.h> #include <linux/mm.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <net/snmp.h> #include <net/ip.h> #include <net/icmp.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <linux/proc_fs.h> #include <linux/export.h> #include <linux/bpf-cgroup.h> #include <net/sock.h> #include <net/ping.h> #include <net/udp.h> #include <net/route.h> #include <net/inet_common.h> #include <net/checksum.h> #if IS_ENABLED(CONFIG_IPV6) #include <linux/in6.h> #include <linux/icmpv6.h> #include <net/addrconf.h> #include <net/ipv6.h> #include <net/transp_v6.h> #endif #define ping_portaddr_for_each_entry(__sk, node, list) \ hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node) #define ping_portaddr_for_each_entry_rcu(__sk, node, list) \ hlist_nulls_for_each_entry_rcu(__sk, node, list, sk_nulls_node) struct ping_table { struct hlist_nulls_head hash[PING_HTABLE_SIZE]; spinlock_t lock; }; static struct ping_table ping_table; struct pingv6_ops pingv6_ops; EXPORT_SYMBOL_GPL(pingv6_ops); static u16 ping_port_rover; static inline u32 ping_hashfn(const struct net *net, u32 num, u32 mask) { u32 res = (num + net_hash_mix(net)) & mask; pr_debug("hash(%u) = %u\n", num, res); return res; } EXPORT_SYMBOL_GPL(ping_hash); static inline struct hlist_nulls_head *ping_hashslot(struct ping_table *table, struct net *net, unsigned int num) { return &table->hash[ping_hashfn(net, num, PING_HTABLE_MASK)]; } int ping_get_port(struct sock *sk, unsigned short ident) { struct hlist_nulls_node *node; struct hlist_nulls_head *hlist; struct inet_sock *isk, *isk2; struct sock *sk2 = NULL; isk = inet_sk(sk); spin_lock(&ping_table.lock); if (ident == 0) { u32 i; u16 result = ping_port_rover + 1; for (i = 0; i < (1L << 16); i++, result++) { if (!result) result++; /* avoid zero */ hlist = ping_hashslot(&ping_table, sock_net(sk), result); ping_portaddr_for_each_entry(sk2, node, hlist) { isk2 = inet_sk(sk2); if (isk2->inet_num == result) goto next_port; } /* found */ ping_port_rover = ident = result; break; next_port: ; } if (i >= (1L << 16)) goto fail; } else { hlist = ping_hashslot(&ping_table, sock_net(sk), ident); ping_portaddr_for_each_entry(sk2, node, hlist) { isk2 = inet_sk(sk2); /* BUG? Why is this reuse and not reuseaddr? ping.c * doesn't turn off SO_REUSEADDR, and it doesn't expect * that other ping processes can steal its packets. */ if ((isk2->inet_num == ident) && (sk2 != sk) && (!sk2->sk_reuse || !sk->sk_reuse)) goto fail; } } pr_debug("found port/ident = %d\n", ident); isk->inet_num = ident; if (sk_unhashed(sk)) { pr_debug("was not hashed\n"); sock_hold(sk); sock_set_flag(sk, SOCK_RCU_FREE); hlist_nulls_add_head_rcu(&sk->sk_nulls_node, hlist); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); } spin_unlock(&ping_table.lock); return 0; fail: spin_unlock(&ping_table.lock); return -EADDRINUSE; } EXPORT_SYMBOL_GPL(ping_get_port); int ping_hash(struct sock *sk) { pr_debug("ping_hash(sk->port=%u)\n", inet_sk(sk)->inet_num); BUG(); /* "Please do not press this button again." */ return 0; } void ping_unhash(struct sock *sk) { struct inet_sock *isk = inet_sk(sk); pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num); spin_lock(&ping_table.lock); if (sk_hashed(sk)) { hlist_nulls_del_init_rcu(&sk->sk_nulls_node); sock_put(sk); isk->inet_num = 0; isk->inet_sport = 0; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); } spin_unlock(&ping_table.lock); } EXPORT_SYMBOL_GPL(ping_unhash); /* Called under rcu_read_lock() */ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident) { struct hlist_nulls_head *hslot = ping_hashslot(&ping_table, net, ident); struct sock *sk = NULL; struct inet_sock *isk; struct hlist_nulls_node *hnode; int dif, sdif; if (skb->protocol == htons(ETH_P_IP)) { dif = inet_iif(skb); sdif = inet_sdif(skb); pr_debug("try to find: num = %d, daddr = %pI4, dif = %d\n", (int)ident, &ip_hdr(skb)->daddr, dif); #if IS_ENABLED(CONFIG_IPV6) } else if (skb->protocol == htons(ETH_P_IPV6)) { dif = inet6_iif(skb); sdif = inet6_sdif(skb); pr_debug("try to find: num = %d, daddr = %pI6c, dif = %d\n", (int)ident, &ipv6_hdr(skb)->daddr, dif); #endif } else { return NULL; } ping_portaddr_for_each_entry_rcu(sk, hnode, hslot) { isk = inet_sk(sk); pr_debug("iterate\n"); if (isk->inet_num != ident) continue; if (skb->protocol == htons(ETH_P_IP) && sk->sk_family == AF_INET) { pr_debug("found: %p: num=%d, daddr=%pI4, dif=%d\n", sk, (int) isk->inet_num, &isk->inet_rcv_saddr, sk->sk_bound_dev_if); if (isk->inet_rcv_saddr && isk->inet_rcv_saddr != ip_hdr(skb)->daddr) continue; #if IS_ENABLED(CONFIG_IPV6) } else if (skb->protocol == htons(ETH_P_IPV6) && sk->sk_family == AF_INET6) { pr_debug("found: %p: num=%d, daddr=%pI6c, dif=%d\n", sk, (int) isk->inet_num, &sk->sk_v6_rcv_saddr, sk->sk_bound_dev_if); if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) && !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, &ipv6_hdr(skb)->daddr)) continue; #endif } else { continue; } if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif && sk->sk_bound_dev_if != sdif) continue; goto exit; } sk = NULL; exit: return sk; } static void inet_get_ping_group_range_net(struct net *net, kgid_t *low, kgid_t *high) { kgid_t *data = net->ipv4.ping_group_range.range; unsigned int seq; do { seq = read_seqbegin(&net->ipv4.ping_group_range.lock); *low = data[0]; *high = data[1]; } while (read_seqretry(&net->ipv4.ping_group_range.lock, seq)); } int ping_init_sock(struct sock *sk) { struct net *net = sock_net(sk); kgid_t group = current_egid(); struct group_info *group_info; int i; kgid_t low, high; int ret = 0; if (sk->sk_family == AF_INET6) sk->sk_ipv6only = 1; inet_get_ping_group_range_net(net, &low, &high); if (gid_lte(low, group) && gid_lte(group, high)) return 0; group_info = get_current_groups(); for (i = 0; i < group_info->ngroups; i++) { kgid_t gid = group_info->gid[i]; if (gid_lte(low, gid) && gid_lte(gid, high)) goto out_release_group; } ret = -EACCES; out_release_group: put_group_info(group_info); return ret; } EXPORT_SYMBOL_GPL(ping_init_sock); void ping_close(struct sock *sk, long timeout) { pr_debug("ping_close(sk=%p,sk->num=%u)\n", inet_sk(sk), inet_sk(sk)->inet_num); pr_debug("isk->refcnt = %d\n", refcount_read(&sk->sk_refcnt)); sk_common_release(sk); } EXPORT_SYMBOL_GPL(ping_close); static int ping_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { /* This check is replicated from __ip4_datagram_connect() and * intended to prevent BPF program called below from accessing bytes * that are out of the bound specified by user in addr_len. */ if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr); } /* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, struct sockaddr *uaddr, int addr_len) { struct net *net = sock_net(sk); if (sk->sk_family == AF_INET) { struct sockaddr_in *addr = (struct sockaddr_in *) uaddr; u32 tb_id = RT_TABLE_LOCAL; int chk_addr_ret; if (addr_len < sizeof(*addr)) return -EINVAL; if (addr->sin_family != AF_INET && !(addr->sin_family == AF_UNSPEC && addr->sin_addr.s_addr == htonl(INADDR_ANY))) return -EAFNOSUPPORT; pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n", sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port)); if (addr->sin_addr.s_addr == htonl(INADDR_ANY)) return 0; tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id; chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id); if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST || (chk_addr_ret != RTN_LOCAL && !inet_can_nonlocal_bind(net, isk))) return -EADDRNOTAVAIL; #if IS_ENABLED(CONFIG_IPV6) } else if (sk->sk_family == AF_INET6) { struct sockaddr_in6 *addr = (struct sockaddr_in6 *) uaddr; int addr_type, scoped, has_addr; struct net_device *dev = NULL; if (addr_len < sizeof(*addr)) return -EINVAL; if (addr->sin6_family != AF_INET6) return -EAFNOSUPPORT; pr_debug("ping_check_bind_addr(sk=%p,addr=%pI6c,port=%d)\n", sk, addr->sin6_addr.s6_addr, ntohs(addr->sin6_port)); addr_type = ipv6_addr_type(&addr->sin6_addr); scoped = __ipv6_addr_needs_scope_id(addr_type); if ((addr_type != IPV6_ADDR_ANY && !(addr_type & IPV6_ADDR_UNICAST)) || (scoped && !addr->sin6_scope_id)) return -EINVAL; rcu_read_lock(); if (addr->sin6_scope_id) { dev = dev_get_by_index_rcu(net, addr->sin6_scope_id); if (!dev) { rcu_read_unlock(); return -ENODEV; } } if (!dev && sk->sk_bound_dev_if) { dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); if (!dev) { rcu_read_unlock(); return -ENODEV; } } has_addr = pingv6_ops.ipv6_chk_addr(net, &addr->sin6_addr, dev, scoped); rcu_read_unlock(); if (!(ipv6_can_nonlocal_bind(net, isk) || has_addr || addr_type == IPV6_ADDR_ANY)) return -EADDRNOTAVAIL; if (scoped) sk->sk_bound_dev_if = addr->sin6_scope_id; #endif } else { return -EAFNOSUPPORT; } return 0; } static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr) { if (saddr->sa_family == AF_INET) { struct inet_sock *isk = inet_sk(sk); struct sockaddr_in *addr = (struct sockaddr_in *) saddr; isk->inet_rcv_saddr = isk->inet_saddr = addr->sin_addr.s_addr; #if IS_ENABLED(CONFIG_IPV6) } else if (saddr->sa_family == AF_INET6) { struct sockaddr_in6 *addr = (struct sockaddr_in6 *) saddr; struct ipv6_pinfo *np = inet6_sk(sk); sk->sk_v6_rcv_saddr = np->saddr = addr->sin6_addr; #endif } } /* * We need our own bind because there are no privileged id's == local ports. * Moreover, we don't allow binding to multi- and broadcast addresses. */ int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct inet_sock *isk = inet_sk(sk); unsigned short snum; int err; int dif = sk->sk_bound_dev_if; err = ping_check_bind_addr(sk, isk, uaddr, addr_len); if (err) return err; lock_sock(sk); err = -EINVAL; if (isk->inet_num != 0) goto out; err = -EADDRINUSE; snum = ntohs(((struct sockaddr_in *)uaddr)->sin_port); if (ping_get_port(sk, snum) != 0) { /* Restore possibly modified sk->sk_bound_dev_if by ping_check_bind_addr(). */ sk->sk_bound_dev_if = dif; goto out; } ping_set_saddr(sk, uaddr); pr_debug("after bind(): num = %hu, dif = %d\n", isk->inet_num, sk->sk_bound_dev_if); err = 0; if (sk->sk_family == AF_INET && isk->inet_rcv_saddr) sk->sk_userlocks |= SOCK_BINDADDR_LOCK; #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6 && !ipv6_addr_any(&sk->sk_v6_rcv_saddr)) sk->sk_userlocks |= SOCK_BINDADDR_LOCK; #endif if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; isk->inet_sport = htons(isk->inet_num); isk->inet_daddr = 0; isk->inet_dport = 0; #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) memset(&sk->sk_v6_daddr, 0, sizeof(sk->sk_v6_daddr)); #endif sk_dst_reset(sk); out: release_sock(sk); pr_debug("ping_v4_bind -> %d\n", err); return err; } EXPORT_SYMBOL_GPL(ping_bind); /* * Is this a supported type of ICMP message? */ static inline int ping_supported(int family, int type, int code) { return (family == AF_INET && type == ICMP_ECHO && code == 0) || (family == AF_INET && type == ICMP_EXT_ECHO && code == 0) || (family == AF_INET6 && type == ICMPV6_ECHO_REQUEST && code == 0) || (family == AF_INET6 && type == ICMPV6_EXT_ECHO_REQUEST && code == 0); } /* * This routine is called by the ICMP module when it gets some * sort of error condition. */ void ping_err(struct sk_buff *skb, int offset, u32 info) { int family; struct icmphdr *icmph; struct inet_sock *inet_sock; int type; int code; struct net *net = dev_net(skb->dev); struct sock *sk; int harderr; int err; if (skb->protocol == htons(ETH_P_IP)) { family = AF_INET; type = icmp_hdr(skb)->type; code = icmp_hdr(skb)->code; icmph = (struct icmphdr *)(skb->data + offset); } else if (skb->protocol == htons(ETH_P_IPV6)) { family = AF_INET6; type = icmp6_hdr(skb)->icmp6_type; code = icmp6_hdr(skb)->icmp6_code; icmph = (struct icmphdr *) (skb->data + offset); } else { BUG(); } /* We assume the packet has already been checked by icmp_unreach */ if (!ping_supported(family, icmph->type, icmph->code)) return; pr_debug("ping_err(proto=0x%x,type=%d,code=%d,id=%04x,seq=%04x)\n", skb->protocol, type, code, ntohs(icmph->un.echo.id), ntohs(icmph->un.echo.sequence)); sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id)); if (!sk) { pr_debug("no socket, dropping\n"); return; /* No socket for error */ } pr_debug("err on socket %p\n", sk); err = 0; harderr = 0; inet_sock = inet_sk(sk); if (skb->protocol == htons(ETH_P_IP)) { switch (type) { default: case ICMP_TIME_EXCEEDED: err = EHOSTUNREACH; break; case ICMP_SOURCE_QUENCH: /* This is not a real error but ping wants to see it. * Report it with some fake errno. */ err = EREMOTEIO; break; case ICMP_PARAMETERPROB: err = EPROTO; harderr = 1; break; case ICMP_DEST_UNREACH: if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */ ipv4_sk_update_pmtu(skb, sk, info); if (inet_sock->pmtudisc != IP_PMTUDISC_DONT) { err = EMSGSIZE; harderr = 1; break; } goto out; } err = EHOSTUNREACH; if (code <= NR_ICMP_UNREACH) { harderr = icmp_err_convert[code].fatal; err = icmp_err_convert[code].errno; } break; case ICMP_REDIRECT: /* See ICMP_SOURCE_QUENCH */ ipv4_sk_redirect(skb, sk); err = EREMOTEIO; break; } #if IS_ENABLED(CONFIG_IPV6) } else if (skb->protocol == htons(ETH_P_IPV6)) { harderr = pingv6_ops.icmpv6_err_convert(type, code, &err); #endif } /* * RFC1122: OK. Passes ICMP errors back to application, as per * 4.1.3.3. */ if ((family == AF_INET && !inet_sock->recverr) || (family == AF_INET6 && !inet6_sk(sk)->recverr)) { if (!harderr || sk->sk_state != TCP_ESTABLISHED) goto out; } else { if (family == AF_INET) { ip_icmp_error(sk, skb, err, 0 /* no remote port */, info, (u8 *)icmph); #if IS_ENABLED(CONFIG_IPV6) } else if (family == AF_INET6) { pingv6_ops.ipv6_icmp_error(sk, skb, err, 0, info, (u8 *)icmph); #endif } } sk->sk_err = err; sk_error_report(sk); out: return; } EXPORT_SYMBOL_GPL(ping_err); /* * Copy and checksum an ICMP Echo packet from user space into a buffer * starting from the payload. */ int ping_getfrag(void *from, char *to, int offset, int fraglen, int odd, struct sk_buff *skb) { struct pingfakehdr *pfh = from; if (!csum_and_copy_from_iter_full(to, fraglen, &pfh->wcheck, &pfh->msg->msg_iter)) return -EFAULT; #if IS_ENABLED(CONFIG_IPV6) /* For IPv6, checksum each skb as we go along, as expected by * icmpv6_push_pending_frames. For IPv4, accumulate the checksum in * wcheck, it will be finalized in ping_v4_push_pending_frames. */ if (pfh->family == AF_INET6) { skb->csum = csum_block_add(skb->csum, pfh->wcheck, odd); skb->ip_summed = CHECKSUM_NONE; pfh->wcheck = 0; } #endif return 0; } EXPORT_SYMBOL_GPL(ping_getfrag); static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh, struct flowi4 *fl4) { struct sk_buff *skb = skb_peek(&sk->sk_write_queue); if (!skb) return 0; pfh->wcheck = csum_partial((char *)&pfh->icmph, sizeof(struct icmphdr), pfh->wcheck); pfh->icmph.checksum = csum_fold(pfh->wcheck); memcpy(icmp_hdr(skb), &pfh->icmph, sizeof(struct icmphdr)); skb->ip_summed = CHECKSUM_NONE; return ip_push_pending_frames(sk, fl4); } int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, void *user_icmph, size_t icmph_len) { u8 type, code; if (len > 0xFFFF) return -EMSGSIZE; /* Must have at least a full ICMP header. */ if (len < icmph_len) return -EINVAL; /* * Check the flags. */ /* Mirror BSD error message compatibility */ if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; /* * Fetch the ICMP header provided by the userland. * iovec is modified! The ICMP header is consumed. */ if (memcpy_from_msg(user_icmph, msg, icmph_len)) return -EFAULT; if (family == AF_INET) { type = ((struct icmphdr *) user_icmph)->type; code = ((struct icmphdr *) user_icmph)->code; #if IS_ENABLED(CONFIG_IPV6) } else if (family == AF_INET6) { type = ((struct icmp6hdr *) user_icmph)->icmp6_type; code = ((struct icmp6hdr *) user_icmph)->icmp6_code; #endif } else { BUG(); } if (!ping_supported(family, type, code)) return -EINVAL; return 0; } EXPORT_SYMBOL_GPL(ping_common_sendmsg); static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct net *net = sock_net(sk); struct flowi4 fl4; struct inet_sock *inet = inet_sk(sk); struct ipcm_cookie ipc; struct icmphdr user_icmph; struct pingfakehdr pfh; struct rtable *rt = NULL; struct ip_options_data opt_copy; int free = 0; __be32 saddr, daddr, faddr; u8 tos; int err; pr_debug("ping_v4_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num); err = ping_common_sendmsg(AF_INET, msg, len, &user_icmph, sizeof(user_icmph)); if (err) return err; /* * Get and verify the address. */ if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name); if (msg->msg_namelen < sizeof(*usin)) return -EINVAL; if (usin->sin_family != AF_INET) return -EAFNOSUPPORT; daddr = usin->sin_addr.s_addr; /* no remote port */ } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; daddr = inet->inet_daddr; /* no remote port */ } ipcm_init_sk(&ipc, inet); if (msg->msg_controllen) { err = ip_cmsg_send(sk, msg, &ipc, false); if (unlikely(err)) { kfree(ipc.opt); return err; } if (ipc.opt) free = 1; } if (!ipc.opt) { struct ip_options_rcu *inet_opt; rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt) { memcpy(&opt_copy, inet_opt, sizeof(*inet_opt) + inet_opt->opt.optlen); ipc.opt = &opt_copy.opt; } rcu_read_unlock(); } saddr = ipc.addr; ipc.addr = faddr = daddr; if (ipc.opt && ipc.opt->opt.srr) { if (!daddr) { err = -EINVAL; goto out_free; } faddr = ipc.opt->opt.faddr; } tos = get_rttos(&ipc, inet); if (sock_flag(sk, SOCK_LOCALROUTE) || (msg->msg_flags & MSG_DONTROUTE) || (ipc.opt && ipc.opt->opt.is_strictroute)) { tos |= RTO_ONLINK; } if (ipv4_is_multicast(daddr)) { if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif)) ipc.oif = inet->mc_index; if (!saddr) saddr = inet->mc_addr; } else if (!ipc.oif) ipc.oif = inet->uc_index; flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, RT_SCOPE_UNIVERSE, sk->sk_protocol, inet_sk_flowi_flags(sk), faddr, saddr, 0, 0, sk->sk_uid); fl4.fl4_icmp_type = user_icmph.type; fl4.fl4_icmp_code = user_icmph.code; security_sk_classify_flow(sk, flowi4_to_flowi_common(&fl4)); rt = ip_route_output_flow(net, &fl4, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; if (err == -ENETUNREACH) IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); goto out; } err = -EACCES; if ((rt->rt_flags & RTCF_BROADCAST) && !sock_flag(sk, SOCK_BROADCAST)) goto out; if (msg->msg_flags & MSG_CONFIRM) goto do_confirm; back_from_confirm: if (!ipc.addr) ipc.addr = fl4.daddr; lock_sock(sk); pfh.icmph.type = user_icmph.type; /* already checked */ pfh.icmph.code = user_icmph.code; /* ditto */ pfh.icmph.checksum = 0; pfh.icmph.un.echo.id = inet->inet_sport; pfh.icmph.un.echo.sequence = user_icmph.un.echo.sequence; pfh.msg = msg; pfh.wcheck = 0; pfh.family = AF_INET; err = ip_append_data(sk, &fl4, ping_getfrag, &pfh, len, sizeof(struct icmphdr), &ipc, &rt, msg->msg_flags); if (err) ip_flush_pending_frames(sk); else err = ping_v4_push_pending_frames(sk, &pfh, &fl4); release_sock(sk); out: ip_rt_put(rt); out_free: if (free) kfree(ipc.opt); if (!err) { icmp_out_count(sock_net(sk), user_icmph.type); return len; } return err; do_confirm: if (msg->msg_flags & MSG_PROBE) dst_confirm_neigh(&rt->dst, &fl4.daddr); if (!(msg->msg_flags & MSG_PROBE) || len) goto back_from_confirm; err = 0; goto out; } int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { struct inet_sock *isk = inet_sk(sk); int family = sk->sk_family; struct sk_buff *skb; int copied, err; pr_debug("ping_recvmsg(sk=%p,sk->num=%u)\n", isk, isk->inet_num); err = -EOPNOTSUPP; if (flags & MSG_OOB) goto out; if (flags & MSG_ERRQUEUE) return inet_recv_error(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, &err); if (!skb) goto out; copied = skb->len; if (copied > len) { msg->msg_flags |= MSG_TRUNC; copied = len; } /* Don't bother checking the checksum */ err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto done; sock_recv_timestamp(msg, sk, skb); /* Copy the address and add cmsg data. */ if (family == AF_INET) { DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); if (sin) { sin->sin_family = AF_INET; sin->sin_port = 0 /* skb->h.uh->source */; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); *addr_len = sizeof(*sin); } if (isk->cmsg_flags) ip_cmsg_recv(msg, skb); #if IS_ENABLED(CONFIG_IPV6) } else if (family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6hdr *ip6 = ipv6_hdr(skb); DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); if (sin6) { sin6->sin6_family = AF_INET6; sin6->sin6_port = 0; sin6->sin6_addr = ip6->saddr; sin6->sin6_flowinfo = 0; if (np->sndflow) sin6->sin6_flowinfo = ip6_flowinfo(ip6); sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, inet6_iif(skb)); *addr_len = sizeof(*sin6); } if (inet6_sk(sk)->rxopt.all) pingv6_ops.ip6_datagram_recv_common_ctl(sk, msg, skb); if (skb->protocol == htons(ETH_P_IPV6) && inet6_sk(sk)->rxopt.all) pingv6_ops.ip6_datagram_recv_specific_ctl(sk, msg, skb); else if (skb->protocol == htons(ETH_P_IP) && isk->cmsg_flags) ip_cmsg_recv(msg, skb); #endif } else { BUG(); } err = copied; done: skb_free_datagram(sk, skb); out: pr_debug("ping_recvmsg -> %d\n", err); return err; } EXPORT_SYMBOL_GPL(ping_recvmsg); static enum skb_drop_reason __ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { enum skb_drop_reason reason; pr_debug("ping_queue_rcv_skb(sk=%p,sk->num=%d,skb=%p)\n", inet_sk(sk), inet_sk(sk)->inet_num, skb); if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) { kfree_skb_reason(skb, reason); pr_debug("ping_queue_rcv_skb -> failed\n"); return reason; } return SKB_NOT_DROPPED_YET; } int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { return __ping_queue_rcv_skb(sk, skb) ? -1 : 0; } EXPORT_SYMBOL_GPL(ping_queue_rcv_skb); /* * All we need to do is get the socket. */ enum skb_drop_reason ping_rcv(struct sk_buff *skb) { enum skb_drop_reason reason = SKB_DROP_REASON_NO_SOCKET; struct sock *sk; struct net *net = dev_net(skb->dev); struct icmphdr *icmph = icmp_hdr(skb); /* We assume the packet has already been checked by icmp_rcv */ pr_debug("ping_rcv(skb=%p,id=%04x,seq=%04x)\n", skb, ntohs(icmph->un.echo.id), ntohs(icmph->un.echo.sequence)); /* Push ICMP header back */ skb_push(skb, skb->data - (u8 *)icmph); sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id)); if (sk) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); pr_debug("rcv on socket %p\n", sk); if (skb2) reason = __ping_queue_rcv_skb(sk, skb2); else reason = SKB_DROP_REASON_NOMEM; } if (reason) pr_debug("no socket, dropping\n"); return reason; } EXPORT_SYMBOL_GPL(ping_rcv); struct proto ping_prot = { .name = "PING", .owner = THIS_MODULE, .init = ping_init_sock, .close = ping_close, .pre_connect = ping_pre_connect, .connect = ip4_datagram_connect, .disconnect = __udp_disconnect, .setsockopt = ip_setsockopt, .getsockopt = ip_getsockopt, .sendmsg = ping_v4_sendmsg, .recvmsg = ping_recvmsg, .bind = ping_bind, .backlog_rcv = ping_queue_rcv_skb, .release_cb = ip4_datagram_release_cb, .hash = ping_hash, .unhash = ping_unhash, .get_port = ping_get_port, .put_port = ping_unhash, .obj_size = sizeof(struct inet_sock), }; EXPORT_SYMBOL(ping_prot); #ifdef CONFIG_PROC_FS static struct sock *ping_get_first(struct seq_file *seq, int start) { struct sock *sk; struct ping_iter_state *state = seq->private; struct net *net = seq_file_net(seq); for (state->bucket = start; state->bucket < PING_HTABLE_SIZE; ++state->bucket) { struct hlist_nulls_node *node; struct hlist_nulls_head *hslot; hslot = &ping_table.hash[state->bucket]; if (hlist_nulls_empty(hslot)) continue; sk_nulls_for_each(sk, node, hslot) { if (net_eq(sock_net(sk), net) && sk->sk_family == state->family) goto found; } } sk = NULL; found: return sk; } static struct sock *ping_get_next(struct seq_file *seq, struct sock *sk) { struct ping_iter_state *state = seq->private; struct net *net = seq_file_net(seq); do { sk = sk_nulls_next(sk); } while (sk && (!net_eq(sock_net(sk), net))); if (!sk) return ping_get_first(seq, state->bucket + 1); return sk; } static struct sock *ping_get_idx(struct seq_file *seq, loff_t pos) { struct sock *sk = ping_get_first(seq, 0); if (sk) while (pos && (sk = ping_get_next(seq, sk)) != NULL) --pos; return pos ? NULL : sk; } void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family) __acquires(ping_table.lock) { struct ping_iter_state *state = seq->private; state->bucket = 0; state->family = family; spin_lock(&ping_table.lock); return *pos ? ping_get_idx(seq, *pos-1) : SEQ_START_TOKEN; } EXPORT_SYMBOL_GPL(ping_seq_start); static void *ping_v4_seq_start(struct seq_file *seq, loff_t *pos) { return ping_seq_start(seq, pos, AF_INET); } void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct sock *sk; if (v == SEQ_START_TOKEN) sk = ping_get_idx(seq, 0); else sk = ping_get_next(seq, v); ++*pos; return sk; } EXPORT_SYMBOL_GPL(ping_seq_next); void ping_seq_stop(struct seq_file *seq, void *v) __releases(ping_table.lock) { spin_unlock(&ping_table.lock); } EXPORT_SYMBOL_GPL(ping_seq_stop); static void ping_v4_format_sock(struct sock *sp, struct seq_file *f, int bucket) { struct inet_sock *inet = inet_sk(sp); __be32 dest = inet->inet_daddr; __be32 src = inet->inet_rcv_saddr; __u16 destp = ntohs(inet->inet_dport); __u16 srcp = ntohs(inet->inet_sport); seq_printf(f, "%5d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %u", bucket, src, srcp, dest, destp, sp->sk_state, sk_wmem_alloc_get(sp), sk_rmem_alloc_get(sp), 0, 0L, 0, from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)), 0, sock_i_ino(sp), refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } static int ping_v4_seq_show(struct seq_file *seq, void *v) { seq_setwidth(seq, 127); if (v == SEQ_START_TOKEN) seq_puts(seq, " sl local_address rem_address st tx_queue " "rx_queue tr tm->when retrnsmt uid timeout " "inode ref pointer drops"); else { struct ping_iter_state *state = seq->private; ping_v4_format_sock(v, seq, state->bucket); } seq_pad(seq, '\n'); return 0; } static const struct seq_operations ping_v4_seq_ops = { .start = ping_v4_seq_start, .show = ping_v4_seq_show, .next = ping_seq_next, .stop = ping_seq_stop, }; static int __net_init ping_v4_proc_init_net(struct net *net) { if (!proc_create_net("icmp", 0444, net->proc_net, &ping_v4_seq_ops, sizeof(struct ping_iter_state))) return -ENOMEM; return 0; } static void __net_exit ping_v4_proc_exit_net(struct net *net) { remove_proc_entry("icmp", net->proc_net); } static struct pernet_operations ping_v4_net_ops = { .init = ping_v4_proc_init_net, .exit = ping_v4_proc_exit_net, }; int __init ping_proc_init(void) { return register_pernet_subsys(&ping_v4_net_ops); } void ping_proc_exit(void) { unregister_pernet_subsys(&ping_v4_net_ops); } #endif void __init ping_init(void) { int i; for (i = 0; i < PING_HTABLE_SIZE; i++) INIT_HLIST_NULLS_HEAD(&ping_table.hash[i], i); spin_lock_init(&ping_table.lock); } |
| 1939 1939 1939 1938 1939 1862 1929 1939 1949 1680 591 1647 1929 1873 1862 1928 16 1929 1862 604 1661 1939 1938 1939 1939 1939 640 640 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 | // SPDX-License-Identifier: GPL-2.0 /* * kernel userspace event delivery * * Copyright (C) 2004 Red Hat, Inc. All rights reserved. * Copyright (C) 2004 Novell, Inc. All rights reserved. * Copyright (C) 2004 IBM, Inc. All rights reserved. * * Authors: * Robert Love <rml@novell.com> * Kay Sievers <kay.sievers@vrfy.org> * Arjan van de Ven <arjanv@redhat.com> * Greg Kroah-Hartman <greg@kroah.com> */ #include <linux/spinlock.h> #include <linux/string.h> #include <linux/kobject.h> #include <linux/export.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/socket.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/uidgid.h> #include <linux/uuid.h> #include <linux/ctype.h> #include <net/sock.h> #include <net/netlink.h> #include <net/net_namespace.h> u64 uevent_seqnum; #ifdef CONFIG_UEVENT_HELPER char uevent_helper[UEVENT_HELPER_PATH_LEN] = CONFIG_UEVENT_HELPER_PATH; #endif struct uevent_sock { struct list_head list; struct sock *sk; }; #ifdef CONFIG_NET static LIST_HEAD(uevent_sock_list); #endif /* This lock protects uevent_seqnum and uevent_sock_list */ static DEFINE_MUTEX(uevent_sock_mutex); /* the strings here must match the enum in include/linux/kobject.h */ static const char *kobject_actions[] = { [KOBJ_ADD] = "add", [KOBJ_REMOVE] = "remove", [KOBJ_CHANGE] = "change", [KOBJ_MOVE] = "move", [KOBJ_ONLINE] = "online", [KOBJ_OFFLINE] = "offline", [KOBJ_BIND] = "bind", [KOBJ_UNBIND] = "unbind", }; static int kobject_action_type(const char *buf, size_t count, enum kobject_action *type, const char **args) { enum kobject_action action; size_t count_first; const char *args_start; int ret = -EINVAL; if (count && (buf[count-1] == '\n' || buf[count-1] == '\0')) count--; if (!count) goto out; args_start = strnchr(buf, count, ' '); if (args_start) { count_first = args_start - buf; args_start = args_start + 1; } else count_first = count; for (action = 0; action < ARRAY_SIZE(kobject_actions); action++) { if (strncmp(kobject_actions[action], buf, count_first) != 0) continue; if (kobject_actions[action][count_first] != '\0') continue; if (args) *args = args_start; *type = action; ret = 0; break; } out: return ret; } static const char *action_arg_word_end(const char *buf, const char *buf_end, char delim) { const char *next = buf; while (next <= buf_end && *next != delim) if (!isalnum(*next++)) return NULL; if (next == buf) return NULL; return next; } static int kobject_action_args(const char *buf, size_t count, struct kobj_uevent_env **ret_env) { struct kobj_uevent_env *env = NULL; const char *next, *buf_end, *key; int key_len; int r = -EINVAL; if (count && (buf[count - 1] == '\n' || buf[count - 1] == '\0')) count--; if (!count) return -EINVAL; env = kzalloc(sizeof(*env), GFP_KERNEL); if (!env) return -ENOMEM; /* first arg is UUID */ if (count < UUID_STRING_LEN || !uuid_is_valid(buf) || add_uevent_var(env, "SYNTH_UUID=%.*s", UUID_STRING_LEN, buf)) goto out; /* * the rest are custom environment variables in KEY=VALUE * format with ' ' delimiter between each KEY=VALUE pair */ next = buf + UUID_STRING_LEN; buf_end = buf + count - 1; while (next <= buf_end) { if (*next != ' ') goto out; /* skip the ' ', key must follow */ key = ++next; if (key > buf_end) goto out; buf = next; next = action_arg_word_end(buf, buf_end, '='); if (!next || next > buf_end || *next != '=') goto out; key_len = next - buf; /* skip the '=', value must follow */ if (++next > buf_end) goto out; buf = next; next = action_arg_word_end(buf, buf_end, ' '); if (!next) goto out; if (add_uevent_var(env, "SYNTH_ARG_%.*s=%.*s", key_len, key, (int) (next - buf), buf)) goto out; } r = 0; out: if (r) kfree(env); else *ret_env = env; return r; } /** * kobject_synth_uevent - send synthetic uevent with arguments * * @kobj: struct kobject for which synthetic uevent is to be generated * @buf: buffer containing action type and action args, newline is ignored * @count: length of buffer * * Returns 0 if kobject_synthetic_uevent() is completed with success or the * corresponding error when it fails. */ int kobject_synth_uevent(struct kobject *kobj, const char *buf, size_t count) { char *no_uuid_envp[] = { "SYNTH_UUID=0", NULL }; enum kobject_action action; const char *action_args; struct kobj_uevent_env *env; const char *msg = NULL, *devpath; int r; r = kobject_action_type(buf, count, &action, &action_args); if (r) { msg = "unknown uevent action string"; goto out; } if (!action_args) { r = kobject_uevent_env(kobj, action, no_uuid_envp); goto out; } r = kobject_action_args(action_args, count - (action_args - buf), &env); if (r == -EINVAL) { msg = "incorrect uevent action arguments"; goto out; } if (r) goto out; r = kobject_uevent_env(kobj, action, env->envp); kfree(env); out: if (r) { devpath = kobject_get_path(kobj, GFP_KERNEL); pr_warn("synth uevent: %s: %s\n", devpath ?: "unknown device", msg ?: "failed to send uevent"); kfree(devpath); } return r; } #ifdef CONFIG_UEVENT_HELPER static int kobj_usermode_filter(struct kobject *kobj) { const struct kobj_ns_type_operations *ops; ops = kobj_ns_ops(kobj); if (ops) { const void *init_ns, *ns; ns = kobj->ktype->namespace(kobj); init_ns = ops->initial_ns(); return ns != init_ns; } return 0; } static int init_uevent_argv(struct kobj_uevent_env *env, const char *subsystem) { int buffer_size = sizeof(env->buf) - env->buflen; int len; len = strlcpy(&env->buf[env->buflen], subsystem, buffer_size); if (len >= buffer_size) { pr_warn("init_uevent_argv: buffer size of %d too small, needed %d\n", buffer_size, len); return -ENOMEM; } env->argv[0] = uevent_helper; env->argv[1] = &env->buf[env->buflen]; env->argv[2] = NULL; env->buflen += len + 1; return 0; } static void cleanup_uevent_env(struct subprocess_info *info) { kfree(info->data); } #endif #ifdef CONFIG_NET static struct sk_buff *alloc_uevent_skb(struct kobj_uevent_env *env, const char *action_string, const char *devpath) { struct netlink_skb_parms *parms; struct sk_buff *skb = NULL; char *scratch; size_t len; /* allocate message with maximum possible size */ len = strlen(action_string) + strlen(devpath) + 2; skb = alloc_skb(len + env->buflen, GFP_KERNEL); if (!skb) return NULL; /* add header */ scratch = skb_put(skb, len); sprintf(scratch, "%s@%s", action_string, devpath); skb_put_data(skb, env->buf, env->buflen); parms = &NETLINK_CB(skb); parms->creds.uid = GLOBAL_ROOT_UID; parms->creds.gid = GLOBAL_ROOT_GID; parms->dst_group = 1; parms->portid = 0; return skb; } static int uevent_net_broadcast_untagged(struct kobj_uevent_env *env, const char *action_string, const char *devpath) { struct sk_buff *skb = NULL; struct uevent_sock *ue_sk; int retval = 0; /* send netlink message */ list_for_each_entry(ue_sk, &uevent_sock_list, list) { struct sock *uevent_sock = ue_sk->sk; if (!netlink_has_listeners(uevent_sock, 1)) continue; if (!skb) { retval = -ENOMEM; skb = alloc_uevent_skb(env, action_string, devpath); if (!skb) continue; } retval = netlink_broadcast(uevent_sock, skb_get(skb), 0, 1, GFP_KERNEL); /* ENOBUFS should be handled in userspace */ if (retval == -ENOBUFS || retval == -ESRCH) retval = 0; } consume_skb(skb); return retval; } static int uevent_net_broadcast_tagged(struct sock *usk, struct kobj_uevent_env *env, const char *action_string, const char *devpath) { struct user_namespace *owning_user_ns = sock_net(usk)->user_ns; struct sk_buff *skb = NULL; int ret = 0; skb = alloc_uevent_skb(env, action_string, devpath); if (!skb) return -ENOMEM; /* fix credentials */ if (owning_user_ns != &init_user_ns) { struct netlink_skb_parms *parms = &NETLINK_CB(skb); kuid_t root_uid; kgid_t root_gid; /* fix uid */ root_uid = make_kuid(owning_user_ns, 0); if (uid_valid(root_uid)) parms->creds.uid = root_uid; /* fix gid */ root_gid = make_kgid(owning_user_ns, 0); if (gid_valid(root_gid)) parms->creds.gid = root_gid; } ret = netlink_broadcast(usk, skb, 0, 1, GFP_KERNEL); /* ENOBUFS should be handled in userspace */ if (ret == -ENOBUFS || ret == -ESRCH) ret = 0; return ret; } #endif static int kobject_uevent_net_broadcast(struct kobject *kobj, struct kobj_uevent_env *env, const char *action_string, const char *devpath) { int ret = 0; #ifdef CONFIG_NET const struct kobj_ns_type_operations *ops; const struct net *net = NULL; ops = kobj_ns_ops(kobj); if (!ops && kobj->kset) { struct kobject *ksobj = &kobj->kset->kobj; if (ksobj->parent != NULL) ops = kobj_ns_ops(ksobj->parent); } /* kobjects currently only carry network namespace tags and they * are the only tag relevant here since we want to decide which * network namespaces to broadcast the uevent into. */ if (ops && ops->netlink_ns && kobj->ktype->namespace) if (ops->type == KOBJ_NS_TYPE_NET) net = kobj->ktype->namespace(kobj); if (!net) ret = uevent_net_broadcast_untagged(env, action_string, devpath); else ret = uevent_net_broadcast_tagged(net->uevent_sock->sk, env, action_string, devpath); #endif return ret; } static void zap_modalias_env(struct kobj_uevent_env *env) { static const char modalias_prefix[] = "MODALIAS="; size_t len; int i, j; for (i = 0; i < env->envp_idx;) { if (strncmp(env->envp[i], modalias_prefix, sizeof(modalias_prefix) - 1)) { i++; continue; } len = strlen(env->envp[i]) + 1; if (i != env->envp_idx - 1) { /* @env->envp[] contains pointers to @env->buf[] * with @env->buflen chars, and we are removing * variable MODALIAS here pointed by @env->envp[i] * with length @len as shown below: * * 0 @env->buf[] @env->buflen * --------------------------------------------- * ^ ^ ^ ^ * | |-> @len <-| target block | * @env->envp[0] @env->envp[i] @env->envp[i + 1] * * so the "target block" indicated above is moved * backward by @len, and its right size is * @env->buflen - (@env->envp[i + 1] - @env->envp[0]). */ memmove(env->envp[i], env->envp[i + 1], env->buflen - (env->envp[i + 1] - env->envp[0])); for (j = i; j < env->envp_idx - 1; j++) env->envp[j] = env->envp[j + 1] - len; } env->envp_idx--; env->buflen -= len; } } /** * kobject_uevent_env - send an uevent with environmental data * * @kobj: struct kobject that the action is happening to * @action: action that is happening * @envp_ext: pointer to environmental data * * Returns 0 if kobject_uevent_env() is completed with success or the * corresponding error when it fails. */ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, char *envp_ext[]) { struct kobj_uevent_env *env; const char *action_string = kobject_actions[action]; const char *devpath = NULL; const char *subsystem; struct kobject *top_kobj; struct kset *kset; const struct kset_uevent_ops *uevent_ops; int i = 0; int retval = 0; /* * Mark "remove" event done regardless of result, for some subsystems * do not want to re-trigger "remove" event via automatic cleanup. */ if (action == KOBJ_REMOVE) kobj->state_remove_uevent_sent = 1; pr_debug("kobject: '%s' (%p): %s\n", kobject_name(kobj), kobj, __func__); /* search the kset we belong to */ top_kobj = kobj; while (!top_kobj->kset && top_kobj->parent) top_kobj = top_kobj->parent; if (!top_kobj->kset) { pr_debug("kobject: '%s' (%p): %s: attempted to send uevent " "without kset!\n", kobject_name(kobj), kobj, __func__); return -EINVAL; } kset = top_kobj->kset; uevent_ops = kset->uevent_ops; /* skip the event, if uevent_suppress is set*/ if (kobj->uevent_suppress) { pr_debug("kobject: '%s' (%p): %s: uevent_suppress " "caused the event to drop!\n", kobject_name(kobj), kobj, __func__); return 0; } /* skip the event, if the filter returns zero. */ if (uevent_ops && uevent_ops->filter) if (!uevent_ops->filter(kobj)) { pr_debug("kobject: '%s' (%p): %s: filter function " "caused the event to drop!\n", kobject_name(kobj), kobj, __func__); return 0; } /* originating subsystem */ if (uevent_ops && uevent_ops->name) subsystem = uevent_ops->name(kobj); else subsystem = kobject_name(&kset->kobj); if (!subsystem) { pr_debug("kobject: '%s' (%p): %s: unset subsystem caused the " "event to drop!\n", kobject_name(kobj), kobj, __func__); return 0; } /* environment buffer */ env = kzalloc(sizeof(struct kobj_uevent_env), GFP_KERNEL); if (!env) return -ENOMEM; /* complete object path */ devpath = kobject_get_path(kobj, GFP_KERNEL); if (!devpath) { retval = -ENOENT; goto exit; } /* default keys */ retval = add_uevent_var(env, "ACTION=%s", action_string); if (retval) goto exit; retval = add_uevent_var(env, "DEVPATH=%s", devpath); if (retval) goto exit; retval = add_uevent_var(env, "SUBSYSTEM=%s", subsystem); if (retval) goto exit; /* keys passed in from the caller */ if (envp_ext) { for (i = 0; envp_ext[i]; i++) { retval = add_uevent_var(env, "%s", envp_ext[i]); if (retval) goto exit; } } /* let the kset specific function add its stuff */ if (uevent_ops && uevent_ops->uevent) { retval = uevent_ops->uevent(kobj, env); if (retval) { pr_debug("kobject: '%s' (%p): %s: uevent() returned " "%d\n", kobject_name(kobj), kobj, __func__, retval); goto exit; } } switch (action) { case KOBJ_ADD: /* * Mark "add" event so we can make sure we deliver "remove" * event to userspace during automatic cleanup. If * the object did send an "add" event, "remove" will * automatically generated by the core, if not already done * by the caller. */ kobj->state_add_uevent_sent = 1; break; case KOBJ_UNBIND: zap_modalias_env(env); break; default: break; } mutex_lock(&uevent_sock_mutex); /* we will send an event, so request a new sequence number */ retval = add_uevent_var(env, "SEQNUM=%llu", ++uevent_seqnum); if (retval) { mutex_unlock(&uevent_sock_mutex); goto exit; } retval = kobject_uevent_net_broadcast(kobj, env, action_string, devpath); mutex_unlock(&uevent_sock_mutex); #ifdef CONFIG_UEVENT_HELPER /* call uevent_helper, usually only enabled during early boot */ if (uevent_helper[0] && !kobj_usermode_filter(kobj)) { struct subprocess_info *info; retval = add_uevent_var(env, "HOME=/"); if (retval) goto exit; retval = add_uevent_var(env, "PATH=/sbin:/bin:/usr/sbin:/usr/bin"); if (retval) goto exit; retval = init_uevent_argv(env, subsystem); if (retval) goto exit; retval = -ENOMEM; info = call_usermodehelper_setup(env->argv[0], env->argv, env->envp, GFP_KERNEL, NULL, cleanup_uevent_env, env); if (info) { retval = call_usermodehelper_exec(info, UMH_NO_WAIT); env = NULL; /* freed by cleanup_uevent_env */ } } #endif exit: kfree(devpath); kfree(env); return retval; } EXPORT_SYMBOL_GPL(kobject_uevent_env); /** * kobject_uevent - notify userspace by sending an uevent * * @kobj: struct kobject that the action is happening to * @action: action that is happening * * Returns 0 if kobject_uevent() is completed with success or the * corresponding error when it fails. */ int kobject_uevent(struct kobject *kobj, enum kobject_action action) { return kobject_uevent_env(kobj, action, NULL); } EXPORT_SYMBOL_GPL(kobject_uevent); /** * add_uevent_var - add key value string to the environment buffer * @env: environment buffer structure * @format: printf format for the key=value pair * * Returns 0 if environment variable was added successfully or -ENOMEM * if no space was available. */ int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...) { va_list args; int len; if (env->envp_idx >= ARRAY_SIZE(env->envp)) { WARN(1, KERN_ERR "add_uevent_var: too many keys\n"); return -ENOMEM; } va_start(args, format); len = vsnprintf(&env->buf[env->buflen], sizeof(env->buf) - env->buflen, format, args); va_end(args); if (len >= (sizeof(env->buf) - env->buflen)) { WARN(1, KERN_ERR "add_uevent_var: buffer size too small\n"); return -ENOMEM; } env->envp[env->envp_idx++] = &env->buf[env->buflen]; env->buflen += len + 1; return 0; } EXPORT_SYMBOL_GPL(add_uevent_var); #if defined(CONFIG_NET) static int uevent_net_broadcast(struct sock *usk, struct sk_buff *skb, struct netlink_ext_ack *extack) { /* u64 to chars: 2^64 - 1 = 21 chars */ char buf[sizeof("SEQNUM=") + 21]; struct sk_buff *skbc; int ret; /* bump and prepare sequence number */ ret = snprintf(buf, sizeof(buf), "SEQNUM=%llu", ++uevent_seqnum); if (ret < 0 || (size_t)ret >= sizeof(buf)) return -ENOMEM; ret++; /* verify message does not overflow */ if ((skb->len + ret) > UEVENT_BUFFER_SIZE) { NL_SET_ERR_MSG(extack, "uevent message too big"); return -EINVAL; } /* copy skb and extend to accommodate sequence number */ skbc = skb_copy_expand(skb, 0, ret, GFP_KERNEL); if (!skbc) return -ENOMEM; /* append sequence number */ skb_put_data(skbc, buf, ret); /* remove msg header */ skb_pull(skbc, NLMSG_HDRLEN); /* set portid 0 to inform userspace message comes from kernel */ NETLINK_CB(skbc).portid = 0; NETLINK_CB(skbc).dst_group = 1; ret = netlink_broadcast(usk, skbc, 0, 1, GFP_KERNEL); /* ENOBUFS should be handled in userspace */ if (ret == -ENOBUFS || ret == -ESRCH) ret = 0; return ret; } static int uevent_net_rcv_skb(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net; int ret; if (!nlmsg_data(nlh)) return -EINVAL; /* * Verify that we are allowed to send messages to the target * network namespace. The caller must have CAP_SYS_ADMIN in the * owning user namespace of the target network namespace. */ net = sock_net(NETLINK_CB(skb).sk); if (!netlink_ns_capable(skb, net->user_ns, CAP_SYS_ADMIN)) { NL_SET_ERR_MSG(extack, "missing CAP_SYS_ADMIN capability"); return -EPERM; } mutex_lock(&uevent_sock_mutex); ret = uevent_net_broadcast(net->uevent_sock->sk, skb, extack); mutex_unlock(&uevent_sock_mutex); return ret; } static void uevent_net_rcv(struct sk_buff *skb) { netlink_rcv_skb(skb, &uevent_net_rcv_skb); } static int uevent_net_init(struct net *net) { struct uevent_sock *ue_sk; struct netlink_kernel_cfg cfg = { .groups = 1, .input = uevent_net_rcv, .flags = NL_CFG_F_NONROOT_RECV }; ue_sk = kzalloc(sizeof(*ue_sk), GFP_KERNEL); if (!ue_sk) return -ENOMEM; ue_sk->sk = netlink_kernel_create(net, NETLINK_KOBJECT_UEVENT, &cfg); if (!ue_sk->sk) { pr_err("kobject_uevent: unable to create netlink socket!\n"); kfree(ue_sk); return -ENODEV; } net->uevent_sock = ue_sk; /* Restrict uevents to initial user namespace. */ if (sock_net(ue_sk->sk)->user_ns == &init_user_ns) { mutex_lock(&uevent_sock_mutex); list_add_tail(&ue_sk->list, &uevent_sock_list); mutex_unlock(&uevent_sock_mutex); } return 0; } static void uevent_net_exit(struct net *net) { struct uevent_sock *ue_sk = net->uevent_sock; if (sock_net(ue_sk->sk)->user_ns == &init_user_ns) { mutex_lock(&uevent_sock_mutex); list_del(&ue_sk->list); mutex_unlock(&uevent_sock_mutex); } netlink_kernel_release(ue_sk->sk); kfree(ue_sk); } static struct pernet_operations uevent_net_ops = { .init = uevent_net_init, .exit = uevent_net_exit, }; static int __init kobject_uevent_init(void) { return register_pernet_subsys(&uevent_net_ops); } postcore_initcall(kobject_uevent_init); #endif |
| 1 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Linux NET3: Internet Group Management Protocol [IGMP] * * Authors: * Alan Cox <alan@lxorguk.ukuu.org.uk> * * Extended to talk the BSD extended IGMP protocol of mrouted 3.6 */ #ifndef _LINUX_IGMP_H #define _LINUX_IGMP_H #include <linux/skbuff.h> #include <linux/timer.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/refcount.h> #include <uapi/linux/igmp.h> static inline struct igmphdr *igmp_hdr(const struct sk_buff *skb) { return (struct igmphdr *)skb_transport_header(skb); } static inline struct igmpv3_report * igmpv3_report_hdr(const struct sk_buff *skb) { return (struct igmpv3_report *)skb_transport_header(skb); } static inline struct igmpv3_query * igmpv3_query_hdr(const struct sk_buff *skb) { return (struct igmpv3_query *)skb_transport_header(skb); } struct ip_sf_socklist { unsigned int sl_max; unsigned int sl_count; struct rcu_head rcu; __be32 sl_addr[]; }; #define IP_SFBLOCK 10 /* allocate this many at once */ /* ip_mc_socklist is real list now. Speed is not argument; this list never used in fast path code */ struct ip_mc_socklist { struct ip_mc_socklist __rcu *next_rcu; struct ip_mreqn multi; unsigned int sfmode; /* MCAST_{INCLUDE,EXCLUDE} */ struct ip_sf_socklist __rcu *sflist; struct rcu_head rcu; }; struct ip_sf_list { struct ip_sf_list *sf_next; unsigned long sf_count[2]; /* include/exclude counts */ __be32 sf_inaddr; unsigned char sf_gsresp; /* include in g & s response? */ unsigned char sf_oldin; /* change state */ unsigned char sf_crcount; /* retrans. left to send */ }; struct ip_mc_list { struct in_device *interface; __be32 multiaddr; unsigned int sfmode; struct ip_sf_list *sources; struct ip_sf_list *tomb; unsigned long sfcount[2]; union { struct ip_mc_list *next; struct ip_mc_list __rcu *next_rcu; }; struct ip_mc_list __rcu *next_hash; struct timer_list timer; int users; refcount_t refcnt; spinlock_t lock; char tm_running; char reporter; char unsolicit_count; char loaded; unsigned char gsquery; /* check source marks? */ unsigned char crcount; struct rcu_head rcu; }; /* V3 exponential field decoding */ #define IGMPV3_MASK(value, nb) ((nb)>=32 ? (value) : ((1<<(nb))-1) & (value)) #define IGMPV3_EXP(thresh, nbmant, nbexp, value) \ ((value) < (thresh) ? (value) : \ ((IGMPV3_MASK(value, nbmant) | (1<<(nbmant))) << \ (IGMPV3_MASK((value) >> (nbmant), nbexp) + (nbexp)))) #define IGMPV3_QQIC(value) IGMPV3_EXP(0x80, 4, 3, value) #define IGMPV3_MRC(value) IGMPV3_EXP(0x80, 4, 3, value) static inline int ip_mc_may_pull(struct sk_buff *skb, unsigned int len) { if (skb_transport_offset(skb) + ip_transport_len(skb) < len) return 0; return pskb_may_pull(skb, len); } extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u8 proto); extern int igmp_rcv(struct sk_buff *); extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr); extern int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr, unsigned int mode); extern int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr); extern void ip_mc_drop_socket(struct sock *sk); extern int ip_mc_source(int add, int omode, struct sock *sk, struct ip_mreq_source *mreqs, int ifindex); extern int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf,int ifindex); extern int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, sockptr_t optval, sockptr_t optlen); extern int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, sockptr_t optval, size_t offset); extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, int dif, int sdif); extern void ip_mc_init_dev(struct in_device *); extern void ip_mc_destroy_dev(struct in_device *); extern void ip_mc_up(struct in_device *); extern void ip_mc_down(struct in_device *); extern void ip_mc_unmap(struct in_device *); extern void ip_mc_remap(struct in_device *); extern void __ip_mc_dec_group(struct in_device *in_dev, __be32 addr, gfp_t gfp); static inline void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) { return __ip_mc_dec_group(in_dev, addr, GFP_KERNEL); } extern void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, gfp_t gfp); extern void ip_mc_inc_group(struct in_device *in_dev, __be32 addr); int ip_mc_check_igmp(struct sk_buff *skb); #endif |
| 74 73 74 74 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | #include <linux/gfp.h> #include <linux/initrd.h> #include <linux/ioport.h> #include <linux/swap.h> #include <linux/memblock.h> #include <linux/swapfile.h> #include <linux/swapops.h> #include <linux/kmemleak.h> #include <linux/sched/task.h> #include <asm/set_memory.h> #include <asm/cpu_device_id.h> #include <asm/e820/api.h> #include <asm/init.h> #include <asm/page.h> #include <asm/page_types.h> #include <asm/sections.h> #include <asm/setup.h> #include <asm/tlbflush.h> #include <asm/tlb.h> #include <asm/proto.h> #include <asm/dma.h> /* for MAX_DMA_PFN */ #include <asm/microcode.h> #include <asm/kaslr.h> #include <asm/hypervisor.h> #include <asm/cpufeature.h> #include <asm/pti.h> #include <asm/text-patching.h> #include <asm/memtype.h> #include <asm/paravirt.h> /* * We need to define the tracepoints somewhere, and tlb.c * is only compiled when SMP=y. */ #include <trace/events/tlb.h> #include "mm_internal.h" /* * Tables translating between page_cache_type_t and pte encoding. * * The default values are defined statically as minimal supported mode; * WC and WT fall back to UC-. pat_init() updates these values to support * more cache modes, WC and WT, when it is safe to do so. See pat_init() * for the details. Note, __early_ioremap() used during early boot-time * takes pgprot_t (pte encoding) and does not use these tables. * * Index into __cachemode2pte_tbl[] is the cachemode. * * Index into __pte2cachemode_tbl[] are the caching attribute bits of the pte * (_PAGE_PWT, _PAGE_PCD, _PAGE_PAT) at index bit positions 0, 1, 2. */ static uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM] = { [_PAGE_CACHE_MODE_WB ] = 0 | 0 , [_PAGE_CACHE_MODE_WC ] = 0 | _PAGE_PCD, [_PAGE_CACHE_MODE_UC_MINUS] = 0 | _PAGE_PCD, [_PAGE_CACHE_MODE_UC ] = _PAGE_PWT | _PAGE_PCD, [_PAGE_CACHE_MODE_WT ] = 0 | _PAGE_PCD, [_PAGE_CACHE_MODE_WP ] = 0 | _PAGE_PCD, }; unsigned long cachemode2protval(enum page_cache_mode pcm) { if (likely(pcm == 0)) return 0; return __cachemode2pte_tbl[pcm]; } EXPORT_SYMBOL(cachemode2protval); static uint8_t __pte2cachemode_tbl[8] = { [__pte2cm_idx( 0 | 0 | 0 )] = _PAGE_CACHE_MODE_WB, [__pte2cm_idx(_PAGE_PWT | 0 | 0 )] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx( 0 | _PAGE_PCD | 0 )] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | 0 )] = _PAGE_CACHE_MODE_UC, [__pte2cm_idx( 0 | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_WB, [__pte2cm_idx(_PAGE_PWT | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx(0 | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC, }; /* * Check that the write-protect PAT entry is set for write-protect. * To do this without making assumptions how PAT has been set up (Xen has * another layout than the kernel), translate the _PAGE_CACHE_MODE_WP cache * mode via the __cachemode2pte_tbl[] into protection bits (those protection * bits will select a cache mode of WP or better), and then translate the * protection bits back into the cache mode using __pte2cm_idx() and the * __pte2cachemode_tbl[] array. This will return the really used cache mode. */ bool x86_has_pat_wp(void) { uint16_t prot = __cachemode2pte_tbl[_PAGE_CACHE_MODE_WP]; return __pte2cachemode_tbl[__pte2cm_idx(prot)] == _PAGE_CACHE_MODE_WP; } enum page_cache_mode pgprot2cachemode(pgprot_t pgprot) { unsigned long masked; masked = pgprot_val(pgprot) & _PAGE_CACHE_MASK; if (likely(masked == 0)) return 0; return __pte2cachemode_tbl[__pte2cm_idx(masked)]; } static unsigned long __initdata pgt_buf_start; static unsigned long __initdata pgt_buf_end; static unsigned long __initdata pgt_buf_top; static unsigned long min_pfn_mapped; static bool __initdata can_use_brk_pgt = true; /* * Provide a run-time mean of disabling ZONE_DMA32 if it is enabled via * CONFIG_ZONE_DMA32. */ static bool disable_dma32 __ro_after_init; /* * Pages returned are already directly mapped. * * Changing that is likely to break Xen, see commit: * * 279b706 x86,xen: introduce x86_init.mapping.pagetable_reserve * * for detailed information. */ __ref void *alloc_low_pages(unsigned int num) { unsigned long pfn; int i; if (after_bootmem) { unsigned int order; order = get_order((unsigned long)num << PAGE_SHIFT); return (void *)__get_free_pages(GFP_ATOMIC | __GFP_ZERO, order); } if ((pgt_buf_end + num) > pgt_buf_top || !can_use_brk_pgt) { unsigned long ret = 0; if (min_pfn_mapped < max_pfn_mapped) { ret = memblock_phys_alloc_range( PAGE_SIZE * num, PAGE_SIZE, min_pfn_mapped << PAGE_SHIFT, max_pfn_mapped << PAGE_SHIFT); } if (!ret && can_use_brk_pgt) ret = __pa(extend_brk(PAGE_SIZE * num, PAGE_SIZE)); if (!ret) panic("alloc_low_pages: can not alloc memory"); pfn = ret >> PAGE_SHIFT; } else { pfn = pgt_buf_end; pgt_buf_end += num; } for (i = 0; i < num; i++) { void *adr; adr = __va((pfn + i) << PAGE_SHIFT); clear_page(adr); } return __va(pfn << PAGE_SHIFT); } /* * By default need to be able to allocate page tables below PGD firstly for * the 0-ISA_END_ADDRESS range and secondly for the initial PMD_SIZE mapping. * With KASLR memory randomization, depending on the machine e820 memory and the * PUD alignment, twice that many pages may be needed when KASLR memory * randomization is enabled. */ #ifndef CONFIG_X86_5LEVEL #define INIT_PGD_PAGE_TABLES 3 #else #define INIT_PGD_PAGE_TABLES 4 #endif #ifndef CONFIG_RANDOMIZE_MEMORY #define INIT_PGD_PAGE_COUNT (2 * INIT_PGD_PAGE_TABLES) #else #define INIT_PGD_PAGE_COUNT (4 * INIT_PGD_PAGE_TABLES) #endif #define INIT_PGT_BUF_SIZE (INIT_PGD_PAGE_COUNT * PAGE_SIZE) RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE); void __init early_alloc_pgt_buf(void) { unsigned long tables = INIT_PGT_BUF_SIZE; phys_addr_t base; base = __pa(extend_brk(tables, PAGE_SIZE)); pgt_buf_start = base >> PAGE_SHIFT; pgt_buf_end = pgt_buf_start; pgt_buf_top = pgt_buf_start + (tables >> PAGE_SHIFT); } int after_bootmem; early_param_on_off("gbpages", "nogbpages", direct_gbpages, CONFIG_X86_DIRECT_GBPAGES); struct map_range { unsigned long start; unsigned long end; unsigned page_size_mask; }; static int page_size_mask; /* * Save some of cr4 feature set we're using (e.g. Pentium 4MB * enable and PPro Global page enable), so that any CPU's that boot * up after us can get the correct flags. Invoked on the boot CPU. */ static inline void cr4_set_bits_and_update_boot(unsigned long mask) { mmu_cr4_features |= mask; if (trampoline_cr4_features) *trampoline_cr4_features = mmu_cr4_features; cr4_set_bits(mask); } static void __init probe_page_size_mask(void) { /* * For pagealloc debugging, identity mapping will use small pages. * This will simplify cpa(), which otherwise needs to support splitting * large pages into small in interrupt context, etc. */ if (boot_cpu_has(X86_FEATURE_PSE) && !debug_pagealloc_enabled()) page_size_mask |= 1 << PG_LEVEL_2M; else direct_gbpages = 0; /* Enable PSE if available */ if (boot_cpu_has(X86_FEATURE_PSE)) cr4_set_bits_and_update_boot(X86_CR4_PSE); /* Enable PGE if available */ __supported_pte_mask &= ~_PAGE_GLOBAL; if (boot_cpu_has(X86_FEATURE_PGE)) { cr4_set_bits_and_update_boot(X86_CR4_PGE); __supported_pte_mask |= _PAGE_GLOBAL; } /* By the default is everything supported: */ __default_kernel_pte_mask = __supported_pte_mask; /* Except when with PTI where the kernel is mostly non-Global: */ if (cpu_feature_enabled(X86_FEATURE_PTI)) __default_kernel_pte_mask &= ~_PAGE_GLOBAL; /* Enable 1 GB linear kernel mappings if available: */ if (direct_gbpages && boot_cpu_has(X86_FEATURE_GBPAGES)) { printk(KERN_INFO "Using GB pages for direct mapping\n"); page_size_mask |= 1 << PG_LEVEL_1G; } else { direct_gbpages = 0; } } /* * INVLPG may not properly flush Global entries * on these CPUs when PCIDs are enabled. */ static const struct x86_cpu_id invlpg_miss_ids[] = { X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, 0), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, 0), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, 0), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, 0), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, 0), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, 0), {} }; static void setup_pcid(void) { if (!IS_ENABLED(CONFIG_X86_64)) return; if (!boot_cpu_has(X86_FEATURE_PCID)) return; if (x86_match_cpu(invlpg_miss_ids)) { pr_info("Incomplete global flushes, disabling PCID"); setup_clear_cpu_cap(X86_FEATURE_PCID); return; } if (boot_cpu_has(X86_FEATURE_PGE)) { /* * This can't be cr4_set_bits_and_update_boot() -- the * trampoline code can't handle CR4.PCIDE and it wouldn't * do any good anyway. Despite the name, * cr4_set_bits_and_update_boot() doesn't actually cause * the bits in question to remain set all the way through * the secondary boot asm. * * Instead, we brute-force it and set CR4.PCIDE manually in * start_secondary(). */ cr4_set_bits(X86_CR4_PCIDE); /* * INVPCID's single-context modes (2/3) only work if we set * X86_CR4_PCIDE, *and* we INVPCID support. It's unusable * on systems that have X86_CR4_PCIDE clear, or that have * no INVPCID support at all. */ if (boot_cpu_has(X86_FEATURE_INVPCID)) setup_force_cpu_cap(X86_FEATURE_INVPCID_SINGLE); } else { /* * flush_tlb_all(), as currently implemented, won't work if * PCID is on but PGE is not. Since that combination * doesn't exist on real hardware, there's no reason to try * to fully support it, but it's polite to avoid corrupting * data if we're on an improperly configured VM. */ setup_clear_cpu_cap(X86_FEATURE_PCID); } } #ifdef CONFIG_X86_32 #define NR_RANGE_MR 3 #else /* CONFIG_X86_64 */ #define NR_RANGE_MR 5 #endif static int __meminit save_mr(struct map_range *mr, int nr_range, unsigned long start_pfn, unsigned long end_pfn, unsigned long page_size_mask) { if (start_pfn < end_pfn) { if (nr_range >= NR_RANGE_MR) panic("run out of range for init_memory_mapping\n"); mr[nr_range].start = start_pfn<<PAGE_SHIFT; mr[nr_range].end = end_pfn<<PAGE_SHIFT; mr[nr_range].page_size_mask = page_size_mask; nr_range++; } return nr_range; } /* * adjust the page_size_mask for small range to go with * big page size instead small one if nearby are ram too. */ static void __ref adjust_range_page_size_mask(struct map_range *mr, int nr_range) { int i; for (i = 0; i < nr_range; i++) { if ((page_size_mask & (1<<PG_LEVEL_2M)) && !(mr[i].page_size_mask & (1<<PG_LEVEL_2M))) { unsigned long start = round_down(mr[i].start, PMD_SIZE); unsigned long end = round_up(mr[i].end, PMD_SIZE); #ifdef CONFIG_X86_32 if ((end >> PAGE_SHIFT) > max_low_pfn) continue; #endif if (memblock_is_region_memory(start, end - start)) mr[i].page_size_mask |= 1<<PG_LEVEL_2M; } if ((page_size_mask & (1<<PG_LEVEL_1G)) && !(mr[i].page_size_mask & (1<<PG_LEVEL_1G))) { unsigned long start = round_down(mr[i].start, PUD_SIZE); unsigned long end = round_up(mr[i].end, PUD_SIZE); if (memblock_is_region_memory(start, end - start)) mr[i].page_size_mask |= 1<<PG_LEVEL_1G; } } } static const char *page_size_string(struct map_range *mr) { static const char str_1g[] = "1G"; static const char str_2m[] = "2M"; static const char str_4m[] = "4M"; static const char str_4k[] = "4k"; if (mr->page_size_mask & (1<<PG_LEVEL_1G)) return str_1g; /* * 32-bit without PAE has a 4M large page size. * PG_LEVEL_2M is misnamed, but we can at least * print out the right size in the string. */ if (IS_ENABLED(CONFIG_X86_32) && !IS_ENABLED(CONFIG_X86_PAE) && mr->page_size_mask & (1<<PG_LEVEL_2M)) return str_4m; if (mr->page_size_mask & (1<<PG_LEVEL_2M)) return str_2m; return str_4k; } static int __meminit split_mem_range(struct map_range *mr, int nr_range, unsigned long start, unsigned long end) { unsigned long start_pfn, end_pfn, limit_pfn; unsigned long pfn; int i; limit_pfn = PFN_DOWN(end); /* head if not big page alignment ? */ pfn = start_pfn = PFN_DOWN(start); #ifdef CONFIG_X86_32 /* * Don't use a large page for the first 2/4MB of memory * because there are often fixed size MTRRs in there * and overlapping MTRRs into large pages can cause * slowdowns. */ if (pfn == 0) end_pfn = PFN_DOWN(PMD_SIZE); else end_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE)); #else /* CONFIG_X86_64 */ end_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE)); #endif if (end_pfn > limit_pfn) end_pfn = limit_pfn; if (start_pfn < end_pfn) { nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); pfn = end_pfn; } /* big page (2M) range */ start_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE)); #ifdef CONFIG_X86_32 end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE)); #else /* CONFIG_X86_64 */ end_pfn = round_up(pfn, PFN_DOWN(PUD_SIZE)); if (end_pfn > round_down(limit_pfn, PFN_DOWN(PMD_SIZE))) end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE)); #endif if (start_pfn < end_pfn) { nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, page_size_mask & (1<<PG_LEVEL_2M)); pfn = end_pfn; } #ifdef CONFIG_X86_64 /* big page (1G) range */ start_pfn = round_up(pfn, PFN_DOWN(PUD_SIZE)); end_pfn = round_down(limit_pfn, PFN_DOWN(PUD_SIZE)); if (start_pfn < end_pfn) { nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, page_size_mask & ((1<<PG_LEVEL_2M)|(1<<PG_LEVEL_1G))); pfn = end_pfn; } /* tail is not big page (1G) alignment */ start_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE)); end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE)); if (start_pfn < end_pfn) { nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, page_size_mask & (1<<PG_LEVEL_2M)); pfn = end_pfn; } #endif /* tail is not big page (2M) alignment */ start_pfn = pfn; end_pfn = limit_pfn; nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); if (!after_bootmem) adjust_range_page_size_mask(mr, nr_range); /* try to merge same page size and continuous */ for (i = 0; nr_range > 1 && i < nr_range - 1; i++) { unsigned long old_start; if (mr[i].end != mr[i+1].start || mr[i].page_size_mask != mr[i+1].page_size_mask) continue; /* move it */ old_start = mr[i].start; memmove(&mr[i], &mr[i+1], (nr_range - 1 - i) * sizeof(struct map_range)); mr[i--].start = old_start; nr_range--; } for (i = 0; i < nr_range; i++) pr_debug(" [mem %#010lx-%#010lx] page %s\n", mr[i].start, mr[i].end - 1, page_size_string(&mr[i])); return nr_range; } struct range pfn_mapped[E820_MAX_ENTRIES]; int nr_pfn_mapped; static void add_pfn_range_mapped(unsigned long start_pfn, unsigned long end_pfn) { nr_pfn_mapped = add_range_with_merge(pfn_mapped, E820_MAX_ENTRIES, nr_pfn_mapped, start_pfn, end_pfn); nr_pfn_mapped = clean_sort_range(pfn_mapped, E820_MAX_ENTRIES); max_pfn_mapped = max(max_pfn_mapped, end_pfn); if (start_pfn < (1UL<<(32-PAGE_SHIFT))) max_low_pfn_mapped = max(max_low_pfn_mapped, min(end_pfn, 1UL<<(32-PAGE_SHIFT))); } bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn) { int i; for (i = 0; i < nr_pfn_mapped; i++) if ((start_pfn >= pfn_mapped[i].start) && (end_pfn <= pfn_mapped[i].end)) return true; return false; } /* * Setup the direct mapping of the physical memory at PAGE_OFFSET. * This runs before bootmem is initialized and gets pages directly from * the physical memory. To access them they are temporarily mapped. */ unsigned long __ref init_memory_mapping(unsigned long start, unsigned long end, pgprot_t prot) { struct map_range mr[NR_RANGE_MR]; unsigned long ret = 0; int nr_range, i; pr_debug("init_memory_mapping: [mem %#010lx-%#010lx]\n", start, end - 1); memset(mr, 0, sizeof(mr)); nr_range = split_mem_range(mr, 0, start, end); for (i = 0; i < nr_range; i++) ret = kernel_physical_mapping_init(mr[i].start, mr[i].end, mr[i].page_size_mask, prot); add_pfn_range_mapped(start >> PAGE_SHIFT, ret >> PAGE_SHIFT); return ret >> PAGE_SHIFT; } /* * We need to iterate through the E820 memory map and create direct mappings * for only E820_TYPE_RAM and E820_KERN_RESERVED regions. We cannot simply * create direct mappings for all pfns from [0 to max_low_pfn) and * [4GB to max_pfn) because of possible memory holes in high addresses * that cannot be marked as UC by fixed/variable range MTRRs. * Depending on the alignment of E820 ranges, this may possibly result * in using smaller size (i.e. 4K instead of 2M or 1G) page tables. * * init_mem_mapping() calls init_range_memory_mapping() with big range. * That range would have hole in the middle or ends, and only ram parts * will be mapped in init_range_memory_mapping(). */ static unsigned long __init init_range_memory_mapping( unsigned long r_start, unsigned long r_end) { unsigned long start_pfn, end_pfn; unsigned long mapped_ram_size = 0; int i; for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) { u64 start = clamp_val(PFN_PHYS(start_pfn), r_start, r_end); u64 end = clamp_val(PFN_PHYS(end_pfn), r_start, r_end); if (start >= end) continue; /* * if it is overlapping with brk pgt, we need to * alloc pgt buf from memblock instead. */ can_use_brk_pgt = max(start, (u64)pgt_buf_end<<PAGE_SHIFT) >= min(end, (u64)pgt_buf_top<<PAGE_SHIFT); init_memory_mapping(start, end, PAGE_KERNEL); mapped_ram_size += end - start; can_use_brk_pgt = true; } return mapped_ram_size; } static unsigned long __init get_new_step_size(unsigned long step_size) { /* * Initial mapped size is PMD_SIZE (2M). * We can not set step_size to be PUD_SIZE (1G) yet. * In worse case, when we cross the 1G boundary, and * PG_LEVEL_2M is not set, we will need 1+1+512 pages (2M + 8k) * to map 1G range with PTE. Hence we use one less than the * difference of page table level shifts. * * Don't need to worry about overflow in the top-down case, on 32bit, * when step_size is 0, round_down() returns 0 for start, and that * turns it into 0x100000000ULL. * In the bottom-up case, round_up(x, 0) returns 0 though too, which * needs to be taken into consideration by the code below. */ return step_size << (PMD_SHIFT - PAGE_SHIFT - 1); } /** * memory_map_top_down - Map [map_start, map_end) top down * @map_start: start address of the target memory range * @map_end: end address of the target memory range * * This function will setup direct mapping for memory range * [map_start, map_end) in top-down. That said, the page tables * will be allocated at the end of the memory, and we map the * memory in top-down. */ static void __init memory_map_top_down(unsigned long map_start, unsigned long map_end) { unsigned long real_end, last_start; unsigned long step_size; unsigned long addr; unsigned long mapped_ram_size = 0; /* * Systems that have many reserved areas near top of the memory, * e.g. QEMU with less than 1G RAM and EFI enabled, or Xen, will * require lots of 4K mappings which may exhaust pgt_buf. * Start with top-most PMD_SIZE range aligned at PMD_SIZE to ensure * there is enough mapped memory that can be allocated from * memblock. */ addr = memblock_phys_alloc_range(PMD_SIZE, PMD_SIZE, map_start, map_end); memblock_phys_free(addr, PMD_SIZE); real_end = addr + PMD_SIZE; /* step_size need to be small so pgt_buf from BRK could cover it */ step_size = PMD_SIZE; max_pfn_mapped = 0; /* will get exact value next */ min_pfn_mapped = real_end >> PAGE_SHIFT; last_start = real_end; /* * We start from the top (end of memory) and go to the bottom. * The memblock_find_in_range() gets us a block of RAM from the * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages * for page table. */ while (last_start > map_start) { unsigned long start; if (last_start > step_size) { start = round_down(last_start - 1, step_size); if (start < map_start) start = map_start; } else start = map_start; mapped_ram_size += init_range_memory_mapping(start, last_start); last_start = start; min_pfn_mapped = last_start >> PAGE_SHIFT; if (mapped_ram_size >= step_size) step_size = get_new_step_size(step_size); } if (real_end < map_end) init_range_memory_mapping(real_end, map_end); } /** * memory_map_bottom_up - Map [map_start, map_end) bottom up * @map_start: start address of the target memory range * @map_end: end address of the target memory range * * This function will setup direct mapping for memory range * [map_start, map_end) in bottom-up. Since we have limited the * bottom-up allocation above the kernel, the page tables will * be allocated just above the kernel and we map the memory * in [map_start, map_end) in bottom-up. */ static void __init memory_map_bottom_up(unsigned long map_start, unsigned long map_end) { unsigned long next, start; unsigned long mapped_ram_size = 0; /* step_size need to be small so pgt_buf from BRK could cover it */ unsigned long step_size = PMD_SIZE; start = map_start; min_pfn_mapped = start >> PAGE_SHIFT; /* * We start from the bottom (@map_start) and go to the top (@map_end). * The memblock_find_in_range() gets us a block of RAM from the * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages * for page table. */ while (start < map_end) { if (step_size && map_end - start > step_size) { next = round_up(start + 1, step_size); if (next > map_end) next = map_end; } else { next = map_end; } mapped_ram_size += init_range_memory_mapping(start, next); start = next; if (mapped_ram_size >= step_size) step_size = get_new_step_size(step_size); } } /* * The real mode trampoline, which is required for bootstrapping CPUs * occupies only a small area under the low 1MB. See reserve_real_mode() * for details. * * If KASLR is disabled the first PGD entry of the direct mapping is copied * to map the real mode trampoline. * * If KASLR is enabled, copy only the PUD which covers the low 1MB * area. This limits the randomization granularity to 1GB for both 4-level * and 5-level paging. */ static void __init init_trampoline(void) { #ifdef CONFIG_X86_64 /* * The code below will alias kernel page-tables in the user-range of the * address space, including the Global bit. So global TLB entries will * be created when using the trampoline page-table. */ if (!kaslr_memory_enabled()) trampoline_pgd_entry = init_top_pgt[pgd_index(__PAGE_OFFSET)]; else init_trampoline_kaslr(); #endif } void __init init_mem_mapping(void) { unsigned long end; pti_check_boottime_disable(); probe_page_size_mask(); setup_pcid(); #ifdef CONFIG_X86_64 end = max_pfn << PAGE_SHIFT; #else end = max_low_pfn << PAGE_SHIFT; #endif /* the ISA range is always mapped regardless of memory holes */ init_memory_mapping(0, ISA_END_ADDRESS, PAGE_KERNEL); /* Init the trampoline, possibly with KASLR memory offset */ init_trampoline(); /* * If the allocation is in bottom-up direction, we setup direct mapping * in bottom-up, otherwise we setup direct mapping in top-down. */ if (memblock_bottom_up()) { unsigned long kernel_end = __pa_symbol(_end); /* * we need two separate calls here. This is because we want to * allocate page tables above the kernel. So we first map * [kernel_end, end) to make memory above the kernel be mapped * as soon as possible. And then use page tables allocated above * the kernel to map [ISA_END_ADDRESS, kernel_end). */ memory_map_bottom_up(kernel_end, end); memory_map_bottom_up(ISA_END_ADDRESS, kernel_end); } else { memory_map_top_down(ISA_END_ADDRESS, end); } #ifdef CONFIG_X86_64 if (max_pfn > max_low_pfn) { /* can we preserve max_low_pfn ?*/ max_low_pfn = max_pfn; } #else early_ioremap_page_table_range_init(); #endif load_cr3(swapper_pg_dir); __flush_tlb_all(); x86_init.hyper.init_mem_mapping(); early_memtest(0, max_pfn_mapped << PAGE_SHIFT); } /* * Initialize an mm_struct to be used during poking and a pointer to be used * during patching. */ void __init poking_init(void) { spinlock_t *ptl; pte_t *ptep; poking_mm = mm_alloc(); BUG_ON(!poking_mm); /* Xen PV guests need the PGD to be pinned. */ paravirt_arch_dup_mmap(NULL, poking_mm); /* * Randomize the poking address, but make sure that the following page * will be mapped at the same PMD. We need 2 pages, so find space for 3, * and adjust the address if the PMD ends after the first one. */ poking_addr = TASK_UNMAPPED_BASE; if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) poking_addr += (kaslr_get_random_long("Poking") & PAGE_MASK) % (TASK_SIZE - TASK_UNMAPPED_BASE - 3 * PAGE_SIZE); if (((poking_addr + PAGE_SIZE) & ~PMD_MASK) == 0) poking_addr += PAGE_SIZE; /* * We need to trigger the allocation of the page-tables that will be * needed for poking now. Later, poking may be performed in an atomic * section, which might cause allocation to fail. */ ptep = get_locked_pte(poking_mm, poking_addr, &ptl); BUG_ON(!ptep); pte_unmap_unlock(ptep, ptl); } /* * devmem_is_allowed() checks to see if /dev/mem access to a certain address * is valid. The argument is a physical page number. * * On x86, access has to be given to the first megabyte of RAM because that * area traditionally contains BIOS code and data regions used by X, dosemu, * and similar apps. Since they map the entire memory range, the whole range * must be allowed (for mapping), but any areas that would otherwise be * disallowed are flagged as being "zero filled" instead of rejected. * Access has to be given to non-kernel-ram areas as well, these contain the * PCI mmio resources as well as potential bios/acpi data regions. */ int devmem_is_allowed(unsigned long pagenr) { if (region_intersects(PFN_PHYS(pagenr), PAGE_SIZE, IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE) != REGION_DISJOINT) { /* * For disallowed memory regions in the low 1MB range, * request that the page be shown as all zeros. */ if (pagenr < 256) return 2; return 0; } /* * This must follow RAM test, since System RAM is considered a * restricted resource under CONFIG_STRICT_DEVMEM. */ if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) { /* Low 1MB bypasses iomem restrictions. */ if (pagenr < 256) return 1; return 0; } return 1; } void free_init_pages(const char *what, unsigned long begin, unsigned long end) { unsigned long begin_aligned, end_aligned; /* Make sure boundaries are page aligned */ begin_aligned = PAGE_ALIGN(begin); end_aligned = end & PAGE_MASK; if (WARN_ON(begin_aligned != begin || end_aligned != end)) { begin = begin_aligned; end = end_aligned; } if (begin >= end) return; /* * If debugging page accesses then do not free this memory but * mark them not present - any buggy init-section access will * create a kernel page fault: */ if (debug_pagealloc_enabled()) { pr_info("debug: unmapping init [mem %#010lx-%#010lx]\n", begin, end - 1); /* * Inform kmemleak about the hole in the memory since the * corresponding pages will be unmapped. */ kmemleak_free_part((void *)begin, end - begin); set_memory_np(begin, (end - begin) >> PAGE_SHIFT); } else { /* * We just marked the kernel text read only above, now that * we are going to free part of that, we need to make that * writeable and non-executable first. */ set_memory_nx(begin, (end - begin) >> PAGE_SHIFT); set_memory_rw(begin, (end - begin) >> PAGE_SHIFT); free_reserved_area((void *)begin, (void *)end, POISON_FREE_INITMEM, what); } } /* * begin/end can be in the direct map or the "high kernel mapping" * used for the kernel image only. free_init_pages() will do the * right thing for either kind of address. */ void free_kernel_image_pages(const char *what, void *begin, void *end) { unsigned long begin_ul = (unsigned long)begin; unsigned long end_ul = (unsigned long)end; unsigned long len_pages = (end_ul - begin_ul) >> PAGE_SHIFT; free_init_pages(what, begin_ul, end_ul); /* * PTI maps some of the kernel into userspace. For performance, * this includes some kernel areas that do not contain secrets. * Those areas might be adjacent to the parts of the kernel image * being freed, which may contain secrets. Remove the "high kernel * image mapping" for these freed areas, ensuring they are not even * potentially vulnerable to Meltdown regardless of the specific * optimizations PTI is currently using. * * The "noalias" prevents unmapping the direct map alias which is * needed to access the freed pages. * * This is only valid for 64bit kernels. 32bit has only one mapping * which can't be treated in this way for obvious reasons. */ if (IS_ENABLED(CONFIG_X86_64) && cpu_feature_enabled(X86_FEATURE_PTI)) set_memory_np_noalias(begin_ul, len_pages); } void __ref free_initmem(void) { e820__reallocate_tables(); mem_encrypt_free_decrypted_mem(); free_kernel_image_pages("unused kernel image (initmem)", &__init_begin, &__init_end); } #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { /* * end could be not aligned, and We can not align that, * decompressor could be confused by aligned initrd_end * We already reserve the end partial page before in * - i386_start_kernel() * - x86_64_start_kernel() * - relocate_initrd() * So here We can do PAGE_ALIGN() safely to get partial page to be freed */ free_init_pages("initrd", start, PAGE_ALIGN(end)); } #endif /* * Calculate the precise size of the DMA zone (first 16 MB of RAM), * and pass it to the MM layer - to help it set zone watermarks more * accurately. * * Done on 64-bit systems only for the time being, although 32-bit systems * might benefit from this as well. */ void __init memblock_find_dma_reserve(void) { #ifdef CONFIG_X86_64 u64 nr_pages = 0, nr_free_pages = 0; unsigned long start_pfn, end_pfn; phys_addr_t start_addr, end_addr; int i; u64 u; /* * Iterate over all memory ranges (free and reserved ones alike), * to calculate the total number of pages in the first 16 MB of RAM: */ nr_pages = 0; for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) { start_pfn = min(start_pfn, MAX_DMA_PFN); end_pfn = min(end_pfn, MAX_DMA_PFN); nr_pages += end_pfn - start_pfn; } /* * Iterate over free memory ranges to calculate the number of free * pages in the DMA zone, while not counting potential partial * pages at the beginning or the end of the range: */ nr_free_pages = 0; for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start_addr, &end_addr, NULL) { start_pfn = min_t(unsigned long, PFN_UP(start_addr), MAX_DMA_PFN); end_pfn = min_t(unsigned long, PFN_DOWN(end_addr), MAX_DMA_PFN); if (start_pfn < end_pfn) nr_free_pages += end_pfn - start_pfn; } set_dma_reserve(nr_pages - nr_free_pages); #endif } void __init zone_sizes_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES]; memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); #ifdef CONFIG_ZONE_DMA max_zone_pfns[ZONE_DMA] = min(MAX_DMA_PFN, max_low_pfn); #endif #ifdef CONFIG_ZONE_DMA32 max_zone_pfns[ZONE_DMA32] = disable_dma32 ? 0 : min(MAX_DMA32_PFN, max_low_pfn); #endif max_zone_pfns[ZONE_NORMAL] = max_low_pfn; #ifdef CONFIG_HIGHMEM max_zone_pfns[ZONE_HIGHMEM] = max_pfn; #endif free_area_init(max_zone_pfns); } static int __init early_disable_dma32(char *buf) { if (!buf) return -EINVAL; if (!strcmp(buf, "on")) disable_dma32 = true; return 0; } early_param("disable_dma32", early_disable_dma32); __visible DEFINE_PER_CPU_ALIGNED(struct tlb_state, cpu_tlbstate) = { .loaded_mm = &init_mm, .next_asid = 1, .cr4 = ~0UL, /* fail hard if we screw up cr4 shadow initialization */ }; void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache) { /* entry 0 MUST be WB (hardwired to speed up translations) */ BUG_ON(!entry && cache != _PAGE_CACHE_MODE_WB); __cachemode2pte_tbl[cache] = __cm_idx2pte(entry); __pte2cachemode_tbl[entry] = cache; } #ifdef CONFIG_SWAP unsigned long arch_max_swapfile_size(void) { unsigned long pages; pages = generic_max_swapfile_size(); if (boot_cpu_has_bug(X86_BUG_L1TF) && l1tf_mitigation != L1TF_MITIGATION_OFF) { /* Limit the swap file size to MAX_PA/2 for L1TF workaround */ unsigned long long l1tf_limit = l1tf_pfn_limit(); /* * We encode swap offsets also with 3 bits below those for pfn * which makes the usable limit higher. */ #if CONFIG_PGTABLE_LEVELS > 2 l1tf_limit <<= PAGE_SHIFT - SWP_OFFSET_FIRST_BIT; #endif pages = min_t(unsigned long long, l1tf_limit, pages); } return pages; } #endif |
| 603 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM fib6 #if !defined(_TRACE_FIB6_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FIB6_H #include <linux/in6.h> #include <net/flow.h> #include <net/ip6_fib.h> #include <linux/tracepoint.h> TRACE_EVENT(fib6_table_lookup, TP_PROTO(const struct net *net, const struct fib6_result *res, struct fib6_table *table, const struct flowi6 *flp), TP_ARGS(net, res, table, flp), TP_STRUCT__entry( __field( u32, tb_id ) __field( int, err ) __field( int, oif ) __field( int, iif ) __field( __u8, tos ) __field( __u8, scope ) __field( __u8, flags ) __array( __u8, src, 16 ) __array( __u8, dst, 16 ) __field( u16, sport ) __field( u16, dport ) __field( u8, proto ) __field( u8, rt_type ) __array( char, name, IFNAMSIZ ) __array( __u8, gw, 16 ) ), TP_fast_assign( struct in6_addr *in6; __entry->tb_id = table->tb6_id; __entry->err = ip6_rt_type_to_error(res->fib6_type); __entry->oif = flp->flowi6_oif; __entry->iif = flp->flowi6_iif; __entry->tos = ip6_tclass(flp->flowlabel); __entry->scope = flp->flowi6_scope; __entry->flags = flp->flowi6_flags; in6 = (struct in6_addr *)__entry->src; *in6 = flp->saddr; in6 = (struct in6_addr *)__entry->dst; *in6 = flp->daddr; __entry->proto = flp->flowi6_proto; if (__entry->proto == IPPROTO_TCP || __entry->proto == IPPROTO_UDP) { __entry->sport = ntohs(flp->fl6_sport); __entry->dport = ntohs(flp->fl6_dport); } else { __entry->sport = 0; __entry->dport = 0; } if (res->nh && res->nh->fib_nh_dev) { strlcpy(__entry->name, res->nh->fib_nh_dev->name, IFNAMSIZ); } else { strcpy(__entry->name, "-"); } if (res->f6i == net->ipv6.fib6_null_entry) { in6 = (struct in6_addr *)__entry->gw; *in6 = in6addr_any; } else if (res->nh) { in6 = (struct in6_addr *)__entry->gw; *in6 = res->nh->fib_nh_gw6; } ), TP_printk("table %3u oif %d iif %d proto %u %pI6c/%u -> %pI6c/%u tos %d scope %d flags %x ==> dev %s gw %pI6c err %d", __entry->tb_id, __entry->oif, __entry->iif, __entry->proto, __entry->src, __entry->sport, __entry->dst, __entry->dport, __entry->tos, __entry->scope, __entry->flags, __entry->name, __entry->gw, __entry->err) ); #endif /* _TRACE_FIB6_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 4 14 14 1 14 14 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #ifndef _WG_QUEUEING_H #define _WG_QUEUEING_H #include "peer.h" #include <linux/types.h> #include <linux/skbuff.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <net/ip_tunnels.h> struct wg_device; struct wg_peer; struct multicore_worker; struct crypt_queue; struct prev_queue; struct sk_buff; /* queueing.c APIs: */ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function, unsigned int len); void wg_packet_queue_free(struct crypt_queue *queue, bool purge); struct multicore_worker __percpu * wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr); /* receive.c APIs: */ void wg_packet_receive(struct wg_device *wg, struct sk_buff *skb); void wg_packet_handshake_receive_worker(struct work_struct *work); /* NAPI poll function: */ int wg_packet_rx_poll(struct napi_struct *napi, int budget); /* Workqueue worker: */ void wg_packet_decrypt_worker(struct work_struct *work); /* send.c APIs: */ void wg_packet_send_queued_handshake_initiation(struct wg_peer *peer, bool is_retry); void wg_packet_send_handshake_response(struct wg_peer *peer); void wg_packet_send_handshake_cookie(struct wg_device *wg, struct sk_buff *initiating_skb, __le32 sender_index); void wg_packet_send_keepalive(struct wg_peer *peer); void wg_packet_purge_staged_packets(struct wg_peer *peer); void wg_packet_send_staged_packets(struct wg_peer *peer); /* Workqueue workers: */ void wg_packet_handshake_send_worker(struct work_struct *work); void wg_packet_tx_worker(struct work_struct *work); void wg_packet_encrypt_worker(struct work_struct *work); enum packet_state { PACKET_STATE_UNCRYPTED, PACKET_STATE_CRYPTED, PACKET_STATE_DEAD }; struct packet_cb { u64 nonce; struct noise_keypair *keypair; atomic_t state; u32 mtu; u8 ds; }; #define PACKET_CB(skb) ((struct packet_cb *)((skb)->cb)) #define PACKET_PEER(skb) (PACKET_CB(skb)->keypair->entry.peer) static inline bool wg_check_packet_protocol(struct sk_buff *skb) { __be16 real_protocol = ip_tunnel_parse_protocol(skb); return real_protocol && skb->protocol == real_protocol; } static inline void wg_reset_packet(struct sk_buff *skb, bool encapsulating) { u8 l4_hash = skb->l4_hash; u8 sw_hash = skb->sw_hash; u32 hash = skb->hash; skb_scrub_packet(skb, true); memset(&skb->headers, 0, sizeof(skb->headers)); if (encapsulating) { skb->l4_hash = l4_hash; skb->sw_hash = sw_hash; skb->hash = hash; } skb->queue_mapping = 0; skb->nohdr = 0; skb->peeked = 0; skb->mac_len = 0; skb->dev = NULL; #ifdef CONFIG_NET_SCHED skb->tc_index = 0; #endif skb_reset_redirect(skb); skb->hdr_len = skb_headroom(skb); skb_reset_mac_header(skb); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb_probe_transport_header(skb); skb_reset_inner_headers(skb); } static inline int wg_cpumask_choose_online(int *stored_cpu, unsigned int id) { unsigned int cpu = *stored_cpu, cpu_index, i; if (unlikely(cpu == nr_cpumask_bits || !cpumask_test_cpu(cpu, cpu_online_mask))) { cpu_index = id % cpumask_weight(cpu_online_mask); cpu = cpumask_first(cpu_online_mask); for (i = 0; i < cpu_index; ++i) cpu = cpumask_next(cpu, cpu_online_mask); *stored_cpu = cpu; } return cpu; } /* This function is racy, in the sense that it's called while last_cpu is * unlocked, so it could return the same CPU twice. Adding locking or using * atomic sequence numbers is slower though, and the consequences of racing are * harmless, so live with it. */ static inline int wg_cpumask_next_online(int *last_cpu) { int cpu = cpumask_next(READ_ONCE(*last_cpu), cpu_online_mask); if (cpu >= nr_cpu_ids) cpu = cpumask_first(cpu_online_mask); WRITE_ONCE(*last_cpu, cpu); return cpu; } void wg_prev_queue_init(struct prev_queue *queue); /* Multi producer */ bool wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb); /* Single consumer */ struct sk_buff *wg_prev_queue_dequeue(struct prev_queue *queue); /* Single consumer */ static inline struct sk_buff *wg_prev_queue_peek(struct prev_queue *queue) { if (queue->peeked) return queue->peeked; queue->peeked = wg_prev_queue_dequeue(queue); return queue->peeked; } /* Single consumer */ static inline void wg_prev_queue_drop_peeked(struct prev_queue *queue) { queue->peeked = NULL; } static inline int wg_queue_enqueue_per_device_and_peer( struct crypt_queue *device_queue, struct prev_queue *peer_queue, struct sk_buff *skb, struct workqueue_struct *wq) { int cpu; atomic_set_release(&PACKET_CB(skb)->state, PACKET_STATE_UNCRYPTED); /* We first queue this up for the peer ingestion, but the consumer * will wait for the state to change to CRYPTED or DEAD before. */ if (unlikely(!wg_prev_queue_enqueue(peer_queue, skb))) return -ENOSPC; /* Then we queue it up in the device queue, which consumes the * packet as soon as it can. */ cpu = wg_cpumask_next_online(&device_queue->last_cpu); if (unlikely(ptr_ring_produce_bh(&device_queue->ring, skb))) return -EPIPE; queue_work_on(cpu, wq, &per_cpu_ptr(device_queue->worker, cpu)->work); return 0; } static inline void wg_queue_enqueue_per_peer_tx(struct sk_buff *skb, enum packet_state state) { /* We take a reference, because as soon as we call atomic_set, the * peer can be freed from below us. */ struct wg_peer *peer = wg_peer_get(PACKET_PEER(skb)); atomic_set_release(&PACKET_CB(skb)->state, state); queue_work_on(wg_cpumask_choose_online(&peer->serial_work_cpu, peer->internal_id), peer->device->packet_crypt_wq, &peer->transmit_packet_work); wg_peer_put(peer); } static inline void wg_queue_enqueue_per_peer_rx(struct sk_buff *skb, enum packet_state state) { /* We take a reference, because as soon as we call atomic_set, the * peer can be freed from below us. */ struct wg_peer *peer = wg_peer_get(PACKET_PEER(skb)); atomic_set_release(&PACKET_CB(skb)->state, state); napi_schedule(&peer->napi); wg_peer_put(peer); } #ifdef DEBUG bool wg_packet_counter_selftest(void); #endif #endif /* _WG_QUEUEING_H */ |
| 640 640 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 | // SPDX-License-Identifier: GPL-2.0-or-later /* * SR-IPv6 implementation * * Author: * David Lebrun <david.lebrun@uclouvain.be> */ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/slab.h> #include <linux/rhashtable.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/seg6.h> #include <net/genetlink.h> #include <linux/seg6.h> #include <linux/seg6_genl.h> #ifdef CONFIG_IPV6_SEG6_HMAC #include <net/seg6_hmac.h> #endif bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len, bool reduced) { unsigned int tlv_offset; int max_last_entry; int trailing; if (srh->type != IPV6_SRCRT_TYPE_4) return false; if (((srh->hdrlen + 1) << 3) != len) return false; if (!reduced && srh->segments_left > srh->first_segment) { return false; } else { max_last_entry = (srh->hdrlen / 2) - 1; if (srh->first_segment > max_last_entry) return false; if (srh->segments_left > srh->first_segment + 1) return false; } tlv_offset = sizeof(*srh) + ((srh->first_segment + 1) << 4); trailing = len - tlv_offset; if (trailing < 0) return false; while (trailing) { struct sr6_tlv *tlv; unsigned int tlv_len; if (trailing < sizeof(*tlv)) return false; tlv = (struct sr6_tlv *)((unsigned char *)srh + tlv_offset); tlv_len = sizeof(*tlv) + tlv->len; trailing -= tlv_len; if (trailing < 0) return false; tlv_offset += tlv_len; } return true; } struct ipv6_sr_hdr *seg6_get_srh(struct sk_buff *skb, int flags) { struct ipv6_sr_hdr *srh; int len, srhoff = 0; if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, &flags) < 0) return NULL; if (!pskb_may_pull(skb, srhoff + sizeof(*srh))) return NULL; srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); len = (srh->hdrlen + 1) << 3; if (!pskb_may_pull(skb, srhoff + len)) return NULL; /* note that pskb_may_pull may change pointers in header; * for this reason it is necessary to reload them when needed. */ srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); if (!seg6_validate_srh(srh, len, true)) return NULL; return srh; } /* Determine if an ICMP invoking packet contains a segment routing * header. If it does, extract the offset to the true destination * address, which is in the first segment address. */ void seg6_icmp_srh(struct sk_buff *skb, struct inet6_skb_parm *opt) { __u16 network_header = skb->network_header; struct ipv6_sr_hdr *srh; /* Update network header to point to the invoking packet * inside the ICMP packet, so we can use the seg6_get_srh() * helper. */ skb_reset_network_header(skb); srh = seg6_get_srh(skb, 0); if (!srh) goto out; if (srh->type != IPV6_SRCRT_TYPE_4) goto out; opt->flags |= IP6SKB_SEG6; opt->srhoff = (unsigned char *)srh - skb->data; out: /* Restore the network header back to the ICMP packet */ skb->network_header = network_header; } static struct genl_family seg6_genl_family; static const struct nla_policy seg6_genl_policy[SEG6_ATTR_MAX + 1] = { [SEG6_ATTR_DST] = { .type = NLA_BINARY, .len = sizeof(struct in6_addr) }, [SEG6_ATTR_DSTLEN] = { .type = NLA_S32, }, [SEG6_ATTR_HMACKEYID] = { .type = NLA_U32, }, [SEG6_ATTR_SECRET] = { .type = NLA_BINARY, }, [SEG6_ATTR_SECRETLEN] = { .type = NLA_U8, }, [SEG6_ATTR_ALGID] = { .type = NLA_U8, }, [SEG6_ATTR_HMACINFO] = { .type = NLA_NESTED, }, }; #ifdef CONFIG_IPV6_SEG6_HMAC static int seg6_genl_sethmac(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct seg6_pernet_data *sdata; struct seg6_hmac_info *hinfo; u32 hmackeyid; char *secret; int err = 0; u8 algid; u8 slen; sdata = seg6_pernet(net); if (!info->attrs[SEG6_ATTR_HMACKEYID] || !info->attrs[SEG6_ATTR_SECRETLEN] || !info->attrs[SEG6_ATTR_ALGID]) return -EINVAL; hmackeyid = nla_get_u32(info->attrs[SEG6_ATTR_HMACKEYID]); slen = nla_get_u8(info->attrs[SEG6_ATTR_SECRETLEN]); algid = nla_get_u8(info->attrs[SEG6_ATTR_ALGID]); if (hmackeyid == 0) return -EINVAL; if (slen > SEG6_HMAC_SECRET_LEN) return -EINVAL; mutex_lock(&sdata->lock); hinfo = seg6_hmac_info_lookup(net, hmackeyid); if (!slen) { err = seg6_hmac_info_del(net, hmackeyid); goto out_unlock; } if (!info->attrs[SEG6_ATTR_SECRET]) { err = -EINVAL; goto out_unlock; } if (slen > nla_len(info->attrs[SEG6_ATTR_SECRET])) { err = -EINVAL; goto out_unlock; } if (hinfo) { err = seg6_hmac_info_del(net, hmackeyid); if (err) goto out_unlock; } secret = (char *)nla_data(info->attrs[SEG6_ATTR_SECRET]); hinfo = kzalloc(sizeof(*hinfo), GFP_KERNEL); if (!hinfo) { err = -ENOMEM; goto out_unlock; } memcpy(hinfo->secret, secret, slen); hinfo->slen = slen; hinfo->alg_id = algid; hinfo->hmackeyid = hmackeyid; err = seg6_hmac_info_add(net, hmackeyid, hinfo); if (err) kfree(hinfo); out_unlock: mutex_unlock(&sdata->lock); return err; } #else static int seg6_genl_sethmac(struct sk_buff *skb, struct genl_info *info) { return -ENOTSUPP; } #endif static int seg6_genl_set_tunsrc(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct in6_addr *val, *t_old, *t_new; struct seg6_pernet_data *sdata; sdata = seg6_pernet(net); if (!info->attrs[SEG6_ATTR_DST]) return -EINVAL; val = nla_data(info->attrs[SEG6_ATTR_DST]); t_new = kmemdup(val, sizeof(*val), GFP_KERNEL); if (!t_new) return -ENOMEM; mutex_lock(&sdata->lock); t_old = sdata->tun_src; rcu_assign_pointer(sdata->tun_src, t_new); mutex_unlock(&sdata->lock); synchronize_net(); kfree(t_old); return 0; } static int seg6_genl_get_tunsrc(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct in6_addr *tun_src; struct sk_buff *msg; void *hdr; msg = genlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &seg6_genl_family, 0, SEG6_CMD_GET_TUNSRC); if (!hdr) goto free_msg; rcu_read_lock(); tun_src = rcu_dereference(seg6_pernet(net)->tun_src); if (nla_put(msg, SEG6_ATTR_DST, sizeof(struct in6_addr), tun_src)) goto nla_put_failure; rcu_read_unlock(); genlmsg_end(msg, hdr); return genlmsg_reply(msg, info); nla_put_failure: rcu_read_unlock(); free_msg: nlmsg_free(msg); return -ENOMEM; } #ifdef CONFIG_IPV6_SEG6_HMAC static int __seg6_hmac_fill_info(struct seg6_hmac_info *hinfo, struct sk_buff *msg) { if (nla_put_u32(msg, SEG6_ATTR_HMACKEYID, hinfo->hmackeyid) || nla_put_u8(msg, SEG6_ATTR_SECRETLEN, hinfo->slen) || nla_put(msg, SEG6_ATTR_SECRET, hinfo->slen, hinfo->secret) || nla_put_u8(msg, SEG6_ATTR_ALGID, hinfo->alg_id)) return -1; return 0; } static int __seg6_genl_dumphmac_element(struct seg6_hmac_info *hinfo, u32 portid, u32 seq, u32 flags, struct sk_buff *skb, u8 cmd) { void *hdr; hdr = genlmsg_put(skb, portid, seq, &seg6_genl_family, flags, cmd); if (!hdr) return -ENOMEM; if (__seg6_hmac_fill_info(hinfo, skb) < 0) goto nla_put_failure; genlmsg_end(skb, hdr); return 0; nla_put_failure: genlmsg_cancel(skb, hdr); return -EMSGSIZE; } static int seg6_genl_dumphmac_start(struct netlink_callback *cb) { struct net *net = sock_net(cb->skb->sk); struct seg6_pernet_data *sdata; struct rhashtable_iter *iter; sdata = seg6_pernet(net); iter = (struct rhashtable_iter *)cb->args[0]; if (!iter) { iter = kmalloc(sizeof(*iter), GFP_KERNEL); if (!iter) return -ENOMEM; cb->args[0] = (long)iter; } rhashtable_walk_enter(&sdata->hmac_infos, iter); return 0; } static int seg6_genl_dumphmac_done(struct netlink_callback *cb) { struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0]; rhashtable_walk_exit(iter); kfree(iter); return 0; } static int seg6_genl_dumphmac(struct sk_buff *skb, struct netlink_callback *cb) { struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0]; struct seg6_hmac_info *hinfo; int ret; rhashtable_walk_start(iter); for (;;) { hinfo = rhashtable_walk_next(iter); if (IS_ERR(hinfo)) { if (PTR_ERR(hinfo) == -EAGAIN) continue; ret = PTR_ERR(hinfo); goto done; } else if (!hinfo) { break; } ret = __seg6_genl_dumphmac_element(hinfo, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, skb, SEG6_CMD_DUMPHMAC); if (ret) goto done; } ret = skb->len; done: rhashtable_walk_stop(iter); return ret; } #else static int seg6_genl_dumphmac_start(struct netlink_callback *cb) { return 0; } static int seg6_genl_dumphmac_done(struct netlink_callback *cb) { return 0; } static int seg6_genl_dumphmac(struct sk_buff *skb, struct netlink_callback *cb) { return -ENOTSUPP; } #endif static int __net_init seg6_net_init(struct net *net) { struct seg6_pernet_data *sdata; sdata = kzalloc(sizeof(*sdata), GFP_KERNEL); if (!sdata) return -ENOMEM; mutex_init(&sdata->lock); sdata->tun_src = kzalloc(sizeof(*sdata->tun_src), GFP_KERNEL); if (!sdata->tun_src) { kfree(sdata); return -ENOMEM; } net->ipv6.seg6_data = sdata; #ifdef CONFIG_IPV6_SEG6_HMAC if (seg6_hmac_net_init(net)) { kfree(rcu_dereference_raw(sdata->tun_src)); kfree(sdata); return -ENOMEM; } #endif return 0; } static void __net_exit seg6_net_exit(struct net *net) { struct seg6_pernet_data *sdata = seg6_pernet(net); #ifdef CONFIG_IPV6_SEG6_HMAC seg6_hmac_net_exit(net); #endif kfree(rcu_dereference_raw(sdata->tun_src)); kfree(sdata); } static struct pernet_operations ip6_segments_ops = { .init = seg6_net_init, .exit = seg6_net_exit, }; static const struct genl_ops seg6_genl_ops[] = { { .cmd = SEG6_CMD_SETHMAC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = seg6_genl_sethmac, .flags = GENL_ADMIN_PERM, }, { .cmd = SEG6_CMD_DUMPHMAC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .start = seg6_genl_dumphmac_start, .dumpit = seg6_genl_dumphmac, .done = seg6_genl_dumphmac_done, .flags = GENL_ADMIN_PERM, }, { .cmd = SEG6_CMD_SET_TUNSRC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = seg6_genl_set_tunsrc, .flags = GENL_ADMIN_PERM, }, { .cmd = SEG6_CMD_GET_TUNSRC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = seg6_genl_get_tunsrc, .flags = GENL_ADMIN_PERM, }, }; static struct genl_family seg6_genl_family __ro_after_init = { .hdrsize = 0, .name = SEG6_GENL_NAME, .version = SEG6_GENL_VERSION, .maxattr = SEG6_ATTR_MAX, .policy = seg6_genl_policy, .netnsok = true, .parallel_ops = true, .ops = seg6_genl_ops, .n_ops = ARRAY_SIZE(seg6_genl_ops), .resv_start_op = SEG6_CMD_GET_TUNSRC + 1, .module = THIS_MODULE, }; int __init seg6_init(void) { int err; err = register_pernet_subsys(&ip6_segments_ops); if (err) goto out; err = genl_register_family(&seg6_genl_family); if (err) goto out_unregister_pernet; #ifdef CONFIG_IPV6_SEG6_LWTUNNEL err = seg6_iptunnel_init(); if (err) goto out_unregister_genl; err = seg6_local_init(); if (err) { seg6_iptunnel_exit(); goto out_unregister_genl; } #endif #ifdef CONFIG_IPV6_SEG6_HMAC err = seg6_hmac_init(); if (err) goto out_unregister_iptun; #endif pr_info("Segment Routing with IPv6\n"); out: return err; #ifdef CONFIG_IPV6_SEG6_HMAC out_unregister_iptun: #ifdef CONFIG_IPV6_SEG6_LWTUNNEL seg6_local_exit(); seg6_iptunnel_exit(); #endif #endif #ifdef CONFIG_IPV6_SEG6_LWTUNNEL out_unregister_genl: #endif #if IS_ENABLED(CONFIG_IPV6_SEG6_LWTUNNEL) || IS_ENABLED(CONFIG_IPV6_SEG6_HMAC) genl_unregister_family(&seg6_genl_family); #endif out_unregister_pernet: unregister_pernet_subsys(&ip6_segments_ops); goto out; } void seg6_exit(void) { #ifdef CONFIG_IPV6_SEG6_HMAC seg6_hmac_exit(); #endif #ifdef CONFIG_IPV6_SEG6_LWTUNNEL seg6_local_exit(); seg6_iptunnel_exit(); #endif genl_unregister_family(&seg6_genl_family); unregister_pernet_subsys(&ip6_segments_ops); } |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* Generic support for BUG() This respects the following config options: CONFIG_BUG - emit BUG traps. Nothing happens without this. CONFIG_GENERIC_BUG - enable this code. CONFIG_GENERIC_BUG_RELATIVE_POINTERS - use 32-bit relative pointers for bug_addr and file CONFIG_DEBUG_BUGVERBOSE - emit full file+line information for each BUG CONFIG_BUG and CONFIG_DEBUG_BUGVERBOSE are potentially user-settable (though they're generally always on). CONFIG_GENERIC_BUG is set by each architecture using this code. To use this, your architecture must: 1. Set up the config options: - Enable CONFIG_GENERIC_BUG if CONFIG_BUG 2. Implement BUG (and optionally BUG_ON, WARN, WARN_ON) - Define HAVE_ARCH_BUG - Implement BUG() to generate a faulting instruction - NOTE: struct bug_entry does not have "file" or "line" entries when CONFIG_DEBUG_BUGVERBOSE is not enabled, so you must generate the values accordingly. 3. Implement the trap - In the illegal instruction trap handler (typically), verify that the fault was in kernel mode, and call report_bug() - report_bug() will return whether it was a false alarm, a warning, or an actual bug. - You must implement the is_valid_bugaddr(bugaddr) callback which returns true if the eip is a real kernel address, and it points to the expected BUG trap instruction. Jeremy Fitzhardinge <jeremy@goop.org> 2006 */ #define pr_fmt(fmt) fmt #include <linux/list.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/bug.h> #include <linux/sched.h> #include <linux/rculist.h> #include <linux/ftrace.h> #include <linux/context_tracking.h> #include <trace/hooks/bug.h> extern struct bug_entry __start___bug_table[], __stop___bug_table[]; static inline unsigned long bug_addr(const struct bug_entry *bug) { #ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS return (unsigned long)&bug->bug_addr_disp + bug->bug_addr_disp; #else return bug->bug_addr; #endif } #ifdef CONFIG_MODULES /* Updates are protected by module mutex */ static LIST_HEAD(module_bug_list); static struct bug_entry *module_find_bug(unsigned long bugaddr) { struct module *mod; struct bug_entry *bug = NULL; rcu_read_lock_sched(); list_for_each_entry_rcu(mod, &module_bug_list, bug_list) { unsigned i; bug = mod->bug_table; for (i = 0; i < mod->num_bugs; ++i, ++bug) if (bugaddr == bug_addr(bug)) goto out; } bug = NULL; out: rcu_read_unlock_sched(); return bug; } void module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod) { char *secstrings; unsigned int i; mod->bug_table = NULL; mod->num_bugs = 0; /* Find the __bug_table section, if present */ secstrings = (char *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; for (i = 1; i < hdr->e_shnum; i++) { if (strcmp(secstrings+sechdrs[i].sh_name, "__bug_table")) continue; mod->bug_table = (void *) sechdrs[i].sh_addr; mod->num_bugs = sechdrs[i].sh_size / sizeof(struct bug_entry); break; } /* * Strictly speaking this should have a spinlock to protect against * traversals, but since we only traverse on BUG()s, a spinlock * could potentially lead to deadlock and thus be counter-productive. * Thus, this uses RCU to safely manipulate the bug list, since BUG * must run in non-interruptive state. */ list_add_rcu(&mod->bug_list, &module_bug_list); } void module_bug_cleanup(struct module *mod) { list_del_rcu(&mod->bug_list); } #else static inline struct bug_entry *module_find_bug(unsigned long bugaddr) { return NULL; } #endif void bug_get_file_line(struct bug_entry *bug, const char **file, unsigned int *line) { #ifdef CONFIG_DEBUG_BUGVERBOSE #ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS *file = (const char *)&bug->file_disp + bug->file_disp; #else *file = bug->file; #endif *line = bug->line; #else *file = NULL; *line = 0; #endif } struct bug_entry *find_bug(unsigned long bugaddr) { struct bug_entry *bug; for (bug = __start___bug_table; bug < __stop___bug_table; ++bug) if (bugaddr == bug_addr(bug)) return bug; return module_find_bug(bugaddr); } static enum bug_trap_type __report_bug(unsigned long bugaddr, struct pt_regs *regs) { struct bug_entry *bug; const char *file; unsigned line, warning, once, done; if (!is_valid_bugaddr(bugaddr)) return BUG_TRAP_TYPE_NONE; bug = find_bug(bugaddr); if (!bug) return BUG_TRAP_TYPE_NONE; disable_trace_on_warning(); bug_get_file_line(bug, &file, &line); warning = (bug->flags & BUGFLAG_WARNING) != 0; once = (bug->flags & BUGFLAG_ONCE) != 0; done = (bug->flags & BUGFLAG_DONE) != 0; if (warning && once) { if (done) return BUG_TRAP_TYPE_WARN; /* * Since this is the only store, concurrency is not an issue. */ bug->flags |= BUGFLAG_DONE; } /* * BUG() and WARN_ON() families don't print a custom debug message * before triggering the exception handler, so we must add the * "cut here" line now. WARN() issues its own "cut here" before the * extra debugging message it writes before triggering the handler. */ if ((bug->flags & BUGFLAG_NO_CUT_HERE) == 0) printk(KERN_DEFAULT CUT_HERE); if (warning) { /* this is a WARN_ON rather than BUG/BUG_ON */ __warn(file, line, (void *)bugaddr, BUG_GET_TAINT(bug), regs, NULL); return BUG_TRAP_TYPE_WARN; } if (file) pr_crit("kernel BUG at %s:%u!\n", file, line); else pr_crit("Kernel BUG at %pB [verbose debug info unavailable]\n", (void *)bugaddr); trace_android_rvh_report_bug(file, line, bugaddr); return BUG_TRAP_TYPE_BUG; } enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs) { enum bug_trap_type ret; bool rcu = false; rcu = warn_rcu_enter(); ret = __report_bug(bugaddr, regs); warn_rcu_exit(rcu); return ret; } static void clear_once_table(struct bug_entry *start, struct bug_entry *end) { struct bug_entry *bug; for (bug = start; bug < end; bug++) bug->flags &= ~BUGFLAG_DONE; } void generic_bug_clear_once(void) { #ifdef CONFIG_MODULES struct module *mod; rcu_read_lock_sched(); list_for_each_entry_rcu(mod, &module_bug_list, bug_list) clear_once_table(mod->bug_table, mod->bug_table + mod->num_bugs); rcu_read_unlock_sched(); #endif clear_once_table(__start___bug_table, __stop___bug_table); } |
| 191 89 89 89 791 608 191 191 191 95 95 95 95 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 | // SPDX-License-Identifier: GPL-2.0 #include "cgroup-internal.h" #include <linux/sched/task.h> #include <linux/slab.h> #include <linux/nsproxy.h> #include <linux/proc_ns.h> /* cgroup namespaces */ static struct ucounts *inc_cgroup_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_CGROUP_NAMESPACES); } static void dec_cgroup_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_CGROUP_NAMESPACES); } static struct cgroup_namespace *alloc_cgroup_ns(void) { struct cgroup_namespace *new_ns; int ret; new_ns = kzalloc(sizeof(struct cgroup_namespace), GFP_KERNEL_ACCOUNT); if (!new_ns) return ERR_PTR(-ENOMEM); ret = ns_alloc_inum(&new_ns->ns); if (ret) { kfree(new_ns); return ERR_PTR(ret); } refcount_set(&new_ns->ns.count, 1); new_ns->ns.ops = &cgroupns_operations; return new_ns; } void free_cgroup_ns(struct cgroup_namespace *ns) { put_css_set(ns->root_cset); dec_cgroup_namespaces(ns->ucounts); put_user_ns(ns->user_ns); ns_free_inum(&ns->ns); kfree(ns); } EXPORT_SYMBOL(free_cgroup_ns); struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns, struct cgroup_namespace *old_ns) { struct cgroup_namespace *new_ns; struct ucounts *ucounts; struct css_set *cset; BUG_ON(!old_ns); if (!(flags & CLONE_NEWCGROUP)) { get_cgroup_ns(old_ns); return old_ns; } /* Allow only sysadmin to create cgroup namespace. */ if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); ucounts = inc_cgroup_namespaces(user_ns); if (!ucounts) return ERR_PTR(-ENOSPC); /* It is not safe to take cgroup_mutex here */ spin_lock_irq(&css_set_lock); cset = task_css_set(current); get_css_set(cset); spin_unlock_irq(&css_set_lock); new_ns = alloc_cgroup_ns(); if (IS_ERR(new_ns)) { put_css_set(cset); dec_cgroup_namespaces(ucounts); return new_ns; } new_ns->user_ns = get_user_ns(user_ns); new_ns->ucounts = ucounts; new_ns->root_cset = cset; return new_ns; } static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns) { return container_of(ns, struct cgroup_namespace, ns); } static int cgroupns_install(struct nsset *nsset, struct ns_common *ns) { struct nsproxy *nsproxy = nsset->nsproxy; struct cgroup_namespace *cgroup_ns = to_cg_ns(ns); if (!ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN) || !ns_capable(cgroup_ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; /* Don't need to do anything if we are attaching to our own cgroupns. */ if (cgroup_ns == nsproxy->cgroup_ns) return 0; get_cgroup_ns(cgroup_ns); put_cgroup_ns(nsproxy->cgroup_ns); nsproxy->cgroup_ns = cgroup_ns; return 0; } static struct ns_common *cgroupns_get(struct task_struct *task) { struct cgroup_namespace *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) { ns = nsproxy->cgroup_ns; get_cgroup_ns(ns); } task_unlock(task); return ns ? &ns->ns : NULL; } static void cgroupns_put(struct ns_common *ns) { put_cgroup_ns(to_cg_ns(ns)); } static struct user_namespace *cgroupns_owner(struct ns_common *ns) { return to_cg_ns(ns)->user_ns; } const struct proc_ns_operations cgroupns_operations = { .name = "cgroup", .type = CLONE_NEWCGROUP, .get = cgroupns_get, .put = cgroupns_put, .install = cgroupns_install, .owner = cgroupns_owner, }; |
| 1416 903 781 684 1327 1775 151 1354 497 387 1324 340 1327 1328 1355 516 1324 2586 2585 2586 498 10 362 361 341 785 396 2172 69 75 4 4 4 3 2 4 2 99 74 69 69 90 78 785 6 396 340 411 359 359 359 10 359 345 340 359 960 786 786 412 529 960 343 343 359 362 362 175 508 470 99 997 102 998 999 770 575 575 960 102 998 999 537 99 99 99 575 897 375 897 374 784 78 3 781 684 3 102 102 102 102 163 4 163 150 151 151 78 99 69 99 92 2236 1837 577 1839 1838 1839 1839 1661 1661 1839 79 1839 380 378 221 354 354 204 354 10 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0+ /* * XArray implementation * Copyright (c) 2017-2018 Microsoft Corporation * Copyright (c) 2018-2020 Oracle * Author: Matthew Wilcox <willy@infradead.org> */ #include <linux/bitmap.h> #include <linux/export.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/xarray.h> /* * Coding conventions in this file: * * @xa is used to refer to the entire xarray. * @xas is the 'xarray operation state'. It may be either a pointer to * an xa_state, or an xa_state stored on the stack. This is an unfortunate * ambiguity. * @index is the index of the entry being operated on * @mark is an xa_mark_t; a small number indicating one of the mark bits. * @node refers to an xa_node; usually the primary one being operated on by * this function. * @offset is the index into the slots array inside an xa_node. * @parent refers to the @xa_node closer to the head than @node. * @entry refers to something stored in a slot in the xarray */ static inline unsigned int xa_lock_type(const struct xarray *xa) { return (__force unsigned int)xa->xa_flags & 3; } static inline void xas_lock_type(struct xa_state *xas, unsigned int lock_type) { if (lock_type == XA_LOCK_IRQ) xas_lock_irq(xas); else if (lock_type == XA_LOCK_BH) xas_lock_bh(xas); else xas_lock(xas); } static inline void xas_unlock_type(struct xa_state *xas, unsigned int lock_type) { if (lock_type == XA_LOCK_IRQ) xas_unlock_irq(xas); else if (lock_type == XA_LOCK_BH) xas_unlock_bh(xas); else xas_unlock(xas); } static inline bool xa_track_free(const struct xarray *xa) { return xa->xa_flags & XA_FLAGS_TRACK_FREE; } static inline bool xa_zero_busy(const struct xarray *xa) { return xa->xa_flags & XA_FLAGS_ZERO_BUSY; } static inline void xa_mark_set(struct xarray *xa, xa_mark_t mark) { if (!(xa->xa_flags & XA_FLAGS_MARK(mark))) xa->xa_flags |= XA_FLAGS_MARK(mark); } static inline void xa_mark_clear(struct xarray *xa, xa_mark_t mark) { if (xa->xa_flags & XA_FLAGS_MARK(mark)) xa->xa_flags &= ~(XA_FLAGS_MARK(mark)); } static inline unsigned long *node_marks(struct xa_node *node, xa_mark_t mark) { return node->marks[(__force unsigned)mark]; } static inline bool node_get_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return test_bit(offset, node_marks(node, mark)); } /* returns true if the bit was set */ static inline bool node_set_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return __test_and_set_bit(offset, node_marks(node, mark)); } /* returns true if the bit was set */ static inline bool node_clear_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return __test_and_clear_bit(offset, node_marks(node, mark)); } static inline bool node_any_mark(struct xa_node *node, xa_mark_t mark) { return !bitmap_empty(node_marks(node, mark), XA_CHUNK_SIZE); } static inline void node_mark_all(struct xa_node *node, xa_mark_t mark) { bitmap_fill(node_marks(node, mark), XA_CHUNK_SIZE); } #define mark_inc(mark) do { \ mark = (__force xa_mark_t)((__force unsigned)(mark) + 1); \ } while (0) /* * xas_squash_marks() - Merge all marks to the first entry * @xas: Array operation state. * * Set a mark on the first entry if any entry has it set. Clear marks on * all sibling entries. */ static void xas_squash_marks(const struct xa_state *xas) { unsigned int mark = 0; unsigned int limit = xas->xa_offset + xas->xa_sibs + 1; if (!xas->xa_sibs) return; do { unsigned long *marks = xas->xa_node->marks[mark]; if (find_next_bit(marks, limit, xas->xa_offset + 1) == limit) continue; __set_bit(xas->xa_offset, marks); bitmap_clear(marks, xas->xa_offset + 1, xas->xa_sibs); } while (mark++ != (__force unsigned)XA_MARK_MAX); } /* extracts the offset within this node from the index */ static unsigned int get_offset(unsigned long index, struct xa_node *node) { return (index >> node->shift) & XA_CHUNK_MASK; } static void xas_set_offset(struct xa_state *xas) { xas->xa_offset = get_offset(xas->xa_index, xas->xa_node); } /* move the index either forwards (find) or backwards (sibling slot) */ static void xas_move_index(struct xa_state *xas, unsigned long offset) { unsigned int shift = xas->xa_node->shift; xas->xa_index &= ~XA_CHUNK_MASK << shift; xas->xa_index += offset << shift; } static void xas_next_offset(struct xa_state *xas) { xas->xa_offset++; xas_move_index(xas, xas->xa_offset); } static void *set_bounds(struct xa_state *xas) { xas->xa_node = XAS_BOUNDS; return NULL; } /* * Starts a walk. If the @xas is already valid, we assume that it's on * the right path and just return where we've got to. If we're in an * error state, return NULL. If the index is outside the current scope * of the xarray, return NULL without changing @xas->xa_node. Otherwise * set @xas->xa_node to NULL and return the current head of the array. */ static void *xas_start(struct xa_state *xas) { void *entry; if (xas_valid(xas)) return xas_reload(xas); if (xas_error(xas)) return NULL; entry = xa_head(xas->xa); if (!xa_is_node(entry)) { if (xas->xa_index) return set_bounds(xas); } else { if ((xas->xa_index >> xa_to_node(entry)->shift) > XA_CHUNK_MASK) return set_bounds(xas); } xas->xa_node = NULL; return entry; } static void *xas_descend(struct xa_state *xas, struct xa_node *node) { unsigned int offset = get_offset(xas->xa_index, node); void *entry = xa_entry(xas->xa, node, offset); xas->xa_node = node; while (xa_is_sibling(entry)) { offset = xa_to_sibling(entry); entry = xa_entry(xas->xa, node, offset); if (node->shift && xa_is_node(entry)) entry = XA_RETRY_ENTRY; } xas->xa_offset = offset; return entry; } /** * xas_load() - Load an entry from the XArray (advanced). * @xas: XArray operation state. * * Usually walks the @xas to the appropriate state to load the entry * stored at xa_index. However, it will do nothing and return %NULL if * @xas is in an error state. xas_load() will never expand the tree. * * If the xa_state is set up to operate on a multi-index entry, xas_load() * may return %NULL or an internal entry, even if there are entries * present within the range specified by @xas. * * Context: Any context. The caller should hold the xa_lock or the RCU lock. * Return: Usually an entry in the XArray, but see description for exceptions. */ void *xas_load(struct xa_state *xas) { void *entry = xas_start(xas); while (xa_is_node(entry)) { struct xa_node *node = xa_to_node(entry); if (xas->xa_shift > node->shift) break; entry = xas_descend(xas, node); if (node->shift == 0) break; } return entry; } EXPORT_SYMBOL_GPL(xas_load); /* Move the radix tree node cache here */ extern struct kmem_cache *radix_tree_node_cachep; extern void radix_tree_node_rcu_free(struct rcu_head *head); #define XA_RCU_FREE ((struct xarray *)1) static void xa_node_free(struct xa_node *node) { XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); node->array = XA_RCU_FREE; call_rcu(&node->rcu_head, radix_tree_node_rcu_free); } /* * xas_destroy() - Free any resources allocated during the XArray operation. * @xas: XArray operation state. * * Most users will not need to call this function; it is called for you * by xas_nomem(). */ void xas_destroy(struct xa_state *xas) { struct xa_node *next, *node = xas->xa_alloc; while (node) { XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); next = rcu_dereference_raw(node->parent); radix_tree_node_rcu_free(&node->rcu_head); xas->xa_alloc = node = next; } } /** * xas_nomem() - Allocate memory if needed. * @xas: XArray operation state. * @gfp: Memory allocation flags. * * If we need to add new nodes to the XArray, we try to allocate memory * with GFP_NOWAIT while holding the lock, which will usually succeed. * If it fails, @xas is flagged as needing memory to continue. The caller * should drop the lock and call xas_nomem(). If xas_nomem() succeeds, * the caller should retry the operation. * * Forward progress is guaranteed as one node is allocated here and * stored in the xa_state where it will be found by xas_alloc(). More * nodes will likely be found in the slab allocator, but we do not tie * them up here. * * Return: true if memory was needed, and was successfully allocated. */ bool xas_nomem(struct xa_state *xas, gfp_t gfp) { if (xas->xa_node != XA_ERROR(-ENOMEM)) { xas_destroy(xas); return false; } if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; xas->xa_alloc = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp); if (!xas->xa_alloc) return false; xas->xa_alloc->parent = NULL; XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list)); xas->xa_node = XAS_RESTART; return true; } EXPORT_SYMBOL_GPL(xas_nomem); /* * __xas_nomem() - Drop locks and allocate memory if needed. * @xas: XArray operation state. * @gfp: Memory allocation flags. * * Internal variant of xas_nomem(). * * Return: true if memory was needed, and was successfully allocated. */ static bool __xas_nomem(struct xa_state *xas, gfp_t gfp) __must_hold(xas->xa->xa_lock) { unsigned int lock_type = xa_lock_type(xas->xa); if (xas->xa_node != XA_ERROR(-ENOMEM)) { xas_destroy(xas); return false; } if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; if (gfpflags_allow_blocking(gfp)) { xas_unlock_type(xas, lock_type); xas->xa_alloc = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp); xas_lock_type(xas, lock_type); } else { xas->xa_alloc = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp); } if (!xas->xa_alloc) return false; xas->xa_alloc->parent = NULL; XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list)); xas->xa_node = XAS_RESTART; return true; } static void xas_update(struct xa_state *xas, struct xa_node *node) { if (xas->xa_update) xas->xa_update(node); else XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); } static void *xas_alloc(struct xa_state *xas, unsigned int shift) { struct xa_node *parent = xas->xa_node; struct xa_node *node = xas->xa_alloc; if (xas_invalid(xas)) return NULL; if (node) { xas->xa_alloc = NULL; } else { gfp_t gfp = GFP_NOWAIT | __GFP_NOWARN; if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; node = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp); if (!node) { xas_set_err(xas, -ENOMEM); return NULL; } } if (parent) { node->offset = xas->xa_offset; parent->count++; XA_NODE_BUG_ON(node, parent->count > XA_CHUNK_SIZE); xas_update(xas, parent); } XA_NODE_BUG_ON(node, shift > BITS_PER_LONG); XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); node->shift = shift; node->count = 0; node->nr_values = 0; RCU_INIT_POINTER(node->parent, xas->xa_node); node->array = xas->xa; return node; } #ifdef CONFIG_XARRAY_MULTI /* Returns the number of indices covered by a given xa_state */ static unsigned long xas_size(const struct xa_state *xas) { return (xas->xa_sibs + 1UL) << xas->xa_shift; } #endif /* * Use this to calculate the maximum index that will need to be created * in order to add the entry described by @xas. Because we cannot store a * multi-index entry at index 0, the calculation is a little more complex * than you might expect. */ static unsigned long xas_max(struct xa_state *xas) { unsigned long max = xas->xa_index; #ifdef CONFIG_XARRAY_MULTI if (xas->xa_shift || xas->xa_sibs) { unsigned long mask = xas_size(xas) - 1; max |= mask; if (mask == max) max++; } #endif return max; } /* The maximum index that can be contained in the array without expanding it */ static unsigned long max_index(void *entry) { if (!xa_is_node(entry)) return 0; return (XA_CHUNK_SIZE << xa_to_node(entry)->shift) - 1; } static void xas_shrink(struct xa_state *xas) { struct xarray *xa = xas->xa; struct xa_node *node = xas->xa_node; for (;;) { void *entry; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); if (node->count != 1) break; entry = xa_entry_locked(xa, node, 0); if (!entry) break; if (!xa_is_node(entry) && node->shift) break; if (xa_is_zero(entry) && xa_zero_busy(xa)) entry = NULL; xas->xa_node = XAS_BOUNDS; RCU_INIT_POINTER(xa->xa_head, entry); if (xa_track_free(xa) && !node_get_mark(node, 0, XA_FREE_MARK)) xa_mark_clear(xa, XA_FREE_MARK); node->count = 0; node->nr_values = 0; if (!xa_is_node(entry)) RCU_INIT_POINTER(node->slots[0], XA_RETRY_ENTRY); xas_update(xas, node); xa_node_free(node); if (!xa_is_node(entry)) break; node = xa_to_node(entry); node->parent = NULL; } } /* * xas_delete_node() - Attempt to delete an xa_node * @xas: Array operation state. * * Attempts to delete the @xas->xa_node. This will fail if xa->node has * a non-zero reference count. */ static void xas_delete_node(struct xa_state *xas) { struct xa_node *node = xas->xa_node; for (;;) { struct xa_node *parent; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); if (node->count) break; parent = xa_parent_locked(xas->xa, node); xas->xa_node = parent; xas->xa_offset = node->offset; xa_node_free(node); if (!parent) { xas->xa->xa_head = NULL; xas->xa_node = XAS_BOUNDS; return; } parent->slots[xas->xa_offset] = NULL; parent->count--; XA_NODE_BUG_ON(parent, parent->count > XA_CHUNK_SIZE); node = parent; xas_update(xas, node); } if (!node->parent) xas_shrink(xas); } /** * xas_free_nodes() - Free this node and all nodes that it references * @xas: Array operation state. * @top: Node to free * * This node has been removed from the tree. We must now free it and all * of its subnodes. There may be RCU walkers with references into the tree, * so we must replace all entries with retry markers. */ static void xas_free_nodes(struct xa_state *xas, struct xa_node *top) { unsigned int offset = 0; struct xa_node *node = top; for (;;) { void *entry = xa_entry_locked(xas->xa, node, offset); if (node->shift && xa_is_node(entry)) { node = xa_to_node(entry); offset = 0; continue; } if (entry) RCU_INIT_POINTER(node->slots[offset], XA_RETRY_ENTRY); offset++; while (offset == XA_CHUNK_SIZE) { struct xa_node *parent; parent = xa_parent_locked(xas->xa, node); offset = node->offset + 1; node->count = 0; node->nr_values = 0; xas_update(xas, node); xa_node_free(node); if (node == top) return; node = parent; } } } /* * xas_expand adds nodes to the head of the tree until it has reached * sufficient height to be able to contain @xas->xa_index */ static int xas_expand(struct xa_state *xas, void *head) { struct xarray *xa = xas->xa; struct xa_node *node = NULL; unsigned int shift = 0; unsigned long max = xas_max(xas); if (!head) { if (max == 0) return 0; while ((max >> shift) >= XA_CHUNK_SIZE) shift += XA_CHUNK_SHIFT; return shift + XA_CHUNK_SHIFT; } else if (xa_is_node(head)) { node = xa_to_node(head); shift = node->shift + XA_CHUNK_SHIFT; } xas->xa_node = NULL; while (max > max_index(head)) { xa_mark_t mark = 0; XA_NODE_BUG_ON(node, shift > BITS_PER_LONG); node = xas_alloc(xas, shift); if (!node) return -ENOMEM; node->count = 1; if (xa_is_value(head)) node->nr_values = 1; RCU_INIT_POINTER(node->slots[0], head); /* Propagate the aggregated mark info to the new child */ for (;;) { if (xa_track_free(xa) && mark == XA_FREE_MARK) { node_mark_all(node, XA_FREE_MARK); if (!xa_marked(xa, XA_FREE_MARK)) { node_clear_mark(node, 0, XA_FREE_MARK); xa_mark_set(xa, XA_FREE_MARK); } } else if (xa_marked(xa, mark)) { node_set_mark(node, 0, mark); } if (mark == XA_MARK_MAX) break; mark_inc(mark); } /* * Now that the new node is fully initialised, we can add * it to the tree */ if (xa_is_node(head)) { xa_to_node(head)->offset = 0; rcu_assign_pointer(xa_to_node(head)->parent, node); } head = xa_mk_node(node); rcu_assign_pointer(xa->xa_head, head); xas_update(xas, node); shift += XA_CHUNK_SHIFT; } xas->xa_node = node; return shift; } /* * xas_create() - Create a slot to store an entry in. * @xas: XArray operation state. * @allow_root: %true if we can store the entry in the root directly * * Most users will not need to call this function directly, as it is called * by xas_store(). It is useful for doing conditional store operations * (see the xa_cmpxchg() implementation for an example). * * Return: If the slot already existed, returns the contents of this slot. * If the slot was newly created, returns %NULL. If it failed to create the * slot, returns %NULL and indicates the error in @xas. */ static void *xas_create(struct xa_state *xas, bool allow_root) { struct xarray *xa = xas->xa; void *entry; void __rcu **slot; struct xa_node *node = xas->xa_node; int shift; unsigned int order = xas->xa_shift; if (xas_top(node)) { entry = xa_head_locked(xa); xas->xa_node = NULL; if (!entry && xa_zero_busy(xa)) entry = XA_ZERO_ENTRY; shift = xas_expand(xas, entry); if (shift < 0) return NULL; if (!shift && !allow_root) shift = XA_CHUNK_SHIFT; entry = xa_head_locked(xa); slot = &xa->xa_head; } else if (xas_error(xas)) { return NULL; } else if (node) { unsigned int offset = xas->xa_offset; shift = node->shift; entry = xa_entry_locked(xa, node, offset); slot = &node->slots[offset]; } else { shift = 0; entry = xa_head_locked(xa); slot = &xa->xa_head; } while (shift > order) { shift -= XA_CHUNK_SHIFT; if (!entry) { node = xas_alloc(xas, shift); if (!node) break; if (xa_track_free(xa)) node_mark_all(node, XA_FREE_MARK); rcu_assign_pointer(*slot, xa_mk_node(node)); } else if (xa_is_node(entry)) { node = xa_to_node(entry); } else { break; } entry = xas_descend(xas, node); slot = &node->slots[xas->xa_offset]; } return entry; } /** * xas_create_range() - Ensure that stores to this range will succeed * @xas: XArray operation state. * * Creates all of the slots in the range covered by @xas. Sets @xas to * create single-index entries and positions it at the beginning of the * range. This is for the benefit of users which have not yet been * converted to use multi-index entries. */ void xas_create_range(struct xa_state *xas) { unsigned long index = xas->xa_index; unsigned char shift = xas->xa_shift; unsigned char sibs = xas->xa_sibs; xas->xa_index |= ((sibs + 1UL) << shift) - 1; if (xas_is_node(xas) && xas->xa_node->shift == xas->xa_shift) xas->xa_offset |= sibs; xas->xa_shift = 0; xas->xa_sibs = 0; for (;;) { xas_create(xas, true); if (xas_error(xas)) goto restore; if (xas->xa_index <= (index | XA_CHUNK_MASK)) goto success; xas->xa_index -= XA_CHUNK_SIZE; for (;;) { struct xa_node *node = xas->xa_node; if (node->shift >= shift) break; xas->xa_node = xa_parent_locked(xas->xa, node); xas->xa_offset = node->offset - 1; if (node->offset != 0) break; } } restore: xas->xa_shift = shift; xas->xa_sibs = sibs; xas->xa_index = index; return; success: xas->xa_index = index; if (xas->xa_node) xas_set_offset(xas); } EXPORT_SYMBOL_GPL(xas_create_range); static void update_node(struct xa_state *xas, struct xa_node *node, int count, int values) { if (!node || (!count && !values)) return; node->count += count; node->nr_values += values; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); XA_NODE_BUG_ON(node, node->nr_values > XA_CHUNK_SIZE); xas_update(xas, node); if (count < 0) xas_delete_node(xas); } /** * xas_store() - Store this entry in the XArray. * @xas: XArray operation state. * @entry: New entry. * * If @xas is operating on a multi-index entry, the entry returned by this * function is essentially meaningless (it may be an internal entry or it * may be %NULL, even if there are non-NULL entries at some of the indices * covered by the range). This is not a problem for any current users, * and can be changed if needed. * * Return: The old entry at this index. */ void *xas_store(struct xa_state *xas, void *entry) { struct xa_node *node; void __rcu **slot = &xas->xa->xa_head; unsigned int offset, max; int count = 0; int values = 0; void *first, *next; bool value = xa_is_value(entry); if (entry) { bool allow_root = !xa_is_node(entry) && !xa_is_zero(entry); first = xas_create(xas, allow_root); } else { first = xas_load(xas); } if (xas_invalid(xas)) return first; node = xas->xa_node; if (node && (xas->xa_shift < node->shift)) xas->xa_sibs = 0; if ((first == entry) && !xas->xa_sibs) return first; next = first; offset = xas->xa_offset; max = xas->xa_offset + xas->xa_sibs; if (node) { slot = &node->slots[offset]; if (xas->xa_sibs) xas_squash_marks(xas); } if (!entry) xas_init_marks(xas); for (;;) { /* * Must clear the marks before setting the entry to NULL, * otherwise xas_for_each_marked may find a NULL entry and * stop early. rcu_assign_pointer contains a release barrier * so the mark clearing will appear to happen before the * entry is set to NULL. */ rcu_assign_pointer(*slot, entry); if (xa_is_node(next) && (!node || node->shift)) xas_free_nodes(xas, xa_to_node(next)); if (!node) break; count += !next - !entry; values += !xa_is_value(first) - !value; if (entry) { if (offset == max) break; if (!xa_is_sibling(entry)) entry = xa_mk_sibling(xas->xa_offset); } else { if (offset == XA_CHUNK_MASK) break; } next = xa_entry_locked(xas->xa, node, ++offset); if (!xa_is_sibling(next)) { if (!entry && (offset > max)) break; first = next; } slot++; } update_node(xas, node, count, values); return first; } EXPORT_SYMBOL_GPL(xas_store); /** * xas_get_mark() - Returns the state of this mark. * @xas: XArray operation state. * @mark: Mark number. * * Return: true if the mark is set, false if the mark is clear or @xas * is in an error state. */ bool xas_get_mark(const struct xa_state *xas, xa_mark_t mark) { if (xas_invalid(xas)) return false; if (!xas->xa_node) return xa_marked(xas->xa, mark); return node_get_mark(xas->xa_node, xas->xa_offset, mark); } EXPORT_SYMBOL_GPL(xas_get_mark); /** * xas_set_mark() - Sets the mark on this entry and its parents. * @xas: XArray operation state. * @mark: Mark number. * * Sets the specified mark on this entry, and walks up the tree setting it * on all the ancestor entries. Does nothing if @xas has not been walked to * an entry, or is in an error state. */ void xas_set_mark(const struct xa_state *xas, xa_mark_t mark) { struct xa_node *node = xas->xa_node; unsigned int offset = xas->xa_offset; if (xas_invalid(xas)) return; while (node) { if (node_set_mark(node, offset, mark)) return; offset = node->offset; node = xa_parent_locked(xas->xa, node); } if (!xa_marked(xas->xa, mark)) xa_mark_set(xas->xa, mark); } EXPORT_SYMBOL_GPL(xas_set_mark); /** * xas_clear_mark() - Clears the mark on this entry and its parents. * @xas: XArray operation state. * @mark: Mark number. * * Clears the specified mark on this entry, and walks back to the head * attempting to clear it on all the ancestor entries. Does nothing if * @xas has not been walked to an entry, or is in an error state. */ void xas_clear_mark(const struct xa_state *xas, xa_mark_t mark) { struct xa_node *node = xas->xa_node; unsigned int offset = xas->xa_offset; if (xas_invalid(xas)) return; while (node) { if (!node_clear_mark(node, offset, mark)) return; if (node_any_mark(node, mark)) return; offset = node->offset; node = xa_parent_locked(xas->xa, node); } if (xa_marked(xas->xa, mark)) xa_mark_clear(xas->xa, mark); } EXPORT_SYMBOL_GPL(xas_clear_mark); /** * xas_init_marks() - Initialise all marks for the entry * @xas: Array operations state. * * Initialise all marks for the entry specified by @xas. If we're tracking * free entries with a mark, we need to set it on all entries. All other * marks are cleared. * * This implementation is not as efficient as it could be; we may walk * up the tree multiple times. */ void xas_init_marks(const struct xa_state *xas) { xa_mark_t mark = 0; for (;;) { if (xa_track_free(xas->xa) && mark == XA_FREE_MARK) xas_set_mark(xas, mark); else xas_clear_mark(xas, mark); if (mark == XA_MARK_MAX) break; mark_inc(mark); } } EXPORT_SYMBOL_GPL(xas_init_marks); #ifdef CONFIG_XARRAY_MULTI static unsigned int node_get_marks(struct xa_node *node, unsigned int offset) { unsigned int marks = 0; xa_mark_t mark = XA_MARK_0; for (;;) { if (node_get_mark(node, offset, mark)) marks |= 1 << (__force unsigned int)mark; if (mark == XA_MARK_MAX) break; mark_inc(mark); } return marks; } static void node_set_marks(struct xa_node *node, unsigned int offset, struct xa_node *child, unsigned int marks) { xa_mark_t mark = XA_MARK_0; for (;;) { if (marks & (1 << (__force unsigned int)mark)) { node_set_mark(node, offset, mark); if (child) node_mark_all(child, mark); } if (mark == XA_MARK_MAX) break; mark_inc(mark); } } /** * xas_split_alloc() - Allocate memory for splitting an entry. * @xas: XArray operation state. * @entry: New entry which will be stored in the array. * @order: Current entry order. * @gfp: Memory allocation flags. * * This function should be called before calling xas_split(). * If necessary, it will allocate new nodes (and fill them with @entry) * to prepare for the upcoming split of an entry of @order size into * entries of the order stored in the @xas. * * Context: May sleep if @gfp flags permit. */ void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order, gfp_t gfp) { unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; unsigned int mask = xas->xa_sibs; /* XXX: no support for splitting really large entries yet */ if (WARN_ON(xas->xa_shift + 2 * XA_CHUNK_SHIFT < order)) goto nomem; if (xas->xa_shift + XA_CHUNK_SHIFT > order) return; do { unsigned int i; void *sibling = NULL; struct xa_node *node; node = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp); if (!node) goto nomem; node->array = xas->xa; for (i = 0; i < XA_CHUNK_SIZE; i++) { if ((i & mask) == 0) { RCU_INIT_POINTER(node->slots[i], entry); sibling = xa_mk_sibling(i); } else { RCU_INIT_POINTER(node->slots[i], sibling); } } RCU_INIT_POINTER(node->parent, xas->xa_alloc); xas->xa_alloc = node; } while (sibs-- > 0); return; nomem: xas_destroy(xas); xas_set_err(xas, -ENOMEM); } EXPORT_SYMBOL_GPL(xas_split_alloc); /** * xas_split() - Split a multi-index entry into smaller entries. * @xas: XArray operation state. * @entry: New entry to store in the array. * @order: Current entry order. * * The size of the new entries is set in @xas. The value in @entry is * copied to all the replacement entries. * * Context: Any context. The caller should hold the xa_lock. */ void xas_split(struct xa_state *xas, void *entry, unsigned int order) { unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; unsigned int offset, marks; struct xa_node *node; void *curr = xas_load(xas); int values = 0; node = xas->xa_node; if (xas_top(node)) return; marks = node_get_marks(node, xas->xa_offset); offset = xas->xa_offset + sibs; do { if (xas->xa_shift < node->shift) { struct xa_node *child = xas->xa_alloc; xas->xa_alloc = rcu_dereference_raw(child->parent); child->shift = node->shift - XA_CHUNK_SHIFT; child->offset = offset; child->count = XA_CHUNK_SIZE; child->nr_values = xa_is_value(entry) ? XA_CHUNK_SIZE : 0; RCU_INIT_POINTER(child->parent, node); node_set_marks(node, offset, child, marks); rcu_assign_pointer(node->slots[offset], xa_mk_node(child)); if (xa_is_value(curr)) values--; xas_update(xas, child); } else { unsigned int canon = offset - xas->xa_sibs; node_set_marks(node, canon, NULL, marks); rcu_assign_pointer(node->slots[canon], entry); while (offset > canon) rcu_assign_pointer(node->slots[offset--], xa_mk_sibling(canon)); values += (xa_is_value(entry) - xa_is_value(curr)) * (xas->xa_sibs + 1); } } while (offset-- > xas->xa_offset); node->nr_values += values; xas_update(xas, node); } EXPORT_SYMBOL_GPL(xas_split); #endif /** * xas_pause() - Pause a walk to drop a lock. * @xas: XArray operation state. * * Some users need to pause a walk and drop the lock they're holding in * order to yield to a higher priority thread or carry out an operation * on an entry. Those users should call this function before they drop * the lock. It resets the @xas to be suitable for the next iteration * of the loop after the user has reacquired the lock. If most entries * found during a walk require you to call xas_pause(), the xa_for_each() * iterator may be more appropriate. * * Note that xas_pause() only works for forward iteration. If a user needs * to pause a reverse iteration, we will need a xas_pause_rev(). */ void xas_pause(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (xas_invalid(xas)) return; xas->xa_node = XAS_RESTART; if (node) { unsigned long offset = xas->xa_offset; while (++offset < XA_CHUNK_SIZE) { if (!xa_is_sibling(xa_entry(xas->xa, node, offset))) break; } xas->xa_index += (offset - xas->xa_offset) << node->shift; if (xas->xa_index == 0) xas->xa_node = XAS_BOUNDS; } else { xas->xa_index++; } } EXPORT_SYMBOL_GPL(xas_pause); /* * __xas_prev() - Find the previous entry in the XArray. * @xas: XArray operation state. * * Helper function for xas_prev() which handles all the complex cases * out of line. */ void *__xas_prev(struct xa_state *xas) { void *entry; if (!xas_frozen(xas->xa_node)) xas->xa_index--; if (!xas->xa_node) return set_bounds(xas); if (xas_not_node(xas->xa_node)) return xas_load(xas); if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node)) xas->xa_offset--; while (xas->xa_offset == 255) { xas->xa_offset = xas->xa_node->offset - 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) return set_bounds(xas); } for (;;) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } } EXPORT_SYMBOL_GPL(__xas_prev); /* * __xas_next() - Find the next entry in the XArray. * @xas: XArray operation state. * * Helper function for xas_next() which handles all the complex cases * out of line. */ void *__xas_next(struct xa_state *xas) { void *entry; if (!xas_frozen(xas->xa_node)) xas->xa_index++; if (!xas->xa_node) return set_bounds(xas); if (xas_not_node(xas->xa_node)) return xas_load(xas); if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node)) xas->xa_offset++; while (xas->xa_offset == XA_CHUNK_SIZE) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) return set_bounds(xas); } for (;;) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } } EXPORT_SYMBOL_GPL(__xas_next); /** * xas_find() - Find the next present entry in the XArray. * @xas: XArray operation state. * @max: Highest index to return. * * If the @xas has not yet been walked to an entry, return the entry * which has an index >= xas.xa_index. If it has been walked, the entry * currently being pointed at has been processed, and so we move to the * next entry. * * If no entry is found and the array is smaller than @max, the iterator * is set to the smallest index not yet in the array. This allows @xas * to be immediately passed to xas_store(). * * Return: The entry, if found, otherwise %NULL. */ void *xas_find(struct xa_state *xas, unsigned long max) { void *entry; if (xas_error(xas) || xas->xa_node == XAS_BOUNDS) return NULL; if (xas->xa_index > max) return set_bounds(xas); if (!xas->xa_node) { xas->xa_index = 1; return set_bounds(xas); } else if (xas->xa_node == XAS_RESTART) { entry = xas_load(xas); if (entry || xas_not_node(xas->xa_node)) return entry; } else if (!xas->xa_node->shift && xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK)) { xas->xa_offset = ((xas->xa_index - 1) & XA_CHUNK_MASK) + 1; } xas_next_offset(xas); while (xas->xa_node && (xas->xa_index <= max)) { if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); continue; } entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (xa_is_node(entry)) { xas->xa_node = xa_to_node(entry); xas->xa_offset = 0; continue; } if (entry && !xa_is_sibling(entry)) return entry; xas_next_offset(xas); } if (!xas->xa_node) xas->xa_node = XAS_BOUNDS; return NULL; } EXPORT_SYMBOL_GPL(xas_find); /** * xas_find_marked() - Find the next marked entry in the XArray. * @xas: XArray operation state. * @max: Highest index to return. * @mark: Mark number to search for. * * If the @xas has not yet been walked to an entry, return the marked entry * which has an index >= xas.xa_index. If it has been walked, the entry * currently being pointed at has been processed, and so we return the * first marked entry with an index > xas.xa_index. * * If no marked entry is found and the array is smaller than @max, @xas is * set to the bounds state and xas->xa_index is set to the smallest index * not yet in the array. This allows @xas to be immediately passed to * xas_store(). * * If no entry is found before @max is reached, @xas is set to the restart * state. * * Return: The entry, if found, otherwise %NULL. */ void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) { bool advance = true; unsigned int offset; void *entry; if (xas_error(xas)) return NULL; if (xas->xa_index > max) goto max; if (!xas->xa_node) { xas->xa_index = 1; goto out; } else if (xas_top(xas->xa_node)) { advance = false; entry = xa_head(xas->xa); xas->xa_node = NULL; if (xas->xa_index > max_index(entry)) goto out; if (!xa_is_node(entry)) { if (xa_marked(xas->xa, mark)) return entry; xas->xa_index = 1; goto out; } xas->xa_node = xa_to_node(entry); xas->xa_offset = xas->xa_index >> xas->xa_node->shift; } while (xas->xa_index <= max) { if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) break; advance = false; continue; } if (!advance) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (xa_is_sibling(entry)) { xas->xa_offset = xa_to_sibling(entry); xas_move_index(xas, xas->xa_offset); } } offset = xas_find_chunk(xas, advance, mark); if (offset > xas->xa_offset) { advance = false; xas_move_index(xas, offset); /* Mind the wrap */ if ((xas->xa_index - 1) >= max) goto max; xas->xa_offset = offset; if (offset == XA_CHUNK_SIZE) continue; } entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!entry && !(xa_track_free(xas->xa) && mark == XA_FREE_MARK)) continue; if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } out: if (xas->xa_index > max) goto max; return set_bounds(xas); max: xas->xa_node = XAS_RESTART; return NULL; } EXPORT_SYMBOL_GPL(xas_find_marked); /** * xas_find_conflict() - Find the next present entry in a range. * @xas: XArray operation state. * * The @xas describes both a range and a position within that range. * * Context: Any context. Expects xa_lock to be held. * Return: The next entry in the range covered by @xas or %NULL. */ void *xas_find_conflict(struct xa_state *xas) { void *curr; if (xas_error(xas)) return NULL; if (!xas->xa_node) return NULL; if (xas_top(xas->xa_node)) { curr = xas_start(xas); if (!curr) return NULL; while (xa_is_node(curr)) { struct xa_node *node = xa_to_node(curr); curr = xas_descend(xas, node); } if (curr) return curr; } if (xas->xa_node->shift > xas->xa_shift) return NULL; for (;;) { if (xas->xa_node->shift == xas->xa_shift) { if ((xas->xa_offset & xas->xa_sibs) == xas->xa_sibs) break; } else if (xas->xa_offset == XA_CHUNK_MASK) { xas->xa_offset = xas->xa_node->offset; xas->xa_node = xa_parent_locked(xas->xa, xas->xa_node); if (!xas->xa_node) break; continue; } curr = xa_entry_locked(xas->xa, xas->xa_node, ++xas->xa_offset); if (xa_is_sibling(curr)) continue; while (xa_is_node(curr)) { xas->xa_node = xa_to_node(curr); xas->xa_offset = 0; curr = xa_entry_locked(xas->xa, xas->xa_node, 0); } if (curr) return curr; } xas->xa_offset -= xas->xa_sibs; return NULL; } EXPORT_SYMBOL_GPL(xas_find_conflict); /** * xa_load() - Load an entry from an XArray. * @xa: XArray. * @index: index into array. * * Context: Any context. Takes and releases the RCU lock. * Return: The entry at @index in @xa. */ void *xa_load(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); void *entry; rcu_read_lock(); do { entry = xas_load(&xas); if (xa_is_zero(entry)) entry = NULL; } while (xas_retry(&xas, entry)); rcu_read_unlock(); return entry; } EXPORT_SYMBOL(xa_load); static void *xas_result(struct xa_state *xas, void *curr) { if (xa_is_zero(curr)) return NULL; if (xas_error(xas)) curr = xas->xa_node; return curr; } /** * __xa_erase() - Erase this entry from the XArray while locked. * @xa: XArray. * @index: Index into array. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Expects xa_lock to be held on entry. * Return: The entry which used to be at this index. */ void *__xa_erase(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); return xas_result(&xas, xas_store(&xas, NULL)); } EXPORT_SYMBOL(__xa_erase); /** * xa_erase() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Takes and releases the xa_lock. * Return: The entry which used to be at this index. */ void *xa_erase(struct xarray *xa, unsigned long index) { void *entry; xa_lock(xa); entry = __xa_erase(xa, index); xa_unlock(xa); return entry; } EXPORT_SYMBOL(xa_erase); /** * __xa_store() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * You must already be holding the xa_lock when calling this function. * It will drop the lock if needed to allocate memory, and then reacquire * it afterwards. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: The old entry at this index or xa_err() if an error happened. */ void *__xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return XA_ERROR(-EINVAL); if (xa_track_free(xa) && !entry) entry = XA_ZERO_ENTRY; do { curr = xas_store(&xas, entry); if (xa_track_free(xa)) xas_clear_mark(&xas, XA_FREE_MARK); } while (__xas_nomem(&xas, gfp)); return xas_result(&xas, curr); } EXPORT_SYMBOL(__xa_store); /** * xa_store() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * After this function returns, loads from this index will return @entry. * Storing into an existing multi-index entry updates the entry of every index. * The marks associated with @index are unaffected unless @entry is %NULL. * * Context: Any context. Takes and releases the xa_lock. * May sleep if the @gfp flags permit. * Return: The old entry at this index on success, xa_err(-EINVAL) if @entry * cannot be stored in an XArray, or xa_err(-ENOMEM) if memory allocation * failed. */ void *xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; xa_lock(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock(xa); return curr; } EXPORT_SYMBOL(xa_store); /** * __xa_cmpxchg() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New entry. * @gfp: Memory allocation flags. * * You must already be holding the xa_lock when calling this function. * It will drop the lock if needed to allocate memory, and then reacquire * it afterwards. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: The old entry at this index or xa_err() if an error happened. */ void *__xa_cmpxchg(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return XA_ERROR(-EINVAL); do { curr = xas_load(&xas); if (curr == old) { xas_store(&xas, entry); if (xa_track_free(xa) && entry && !curr) xas_clear_mark(&xas, XA_FREE_MARK); } } while (__xas_nomem(&xas, gfp)); return xas_result(&xas, curr); } EXPORT_SYMBOL(__xa_cmpxchg); /** * __xa_insert() - Store this entry in the XArray if no entry is present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ int __xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (!entry) entry = XA_ZERO_ENTRY; do { curr = xas_load(&xas); if (!curr) { xas_store(&xas, entry); if (xa_track_free(xa)) xas_clear_mark(&xas, XA_FREE_MARK); } else { xas_set_err(&xas, -EBUSY); } } while (__xas_nomem(&xas, gfp)); return xas_error(&xas); } EXPORT_SYMBOL(__xa_insert); #ifdef CONFIG_XARRAY_MULTI static void xas_set_range(struct xa_state *xas, unsigned long first, unsigned long last) { unsigned int shift = 0; unsigned long sibs = last - first; unsigned int offset = XA_CHUNK_MASK; xas_set(xas, first); while ((first & XA_CHUNK_MASK) == 0) { if (sibs < XA_CHUNK_MASK) break; if ((sibs == XA_CHUNK_MASK) && (offset < XA_CHUNK_MASK)) break; shift += XA_CHUNK_SHIFT; if (offset == XA_CHUNK_MASK) offset = sibs & XA_CHUNK_MASK; sibs >>= XA_CHUNK_SHIFT; first >>= XA_CHUNK_SHIFT; } offset = first & XA_CHUNK_MASK; if (offset + sibs > XA_CHUNK_MASK) sibs = XA_CHUNK_MASK - offset; if ((((first + sibs + 1) << shift) - 1) > last) sibs -= 1; xas->xa_shift = shift; xas->xa_sibs = sibs; } /** * xa_store_range() - Store this entry at a range of indices in the XArray. * @xa: XArray. * @first: First index to affect. * @last: Last index to affect. * @entry: New entry. * @gfp: Memory allocation flags. * * After this function returns, loads from any index between @first and @last, * inclusive will return @entry. * Storing into an existing multi-index entry updates the entry of every index. * The marks associated with @index are unaffected unless @entry is %NULL. * * Context: Process context. Takes and releases the xa_lock. May sleep * if the @gfp flags permit. * Return: %NULL on success, xa_err(-EINVAL) if @entry cannot be stored in * an XArray, or xa_err(-ENOMEM) if memory allocation failed. */ void *xa_store_range(struct xarray *xa, unsigned long first, unsigned long last, void *entry, gfp_t gfp) { XA_STATE(xas, xa, 0); if (WARN_ON_ONCE(xa_is_internal(entry))) return XA_ERROR(-EINVAL); if (last < first) return XA_ERROR(-EINVAL); do { xas_lock(&xas); if (entry) { unsigned int order = BITS_PER_LONG; if (last + 1) order = __ffs(last + 1); xas_set_order(&xas, last, order); xas_create(&xas, true); if (xas_error(&xas)) goto unlock; } do { xas_set_range(&xas, first, last); xas_store(&xas, entry); if (xas_error(&xas)) goto unlock; first += xas_size(&xas); } while (first <= last); unlock: xas_unlock(&xas); } while (xas_nomem(&xas, gfp)); return xas_result(&xas, NULL); } EXPORT_SYMBOL(xa_store_range); /** * xas_get_order() - Get the order of an entry. * @xas: XArray operation state. * * Called after xas_load, the xas should not be in an error state. * * Return: A number between 0 and 63 indicating the order of the entry. */ int xas_get_order(struct xa_state *xas) { int order = 0; if (!xas->xa_node) return 0; for (;;) { unsigned int slot = xas->xa_offset + (1 << order); if (slot >= XA_CHUNK_SIZE) break; if (!xa_is_sibling(xa_entry(xas->xa, xas->xa_node, slot))) break; order++; } order += xas->xa_node->shift; return order; } EXPORT_SYMBOL_GPL(xas_get_order); /** * xa_get_order() - Get the order of an entry. * @xa: XArray. * @index: Index of the entry. * * Return: A number between 0 and 63 indicating the order of the entry. */ int xa_get_order(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); int order = 0; void *entry; rcu_read_lock(); entry = xas_load(&xas); if (entry) order = xas_get_order(&xas); rcu_read_unlock(); return order; } EXPORT_SYMBOL(xa_get_order); #endif /* CONFIG_XARRAY_MULTI */ /** * __xa_alloc() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @limit: Range for allocated ID. * @entry: New entry. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ int __xa_alloc(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { XA_STATE(xas, xa, 0); if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (WARN_ON_ONCE(!xa_track_free(xa))) return -EINVAL; if (!entry) entry = XA_ZERO_ENTRY; do { xas.xa_index = limit.min; xas_find_marked(&xas, limit.max, XA_FREE_MARK); if (xas.xa_node == XAS_RESTART) xas_set_err(&xas, -EBUSY); else *id = xas.xa_index; xas_store(&xas, entry); xas_clear_mark(&xas, XA_FREE_MARK); } while (__xas_nomem(&xas, gfp)); return xas_error(&xas); } EXPORT_SYMBOL(__xa_alloc); /** * __xa_alloc_cyclic() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ int __xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { u32 min = limit.min; int ret; limit.min = max(min, *next); ret = __xa_alloc(xa, id, entry, limit, gfp); if ((xa->xa_flags & XA_FLAGS_ALLOC_WRAPPED) && ret == 0) { xa->xa_flags &= ~XA_FLAGS_ALLOC_WRAPPED; ret = 1; } if (ret < 0 && limit.min > min) { limit.min = min; ret = __xa_alloc(xa, id, entry, limit, gfp); if (ret == 0) ret = 1; } if (ret >= 0) { *next = *id + 1; if (*next == 0) xa->xa_flags |= XA_FLAGS_ALLOC_WRAPPED; } return ret; } EXPORT_SYMBOL(__xa_alloc_cyclic); /** * __xa_set_mark() - Set this mark on this entry while locked. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Attempting to set a mark on a %NULL entry does not succeed. * * Context: Any context. Expects xa_lock to be held on entry. */ void __xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry = xas_load(&xas); if (entry) xas_set_mark(&xas, mark); } EXPORT_SYMBOL(__xa_set_mark); /** * __xa_clear_mark() - Clear this mark on this entry while locked. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Context: Any context. Expects xa_lock to be held on entry. */ void __xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry = xas_load(&xas); if (entry) xas_clear_mark(&xas, mark); } EXPORT_SYMBOL(__xa_clear_mark); /** * xa_get_mark() - Inquire whether this mark is set on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * This function uses the RCU read lock, so the result may be out of date * by the time it returns. If you need the result to be stable, use a lock. * * Context: Any context. Takes and releases the RCU lock. * Return: True if the entry at @index has this mark set, false if it doesn't. */ bool xa_get_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry; rcu_read_lock(); entry = xas_start(&xas); while (xas_get_mark(&xas, mark)) { if (!xa_is_node(entry)) goto found; entry = xas_descend(&xas, xa_to_node(entry)); } rcu_read_unlock(); return false; found: rcu_read_unlock(); return true; } EXPORT_SYMBOL(xa_get_mark); /** * xa_set_mark() - Set this mark on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Attempting to set a mark on a %NULL entry does not succeed. * * Context: Process context. Takes and releases the xa_lock. */ void xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { xa_lock(xa); __xa_set_mark(xa, index, mark); xa_unlock(xa); } EXPORT_SYMBOL(xa_set_mark); /** * xa_clear_mark() - Clear this mark on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Clearing a mark always succeeds. * * Context: Process context. Takes and releases the xa_lock. */ void xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { xa_lock(xa); __xa_clear_mark(xa, index, mark); xa_unlock(xa); } EXPORT_SYMBOL(xa_clear_mark); /** * xa_find() - Search the XArray for an entry. * @xa: XArray. * @indexp: Pointer to an index. * @max: Maximum index to search to. * @filter: Selection criterion. * * Finds the entry in @xa which matches the @filter, and has the lowest * index that is at least @indexp and no more than @max. * If an entry is found, @indexp is updated to be the index of the entry. * This function is protected by the RCU read lock, so it may not find * entries which are being simultaneously added. It will not return an * %XA_RETRY_ENTRY; if you need to see retry entries, use xas_find(). * * Context: Any context. Takes and releases the RCU lock. * Return: The entry, if found, otherwise %NULL. */ void *xa_find(struct xarray *xa, unsigned long *indexp, unsigned long max, xa_mark_t filter) { XA_STATE(xas, xa, *indexp); void *entry; rcu_read_lock(); do { if ((__force unsigned int)filter < XA_MAX_MARKS) entry = xas_find_marked(&xas, max, filter); else entry = xas_find(&xas, max); } while (xas_retry(&xas, entry)); rcu_read_unlock(); if (entry) *indexp = xas.xa_index; return entry; } EXPORT_SYMBOL(xa_find); static bool xas_sibling(struct xa_state *xas) { struct xa_node *node = xas->xa_node; unsigned long mask; if (!IS_ENABLED(CONFIG_XARRAY_MULTI) || !node) return false; mask = (XA_CHUNK_SIZE << node->shift) - 1; return (xas->xa_index & mask) > ((unsigned long)xas->xa_offset << node->shift); } /** * xa_find_after() - Search the XArray for a present entry. * @xa: XArray. * @indexp: Pointer to an index. * @max: Maximum index to search to. * @filter: Selection criterion. * * Finds the entry in @xa which matches the @filter and has the lowest * index that is above @indexp and no more than @max. * If an entry is found, @indexp is updated to be the index of the entry. * This function is protected by the RCU read lock, so it may miss entries * which are being simultaneously added. It will not return an * %XA_RETRY_ENTRY; if you need to see retry entries, use xas_find(). * * Context: Any context. Takes and releases the RCU lock. * Return: The pointer, if found, otherwise %NULL. */ void *xa_find_after(struct xarray *xa, unsigned long *indexp, unsigned long max, xa_mark_t filter) { XA_STATE(xas, xa, *indexp + 1); void *entry; if (xas.xa_index == 0) return NULL; rcu_read_lock(); for (;;) { if ((__force unsigned int)filter < XA_MAX_MARKS) entry = xas_find_marked(&xas, max, filter); else entry = xas_find(&xas, max); if (xas_invalid(&xas)) break; if (xas_sibling(&xas)) continue; if (!xas_retry(&xas, entry)) break; } rcu_read_unlock(); if (entry) *indexp = xas.xa_index; return entry; } EXPORT_SYMBOL(xa_find_after); static unsigned int xas_extract_present(struct xa_state *xas, void **dst, unsigned long max, unsigned int n) { void *entry; unsigned int i = 0; rcu_read_lock(); xas_for_each(xas, entry, max) { if (xas_retry(xas, entry)) continue; dst[i++] = entry; if (i == n) break; } rcu_read_unlock(); return i; } static unsigned int xas_extract_marked(struct xa_state *xas, void **dst, unsigned long max, unsigned int n, xa_mark_t mark) { void *entry; unsigned int i = 0; rcu_read_lock(); xas_for_each_marked(xas, entry, max, mark) { if (xas_retry(xas, entry)) continue; dst[i++] = entry; if (i == n) break; } rcu_read_unlock(); return i; } /** * xa_extract() - Copy selected entries from the XArray into a normal array. * @xa: The source XArray to copy from. * @dst: The buffer to copy entries into. * @start: The first index in the XArray eligible to be selected. * @max: The last index in the XArray eligible to be selected. * @n: The maximum number of entries to copy. * @filter: Selection criterion. * * Copies up to @n entries that match @filter from the XArray. The * copied entries will have indices between @start and @max, inclusive. * * The @filter may be an XArray mark value, in which case entries which are * marked with that mark will be copied. It may also be %XA_PRESENT, in * which case all entries which are not %NULL will be copied. * * The entries returned may not represent a snapshot of the XArray at a * moment in time. For example, if another thread stores to index 5, then * index 10, calling xa_extract() may return the old contents of index 5 * and the new contents of index 10. Indices not modified while this * function is running will not be skipped. * * If you need stronger guarantees, holding the xa_lock across calls to this * function will prevent concurrent modification. * * Context: Any context. Takes and releases the RCU lock. * Return: The number of entries copied. */ unsigned int xa_extract(struct xarray *xa, void **dst, unsigned long start, unsigned long max, unsigned int n, xa_mark_t filter) { XA_STATE(xas, xa, start); if (!n) return 0; if ((__force unsigned int)filter < XA_MAX_MARKS) return xas_extract_marked(&xas, dst, max, n, filter); return xas_extract_present(&xas, dst, max, n); } EXPORT_SYMBOL(xa_extract); /** * xa_delete_node() - Private interface for workingset code. * @node: Node to be removed from the tree. * @update: Function to call to update ancestor nodes. * * Context: xa_lock must be held on entry and will not be released. */ void xa_delete_node(struct xa_node *node, xa_update_node_t update) { struct xa_state xas = { .xa = node->array, .xa_index = (unsigned long)node->offset << (node->shift + XA_CHUNK_SHIFT), .xa_shift = node->shift + XA_CHUNK_SHIFT, .xa_offset = node->offset, .xa_node = xa_parent_locked(node->array, node), .xa_update = update, }; xas_store(&xas, NULL); } EXPORT_SYMBOL_GPL(xa_delete_node); /* For the benefit of the test suite */ /** * xa_destroy() - Free all internal data structures. * @xa: XArray. * * After calling this function, the XArray is empty and has freed all memory * allocated for its internal data structures. You are responsible for * freeing the objects referenced by the XArray. * * Context: Any context. Takes and releases the xa_lock, interrupt-safe. */ void xa_destroy(struct xarray *xa) { XA_STATE(xas, xa, 0); unsigned long flags; void *entry; xas.xa_node = NULL; xas_lock_irqsave(&xas, flags); entry = xa_head_locked(xa); RCU_INIT_POINTER(xa->xa_head, NULL); xas_init_marks(&xas); if (xa_zero_busy(xa)) xa_mark_clear(xa, XA_FREE_MARK); /* lockdep checks we're still holding the lock in xas_free_nodes() */ if (xa_is_node(entry)) xas_free_nodes(&xas, xa_to_node(entry)); xas_unlock_irqrestore(&xas, flags); } EXPORT_SYMBOL(xa_destroy); #ifdef XA_DEBUG void xa_dump_node(const struct xa_node *node) { unsigned i, j; if (!node) return; if ((unsigned long)node & 3) { pr_cont("node %px\n", node); return; } pr_cont("node %px %s %d parent %px shift %d count %d values %d " "array %px list %px %px marks", node, node->parent ? "offset" : "max", node->offset, node->parent, node->shift, node->count, node->nr_values, node->array, node->private_list.prev, node->private_list.next); for (i = 0; i < XA_MAX_MARKS; i++) for (j = 0; j < XA_MARK_LONGS; j++) pr_cont(" %lx", node->marks[i][j]); pr_cont("\n"); } void xa_dump_index(unsigned long index, unsigned int shift) { if (!shift) pr_info("%lu: ", index); else if (shift >= BITS_PER_LONG) pr_info("0-%lu: ", ~0UL); else pr_info("%lu-%lu: ", index, index | ((1UL << shift) - 1)); } void xa_dump_entry(const void *entry, unsigned long index, unsigned long shift) { if (!entry) return; xa_dump_index(index, shift); if (xa_is_node(entry)) { if (shift == 0) { pr_cont("%px\n", entry); } else { unsigned long i; struct xa_node *node = xa_to_node(entry); xa_dump_node(node); for (i = 0; i < XA_CHUNK_SIZE; i++) xa_dump_entry(node->slots[i], index + (i << node->shift), node->shift); } } else if (xa_is_value(entry)) pr_cont("value %ld (0x%lx) [%px]\n", xa_to_value(entry), xa_to_value(entry), entry); else if (!xa_is_internal(entry)) pr_cont("%px\n", entry); else if (xa_is_retry(entry)) pr_cont("retry (%ld)\n", xa_to_internal(entry)); else if (xa_is_sibling(entry)) pr_cont("sibling (slot %ld)\n", xa_to_sibling(entry)); else if (xa_is_zero(entry)) pr_cont("zero (%ld)\n", xa_to_internal(entry)); else pr_cont("UNKNOWN ENTRY (%px)\n", entry); } void xa_dump(const struct xarray *xa) { void *entry = xa->xa_head; unsigned int shift = 0; pr_info("xarray: %px head %px flags %x marks %d %d %d\n", xa, entry, xa->xa_flags, xa_marked(xa, XA_MARK_0), xa_marked(xa, XA_MARK_1), xa_marked(xa, XA_MARK_2)); if (xa_is_node(entry)) shift = xa_to_node(entry)->shift + XA_CHUNK_SHIFT; xa_dump_entry(entry, 0, shift); } #endif |
| 5 5 419 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 | /* 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); 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); 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 mmu_gather *tlb, 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, }; 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; #define hugepage_flags_enabled() \ (transparent_hugepage_flags & \ ((1<<TRANSPARENT_HUGEPAGE_FLAG) | \ (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG))) #define hugepage_flags_always() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_FLAG)) /* * Do the below checks: * - For file vma, check if the linear page offset of vma is * HPAGE_PMD_NR aligned within the file. The hugepage is * guaranteed to be hugepage-aligned within the file, but we must * check that the PMD-aligned addresses in the VMA map to * PMD-aligned offsets within the file, else the hugepage will * not be PMD-mappable. * - For all vmas, check if the haddr is in an aligned HPAGE_PMD_SIZE * area. */ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, unsigned long addr) { 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; } haddr = addr & HPAGE_PMD_MASK; if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) return false; return true; } static inline bool file_thp_enabled(struct vm_area_struct *vma) { struct inode *inode; if (!vma->vm_file) return false; inode = vma->vm_file->f_inode; return (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS)) && (vma->vm_flags & VM_EXEC) && !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode); } bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags, bool smaps, bool in_pf, bool enforce_sysfs); #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 can_split_folio(struct folio *folio, 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 folio *folio); #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 folio *folio); 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); int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end); 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; } /** * folio_test_pmd_mappable - Can we map this folio with a PMD? * @folio: The folio to test */ static inline bool folio_test_pmd_mappable(struct folio *folio) { return folio_order(folio) >= HPAGE_PMD_ORDER; } 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); 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 pmd_present(pmd) && READ_ONCE(huge_zero_pfn) == pmd_pfn(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) { /* * See organization of tail pages of compound page in * "struct page" definition. */ 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 bool folio_test_pmd_mappable(struct folio *folio) { return false; } static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, unsigned long addr) { return false; } static inline bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags, bool smaps, bool in_pf, bool enforce_sysfs) { return false; } static inline void prep_transhuge_page(struct page *page) {} #define transparent_hugepage_flags 0UL #define thp_get_unmapped_area NULL static inline bool can_split_folio(struct folio *folio, int *pextra_pins) { 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 folio *folio) {} static inline void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct folio *folio) {} #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) { return -EINVAL; } static inline int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end) { return -EINVAL; } 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) { 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 */ static inline int split_folio_to_list(struct folio *folio, struct list_head *list) { return split_huge_page_to_list(&folio->page, list); } static inline int split_folio(struct folio *folio) { return split_folio_to_list(folio, NULL); } /* * archs that select ARCH_WANTS_THP_SWAP but don't support THP_SWP due to * limitations in the implementation like arm64 MTE can override this to * false */ #ifndef arch_thp_swp_supported static inline bool arch_thp_swp_supported(void) { return true; } #endif #endif /* _LINUX_HUGE_MM_H */ |
| 640 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 | // SPDX-License-Identifier: GPL-2.0-only /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> * (C) 2006-2010 Patrick McHardy <kaber@trash.net> */ #include <linux/types.h> #include <linux/timer.h> #include <linux/netfilter.h> #include <linux/in.h> #include <linux/icmp.h> #include <linux/seq_file.h> #include <net/ip.h> #include <net/checksum.h> #include <linux/netfilter_ipv4.h> #include <net/netfilter/nf_conntrack_tuple.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_timeout.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_log.h> #include "nf_internals.h" static const unsigned int nf_ct_icmp_timeout = 30*HZ; bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, struct nf_conntrack_tuple *tuple) { const struct icmphdr *hp; struct icmphdr _hdr; hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); if (hp == NULL) return false; tuple->dst.u.icmp.type = hp->type; tuple->src.u.icmp.id = hp->un.echo.id; tuple->dst.u.icmp.code = hp->code; return true; } /* Add 1; spaces filled with 0. */ static const u_int8_t invmap[] = { [ICMP_ECHO] = ICMP_ECHOREPLY + 1, [ICMP_ECHOREPLY] = ICMP_ECHO + 1, [ICMP_TIMESTAMP] = ICMP_TIMESTAMPREPLY + 1, [ICMP_TIMESTAMPREPLY] = ICMP_TIMESTAMP + 1, [ICMP_INFO_REQUEST] = ICMP_INFO_REPLY + 1, [ICMP_INFO_REPLY] = ICMP_INFO_REQUEST + 1, [ICMP_ADDRESS] = ICMP_ADDRESSREPLY + 1, [ICMP_ADDRESSREPLY] = ICMP_ADDRESS + 1 }; bool nf_conntrack_invert_icmp_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig) { if (orig->dst.u.icmp.type >= sizeof(invmap) || !invmap[orig->dst.u.icmp.type]) return false; tuple->src.u.icmp.id = orig->src.u.icmp.id; tuple->dst.u.icmp.type = invmap[orig->dst.u.icmp.type] - 1; tuple->dst.u.icmp.code = orig->dst.u.icmp.code; return true; } /* Returns verdict for packet, or -1 for invalid. */ int nf_conntrack_icmp_packet(struct nf_conn *ct, struct sk_buff *skb, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state) { /* Do not immediately delete the connection after the first successful reply to avoid excessive conntrackd traffic and also to handle correctly ICMP echo reply duplicates. */ unsigned int *timeout = nf_ct_timeout_lookup(ct); static const u_int8_t valid_new[] = { [ICMP_ECHO] = 1, [ICMP_TIMESTAMP] = 1, [ICMP_INFO_REQUEST] = 1, [ICMP_ADDRESS] = 1 }; if (state->pf != NFPROTO_IPV4) return -NF_ACCEPT; if (ct->tuplehash[0].tuple.dst.u.icmp.type >= sizeof(valid_new) || !valid_new[ct->tuplehash[0].tuple.dst.u.icmp.type]) { /* Can't create a new ICMP `conn' with this. */ pr_debug("icmp: can't create new conn with type %u\n", ct->tuplehash[0].tuple.dst.u.icmp.type); nf_ct_dump_tuple_ip(&ct->tuplehash[0].tuple); return -NF_ACCEPT; } if (!timeout) timeout = &nf_icmp_pernet(nf_ct_net(ct))->timeout; nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; } /* Check inner header is related to any of the existing connections */ int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state, u8 l4proto, union nf_inet_addr *outer_daddr) { struct nf_conntrack_tuple innertuple, origtuple; const struct nf_conntrack_tuple_hash *h; const struct nf_conntrack_zone *zone; enum ip_conntrack_info ctinfo; struct nf_conntrack_zone tmp; union nf_inet_addr *ct_daddr; enum ip_conntrack_dir dir; struct nf_conn *ct; WARN_ON(skb_nfct(skb)); zone = nf_ct_zone_tmpl(tmpl, skb, &tmp); /* Are they talking about one of our connections? */ if (!nf_ct_get_tuplepr(skb, dataoff, state->pf, state->net, &origtuple)) return -NF_ACCEPT; /* Ordinarily, we'd expect the inverted tupleproto, but it's been preserved inside the ICMP. */ if (!nf_ct_invert_tuple(&innertuple, &origtuple)) return -NF_ACCEPT; h = nf_conntrack_find_get(state->net, zone, &innertuple); if (!h) return -NF_ACCEPT; /* Consider: A -> T (=This machine) -> B * Conntrack entry will look like this: * Original: A->B * Reply: B->T (SNAT case) OR A * * When this function runs, we got packet that looks like this: * iphdr|icmphdr|inner_iphdr|l4header (tcp, udp, ..). * * Above nf_conntrack_find_get() makes lookup based on inner_hdr, * so we should expect that destination of the found connection * matches outer header destination address. * * In above example, we can consider these two cases: * 1. Error coming in reply direction from B or M (middle box) to * T (SNAT case) or A. * Inner saddr will be B, dst will be T or A. * The found conntrack will be reply tuple (B->T/A). * 2. Error coming in original direction from A or M to B. * Inner saddr will be A, inner daddr will be B. * The found conntrack will be original tuple (A->B). * * In both cases, conntrack[dir].dst == inner.dst. * * A bogus packet could look like this: * Inner: B->T * Outer: B->X (other machine reachable by T). * * In this case, lookup yields connection A->B and will * set packet from B->X as *RELATED*, even though no connection * from X was ever seen. */ ct = nf_ct_tuplehash_to_ctrack(h); dir = NF_CT_DIRECTION(h); ct_daddr = &ct->tuplehash[dir].tuple.dst.u3; if (!nf_inet_addr_cmp(outer_daddr, ct_daddr)) { if (state->pf == AF_INET) { nf_l4proto_log_invalid(skb, state, l4proto, "outer daddr %pI4 != inner %pI4", &outer_daddr->ip, &ct_daddr->ip); } else if (state->pf == AF_INET6) { nf_l4proto_log_invalid(skb, state, l4proto, "outer daddr %pI6 != inner %pI6", &outer_daddr->ip6, &ct_daddr->ip6); } nf_ct_put(ct); return -NF_ACCEPT; } ctinfo = IP_CT_RELATED; if (dir == IP_CT_DIR_REPLY) ctinfo += IP_CT_IS_REPLY; /* Update skb to refer to this connection */ nf_ct_set(skb, ct, ctinfo); return NF_ACCEPT; } static void icmp_error_log(const struct sk_buff *skb, const struct nf_hook_state *state, const char *msg) { nf_l4proto_log_invalid(skb, state, IPPROTO_ICMP, "%s", msg); } /* Small and modified version of icmp_rcv */ int nf_conntrack_icmpv4_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state) { union nf_inet_addr outer_daddr; const struct icmphdr *icmph; struct icmphdr _ih; /* Not enough header? */ icmph = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih); if (icmph == NULL) { icmp_error_log(skb, state, "short packet"); return -NF_ACCEPT; } /* See nf_conntrack_proto_tcp.c */ if (state->net->ct.sysctl_checksum && state->hook == NF_INET_PRE_ROUTING && nf_ip_checksum(skb, state->hook, dataoff, IPPROTO_ICMP)) { icmp_error_log(skb, state, "bad hw icmp checksum"); return -NF_ACCEPT; } /* * 18 is the highest 'known' ICMP type. Anything else is a mystery * * RFC 1122: 3.2.2 Unknown ICMP messages types MUST be silently * discarded. */ if (icmph->type > NR_ICMP_TYPES) { icmp_error_log(skb, state, "invalid icmp type"); return -NF_ACCEPT; } /* Need to track icmp error message? */ if (!icmp_is_err(icmph->type)) return NF_ACCEPT; memset(&outer_daddr, 0, sizeof(outer_daddr)); outer_daddr.ip = ip_hdr(skb)->daddr; dataoff += sizeof(*icmph); return nf_conntrack_inet_error(tmpl, skb, dataoff, state, IPPROTO_ICMP, &outer_daddr); } #if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> static int icmp_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *t) { if (nla_put_be16(skb, CTA_PROTO_ICMP_ID, t->src.u.icmp.id) || nla_put_u8(skb, CTA_PROTO_ICMP_TYPE, t->dst.u.icmp.type) || nla_put_u8(skb, CTA_PROTO_ICMP_CODE, t->dst.u.icmp.code)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static const struct nla_policy icmp_nla_policy[CTA_PROTO_MAX+1] = { [CTA_PROTO_ICMP_TYPE] = { .type = NLA_U8 }, [CTA_PROTO_ICMP_CODE] = { .type = NLA_U8 }, [CTA_PROTO_ICMP_ID] = { .type = NLA_U16 }, }; static int icmp_nlattr_to_tuple(struct nlattr *tb[], struct nf_conntrack_tuple *tuple, u_int32_t flags) { if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_TYPE)) { if (!tb[CTA_PROTO_ICMP_TYPE]) return -EINVAL; tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMP_TYPE]); if (tuple->dst.u.icmp.type >= sizeof(invmap) || !invmap[tuple->dst.u.icmp.type]) return -EINVAL; } if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_CODE)) { if (!tb[CTA_PROTO_ICMP_CODE]) return -EINVAL; tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMP_CODE]); } if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_ID)) { if (!tb[CTA_PROTO_ICMP_ID]) return -EINVAL; tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMP_ID]); } return 0; } static unsigned int icmp_nlattr_tuple_size(void) { static unsigned int size __read_mostly; if (!size) size = nla_policy_len(icmp_nla_policy, CTA_PROTO_MAX + 1); return size; } #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeout = data; struct nf_icmp_net *in = nf_icmp_pernet(net); if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) { if (!timeout) timeout = &in->timeout; *timeout = ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMP_TIMEOUT])) * HZ; } else if (timeout) { /* Set default ICMP timeout. */ *timeout = in->timeout; } return 0; } static int icmp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) { const unsigned int *timeout = data; if (nla_put_be32(skb, CTA_TIMEOUT_ICMP_TIMEOUT, htonl(*timeout / HZ))) goto nla_put_failure; return 0; nla_put_failure: return -ENOSPC; } static const struct nla_policy icmp_timeout_nla_policy[CTA_TIMEOUT_ICMP_MAX+1] = { [CTA_TIMEOUT_ICMP_TIMEOUT] = { .type = NLA_U32 }, }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ void nf_conntrack_icmp_init_net(struct net *net) { struct nf_icmp_net *in = nf_icmp_pernet(net); in->timeout = nf_ct_icmp_timeout; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = { .l4proto = IPPROTO_ICMP, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = icmp_tuple_to_nlattr, .nlattr_tuple_size = icmp_nlattr_tuple_size, .nlattr_to_tuple = icmp_nlattr_to_tuple, .nla_policy = icmp_nla_policy, #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = icmp_timeout_nlattr_to_obj, .obj_to_nlattr = icmp_timeout_obj_to_nlattr, .nlattr_max = CTA_TIMEOUT_ICMP_MAX, .obj_size = sizeof(unsigned int), .nla_policy = icmp_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ }; |
| 515 515 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * drivers/base/dd.c - The core device/driver interactions. * * This file contains the (sometimes tricky) code that controls the * interactions between devices and drivers, which primarily includes * driver binding and unbinding. * * All of this code used to exist in drivers/base/bus.c, but was * relocated to here in the name of compartmentalization (since it wasn't * strictly code just for the 'struct bus_type'. * * Copyright (c) 2002-5 Patrick Mochel * Copyright (c) 2002-3 Open Source Development Labs * Copyright (c) 2007-2009 Greg Kroah-Hartman <gregkh@suse.de> * Copyright (c) 2007-2009 Novell Inc. */ #include <linux/debugfs.h> #include <linux/device.h> #include <linux/delay.h> #include <linux/dma-map-ops.h> #include <linux/init.h> #include <linux/module.h> #include <linux/kthread.h> #include <linux/wait.h> #include <linux/async.h> #include <linux/pm_runtime.h> #include <linux/pinctrl/devinfo.h> #include <linux/slab.h> #include "base.h" #include "power/power.h" /* * Deferred Probe infrastructure. * * Sometimes driver probe order matters, but the kernel doesn't always have * dependency information which means some drivers will get probed before a * resource it depends on is available. For example, an SDHCI driver may * first need a GPIO line from an i2c GPIO controller before it can be * initialized. If a required resource is not available yet, a driver can * request probing to be deferred by returning -EPROBE_DEFER from its probe hook * * Deferred probe maintains two lists of devices, a pending list and an active * list. A driver returning -EPROBE_DEFER causes the device to be added to the * pending list. A successful driver probe will trigger moving all devices * from the pending to the active list so that the workqueue will eventually * retry them. * * The deferred_probe_mutex must be held any time the deferred_probe_*_list * of the (struct device*)->p->deferred_probe pointers are manipulated */ static DEFINE_MUTEX(deferred_probe_mutex); static LIST_HEAD(deferred_probe_pending_list); static LIST_HEAD(deferred_probe_active_list); static atomic_t deferred_trigger_count = ATOMIC_INIT(0); static bool initcalls_done; /* Save the async probe drivers' name from kernel cmdline */ #define ASYNC_DRV_NAMES_MAX_LEN 256 static char async_probe_drv_names[ASYNC_DRV_NAMES_MAX_LEN]; static bool async_probe_default; /* * In some cases, like suspend to RAM or hibernation, It might be reasonable * to prohibit probing of devices as it could be unsafe. * Once defer_all_probes is true all drivers probes will be forcibly deferred. */ static bool defer_all_probes; static void __device_set_deferred_probe_reason(const struct device *dev, char *reason) { kfree(dev->p->deferred_probe_reason); dev->p->deferred_probe_reason = reason; } /* * deferred_probe_work_func() - Retry probing devices in the active list. */ static void deferred_probe_work_func(struct work_struct *work) { struct device *dev; struct device_private *private; /* * This block processes every device in the deferred 'active' list. * Each device is removed from the active list and passed to * bus_probe_device() to re-attempt the probe. The loop continues * until every device in the active list is removed and retried. * * Note: Once the device is removed from the list and the mutex is * released, it is possible for the device get freed by another thread * and cause a illegal pointer dereference. This code uses * get/put_device() to ensure the device structure cannot disappear * from under our feet. */ mutex_lock(&deferred_probe_mutex); while (!list_empty(&deferred_probe_active_list)) { private = list_first_entry(&deferred_probe_active_list, typeof(*dev->p), deferred_probe); dev = private->device; list_del_init(&private->deferred_probe); get_device(dev); __device_set_deferred_probe_reason(dev, NULL); /* * Drop the mutex while probing each device; the probe path may * manipulate the deferred list */ mutex_unlock(&deferred_probe_mutex); /* * Force the device to the end of the dpm_list since * the PM code assumes that the order we add things to * the list is a good order for suspend but deferred * probe makes that very unsafe. */ device_pm_move_to_tail(dev); dev_dbg(dev, "Retrying from deferred list\n"); bus_probe_device(dev); mutex_lock(&deferred_probe_mutex); put_device(dev); } mutex_unlock(&deferred_probe_mutex); } static DECLARE_WORK(deferred_probe_work, deferred_probe_work_func); void driver_deferred_probe_add(struct device *dev) { if (!dev->can_match) return; mutex_lock(&deferred_probe_mutex); if (list_empty(&dev->p->deferred_probe)) { dev_dbg(dev, "Added to deferred list\n"); list_add_tail(&dev->p->deferred_probe, &deferred_probe_pending_list); } mutex_unlock(&deferred_probe_mutex); } void driver_deferred_probe_del(struct device *dev) { mutex_lock(&deferred_probe_mutex); if (!list_empty(&dev->p->deferred_probe)) { dev_dbg(dev, "Removed from deferred list\n"); list_del_init(&dev->p->deferred_probe); __device_set_deferred_probe_reason(dev, NULL); } mutex_unlock(&deferred_probe_mutex); } static bool driver_deferred_probe_enable; /** * driver_deferred_probe_trigger() - Kick off re-probing deferred devices * * This functions moves all devices from the pending list to the active * list and schedules the deferred probe workqueue to process them. It * should be called anytime a driver is successfully bound to a device. * * Note, there is a race condition in multi-threaded probe. In the case where * more than one device is probing at the same time, it is possible for one * probe to complete successfully while another is about to defer. If the second * depends on the first, then it will get put on the pending list after the * trigger event has already occurred and will be stuck there. * * The atomic 'deferred_trigger_count' is used to determine if a successful * trigger has occurred in the midst of probing a driver. If the trigger count * changes in the midst of a probe, then deferred processing should be triggered * again. */ void driver_deferred_probe_trigger(void) { if (!driver_deferred_probe_enable) return; /* * A successful probe means that all the devices in the pending list * should be triggered to be reprobed. Move all the deferred devices * into the active list so they can be retried by the workqueue */ mutex_lock(&deferred_probe_mutex); atomic_inc(&deferred_trigger_count); list_splice_tail_init(&deferred_probe_pending_list, &deferred_probe_active_list); mutex_unlock(&deferred_probe_mutex); /* * Kick the re-probe thread. It may already be scheduled, but it is * safe to kick it again. */ queue_work(system_unbound_wq, &deferred_probe_work); } /** * device_block_probing() - Block/defer device's probes * * It will disable probing of devices and defer their probes instead. */ void device_block_probing(void) { defer_all_probes = true; /* sync with probes to avoid races. */ wait_for_device_probe(); } /** * device_unblock_probing() - Unblock/enable device's probes * * It will restore normal behavior and trigger re-probing of deferred * devices. */ void device_unblock_probing(void) { defer_all_probes = false; driver_deferred_probe_trigger(); } /** * device_set_deferred_probe_reason() - Set defer probe reason message for device * @dev: the pointer to the struct device * @vaf: the pointer to va_format structure with message */ void device_set_deferred_probe_reason(const struct device *dev, struct va_format *vaf) { const char *drv = dev_driver_string(dev); char *reason; mutex_lock(&deferred_probe_mutex); reason = kasprintf(GFP_KERNEL, "%s: %pV", drv, vaf); __device_set_deferred_probe_reason(dev, reason); mutex_unlock(&deferred_probe_mutex); } /* * deferred_devs_show() - Show the devices in the deferred probe pending list. */ static int deferred_devs_show(struct seq_file *s, void *data) { struct device_private *curr; mutex_lock(&deferred_probe_mutex); list_for_each_entry(curr, &deferred_probe_pending_list, deferred_probe) seq_printf(s, "%s\t%s", dev_name(curr->device), curr->device->p->deferred_probe_reason ?: "\n"); mutex_unlock(&deferred_probe_mutex); return 0; } DEFINE_SHOW_ATTRIBUTE(deferred_devs); #ifdef CONFIG_MODULES int driver_deferred_probe_timeout = 10; #else int driver_deferred_probe_timeout; #endif EXPORT_SYMBOL_GPL(driver_deferred_probe_timeout); static int __init deferred_probe_timeout_setup(char *str) { int timeout; if (!kstrtoint(str, 10, &timeout)) driver_deferred_probe_timeout = timeout; return 1; } __setup("deferred_probe_timeout=", deferred_probe_timeout_setup); /** * driver_deferred_probe_check_state() - Check deferred probe state * @dev: device to check * * Return: * * -ENODEV if initcalls have completed and modules are disabled. * * -ETIMEDOUT if the deferred probe timeout was set and has expired * and modules are enabled. * * -EPROBE_DEFER in other cases. * * Drivers or subsystems can opt-in to calling this function instead of directly * returning -EPROBE_DEFER. */ int driver_deferred_probe_check_state(struct device *dev) { if (!IS_ENABLED(CONFIG_MODULES) && initcalls_done) { dev_warn(dev, "ignoring dependency for device, assuming no driver\n"); return -ENODEV; } if (!driver_deferred_probe_timeout && initcalls_done) { dev_warn(dev, "deferred probe timeout, ignoring dependency\n"); return -ETIMEDOUT; } return -EPROBE_DEFER; } EXPORT_SYMBOL_GPL(driver_deferred_probe_check_state); static void deferred_probe_timeout_work_func(struct work_struct *work) { struct device_private *p; fw_devlink_drivers_done(); driver_deferred_probe_timeout = 0; driver_deferred_probe_trigger(); flush_work(&deferred_probe_work); mutex_lock(&deferred_probe_mutex); list_for_each_entry(p, &deferred_probe_pending_list, deferred_probe) dev_info(p->device, "deferred probe pending\n"); mutex_unlock(&deferred_probe_mutex); } static DECLARE_DELAYED_WORK(deferred_probe_timeout_work, deferred_probe_timeout_work_func); void deferred_probe_extend_timeout(void) { /* * If the work hasn't been queued yet or if the work expired, don't * start a new one. */ if (cancel_delayed_work(&deferred_probe_timeout_work)) { schedule_delayed_work(&deferred_probe_timeout_work, driver_deferred_probe_timeout * HZ); pr_debug("Extended deferred probe timeout by %d secs\n", driver_deferred_probe_timeout); } } /** * deferred_probe_initcall() - Enable probing of deferred devices * * We don't want to get in the way when the bulk of drivers are getting probed. * Instead, this initcall makes sure that deferred probing is delayed until * late_initcall time. */ static int deferred_probe_initcall(void) { debugfs_create_file("devices_deferred", 0444, NULL, NULL, &deferred_devs_fops); driver_deferred_probe_enable = true; driver_deferred_probe_trigger(); /* Sort as many dependencies as possible before exiting initcalls */ flush_work(&deferred_probe_work); initcalls_done = true; if (!IS_ENABLED(CONFIG_MODULES)) fw_devlink_drivers_done(); /* * Trigger deferred probe again, this time we won't defer anything * that is optional */ driver_deferred_probe_trigger(); flush_work(&deferred_probe_work); if (driver_deferred_probe_timeout > 0) { schedule_delayed_work(&deferred_probe_timeout_work, driver_deferred_probe_timeout * HZ); } return 0; } late_initcall(deferred_probe_initcall); static void __exit deferred_probe_exit(void) { debugfs_lookup_and_remove("devices_deferred", NULL); } __exitcall(deferred_probe_exit); /** * device_is_bound() - Check if device is bound to a driver * @dev: device to check * * Returns true if passed device has already finished probing successfully * against a driver. * * This function must be called with the device lock held. */ bool device_is_bound(struct device *dev) { return dev->p && klist_node_attached(&dev->p->knode_driver); } static void driver_bound(struct device *dev) { if (device_is_bound(dev)) { pr_warn("%s: device %s already bound\n", __func__, kobject_name(&dev->kobj)); return; } pr_debug("driver: '%s': %s: bound to device '%s'\n", dev->driver->name, __func__, dev_name(dev)); klist_add_tail(&dev->p->knode_driver, &dev->driver->p->klist_devices); device_links_driver_bound(dev); device_pm_check_callbacks(dev); /* * Make sure the device is no longer in one of the deferred lists and * kick off retrying all pending devices */ driver_deferred_probe_del(dev); driver_deferred_probe_trigger(); if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_BOUND_DRIVER, dev); kobject_uevent(&dev->kobj, KOBJ_BIND); } static ssize_t coredump_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { device_lock(dev); dev->driver->coredump(dev); device_unlock(dev); return count; } static DEVICE_ATTR_WO(coredump); static int driver_sysfs_add(struct device *dev) { int ret; if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_BIND_DRIVER, dev); ret = sysfs_create_link(&dev->driver->p->kobj, &dev->kobj, kobject_name(&dev->kobj)); if (ret) goto fail; ret = sysfs_create_link(&dev->kobj, &dev->driver->p->kobj, "driver"); if (ret) goto rm_dev; if (!IS_ENABLED(CONFIG_DEV_COREDUMP) || !dev->driver->coredump) return 0; ret = device_create_file(dev, &dev_attr_coredump); if (!ret) return 0; sysfs_remove_link(&dev->kobj, "driver"); rm_dev: sysfs_remove_link(&dev->driver->p->kobj, kobject_name(&dev->kobj)); fail: return ret; } static void driver_sysfs_remove(struct device *dev) { struct device_driver *drv = dev->driver; if (drv) { if (drv->coredump) device_remove_file(dev, &dev_attr_coredump); sysfs_remove_link(&drv->p->kobj, kobject_name(&dev->kobj)); sysfs_remove_link(&dev->kobj, "driver"); } } /** * device_bind_driver - bind a driver to one device. * @dev: device. * * Allow manual attachment of a driver to a device. * Caller must have already set @dev->driver. * * Note that this does not modify the bus reference count. * Please verify that is accounted for before calling this. * (It is ok to call with no other effort from a driver's probe() method.) * * This function must be called with the device lock held. * * Callers should prefer to use device_driver_attach() instead. */ int device_bind_driver(struct device *dev) { int ret; ret = driver_sysfs_add(dev); if (!ret) { device_links_force_bind(dev); driver_bound(dev); } else if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_DRIVER_NOT_BOUND, dev); return ret; } EXPORT_SYMBOL_GPL(device_bind_driver); static atomic_t probe_count = ATOMIC_INIT(0); static DECLARE_WAIT_QUEUE_HEAD(probe_waitqueue); static ssize_t state_synced_show(struct device *dev, struct device_attribute *attr, char *buf) { bool val; device_lock(dev); val = dev->state_synced; device_unlock(dev); return sysfs_emit(buf, "%u\n", val); } static DEVICE_ATTR_RO(state_synced); static void device_unbind_cleanup(struct device *dev) { devres_release_all(dev); arch_teardown_dma_ops(dev); kfree(dev->dma_range_map); dev->dma_range_map = NULL; dev->driver = NULL; dev_set_drvdata(dev, NULL); if (dev->pm_domain && dev->pm_domain->dismiss) dev->pm_domain->dismiss(dev); pm_runtime_reinit(dev); dev_pm_set_driver_flags(dev, 0); } static void device_remove(struct device *dev) { device_remove_file(dev, &dev_attr_state_synced); device_remove_groups(dev, dev->driver->dev_groups); if (dev->bus && dev->bus->remove) dev->bus->remove(dev); else if (dev->driver->remove) dev->driver->remove(dev); } static int call_driver_probe(struct device *dev, struct device_driver *drv) { int ret = 0; if (dev->bus->probe) ret = dev->bus->probe(dev); else if (drv->probe) ret = drv->probe(dev); switch (ret) { case 0: break; case -EPROBE_DEFER: /* Driver requested deferred probing */ dev_dbg(dev, "Driver %s requests probe deferral\n", drv->name); break; case -ENODEV: case -ENXIO: pr_debug("%s: probe of %s rejects match %d\n", drv->name, dev_name(dev), ret); break; default: /* driver matched but the probe failed */ pr_warn("%s: probe of %s failed with error %d\n", drv->name, dev_name(dev), ret); break; } return ret; } static int really_probe(struct device *dev, struct device_driver *drv) { bool test_remove = IS_ENABLED(CONFIG_DEBUG_TEST_DRIVER_REMOVE) && !drv->suppress_bind_attrs; int ret, link_ret; if (defer_all_probes) { /* * Value of defer_all_probes can be set only by * device_block_probing() which, in turn, will call * wait_for_device_probe() right after that to avoid any races. */ dev_dbg(dev, "Driver %s force probe deferral\n", drv->name); return -EPROBE_DEFER; } link_ret = device_links_check_suppliers(dev); if (link_ret == -EPROBE_DEFER) return link_ret; pr_debug("bus: '%s': %s: probing driver %s with device %s\n", drv->bus->name, __func__, drv->name, dev_name(dev)); if (!list_empty(&dev->devres_head)) { dev_crit(dev, "Resources present before probing\n"); ret = -EBUSY; goto done; } re_probe: dev->driver = drv; /* If using pinctrl, bind pins now before probing */ ret = pinctrl_bind_pins(dev); if (ret) goto pinctrl_bind_failed; if (dev->bus->dma_configure) { ret = dev->bus->dma_configure(dev); if (ret) goto pinctrl_bind_failed; } ret = driver_sysfs_add(dev); if (ret) { pr_err("%s: driver_sysfs_add(%s) failed\n", __func__, dev_name(dev)); goto sysfs_failed; } if (dev->pm_domain && dev->pm_domain->activate) { ret = dev->pm_domain->activate(dev); if (ret) goto probe_failed; } ret = call_driver_probe(dev, drv); if (ret) { /* * If fw_devlink_best_effort is active (denoted by -EAGAIN), the * device might actually probe properly once some of its missing * suppliers have probed. So, treat this as if the driver * returned -EPROBE_DEFER. */ if (link_ret == -EAGAIN) ret = -EPROBE_DEFER; /* * Return probe errors as positive values so that the callers * can distinguish them from other errors. */ ret = -ret; goto probe_failed; } ret = device_add_groups(dev, drv->dev_groups); if (ret) { dev_err(dev, "device_add_groups() failed\n"); goto dev_groups_failed; } if (dev_has_sync_state(dev)) { ret = device_create_file(dev, &dev_attr_state_synced); if (ret) { dev_err(dev, "state_synced sysfs add failed\n"); goto dev_sysfs_state_synced_failed; } } if (test_remove) { test_remove = false; device_remove(dev); driver_sysfs_remove(dev); if (dev->bus && dev->bus->dma_cleanup) dev->bus->dma_cleanup(dev); device_unbind_cleanup(dev); goto re_probe; } pinctrl_init_done(dev); if (dev->pm_domain && dev->pm_domain->sync) dev->pm_domain->sync(dev); driver_bound(dev); pr_debug("bus: '%s': %s: bound device %s to driver %s\n", drv->bus->name, __func__, dev_name(dev), drv->name); goto done; dev_sysfs_state_synced_failed: dev_groups_failed: device_remove(dev); probe_failed: driver_sysfs_remove(dev); sysfs_failed: if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_DRIVER_NOT_BOUND, dev); if (dev->bus && dev->bus->dma_cleanup) dev->bus->dma_cleanup(dev); pinctrl_bind_failed: device_links_no_driver(dev); device_unbind_cleanup(dev); done: return ret; } /* * For initcall_debug, show the driver probe time. */ static int really_probe_debug(struct device *dev, struct device_driver *drv) { ktime_t calltime, rettime; int ret; calltime = ktime_get(); ret = really_probe(dev, drv); rettime = ktime_get(); /* * Don't change this to pr_debug() because that requires * CONFIG_DYNAMIC_DEBUG and we want a simple 'initcall_debug' on the * kernel commandline to print this all the time at the debug level. */ printk(KERN_DEBUG "probe of %s returned %d after %lld usecs\n", dev_name(dev), ret, ktime_us_delta(rettime, calltime)); return ret; } /** * driver_probe_done * Determine if the probe sequence is finished or not. * * Should somehow figure out how to use a semaphore, not an atomic variable... */ int driver_probe_done(void) { int local_probe_count = atomic_read(&probe_count); pr_debug("%s: probe_count = %d\n", __func__, local_probe_count); if (local_probe_count) return -EBUSY; return 0; } /** * wait_for_device_probe * Wait for device probing to be completed. */ void wait_for_device_probe(void) { /* wait for the deferred probe workqueue to finish */ flush_work(&deferred_probe_work); /* wait for the known devices to complete their probing */ wait_event(probe_waitqueue, atomic_read(&probe_count) == 0); async_synchronize_full(); } EXPORT_SYMBOL_GPL(wait_for_device_probe); /** * flush_deferred_probe_now * * This function should be used sparingly. It's meant for when we need to flush * the deferred probe list at earlier initcall levels. Really meant only for KVM * needs. This function should never be exported because it makes no sense for * modules to call this. */ void flush_deferred_probe_now(void) { /* * Really shouldn't using this if deferred probe has already been * enabled */ if (WARN_ON(driver_deferred_probe_enable)) return; driver_deferred_probe_enable = true; driver_deferred_probe_trigger(); wait_for_device_probe(); driver_deferred_probe_enable = false; } static int __driver_probe_device(struct device_driver *drv, struct device *dev) { int ret = 0; if (dev->p->dead || !device_is_registered(dev)) return -ENODEV; if (dev->driver) return -EBUSY; dev->can_match = true; pr_debug("bus: '%s': %s: matched device %s with driver %s\n", drv->bus->name, __func__, dev_name(dev), drv->name); pm_runtime_get_suppliers(dev); if (dev->parent) pm_runtime_get_sync(dev->parent); pm_runtime_barrier(dev); if (initcall_debug) ret = really_probe_debug(dev, drv); else ret = really_probe(dev, drv); pm_request_idle(dev); if (dev->parent) pm_runtime_put(dev->parent); pm_runtime_put_suppliers(dev); return ret; } /** * driver_probe_device - attempt to bind device & driver together * @drv: driver to bind a device to * @dev: device to try to bind to the driver * * This function returns -ENODEV if the device is not registered, -EBUSY if it * already has a driver, 0 if the device is bound successfully and a positive * (inverted) error code for failures from the ->probe method. * * This function must be called with @dev lock held. When called for a * USB interface, @dev->parent lock must be held as well. * * If the device has a parent, runtime-resume the parent before driver probing. */ static int driver_probe_device(struct device_driver *drv, struct device *dev) { int trigger_count = atomic_read(&deferred_trigger_count); int ret; atomic_inc(&probe_count); ret = __driver_probe_device(drv, dev); if (ret == -EPROBE_DEFER || ret == EPROBE_DEFER) { driver_deferred_probe_add(dev); /* * Did a trigger occur while probing? Need to re-trigger if yes */ if (trigger_count != atomic_read(&deferred_trigger_count) && !defer_all_probes) driver_deferred_probe_trigger(); } atomic_dec(&probe_count); wake_up_all(&probe_waitqueue); return ret; } static inline bool cmdline_requested_async_probing(const char *drv_name) { bool async_drv; async_drv = parse_option_str(async_probe_drv_names, drv_name); return (async_probe_default != async_drv); } /* The option format is "driver_async_probe=drv_name1,drv_name2,..." */ static int __init save_async_options(char *buf) { if (strlen(buf) >= ASYNC_DRV_NAMES_MAX_LEN) pr_warn("Too long list of driver names for 'driver_async_probe'!\n"); strscpy(async_probe_drv_names, buf, ASYNC_DRV_NAMES_MAX_LEN); async_probe_default = parse_option_str(async_probe_drv_names, "*"); return 1; } __setup("driver_async_probe=", save_async_options); bool driver_allows_async_probing(struct device_driver *drv) { switch (drv->probe_type) { case PROBE_PREFER_ASYNCHRONOUS: return true; case PROBE_FORCE_SYNCHRONOUS: return false; default: if (cmdline_requested_async_probing(drv->name)) return true; if (module_requested_async_probing(drv->owner)) return true; return false; } } struct device_attach_data { struct device *dev; /* * Indicates whether we are considering asynchronous probing or * not. Only initial binding after device or driver registration * (including deferral processing) may be done asynchronously, the * rest is always synchronous, as we expect it is being done by * request from userspace. */ bool check_async; /* * Indicates if we are binding synchronous or asynchronous drivers. * When asynchronous probing is enabled we'll execute 2 passes * over drivers: first pass doing synchronous probing and second * doing asynchronous probing (if synchronous did not succeed - * most likely because there was no driver requiring synchronous * probing - and we found asynchronous driver during first pass). * The 2 passes are done because we can't shoot asynchronous * probe for given device and driver from bus_for_each_drv() since * driver pointer is not guaranteed to stay valid once * bus_for_each_drv() iterates to the next driver on the bus. */ bool want_async; /* * We'll set have_async to 'true' if, while scanning for matching * driver, we'll encounter one that requests asynchronous probing. */ bool have_async; }; static int __device_attach_driver(struct device_driver *drv, void *_data) { struct device_attach_data *data = _data; struct device *dev = data->dev; bool async_allowed; int ret; ret = driver_match_device(drv, dev); if (ret == 0) { /* no match */ return 0; } else if (ret == -EPROBE_DEFER) { dev_dbg(dev, "Device match requests probe deferral\n"); dev->can_match = true; driver_deferred_probe_add(dev); /* * Device can't match with a driver right now, so don't attempt * to match or bind with other drivers on the bus. */ return ret; } else if (ret < 0) { dev_dbg(dev, "Bus failed to match device: %d\n", ret); return ret; } /* ret > 0 means positive match */ async_allowed = driver_allows_async_probing(drv); if (async_allowed) data->have_async = true; if (data->check_async && async_allowed != data->want_async) return 0; /* * Ignore errors returned by ->probe so that the next driver can try * its luck. */ ret = driver_probe_device(drv, dev); if (ret < 0) return ret; return ret == 0; } static void __device_attach_async_helper(void *_dev, async_cookie_t cookie) { struct device *dev = _dev; struct device_attach_data data = { .dev = dev, .check_async = true, .want_async = true, }; device_lock(dev); /* * Check if device has already been removed or claimed. This may * happen with driver loading, device discovery/registration, * and deferred probe processing happens all at once with * multiple threads. */ if (dev->p->dead || dev->driver) goto out_unlock; if (dev->parent) pm_runtime_get_sync(dev->parent); bus_for_each_drv(dev->bus, NULL, &data, __device_attach_driver); dev_dbg(dev, "async probe completed\n"); pm_request_idle(dev); if (dev->parent) pm_runtime_put(dev->parent); out_unlock: device_unlock(dev); put_device(dev); } static int __device_attach(struct device *dev, bool allow_async) { int ret = 0; bool async = false; device_lock(dev); if (dev->p->dead) { goto out_unlock; } else if (dev->driver) { if (device_is_bound(dev)) { ret = 1; goto out_unlock; } ret = device_bind_driver(dev); if (ret == 0) ret = 1; else { dev->driver = NULL; ret = 0; } } else { struct device_attach_data data = { .dev = dev, .check_async = allow_async, .want_async = false, }; if (dev->parent) pm_runtime_get_sync(dev->parent); ret = bus_for_each_drv(dev->bus, NULL, &data, __device_attach_driver); if (!ret && allow_async && data.have_async) { /* * If we could not find appropriate driver * synchronously and we are allowed to do * async probes and there are drivers that * want to probe asynchronously, we'll * try them. */ dev_dbg(dev, "scheduling asynchronous probe\n"); get_device(dev); async = true; } else { pm_request_idle(dev); } if (dev->parent) pm_runtime_put(dev->parent); } out_unlock: device_unlock(dev); if (async) async_schedule_dev(__device_attach_async_helper, dev); return ret; } /** * device_attach - try to attach device to a driver. * @dev: device. * * Walk the list of drivers that the bus has and call * driver_probe_device() for each pair. If a compatible * pair is found, break out and return. * * Returns 1 if the device was bound to a driver; * 0 if no matching driver was found; * -ENODEV if the device is not registered. * * When called for a USB interface, @dev->parent lock must be held. */ int device_attach(struct device *dev) { return __device_attach(dev, false); } EXPORT_SYMBOL_GPL(device_attach); void device_initial_probe(struct device *dev) { __device_attach(dev, true); } /* * __device_driver_lock - acquire locks needed to manipulate dev->drv * @dev: Device we will update driver info for * @parent: Parent device. Needed if the bus requires parent lock * * This function will take the required locks for manipulating dev->drv. * Normally this will just be the @dev lock, but when called for a USB * interface, @parent lock will be held as well. */ static void __device_driver_lock(struct device *dev, struct device *parent) { if (parent && dev->bus->need_parent_lock) device_lock(parent); device_lock(dev); } /* * __device_driver_unlock - release locks needed to manipulate dev->drv * @dev: Device we will update driver info for * @parent: Parent device. Needed if the bus requires parent lock * * This function will release the required locks for manipulating dev->drv. * Normally this will just be the @dev lock, but when called for a * USB interface, @parent lock will be released as well. */ static void __device_driver_unlock(struct device *dev, struct device *parent) { device_unlock(dev); if (parent && dev->bus->need_parent_lock) device_unlock(parent); } /** * device_driver_attach - attach a specific driver to a specific device * @drv: Driver to attach * @dev: Device to attach it to * * Manually attach driver to a device. Will acquire both @dev lock and * @dev->parent lock if needed. Returns 0 on success, -ERR on failure. */ int device_driver_attach(struct device_driver *drv, struct device *dev) { int ret; __device_driver_lock(dev, dev->parent); ret = __driver_probe_device(drv, dev); __device_driver_unlock(dev, dev->parent); /* also return probe errors as normal negative errnos */ if (ret > 0) ret = -ret; if (ret == -EPROBE_DEFER) return -EAGAIN; return ret; } EXPORT_SYMBOL_GPL(device_driver_attach); static void __driver_attach_async_helper(void *_dev, async_cookie_t cookie) { struct device *dev = _dev; struct device_driver *drv; int ret; __device_driver_lock(dev, dev->parent); drv = dev->p->async_driver; dev->p->async_driver = NULL; ret = driver_probe_device(drv, dev); __device_driver_unlock(dev, dev->parent); dev_dbg(dev, "driver %s async attach completed: %d\n", drv->name, ret); put_device(dev); } static int __driver_attach(struct device *dev, void *data) { struct device_driver *drv = data; bool async = false; int ret; /* * Lock device and try to bind to it. We drop the error * here and always return 0, because we need to keep trying * to bind to devices and some drivers will return an error * simply if it didn't support the device. * * driver_probe_device() will spit a warning if there * is an error. */ ret = driver_match_device(drv, dev); if (ret == 0) { /* no match */ return 0; } else if (ret == -EPROBE_DEFER) { dev_dbg(dev, "Device match requests probe deferral\n"); dev->can_match = true; driver_deferred_probe_add(dev); /* * Driver could not match with device, but may match with * another device on the bus. */ return 0; } else if (ret < 0) { dev_dbg(dev, "Bus failed to match device: %d\n", ret); /* * Driver could not match with device, but may match with * another device on the bus. */ return 0; } /* ret > 0 means positive match */ if (driver_allows_async_probing(drv)) { /* * Instead of probing the device synchronously we will * probe it asynchronously to allow for more parallelism. * * We only take the device lock here in order to guarantee * that the dev->driver and async_driver fields are protected */ dev_dbg(dev, "probing driver %s asynchronously\n", drv->name); device_lock(dev); if (!dev->driver && !dev->p->async_driver) { get_device(dev); dev->p->async_driver = drv; async = true; } device_unlock(dev); if (async) async_schedule_dev(__driver_attach_async_helper, dev); return 0; } __device_driver_lock(dev, dev->parent); driver_probe_device(drv, dev); __device_driver_unlock(dev, dev->parent); return 0; } /** * driver_attach - try to bind driver to devices. * @drv: driver. * * Walk the list of devices that the bus has on it and try to * match the driver with each one. If driver_probe_device() * returns 0 and the @dev->driver is set, we've found a * compatible pair. */ int driver_attach(struct device_driver *drv) { return bus_for_each_dev(drv->bus, NULL, drv, __driver_attach); } EXPORT_SYMBOL_GPL(driver_attach); /* * __device_release_driver() must be called with @dev lock held. * When called for a USB interface, @dev->parent lock must be held as well. */ static void __device_release_driver(struct device *dev, struct device *parent) { struct device_driver *drv; drv = dev->driver; if (drv) { pm_runtime_get_sync(dev); while (device_links_busy(dev)) { __device_driver_unlock(dev, parent); device_links_unbind_consumers(dev); __device_driver_lock(dev, parent); /* * A concurrent invocation of the same function might * have released the driver successfully while this one * was waiting, so check for that. */ if (dev->driver != drv) { pm_runtime_put(dev); return; } } driver_sysfs_remove(dev); if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_UNBIND_DRIVER, dev); pm_runtime_put_sync(dev); device_remove(dev); if (dev->bus && dev->bus->dma_cleanup) dev->bus->dma_cleanup(dev); device_unbind_cleanup(dev); device_links_driver_cleanup(dev); klist_remove(&dev->p->knode_driver); device_pm_check_callbacks(dev); if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_UNBOUND_DRIVER, dev); kobject_uevent(&dev->kobj, KOBJ_UNBIND); } } void device_release_driver_internal(struct device *dev, struct device_driver *drv, struct device *parent) { __device_driver_lock(dev, parent); if (!drv || drv == dev->driver) __device_release_driver(dev, parent); __device_driver_unlock(dev, parent); } /** * device_release_driver - manually detach device from driver. * @dev: device. * * Manually detach device from driver. * When called for a USB interface, @dev->parent lock must be held. * * If this function is to be called with @dev->parent lock held, ensure that * the device's consumers are unbound in advance or that their locks can be * acquired under the @dev->parent lock. */ void device_release_driver(struct device *dev) { /* * If anyone calls device_release_driver() recursively from * within their ->remove callback for the same device, they * will deadlock right here. */ device_release_driver_internal(dev, NULL, NULL); } EXPORT_SYMBOL_GPL(device_release_driver); /** * device_driver_detach - detach driver from a specific device * @dev: device to detach driver from * * Detach driver from device. Will acquire both @dev lock and @dev->parent * lock if needed. */ void device_driver_detach(struct device *dev) { device_release_driver_internal(dev, NULL, dev->parent); } /** * driver_detach - detach driver from all devices it controls. * @drv: driver. */ void driver_detach(struct device_driver *drv) { struct device_private *dev_prv; struct device *dev; if (driver_allows_async_probing(drv)) async_synchronize_full(); for (;;) { spin_lock(&drv->p->klist_devices.k_lock); if (list_empty(&drv->p->klist_devices.k_list)) { spin_unlock(&drv->p->klist_devices.k_lock); break; } dev_prv = list_last_entry(&drv->p->klist_devices.k_list, struct device_private, knode_driver.n_node); dev = dev_prv->device; get_device(dev); spin_unlock(&drv->p->klist_devices.k_lock); device_release_driver_internal(dev, drv, dev->parent); put_device(dev); } } |
| 374 376 376 376 374 375 374 375 375 375 374 375 640 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Packet matching code. * * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling * Copyright (C) 2000-2005 Netfilter Core Team <coreteam@netfilter.org> * Copyright (c) 2006-2010 Patrick McHardy <kaber@trash.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/capability.h> #include <linux/in.h> #include <linux/skbuff.h> #include <linux/kmod.h> #include <linux/vmalloc.h> #include <linux/netdevice.h> #include <linux/module.h> #include <linux/poison.h> #include <linux/icmpv6.h> #include <net/ipv6.h> #include <net/compat.h> #include <linux/uaccess.h> #include <linux/mutex.h> #include <linux/proc_fs.h> #include <linux/err.h> #include <linux/cpumask.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter/x_tables.h> #include <net/netfilter/nf_log.h> #include "../../netfilter/xt_repldata.h" MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("IPv6 packet filter"); MODULE_ALIAS("ip6t_icmp6"); void *ip6t_alloc_initial_table(const struct xt_table *info) { return xt_alloc_initial_table(ip6t, IP6T); } EXPORT_SYMBOL_GPL(ip6t_alloc_initial_table); /* Returns whether matches rule or not. */ /* Performance critical - called for every packet */ static inline bool ip6_packet_match(const struct sk_buff *skb, const char *indev, const char *outdev, const struct ip6t_ip6 *ip6info, unsigned int *protoff, u16 *fragoff, bool *hotdrop) { unsigned long ret; const struct ipv6hdr *ipv6 = ipv6_hdr(skb); if (NF_INVF(ip6info, IP6T_INV_SRCIP, ipv6_masked_addr_cmp(&ipv6->saddr, &ip6info->smsk, &ip6info->src)) || NF_INVF(ip6info, IP6T_INV_DSTIP, ipv6_masked_addr_cmp(&ipv6->daddr, &ip6info->dmsk, &ip6info->dst))) return false; ret = ifname_compare_aligned(indev, ip6info->iniface, ip6info->iniface_mask); if (NF_INVF(ip6info, IP6T_INV_VIA_IN, ret != 0)) return false; ret = ifname_compare_aligned(outdev, ip6info->outiface, ip6info->outiface_mask); if (NF_INVF(ip6info, IP6T_INV_VIA_OUT, ret != 0)) return false; /* ... might want to do something with class and flowlabel here ... */ /* look for the desired protocol header */ if (ip6info->flags & IP6T_F_PROTO) { int protohdr; unsigned short _frag_off; protohdr = ipv6_find_hdr(skb, protoff, -1, &_frag_off, NULL); if (protohdr < 0) { if (_frag_off == 0) *hotdrop = true; return false; } *fragoff = _frag_off; if (ip6info->proto == protohdr) { if (ip6info->invflags & IP6T_INV_PROTO) return false; return true; } /* We need match for the '-p all', too! */ if ((ip6info->proto != 0) && !(ip6info->invflags & IP6T_INV_PROTO)) return false; } return true; } /* should be ip6 safe */ static bool ip6_checkentry(const struct ip6t_ip6 *ipv6) { if (ipv6->flags & ~IP6T_F_MASK) return false; if (ipv6->invflags & ~IP6T_INV_MASK) return false; return true; } static unsigned int ip6t_error(struct sk_buff *skb, const struct xt_action_param *par) { net_info_ratelimited("error: `%s'\n", (const char *)par->targinfo); return NF_DROP; } static inline struct ip6t_entry * get_entry(const void *base, unsigned int offset) { return (struct ip6t_entry *)(base + offset); } /* All zeroes == unconditional rule. */ /* Mildly perf critical (only if packet tracing is on) */ static inline bool unconditional(const struct ip6t_entry *e) { static const struct ip6t_ip6 uncond; return e->target_offset == sizeof(struct ip6t_entry) && memcmp(&e->ipv6, &uncond, sizeof(uncond)) == 0; } static inline const struct xt_entry_target * ip6t_get_target_c(const struct ip6t_entry *e) { return ip6t_get_target((struct ip6t_entry *)e); } #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* This cries for unification! */ static const char *const hooknames[] = { [NF_INET_PRE_ROUTING] = "PREROUTING", [NF_INET_LOCAL_IN] = "INPUT", [NF_INET_FORWARD] = "FORWARD", [NF_INET_LOCAL_OUT] = "OUTPUT", [NF_INET_POST_ROUTING] = "POSTROUTING", }; enum nf_ip_trace_comments { NF_IP6_TRACE_COMMENT_RULE, NF_IP6_TRACE_COMMENT_RETURN, NF_IP6_TRACE_COMMENT_POLICY, }; static const char *const comments[] = { [NF_IP6_TRACE_COMMENT_RULE] = "rule", [NF_IP6_TRACE_COMMENT_RETURN] = "return", [NF_IP6_TRACE_COMMENT_POLICY] = "policy", }; static const struct nf_loginfo trace_loginfo = { .type = NF_LOG_TYPE_LOG, .u = { .log = { .level = LOGLEVEL_WARNING, .logflags = NF_LOG_DEFAULT_MASK, }, }, }; /* Mildly perf critical (only if packet tracing is on) */ static inline int get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e, const char *hookname, const char **chainname, const char **comment, unsigned int *rulenum) { const struct xt_standard_target *t = (void *)ip6t_get_target_c(s); if (strcmp(t->target.u.kernel.target->name, XT_ERROR_TARGET) == 0) { /* Head of user chain: ERROR target with chainname */ *chainname = t->target.data; (*rulenum) = 0; } else if (s == e) { (*rulenum)++; if (unconditional(s) && strcmp(t->target.u.kernel.target->name, XT_STANDARD_TARGET) == 0 && t->verdict < 0) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname ? comments[NF_IP6_TRACE_COMMENT_POLICY] : comments[NF_IP6_TRACE_COMMENT_RETURN]; } return 1; } else (*rulenum)++; return 0; } static void trace_packet(struct net *net, const struct sk_buff *skb, unsigned int hook, const struct net_device *in, const struct net_device *out, const char *tablename, const struct xt_table_info *private, const struct ip6t_entry *e) { const struct ip6t_entry *root; const char *hookname, *chainname, *comment; const struct ip6t_entry *iter; unsigned int rulenum = 0; root = get_entry(private->entries, private->hook_entry[hook]); hookname = chainname = hooknames[hook]; comment = comments[NF_IP6_TRACE_COMMENT_RULE]; xt_entry_foreach(iter, root, private->size - private->hook_entry[hook]) if (get_chainname_rulenum(iter, e, hookname, &chainname, &comment, &rulenum) != 0) break; nf_log_trace(net, AF_INET6, hook, skb, in, out, &trace_loginfo, "TRACE: %s:%s:%s:%u ", tablename, chainname, comment, rulenum); } #endif static inline struct ip6t_entry * ip6t_next_entry(const struct ip6t_entry *entry) { return (void *)entry + entry->next_offset; } /* Returns one of the generic firewall policies, like NF_ACCEPT. */ unsigned int ip6t_do_table(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { const struct xt_table *table = priv; unsigned int hook = state->hook; static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); /* Initializing verdict to NF_DROP keeps gcc happy. */ unsigned int verdict = NF_DROP; const char *indev, *outdev; const void *table_base; struct ip6t_entry *e, **jumpstack; unsigned int stackidx, cpu; const struct xt_table_info *private; struct xt_action_param acpar; unsigned int addend; /* Initialization */ stackidx = 0; indev = state->in ? state->in->name : nulldevname; outdev = state->out ? state->out->name : nulldevname; /* We handle fragments by dealing with the first fragment as * if it was a normal packet. All other fragments are treated * normally, except that they will NEVER match rules that ask * things we don't know, ie. tcp syn flag or ports). If the * rule is also a fragment-specific rule, non-fragments won't * match it. */ acpar.fragoff = 0; acpar.hotdrop = false; acpar.state = state; WARN_ON(!(table->valid_hooks & (1 << hook))); local_bh_disable(); addend = xt_write_recseq_begin(); private = READ_ONCE(table->private); /* Address dependency. */ cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct ip6t_entry **)private->jumpstack[cpu]; /* Switch to alternate jumpstack if we're being invoked via TEE. * TEE issues XT_CONTINUE verdict on original skb so we must not * clobber the jumpstack. * * For recursion via REJECT or SYNPROXY the stack will be clobbered * but it is no problem since absolute verdict is issued by these. */ if (static_key_false(&xt_tee_enabled)) jumpstack += private->stacksize * __this_cpu_read(nf_skb_duplicated); e = get_entry(table_base, private->hook_entry[hook]); do { const struct xt_entry_target *t; const struct xt_entry_match *ematch; struct xt_counters *counter; WARN_ON(!e); acpar.thoff = 0; if (!ip6_packet_match(skb, indev, outdev, &e->ipv6, &acpar.thoff, &acpar.fragoff, &acpar.hotdrop)) { no_match: e = ip6t_next_entry(e); continue; } xt_ematch_foreach(ematch, e) { acpar.match = ematch->u.kernel.match; acpar.matchinfo = ematch->data; if (!acpar.match->match(skb, &acpar)) goto no_match; } counter = xt_get_this_cpu_counter(&e->counters); ADD_COUNTER(*counter, skb->len, 1); t = ip6t_get_target_c(e); WARN_ON(!t->u.kernel.target); #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* The packet is traced: log it */ if (unlikely(skb->nf_trace)) trace_packet(state->net, skb, hook, state->in, state->out, table->name, private, e); #endif /* Standard target? */ if (!t->u.kernel.target->target) { int v; v = ((struct xt_standard_target *)t)->verdict; if (v < 0) { /* Pop from stack? */ if (v != XT_RETURN) { verdict = (unsigned int)(-v) - 1; break; } if (stackidx == 0) e = get_entry(table_base, private->underflow[hook]); else e = ip6t_next_entry(jumpstack[--stackidx]); continue; } if (table_base + v != ip6t_next_entry(e) && !(e->ipv6.flags & IP6T_F_GOTO)) { if (unlikely(stackidx >= private->stacksize)) { verdict = NF_DROP; break; } jumpstack[stackidx++] = e; } e = get_entry(table_base, v); continue; } acpar.target = t->u.kernel.target; acpar.targinfo = t->data; verdict = t->u.kernel.target->target(skb, &acpar); if (verdict == XT_CONTINUE) e = ip6t_next_entry(e); else /* Verdict */ break; } while (!acpar.hotdrop); xt_write_recseq_end(addend); local_bh_enable(); if (acpar.hotdrop) return NF_DROP; else return verdict; } /* Figures out from what hook each rule can be called: returns 0 if there are loops. Puts hook bitmask in comefrom. */ static int mark_source_chains(const struct xt_table_info *newinfo, unsigned int valid_hooks, void *entry0, unsigned int *offsets) { unsigned int hook; /* No recursion; use packet counter to save back ptrs (reset to 0 as we leave), and comefrom to save source hook bitmask */ for (hook = 0; hook < NF_INET_NUMHOOKS; hook++) { unsigned int pos = newinfo->hook_entry[hook]; struct ip6t_entry *e = entry0 + pos; if (!(valid_hooks & (1 << hook))) continue; /* Set initial back pointer. */ e->counters.pcnt = pos; for (;;) { const struct xt_standard_target *t = (void *)ip6t_get_target_c(e); int visited = e->comefrom & (1 << hook); if (e->comefrom & (1 << NF_INET_NUMHOOKS)) return 0; e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); /* Unconditional return/END. */ if ((unconditional(e) && (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0) && t->verdict < 0) || visited) { unsigned int oldpos, size; /* Return: backtrack through the last big jump. */ do { e->comefrom ^= (1<<NF_INET_NUMHOOKS); oldpos = pos; pos = e->counters.pcnt; e->counters.pcnt = 0; /* We're at the start. */ if (pos == oldpos) goto next; e = entry0 + pos; } while (oldpos == pos + e->next_offset); /* Move along one */ size = e->next_offset; e = entry0 + pos + size; if (pos + size >= newinfo->size) return 0; e->counters.pcnt = pos; pos += size; } else { int newpos = t->verdict; if (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0 && newpos >= 0) { /* This a jump; chase it. */ if (!xt_find_jump_offset(offsets, newpos, newinfo->number)) return 0; } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; if (newpos >= newinfo->size) return 0; } e = entry0 + newpos; e->counters.pcnt = pos; pos = newpos; } } next: ; } return 1; } static void cleanup_match(struct xt_entry_match *m, struct net *net) { struct xt_mtdtor_param par; par.net = net; par.match = m->u.kernel.match; par.matchinfo = m->data; par.family = NFPROTO_IPV6; if (par.match->destroy != NULL) par.match->destroy(&par); module_put(par.match->me); } static int check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { const struct ip6t_ip6 *ipv6 = par->entryinfo; par->match = m->u.kernel.match; par->matchinfo = m->data; return xt_check_match(par, m->u.match_size - sizeof(*m), ipv6->proto, ipv6->invflags & IP6T_INV_PROTO); } static int find_check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { struct xt_match *match; int ret; match = xt_request_find_match(NFPROTO_IPV6, m->u.user.name, m->u.user.revision); if (IS_ERR(match)) return PTR_ERR(match); m->u.kernel.match = match; ret = check_match(m, par); if (ret) goto err; return 0; err: module_put(m->u.kernel.match->me); return ret; } static int check_target(struct ip6t_entry *e, struct net *net, const char *name) { struct xt_entry_target *t = ip6t_get_target(e); struct xt_tgchk_param par = { .net = net, .table = name, .entryinfo = e, .target = t->u.kernel.target, .targinfo = t->data, .hook_mask = e->comefrom, .family = NFPROTO_IPV6, }; return xt_check_target(&par, t->u.target_size - sizeof(*t), e->ipv6.proto, e->ipv6.invflags & IP6T_INV_PROTO); } static int find_check_entry(struct ip6t_entry *e, struct net *net, const char *name, unsigned int size, struct xt_percpu_counter_alloc_state *alloc_state) { struct xt_entry_target *t; struct xt_target *target; int ret; unsigned int j; struct xt_mtchk_param mtpar; struct xt_entry_match *ematch; if (!xt_percpu_counter_alloc(alloc_state, &e->counters)) return -ENOMEM; j = 0; memset(&mtpar, 0, sizeof(mtpar)); mtpar.net = net; mtpar.table = name; mtpar.entryinfo = &e->ipv6; mtpar.hook_mask = e->comefrom; mtpar.family = NFPROTO_IPV6; xt_ematch_foreach(ematch, e) { ret = find_check_match(ematch, &mtpar); if (ret != 0) goto cleanup_matches; ++j; } t = ip6t_get_target(e); target = xt_request_find_target(NFPROTO_IPV6, t->u.user.name, t->u.user.revision); if (IS_ERR(target)) { ret = PTR_ERR(target); goto cleanup_matches; } t->u.kernel.target = target; ret = check_target(e, net, name); if (ret) goto err; return 0; err: module_put(t->u.kernel.target->me); cleanup_matches: xt_ematch_foreach(ematch, e) { if (j-- == 0) break; cleanup_match(ematch, net); } xt_percpu_counter_free(&e->counters); return ret; } static bool check_underflow(const struct ip6t_entry *e) { const struct xt_entry_target *t; unsigned int verdict; if (!unconditional(e)) return false; t = ip6t_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) return false; verdict = ((struct xt_standard_target *)t)->verdict; verdict = -verdict - 1; return verdict == NF_DROP || verdict == NF_ACCEPT; } static int check_entry_size_and_hooks(struct ip6t_entry *e, struct xt_table_info *newinfo, const unsigned char *base, const unsigned char *limit, const unsigned int *hook_entries, const unsigned int *underflows, unsigned int valid_hooks) { unsigned int h; int err; if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 || (unsigned char *)e + sizeof(struct ip6t_entry) >= limit || (unsigned char *)e + e->next_offset > limit) return -EINVAL; if (e->next_offset < sizeof(struct ip6t_entry) + sizeof(struct xt_entry_target)) return -EINVAL; if (!ip6_checkentry(&e->ipv6)) return -EINVAL; err = xt_check_entry_offsets(e, e->elems, e->target_offset, e->next_offset); if (err) return err; /* Check hooks & underflows */ for (h = 0; h < NF_INET_NUMHOOKS; h++) { if (!(valid_hooks & (1 << h))) continue; if ((unsigned char *)e - base == hook_entries[h]) newinfo->hook_entry[h] = hook_entries[h]; if ((unsigned char *)e - base == underflows[h]) { if (!check_underflow(e)) return -EINVAL; newinfo->underflow[h] = underflows[h]; } } /* Clear counters and comefrom */ e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; return 0; } static void cleanup_entry(struct ip6t_entry *e, struct net *net) { struct xt_tgdtor_param par; struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ xt_ematch_foreach(ematch, e) cleanup_match(ematch, net); t = ip6t_get_target(e); par.net = net; par.target = t->u.kernel.target; par.targinfo = t->data; par.family = NFPROTO_IPV6; if (par.target->destroy != NULL) par.target->destroy(&par); module_put(par.target->me); xt_percpu_counter_free(&e->counters); } /* Checks and translates the user-supplied table segment (held in newinfo) */ static int translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, const struct ip6t_replace *repl) { struct xt_percpu_counter_alloc_state alloc_state = { 0 }; struct ip6t_entry *iter; unsigned int *offsets; unsigned int i; int ret = 0; newinfo->size = repl->size; newinfo->number = repl->num_entries; /* Init all hooks to impossible value. */ for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = 0xFFFFFFFF; newinfo->underflow[i] = 0xFFFFFFFF; } offsets = xt_alloc_entry_offsets(newinfo->number); if (!offsets) return -ENOMEM; i = 0; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter, entry0, newinfo->size) { ret = check_entry_size_and_hooks(iter, newinfo, entry0, entry0 + repl->size, repl->hook_entry, repl->underflow, repl->valid_hooks); if (ret != 0) goto out_free; if (i < repl->num_entries) offsets[i] = (void *)iter - entry0; ++i; if (strcmp(ip6t_get_target(iter)->u.user.name, XT_ERROR_TARGET) == 0) ++newinfo->stacksize; } ret = -EINVAL; if (i != repl->num_entries) goto out_free; ret = xt_check_table_hooks(newinfo, repl->valid_hooks); if (ret) goto out_free; if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) { ret = -ELOOP; goto out_free; } kvfree(offsets); /* Finally, each sanity check must pass */ i = 0; xt_entry_foreach(iter, entry0, newinfo->size) { ret = find_check_entry(iter, net, repl->name, repl->size, &alloc_state); if (ret != 0) break; ++i; } if (ret != 0) { xt_entry_foreach(iter, entry0, newinfo->size) { if (i-- == 0) break; cleanup_entry(iter, net); } return ret; } return ret; out_free: kvfree(offsets); return ret; } static void get_counters(const struct xt_table_info *t, struct xt_counters counters[]) { struct ip6t_entry *iter; unsigned int cpu; unsigned int i; for_each_possible_cpu(cpu) { seqcount_t *s = &per_cpu(xt_recseq, cpu); i = 0; xt_entry_foreach(iter, t->entries, t->size) { struct xt_counters *tmp; u64 bcnt, pcnt; unsigned int start; tmp = xt_get_per_cpu_counter(&iter->counters, cpu); do { start = read_seqcount_begin(s); bcnt = tmp->bcnt; pcnt = tmp->pcnt; } while (read_seqcount_retry(s, start)); ADD_COUNTER(counters[i], bcnt, pcnt); ++i; cond_resched(); } } } static void get_old_counters(const struct xt_table_info *t, struct xt_counters counters[]) { struct ip6t_entry *iter; unsigned int cpu, i; for_each_possible_cpu(cpu) { i = 0; xt_entry_foreach(iter, t->entries, t->size) { const struct xt_counters *tmp; tmp = xt_get_per_cpu_counter(&iter->counters, cpu); ADD_COUNTER(counters[i], tmp->bcnt, tmp->pcnt); ++i; } cond_resched(); } } static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; const struct xt_table_info *private = table->private; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care about). */ countersize = sizeof(struct xt_counters) * private->number; counters = vzalloc(countersize); if (counters == NULL) return ERR_PTR(-ENOMEM); get_counters(private, counters); return counters; } static int copy_entries_to_user(unsigned int total_size, const struct xt_table *table, void __user *userptr) { unsigned int off, num; const struct ip6t_entry *e; struct xt_counters *counters; const struct xt_table_info *private = table->private; int ret = 0; const void *loc_cpu_entry; counters = alloc_counters(table); if (IS_ERR(counters)) return PTR_ERR(counters); loc_cpu_entry = private->entries; /* FIXME: use iterator macros --RR */ /* ... then go back and fix counters and names */ for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){ unsigned int i; const struct xt_entry_match *m; const struct xt_entry_target *t; e = loc_cpu_entry + off; if (copy_to_user(userptr + off, e, sizeof(*e))) { ret = -EFAULT; goto free_counters; } if (copy_to_user(userptr + off + offsetof(struct ip6t_entry, counters), &counters[num], sizeof(counters[num])) != 0) { ret = -EFAULT; goto free_counters; } for (i = sizeof(struct ip6t_entry); i < e->target_offset; i += m->u.match_size) { m = (void *)e + i; if (xt_match_to_user(m, userptr + off + i)) { ret = -EFAULT; goto free_counters; } } t = ip6t_get_target_c(e); if (xt_target_to_user(t, userptr + off + e->target_offset)) { ret = -EFAULT; goto free_counters; } } free_counters: vfree(counters); return ret; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT static void compat_standard_from_user(void *dst, const void *src) { int v = *(compat_int_t *)src; if (v > 0) v += xt_compat_calc_jump(AF_INET6, v); memcpy(dst, &v, sizeof(v)); } static int compat_standard_to_user(void __user *dst, const void *src) { compat_int_t cv = *(int *)src; if (cv > 0) cv -= xt_compat_calc_jump(AF_INET6, cv); return copy_to_user(dst, &cv, sizeof(cv)) ? -EFAULT : 0; } static int compat_calc_entry(const struct ip6t_entry *e, const struct xt_table_info *info, const void *base, struct xt_table_info *newinfo) { const struct xt_entry_match *ematch; const struct xt_entry_target *t; unsigned int entry_offset; int off, i, ret; off = sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); entry_offset = (void *)e - base; xt_ematch_foreach(ematch, e) off += xt_compat_match_offset(ematch->u.kernel.match); t = ip6t_get_target_c(e); off += xt_compat_target_offset(t->u.kernel.target); newinfo->size -= off; ret = xt_compat_add_offset(AF_INET6, entry_offset, off); if (ret) return ret; for (i = 0; i < NF_INET_NUMHOOKS; i++) { if (info->hook_entry[i] && (e < (struct ip6t_entry *)(base + info->hook_entry[i]))) newinfo->hook_entry[i] -= off; if (info->underflow[i] && (e < (struct ip6t_entry *)(base + info->underflow[i]))) newinfo->underflow[i] -= off; } return 0; } static int compat_table_info(const struct xt_table_info *info, struct xt_table_info *newinfo) { struct ip6t_entry *iter; const void *loc_cpu_entry; int ret; if (!newinfo || !info) return -EINVAL; /* we dont care about newinfo->entries */ memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); newinfo->initial_entries = 0; loc_cpu_entry = info->entries; ret = xt_compat_init_offsets(AF_INET6, info->number); if (ret) return ret; xt_entry_foreach(iter, loc_cpu_entry, info->size) { ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); if (ret != 0) return ret; } return 0; } #endif static int get_info(struct net *net, void __user *user, const int *len) { char name[XT_TABLE_MAXNAMELEN]; struct xt_table *t; int ret; if (*len != sizeof(struct ip6t_getinfo)) return -EINVAL; if (copy_from_user(name, user, sizeof(name)) != 0) return -EFAULT; name[XT_TABLE_MAXNAMELEN-1] = '\0'; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) xt_compat_lock(AF_INET6); #endif t = xt_request_find_table_lock(net, AF_INET6, name); if (!IS_ERR(t)) { struct ip6t_getinfo info; const struct xt_table_info *private = t->private; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct xt_table_info tmp; if (in_compat_syscall()) { ret = compat_table_info(private, &tmp); xt_compat_flush_offsets(AF_INET6); private = &tmp; } #endif memset(&info, 0, sizeof(info)); info.valid_hooks = t->valid_hooks; memcpy(info.hook_entry, private->hook_entry, sizeof(info.hook_entry)); memcpy(info.underflow, private->underflow, sizeof(info.underflow)); info.num_entries = private->number; info.size = private->size; strcpy(info.name, name); if (copy_to_user(user, &info, *len) != 0) ret = -EFAULT; else ret = 0; xt_table_unlock(t); module_put(t->me); } else ret = PTR_ERR(t); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) xt_compat_unlock(AF_INET6); #endif return ret; } static int get_entries(struct net *net, struct ip6t_get_entries __user *uptr, const int *len) { int ret; struct ip6t_get_entries get; struct xt_table *t; if (*len < sizeof(get)) return -EINVAL; if (copy_from_user(&get, uptr, sizeof(get)) != 0) return -EFAULT; if (*len != sizeof(struct ip6t_get_entries) + get.size) return -EINVAL; get.name[sizeof(get.name) - 1] = '\0'; t = xt_find_table_lock(net, AF_INET6, get.name); if (!IS_ERR(t)) { struct xt_table_info *private = t->private; if (get.size == private->size) ret = copy_entries_to_user(private->size, t, uptr->entrytable); else ret = -EAGAIN; module_put(t->me); xt_table_unlock(t); } else ret = PTR_ERR(t); return ret; } static int __do_replace(struct net *net, const char *name, unsigned int valid_hooks, struct xt_table_info *newinfo, unsigned int num_counters, void __user *counters_ptr) { int ret; struct xt_table *t; struct xt_table_info *oldinfo; struct xt_counters *counters; struct ip6t_entry *iter; counters = xt_counters_alloc(num_counters); if (!counters) { ret = -ENOMEM; goto out; } t = xt_request_find_table_lock(net, AF_INET6, name); if (IS_ERR(t)) { ret = PTR_ERR(t); goto free_newinfo_counters_untrans; } /* You lied! */ if (valid_hooks != t->valid_hooks) { ret = -EINVAL; goto put_module; } oldinfo = xt_replace_table(t, num_counters, newinfo, &ret); if (!oldinfo) goto put_module; /* Update module usage count based on number of rules */ if ((oldinfo->number > oldinfo->initial_entries) || (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); if ((oldinfo->number > oldinfo->initial_entries) && (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); xt_table_unlock(t); get_old_counters(oldinfo, counters); /* Decrease module usage counts and free resource */ xt_entry_foreach(iter, oldinfo->entries, oldinfo->size) cleanup_entry(iter, net); xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, sizeof(struct xt_counters) * num_counters) != 0) { /* Silent error, can't fail, new table is already in place */ net_warn_ratelimited("ip6tables: counters copy to user failed while replacing table\n"); } vfree(counters); return 0; put_module: module_put(t->me); xt_table_unlock(t); free_newinfo_counters_untrans: vfree(counters); out: return ret; } static int do_replace(struct net *net, sockptr_t arg, unsigned int len) { int ret; struct ip6t_replace tmp; struct xt_table_info *newinfo; void *loc_cpu_entry; struct ip6t_entry *iter; if (len < sizeof(tmp)) return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; if ((u64)len < (u64)tmp.size + sizeof(tmp)) return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } ret = translate_table(net, newinfo, loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, tmp.num_counters, tmp.counters); if (ret) goto free_newinfo_untrans; return 0; free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; } static int do_add_counters(struct net *net, sockptr_t arg, unsigned int len) { unsigned int i; struct xt_counters_info tmp; struct xt_counters *paddc; struct xt_table *t; const struct xt_table_info *private; int ret = 0; struct ip6t_entry *iter; unsigned int addend; paddc = xt_copy_counters(arg, len, &tmp); if (IS_ERR(paddc)) return PTR_ERR(paddc); t = xt_find_table_lock(net, AF_INET6, tmp.name); if (IS_ERR(t)) { ret = PTR_ERR(t); goto free; } local_bh_disable(); private = t->private; if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; } i = 0; addend = xt_write_recseq_begin(); xt_entry_foreach(iter, private->entries, private->size) { struct xt_counters *tmp; tmp = xt_get_this_cpu_counter(&iter->counters); ADD_COUNTER(*tmp, paddc[i].bcnt, paddc[i].pcnt); ++i; } xt_write_recseq_end(addend); unlock_up_free: local_bh_enable(); xt_table_unlock(t); module_put(t->me); free: vfree(paddc); return ret; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct compat_ip6t_replace { char name[XT_TABLE_MAXNAMELEN]; u32 valid_hooks; u32 num_entries; u32 size; u32 hook_entry[NF_INET_NUMHOOKS]; u32 underflow[NF_INET_NUMHOOKS]; u32 num_counters; compat_uptr_t counters; /* struct xt_counters * */ struct compat_ip6t_entry entries[]; }; static int compat_copy_entry_to_user(struct ip6t_entry *e, void __user **dstptr, unsigned int *size, struct xt_counters *counters, unsigned int i) { struct xt_entry_target *t; struct compat_ip6t_entry __user *ce; u_int16_t target_offset, next_offset; compat_uint_t origsize; const struct xt_entry_match *ematch; int ret = 0; origsize = *size; ce = *dstptr; if (copy_to_user(ce, e, sizeof(struct ip6t_entry)) != 0 || copy_to_user(&ce->counters, &counters[i], sizeof(counters[i])) != 0) return -EFAULT; *dstptr += sizeof(struct compat_ip6t_entry); *size -= sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); xt_ematch_foreach(ematch, e) { ret = xt_compat_match_to_user(ematch, dstptr, size); if (ret != 0) return ret; } target_offset = e->target_offset - (origsize - *size); t = ip6t_get_target(e); ret = xt_compat_target_to_user(t, dstptr, size); if (ret) return ret; next_offset = e->next_offset - (origsize - *size); if (put_user(target_offset, &ce->target_offset) != 0 || put_user(next_offset, &ce->next_offset) != 0) return -EFAULT; return 0; } static int compat_find_calc_match(struct xt_entry_match *m, const struct ip6t_ip6 *ipv6, int *size) { struct xt_match *match; match = xt_request_find_match(NFPROTO_IPV6, m->u.user.name, m->u.user.revision); if (IS_ERR(match)) return PTR_ERR(match); m->u.kernel.match = match; *size += xt_compat_match_offset(match); return 0; } static void compat_release_entry(struct compat_ip6t_entry *e) { struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ xt_ematch_foreach(ematch, e) module_put(ematch->u.kernel.match->me); t = compat_ip6t_get_target(e); module_put(t->u.kernel.target->me); } static int check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, struct xt_table_info *newinfo, unsigned int *size, const unsigned char *base, const unsigned char *limit) { struct xt_entry_match *ematch; struct xt_entry_target *t; struct xt_target *target; unsigned int entry_offset; unsigned int j; int ret, off; if ((unsigned long)e % __alignof__(struct compat_ip6t_entry) != 0 || (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit || (unsigned char *)e + e->next_offset > limit) return -EINVAL; if (e->next_offset < sizeof(struct compat_ip6t_entry) + sizeof(struct compat_xt_entry_target)) return -EINVAL; if (!ip6_checkentry(&e->ipv6)) return -EINVAL; ret = xt_compat_check_entry_offsets(e, e->elems, e->target_offset, e->next_offset); if (ret) return ret; off = sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); entry_offset = (void *)e - (void *)base; j = 0; xt_ematch_foreach(ematch, e) { ret = compat_find_calc_match(ematch, &e->ipv6, &off); if (ret != 0) goto release_matches; ++j; } t = compat_ip6t_get_target(e); target = xt_request_find_target(NFPROTO_IPV6, t->u.user.name, t->u.user.revision); if (IS_ERR(target)) { ret = PTR_ERR(target); goto release_matches; } t->u.kernel.target = target; off += xt_compat_target_offset(target); *size += off; ret = xt_compat_add_offset(AF_INET6, entry_offset, off); if (ret) goto out; return 0; out: module_put(t->u.kernel.target->me); release_matches: xt_ematch_foreach(ematch, e) { if (j-- == 0) break; module_put(ematch->u.kernel.match->me); } return ret; } static void compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr, unsigned int *size, struct xt_table_info *newinfo, unsigned char *base) { struct xt_entry_target *t; struct ip6t_entry *de; unsigned int origsize; int h; struct xt_entry_match *ematch; origsize = *size; de = *dstptr; memcpy(de, e, sizeof(struct ip6t_entry)); memcpy(&de->counters, &e->counters, sizeof(e->counters)); *dstptr += sizeof(struct ip6t_entry); *size += sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); xt_ematch_foreach(ematch, e) xt_compat_match_from_user(ematch, dstptr, size); de->target_offset = e->target_offset - (origsize - *size); t = compat_ip6t_get_target(e); xt_compat_target_from_user(t, dstptr, size); de->next_offset = e->next_offset - (origsize - *size); for (h = 0; h < NF_INET_NUMHOOKS; h++) { if ((unsigned char *)de - base < newinfo->hook_entry[h]) newinfo->hook_entry[h] -= origsize - *size; if ((unsigned char *)de - base < newinfo->underflow[h]) newinfo->underflow[h] -= origsize - *size; } } static int translate_compat_table(struct net *net, struct xt_table_info **pinfo, void **pentry0, const struct compat_ip6t_replace *compatr) { unsigned int i, j; struct xt_table_info *newinfo, *info; void *pos, *entry0, *entry1; struct compat_ip6t_entry *iter0; struct ip6t_replace repl; unsigned int size; int ret; info = *pinfo; entry0 = *pentry0; size = compatr->size; info->number = compatr->num_entries; j = 0; xt_compat_lock(AF_INET6); ret = xt_compat_init_offsets(AF_INET6, compatr->num_entries); if (ret) goto out_unlock; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter0, entry0, compatr->size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, entry0, entry0 + compatr->size); if (ret != 0) goto out_unlock; ++j; } ret = -EINVAL; if (j != compatr->num_entries) goto out_unlock; ret = -ENOMEM; newinfo = xt_alloc_table_info(size); if (!newinfo) goto out_unlock; memset(newinfo->entries, 0, size); newinfo->number = compatr->num_entries; for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = compatr->hook_entry[i]; newinfo->underflow[i] = compatr->underflow[i]; } entry1 = newinfo->entries; pos = entry1; size = compatr->size; xt_entry_foreach(iter0, entry0, compatr->size) compat_copy_entry_from_user(iter0, &pos, &size, newinfo, entry1); /* all module references in entry0 are now gone. */ xt_compat_flush_offsets(AF_INET6); xt_compat_unlock(AF_INET6); memcpy(&repl, compatr, sizeof(*compatr)); for (i = 0; i < NF_INET_NUMHOOKS; i++) { repl.hook_entry[i] = newinfo->hook_entry[i]; repl.underflow[i] = newinfo->underflow[i]; } repl.num_counters = 0; repl.counters = NULL; repl.size = newinfo->size; ret = translate_table(net, newinfo, entry1, &repl); if (ret) goto free_newinfo; *pinfo = newinfo; *pentry0 = entry1; xt_free_table_info(info); return 0; free_newinfo: xt_free_table_info(newinfo); return ret; out_unlock: xt_compat_flush_offsets(AF_INET6); xt_compat_unlock(AF_INET6); xt_entry_foreach(iter0, entry0, compatr->size) { if (j-- == 0) break; compat_release_entry(iter0); } return ret; } static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) { int ret; struct compat_ip6t_replace tmp; struct xt_table_info *newinfo; void *loc_cpu_entry; struct ip6t_entry *iter; if (len < sizeof(tmp)) return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; if ((u64)len < (u64)tmp.size + sizeof(tmp)) return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; if (copy_from_sockptr_offset(loc_cpu_entry, arg, sizeof(tmp), tmp.size) != 0) { ret = -EFAULT; goto free_newinfo; } ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; ret = __do_replace(net, tmp.name, tmp.valid_hooks, newinfo, tmp.num_counters, compat_ptr(tmp.counters)); if (ret) goto free_newinfo_untrans; return 0; free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; } struct compat_ip6t_get_entries { char name[XT_TABLE_MAXNAMELEN]; compat_uint_t size; struct compat_ip6t_entry entrytable[]; }; static int compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, void __user *userptr) { struct xt_counters *counters; const struct xt_table_info *private = table->private; void __user *pos; unsigned int size; int ret = 0; unsigned int i = 0; struct ip6t_entry *iter; counters = alloc_counters(table); if (IS_ERR(counters)) return PTR_ERR(counters); pos = userptr; size = total_size; xt_entry_foreach(iter, private->entries, total_size) { ret = compat_copy_entry_to_user(iter, &pos, &size, counters, i++); if (ret != 0) break; } vfree(counters); return ret; } static int compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr, int *len) { int ret; struct compat_ip6t_get_entries get; struct xt_table *t; if (*len < sizeof(get)) return -EINVAL; if (copy_from_user(&get, uptr, sizeof(get)) != 0) return -EFAULT; if (*len != sizeof(struct compat_ip6t_get_entries) + get.size) return -EINVAL; get.name[sizeof(get.name) - 1] = '\0'; xt_compat_lock(AF_INET6); t = xt_find_table_lock(net, AF_INET6, get.name); if (!IS_ERR(t)) { const struct xt_table_info *private = t->private; struct xt_table_info info; ret = compat_table_info(private, &info); if (!ret && get.size == info.size) ret = compat_copy_entries_to_user(private->size, t, uptr->entrytable); else if (!ret) ret = -EAGAIN; xt_compat_flush_offsets(AF_INET6); module_put(t->me); xt_table_unlock(t); } else ret = PTR_ERR(t); xt_compat_unlock(AF_INET6); return ret; } #endif static int do_ip6t_set_ctl(struct sock *sk, int cmd, sockptr_t arg, unsigned int len) { int ret; if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case IP6T_SO_SET_REPLACE: #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) ret = compat_do_replace(sock_net(sk), arg, len); else #endif ret = do_replace(sock_net(sk), arg, len); break; case IP6T_SO_SET_ADD_COUNTERS: ret = do_add_counters(sock_net(sk), arg, len); break; default: ret = -EINVAL; } return ret; } static int do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { int ret; if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case IP6T_SO_GET_INFO: ret = get_info(sock_net(sk), user, len); break; case IP6T_SO_GET_ENTRIES: #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) ret = compat_get_entries(sock_net(sk), user, len); else #endif ret = get_entries(sock_net(sk), user, len); break; case IP6T_SO_GET_REVISION_MATCH: case IP6T_SO_GET_REVISION_TARGET: { struct xt_get_revision rev; int target; if (*len != sizeof(rev)) { ret = -EINVAL; break; } if (copy_from_user(&rev, user, sizeof(rev)) != 0) { ret = -EFAULT; break; } rev.name[sizeof(rev.name)-1] = 0; if (cmd == IP6T_SO_GET_REVISION_TARGET) target = 1; else target = 0; try_then_request_module(xt_find_revision(AF_INET6, rev.name, rev.revision, target, &ret), "ip6t_%s", rev.name); break; } default: ret = -EINVAL; } return ret; } static void __ip6t_unregister_table(struct net *net, struct xt_table *table) { struct xt_table_info *private; void *loc_cpu_entry; struct module *table_owner = table->me; struct ip6t_entry *iter; private = xt_unregister_table(table); /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries; xt_entry_foreach(iter, loc_cpu_entry, private->size) cleanup_entry(iter, net); if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); } int ip6t_register_table(struct net *net, const struct xt_table *table, const struct ip6t_replace *repl, const struct nf_hook_ops *template_ops) { struct nf_hook_ops *ops; unsigned int num_ops; int ret, i; struct xt_table_info *newinfo; struct xt_table_info bootstrap = {0}; void *loc_cpu_entry; struct xt_table *new_table; newinfo = xt_alloc_table_info(repl->size); if (!newinfo) return -ENOMEM; loc_cpu_entry = newinfo->entries; memcpy(loc_cpu_entry, repl->entries, repl->size); ret = translate_table(net, newinfo, loc_cpu_entry, repl); if (ret != 0) { xt_free_table_info(newinfo); return ret; } new_table = xt_register_table(net, table, &bootstrap, newinfo); if (IS_ERR(new_table)) { struct ip6t_entry *iter; xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) cleanup_entry(iter, net); xt_free_table_info(newinfo); return PTR_ERR(new_table); } if (!template_ops) return 0; num_ops = hweight32(table->valid_hooks); if (num_ops == 0) { ret = -EINVAL; goto out_free; } ops = kmemdup(template_ops, sizeof(*ops) * num_ops, GFP_KERNEL); if (!ops) { ret = -ENOMEM; goto out_free; } for (i = 0; i < num_ops; i++) ops[i].priv = new_table; new_table->ops = ops; ret = nf_register_net_hooks(net, ops, num_ops); if (ret != 0) goto out_free; return ret; out_free: __ip6t_unregister_table(net, new_table); return ret; } void ip6t_unregister_table_pre_exit(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name); if (table) nf_unregister_net_hooks(net, table->ops, hweight32(table->valid_hooks)); } void ip6t_unregister_table_exit(struct net *net, const char *name) { struct xt_table *table = xt_find_table(net, NFPROTO_IPV6, name); if (table) __ip6t_unregister_table(net, table); } /* Returns 1 if the type and code is matched by the range, 0 otherwise */ static inline bool icmp6_type_code_match(u_int8_t test_type, u_int8_t min_code, u_int8_t max_code, u_int8_t type, u_int8_t code, bool invert) { return (type == test_type && code >= min_code && code <= max_code) ^ invert; } static bool icmp6_match(const struct sk_buff *skb, struct xt_action_param *par) { const struct icmp6hdr *ic; struct icmp6hdr _icmph; const struct ip6t_icmp *icmpinfo = par->matchinfo; /* Must not be a fragment. */ if (par->fragoff != 0) return false; ic = skb_header_pointer(skb, par->thoff, sizeof(_icmph), &_icmph); if (ic == NULL) { /* We've been asked to examine this packet, and we * can't. Hence, no choice but to drop. */ par->hotdrop = true; return false; } return icmp6_type_code_match(icmpinfo->type, icmpinfo->code[0], icmpinfo->code[1], ic->icmp6_type, ic->icmp6_code, !!(icmpinfo->invflags&IP6T_ICMP_INV)); } /* Called when user tries to insert an entry of this type. */ static int icmp6_checkentry(const struct xt_mtchk_param *par) { const struct ip6t_icmp *icmpinfo = par->matchinfo; /* Must specify no unknown invflags */ return (icmpinfo->invflags & ~IP6T_ICMP_INV) ? -EINVAL : 0; } /* The built-in targets: standard (NULL) and error. */ static struct xt_target ip6t_builtin_tg[] __read_mostly = { { .name = XT_STANDARD_TARGET, .targetsize = sizeof(int), .family = NFPROTO_IPV6, #ifdef CONFIG_NETFILTER_XTABLES_COMPAT .compatsize = sizeof(compat_int_t), .compat_from_user = compat_standard_from_user, .compat_to_user = compat_standard_to_user, #endif }, { .name = XT_ERROR_TARGET, .target = ip6t_error, .targetsize = XT_FUNCTION_MAXNAMELEN, .family = NFPROTO_IPV6, }, }; static struct nf_sockopt_ops ip6t_sockopts = { .pf = PF_INET6, .set_optmin = IP6T_BASE_CTL, .set_optmax = IP6T_SO_SET_MAX+1, .set = do_ip6t_set_ctl, .get_optmin = IP6T_BASE_CTL, .get_optmax = IP6T_SO_GET_MAX+1, .get = do_ip6t_get_ctl, .owner = THIS_MODULE, }; static struct xt_match ip6t_builtin_mt[] __read_mostly = { { .name = "icmp6", .match = icmp6_match, .matchsize = sizeof(struct ip6t_icmp), .checkentry = icmp6_checkentry, .proto = IPPROTO_ICMPV6, .family = NFPROTO_IPV6, .me = THIS_MODULE, }, }; static int __net_init ip6_tables_net_init(struct net *net) { return xt_proto_init(net, NFPROTO_IPV6); } static void __net_exit ip6_tables_net_exit(struct net *net) { xt_proto_fini(net, NFPROTO_IPV6); } static struct pernet_operations ip6_tables_net_ops = { .init = ip6_tables_net_init, .exit = ip6_tables_net_exit, }; static int __init ip6_tables_init(void) { int ret; ret = register_pernet_subsys(&ip6_tables_net_ops); if (ret < 0) goto err1; /* No one else will be downing sem now, so we won't sleep */ ret = xt_register_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); if (ret < 0) goto err2; ret = xt_register_matches(ip6t_builtin_mt, ARRAY_SIZE(ip6t_builtin_mt)); if (ret < 0) goto err4; /* Register setsockopt */ ret = nf_register_sockopt(&ip6t_sockopts); if (ret < 0) goto err5; return 0; err5: xt_unregister_matches(ip6t_builtin_mt, ARRAY_SIZE(ip6t_builtin_mt)); err4: xt_unregister_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); err2: unregister_pernet_subsys(&ip6_tables_net_ops); err1: return ret; } static void __exit ip6_tables_fini(void) { nf_unregister_sockopt(&ip6t_sockopts); xt_unregister_matches(ip6t_builtin_mt, ARRAY_SIZE(ip6t_builtin_mt)); xt_unregister_targets(ip6t_builtin_tg, ARRAY_SIZE(ip6t_builtin_tg)); unregister_pernet_subsys(&ip6_tables_net_ops); } EXPORT_SYMBOL(ip6t_register_table); EXPORT_SYMBOL(ip6t_unregister_table_pre_exit); EXPORT_SYMBOL(ip6t_unregister_table_exit); EXPORT_SYMBOL(ip6t_do_table); module_init(ip6_tables_init); module_exit(ip6_tables_fini); |
| 403 240 160 35 35 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RCULIST_NULLS_H #define _LINUX_RCULIST_NULLS_H #ifdef __KERNEL__ /* * RCU-protected list version */ #include <linux/list_nulls.h> #include <linux/rcupdate.h> /** * hlist_nulls_del_init_rcu - deletes entry from hash list with re-initialization * @n: the element to delete from the hash list. * * Note: hlist_nulls_unhashed() on the node return true after this. It is * useful for RCU based read lockfree traversal if the writer side * must know if the list entry is still hashed or already unhashed. * * In particular, it means that we can not poison the forward pointers * that may still be used for walking the hash list and we can only * zero the pprev pointer so list_unhashed() will return true after * this. * * The caller must take whatever precautions are necessary (such as * holding appropriate locks) to avoid racing with another * list-mutation primitive, such as hlist_nulls_add_head_rcu() or * hlist_nulls_del_rcu(), running on this same list. However, it is * perfectly legal to run concurrently with the _rcu list-traversal * primitives, such as hlist_nulls_for_each_entry_rcu(). */ static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n) { if (!hlist_nulls_unhashed(n)) { __hlist_nulls_del(n); WRITE_ONCE(n->pprev, NULL); } } /** * hlist_nulls_first_rcu - returns the first element of the hash list. * @head: the head of the list. */ #define hlist_nulls_first_rcu(head) \ (*((struct hlist_nulls_node __rcu __force **)&(head)->first)) /** * hlist_nulls_next_rcu - returns the element of the list after @node. * @node: element of the list. */ #define hlist_nulls_next_rcu(node) \ (*((struct hlist_nulls_node __rcu __force **)&(node)->next)) /** * hlist_nulls_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * * Note: hlist_nulls_unhashed() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the hash list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_nulls_add_head_rcu() * or hlist_nulls_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_nulls_for_each_entry(). */ static inline void hlist_nulls_del_rcu(struct hlist_nulls_node *n) { __hlist_nulls_del(n); WRITE_ONCE(n->pprev, LIST_POISON2); } /** * hlist_nulls_add_head_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist_nulls, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_nulls_add_head_rcu() * or hlist_nulls_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n, struct hlist_nulls_head *h) { struct hlist_nulls_node *first = h->first; n->next = first; WRITE_ONCE(n->pprev, &h->first); rcu_assign_pointer(hlist_nulls_first_rcu(h), n); if (!is_a_nulls(first)) WRITE_ONCE(first->pprev, &n->next); } /** * hlist_nulls_add_tail_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist_nulls, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_nulls_add_head_rcu() * or hlist_nulls_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n, struct hlist_nulls_head *h) { struct hlist_nulls_node *i, *last = NULL; /* Note: write side code, so rcu accessors are not needed. */ for (i = h->first; !is_a_nulls(i); i = i->next) last = i; if (last) { n->next = last->next; n->pprev = &last->next; rcu_assign_pointer(hlist_next_rcu(last), n); } else { hlist_nulls_add_head_rcu(n, h); } } /* after that hlist_nulls_del will work */ static inline void hlist_nulls_add_fake(struct hlist_nulls_node *n) { n->pprev = &n->next; n->next = (struct hlist_nulls_node *)NULLS_MARKER(NULL); } /** * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_nulls_node to use as a loop cursor. * @head: the head of the list. * @member: the name of the hlist_nulls_node within the struct. * * The barrier() is needed to make sure compiler doesn't cache first element [1], * as this loop can be restarted [2] * [1] Documentation/memory-barriers.txt around line 1533 * [2] Documentation/RCU/rculist_nulls.rst around line 146 */ #define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member) \ for (({barrier();}), \ pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \ (!is_a_nulls(pos)) && \ ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos))) /** * hlist_nulls_for_each_entry_safe - * iterate over list of given type safe against removal of list entry * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_nulls_node to use as a loop cursor. * @head: the head of the list. * @member: the name of the hlist_nulls_node within the struct. */ #define hlist_nulls_for_each_entry_safe(tpos, pos, head, member) \ for (({barrier();}), \ pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \ (!is_a_nulls(pos)) && \ ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); \ pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)); 1; });) #endif #endif |
| 10 10 10 10 10 10 10 10 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/ext4/extents_status.c * * Written by Yongqiang Yang <xiaoqiangnk@gmail.com> * Modified by * Allison Henderson <achender@linux.vnet.ibm.com> * Hugh Dickins <hughd@google.com> * Zheng Liu <wenqing.lz@taobao.com> * * Ext4 extents status tree core functions. */ #include <linux/list_sort.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include "ext4.h" #include <trace/events/ext4.h> /* * According to previous discussion in Ext4 Developer Workshop, we * will introduce a new structure called io tree to track all extent * status in order to solve some problems that we have met * (e.g. Reservation space warning), and provide extent-level locking. * Delay extent tree is the first step to achieve this goal. It is * original built by Yongqiang Yang. At that time it is called delay * extent tree, whose goal is only track delayed extents in memory to * simplify the implementation of fiemap and bigalloc, and introduce * lseek SEEK_DATA/SEEK_HOLE support. That is why it is still called * delay extent tree at the first commit. But for better understand * what it does, it has been rename to extent status tree. * * Step1: * Currently the first step has been done. All delayed extents are * tracked in the tree. It maintains the delayed extent when a delayed * allocation is issued, and the delayed extent is written out or * invalidated. Therefore the implementation of fiemap and bigalloc * are simplified, and SEEK_DATA/SEEK_HOLE are introduced. * * The following comment describes the implemenmtation of extent * status tree and future works. * * Step2: * In this step all extent status are tracked by extent status tree. * Thus, we can first try to lookup a block mapping in this tree before * finding it in extent tree. Hence, single extent cache can be removed * because extent status tree can do a better job. Extents in status * tree are loaded on-demand. Therefore, the extent status tree may not * contain all of the extents in a file. Meanwhile we define a shrinker * to reclaim memory from extent status tree because fragmented extent * tree will make status tree cost too much memory. written/unwritten/- * hole extents in the tree will be reclaimed by this shrinker when we * are under high memory pressure. Delayed extents will not be * reclimed because fiemap, bigalloc, and seek_data/hole need it. */ /* * Extent status tree implementation for ext4. * * * ========================================================================== * Extent status tree tracks all extent status. * * 1. Why we need to implement extent status tree? * * Without extent status tree, ext4 identifies a delayed extent by looking * up page cache, this has several deficiencies - complicated, buggy, * and inefficient code. * * FIEMAP, SEEK_HOLE/DATA, bigalloc, and writeout all need to know if a * block or a range of blocks are belonged to a delayed extent. * * Let us have a look at how they do without extent status tree. * -- FIEMAP * FIEMAP looks up page cache to identify delayed allocations from holes. * * -- SEEK_HOLE/DATA * SEEK_HOLE/DATA has the same problem as FIEMAP. * * -- bigalloc * bigalloc looks up page cache to figure out if a block is * already under delayed allocation or not to determine whether * quota reserving is needed for the cluster. * * -- writeout * Writeout looks up whole page cache to see if a buffer is * mapped, If there are not very many delayed buffers, then it is * time consuming. * * With extent status tree implementation, FIEMAP, SEEK_HOLE/DATA, * bigalloc and writeout can figure out if a block or a range of * blocks is under delayed allocation(belonged to a delayed extent) or * not by searching the extent tree. * * * ========================================================================== * 2. Ext4 extent status tree impelmentation * * -- extent * A extent is a range of blocks which are contiguous logically and * physically. Unlike extent in extent tree, this extent in ext4 is * a in-memory struct, there is no corresponding on-disk data. There * is no limit on length of extent, so an extent can contain as many * blocks as they are contiguous logically and physically. * * -- extent status tree * Every inode has an extent status tree and all allocation blocks * are added to the tree with different status. The extent in the * tree are ordered by logical block no. * * -- operations on a extent status tree * There are three important operations on a delayed extent tree: find * next extent, adding a extent(a range of blocks) and removing a extent. * * -- race on a extent status tree * Extent status tree is protected by inode->i_es_lock. * * -- memory consumption * Fragmented extent tree will make extent status tree cost too much * memory. Hence, we will reclaim written/unwritten/hole extents from * the tree under a heavy memory pressure. * * * ========================================================================== * 3. Performance analysis * * -- overhead * 1. There is a cache extent for write access, so if writes are * not very random, adding space operaions are in O(1) time. * * -- gain * 2. Code is much simpler, more readable, more maintainable and * more efficient. * * * ========================================================================== * 4. TODO list * * -- Refactor delayed space reservation * * -- Extent-level locking */ static struct kmem_cache *ext4_es_cachep; static struct kmem_cache *ext4_pending_cachep; static int __es_insert_extent(struct inode *inode, struct extent_status *newes, struct extent_status *prealloc); static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t end, int *reserved, struct extent_status *prealloc); static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan); static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, struct ext4_inode_info *locked_ei); static int __revise_pending(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, struct pending_reservation **prealloc); int __init ext4_init_es(void) { ext4_es_cachep = kmem_cache_create("ext4_extent_status", sizeof(struct extent_status), 0, (SLAB_RECLAIM_ACCOUNT), NULL); if (ext4_es_cachep == NULL) return -ENOMEM; return 0; } void ext4_exit_es(void) { kmem_cache_destroy(ext4_es_cachep); } void ext4_es_init_tree(struct ext4_es_tree *tree) { tree->root = RB_ROOT; tree->cache_es = NULL; } #ifdef ES_DEBUG__ static void ext4_es_print_tree(struct inode *inode) { struct ext4_es_tree *tree; struct rb_node *node; printk(KERN_DEBUG "status extents for inode %lu:", inode->i_ino); tree = &EXT4_I(inode)->i_es_tree; node = rb_first(&tree->root); while (node) { struct extent_status *es; es = rb_entry(node, struct extent_status, rb_node); printk(KERN_DEBUG " [%u/%u) %llu %x", es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); node = rb_next(node); } printk(KERN_DEBUG "\n"); } #else #define ext4_es_print_tree(inode) #endif static inline ext4_lblk_t ext4_es_end(struct extent_status *es) { BUG_ON(es->es_lblk + es->es_len < es->es_lblk); return es->es_lblk + es->es_len - 1; } /* * search through the tree for an delayed extent with a given offset. If * it can't be found, try to find next extent. */ static struct extent_status *__es_tree_search(struct rb_root *root, ext4_lblk_t lblk) { struct rb_node *node = root->rb_node; struct extent_status *es = NULL; while (node) { es = rb_entry(node, struct extent_status, rb_node); if (lblk < es->es_lblk) node = node->rb_left; else if (lblk > ext4_es_end(es)) node = node->rb_right; else return es; } if (es && lblk < es->es_lblk) return es; if (es && lblk > ext4_es_end(es)) { node = rb_next(&es->rb_node); return node ? rb_entry(node, struct extent_status, rb_node) : NULL; } return NULL; } /* * ext4_es_find_extent_range - find extent with specified status within block * range or next extent following block range in * extents status tree * * @inode - file containing the range * @matching_fn - pointer to function that matches extents with desired status * @lblk - logical block defining start of range * @end - logical block defining end of range * @es - extent found, if any * * Find the first extent within the block range specified by @lblk and @end * in the extents status tree that satisfies @matching_fn. If a match * is found, it's returned in @es. If not, and a matching extent is found * beyond the block range, it's returned in @es. If no match is found, an * extent is returned in @es whose es_lblk, es_len, and es_pblk components * are 0. */ static void __es_find_extent_range(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk, ext4_lblk_t end, struct extent_status *es) { struct ext4_es_tree *tree = NULL; struct extent_status *es1 = NULL; struct rb_node *node; WARN_ON(es == NULL); WARN_ON(end < lblk); tree = &EXT4_I(inode)->i_es_tree; /* see if the extent has been cached */ es->es_lblk = es->es_len = es->es_pblk = 0; es1 = READ_ONCE(tree->cache_es); if (es1 && in_range(lblk, es1->es_lblk, es1->es_len)) { es_debug("%u cached by [%u/%u) %llu %x\n", lblk, es1->es_lblk, es1->es_len, ext4_es_pblock(es1), ext4_es_status(es1)); goto out; } es1 = __es_tree_search(&tree->root, lblk); out: if (es1 && !matching_fn(es1)) { while ((node = rb_next(&es1->rb_node)) != NULL) { es1 = rb_entry(node, struct extent_status, rb_node); if (es1->es_lblk > end) { es1 = NULL; break; } if (matching_fn(es1)) break; } } if (es1 && matching_fn(es1)) { WRITE_ONCE(tree->cache_es, es1); es->es_lblk = es1->es_lblk; es->es_len = es1->es_len; es->es_pblk = es1->es_pblk; } } /* * Locking for __es_find_extent_range() for external use */ void ext4_es_find_extent_range(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk, ext4_lblk_t end, struct extent_status *es) { es->es_lblk = es->es_len = es->es_pblk = 0; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; trace_ext4_es_find_extent_range_enter(inode, lblk); read_lock(&EXT4_I(inode)->i_es_lock); __es_find_extent_range(inode, matching_fn, lblk, end, es); read_unlock(&EXT4_I(inode)->i_es_lock); trace_ext4_es_find_extent_range_exit(inode, es); } /* * __es_scan_range - search block range for block with specified status * in extents status tree * * @inode - file containing the range * @matching_fn - pointer to function that matches extents with desired status * @lblk - logical block defining start of range * @end - logical block defining end of range * * Returns true if at least one block in the specified block range satisfies * the criterion specified by @matching_fn, and false if not. If at least * one extent has the specified status, then there is at least one block * in the cluster with that status. Should only be called by code that has * taken i_es_lock. */ static bool __es_scan_range(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t start, ext4_lblk_t end) { struct extent_status es; __es_find_extent_range(inode, matching_fn, start, end, &es); if (es.es_len == 0) return false; /* no matching extent in the tree */ else if (es.es_lblk <= start && start < es.es_lblk + es.es_len) return true; else if (start <= es.es_lblk && es.es_lblk <= end) return true; else return false; } /* * Locking for __es_scan_range() for external use */ bool ext4_es_scan_range(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk, ext4_lblk_t end) { bool ret; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return false; read_lock(&EXT4_I(inode)->i_es_lock); ret = __es_scan_range(inode, matching_fn, lblk, end); read_unlock(&EXT4_I(inode)->i_es_lock); return ret; } /* * __es_scan_clu - search cluster for block with specified status in * extents status tree * * @inode - file containing the cluster * @matching_fn - pointer to function that matches extents with desired status * @lblk - logical block in cluster to be searched * * Returns true if at least one extent in the cluster containing @lblk * satisfies the criterion specified by @matching_fn, and false if not. If at * least one extent has the specified status, then there is at least one block * in the cluster with that status. Should only be called by code that has * taken i_es_lock. */ static bool __es_scan_clu(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t lblk_start, lblk_end; lblk_start = EXT4_LBLK_CMASK(sbi, lblk); lblk_end = lblk_start + sbi->s_cluster_ratio - 1; return __es_scan_range(inode, matching_fn, lblk_start, lblk_end); } /* * Locking for __es_scan_clu() for external use */ bool ext4_es_scan_clu(struct inode *inode, int (*matching_fn)(struct extent_status *es), ext4_lblk_t lblk) { bool ret; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return false; read_lock(&EXT4_I(inode)->i_es_lock); ret = __es_scan_clu(inode, matching_fn, lblk); read_unlock(&EXT4_I(inode)->i_es_lock); return ret; } static void ext4_es_list_add(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); if (!list_empty(&ei->i_es_list)) return; spin_lock(&sbi->s_es_lock); if (list_empty(&ei->i_es_list)) { list_add_tail(&ei->i_es_list, &sbi->s_es_list); sbi->s_es_nr_inode++; } spin_unlock(&sbi->s_es_lock); } static void ext4_es_list_del(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); spin_lock(&sbi->s_es_lock); if (!list_empty(&ei->i_es_list)) { list_del_init(&ei->i_es_list); sbi->s_es_nr_inode--; WARN_ON_ONCE(sbi->s_es_nr_inode < 0); } spin_unlock(&sbi->s_es_lock); } static inline struct pending_reservation *__alloc_pending(bool nofail) { if (!nofail) return kmem_cache_alloc(ext4_pending_cachep, GFP_ATOMIC); return kmem_cache_zalloc(ext4_pending_cachep, GFP_KERNEL | __GFP_NOFAIL); } static inline void __free_pending(struct pending_reservation *pr) { kmem_cache_free(ext4_pending_cachep, pr); } /* * Returns true if we cannot fail to allocate memory for this extent_status * entry and cannot reclaim it until its status changes. */ static inline bool ext4_es_must_keep(struct extent_status *es) { /* fiemap, bigalloc, and seek_data/hole need to use it. */ if (ext4_es_is_delayed(es)) return true; return false; } static inline struct extent_status *__es_alloc_extent(bool nofail) { if (!nofail) return kmem_cache_alloc(ext4_es_cachep, GFP_ATOMIC); return kmem_cache_zalloc(ext4_es_cachep, GFP_KERNEL | __GFP_NOFAIL); } static void ext4_es_init_extent(struct inode *inode, struct extent_status *es, ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk) { es->es_lblk = lblk; es->es_len = len; es->es_pblk = pblk; /* We never try to reclaim a must kept extent, so we don't count it. */ if (!ext4_es_must_keep(es)) { if (!EXT4_I(inode)->i_es_shk_nr++) ext4_es_list_add(inode); percpu_counter_inc(&EXT4_SB(inode->i_sb)-> s_es_stats.es_stats_shk_cnt); } EXT4_I(inode)->i_es_all_nr++; percpu_counter_inc(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt); } static inline void __es_free_extent(struct extent_status *es) { kmem_cache_free(ext4_es_cachep, es); } static void ext4_es_free_extent(struct inode *inode, struct extent_status *es) { EXT4_I(inode)->i_es_all_nr--; percpu_counter_dec(&EXT4_SB(inode->i_sb)->s_es_stats.es_stats_all_cnt); /* Decrease the shrink counter when we can reclaim the extent. */ if (!ext4_es_must_keep(es)) { BUG_ON(EXT4_I(inode)->i_es_shk_nr == 0); if (!--EXT4_I(inode)->i_es_shk_nr) ext4_es_list_del(inode); percpu_counter_dec(&EXT4_SB(inode->i_sb)-> s_es_stats.es_stats_shk_cnt); } __es_free_extent(es); } /* * Check whether or not two extents can be merged * Condition: * - logical block number is contiguous * - physical block number is contiguous * - status is equal */ static int ext4_es_can_be_merged(struct extent_status *es1, struct extent_status *es2) { if (ext4_es_type(es1) != ext4_es_type(es2)) return 0; if (((__u64) es1->es_len) + es2->es_len > EXT_MAX_BLOCKS) { pr_warn("ES assertion failed when merging extents. " "The sum of lengths of es1 (%d) and es2 (%d) " "is bigger than allowed file size (%d)\n", es1->es_len, es2->es_len, EXT_MAX_BLOCKS); WARN_ON(1); return 0; } if (((__u64) es1->es_lblk) + es1->es_len != es2->es_lblk) return 0; if ((ext4_es_is_written(es1) || ext4_es_is_unwritten(es1)) && (ext4_es_pblock(es1) + es1->es_len == ext4_es_pblock(es2))) return 1; if (ext4_es_is_hole(es1)) return 1; /* we need to check delayed extent is without unwritten status */ if (ext4_es_is_delayed(es1) && !ext4_es_is_unwritten(es1)) return 1; return 0; } static struct extent_status * ext4_es_try_to_merge_left(struct inode *inode, struct extent_status *es) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct extent_status *es1; struct rb_node *node; node = rb_prev(&es->rb_node); if (!node) return es; es1 = rb_entry(node, struct extent_status, rb_node); if (ext4_es_can_be_merged(es1, es)) { es1->es_len += es->es_len; if (ext4_es_is_referenced(es)) ext4_es_set_referenced(es1); rb_erase(&es->rb_node, &tree->root); ext4_es_free_extent(inode, es); es = es1; } return es; } static struct extent_status * ext4_es_try_to_merge_right(struct inode *inode, struct extent_status *es) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct extent_status *es1; struct rb_node *node; node = rb_next(&es->rb_node); if (!node) return es; es1 = rb_entry(node, struct extent_status, rb_node); if (ext4_es_can_be_merged(es, es1)) { es->es_len += es1->es_len; if (ext4_es_is_referenced(es1)) ext4_es_set_referenced(es); rb_erase(node, &tree->root); ext4_es_free_extent(inode, es1); } return es; } #ifdef ES_AGGRESSIVE_TEST #include "ext4_extents.h" /* Needed when ES_AGGRESSIVE_TEST is defined */ static void ext4_es_insert_extent_ext_check(struct inode *inode, struct extent_status *es) { struct ext4_ext_path *path = NULL; struct ext4_extent *ex; ext4_lblk_t ee_block; ext4_fsblk_t ee_start; unsigned short ee_len; int depth, ee_status, es_status; path = ext4_find_extent(inode, es->es_lblk, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path)) return; depth = ext_depth(inode); ex = path[depth].p_ext; if (ex) { ee_block = le32_to_cpu(ex->ee_block); ee_start = ext4_ext_pblock(ex); ee_len = ext4_ext_get_actual_len(ex); ee_status = ext4_ext_is_unwritten(ex) ? 1 : 0; es_status = ext4_es_is_unwritten(es) ? 1 : 0; /* * Make sure ex and es are not overlap when we try to insert * a delayed/hole extent. */ if (!ext4_es_is_written(es) && !ext4_es_is_unwritten(es)) { if (in_range(es->es_lblk, ee_block, ee_len)) { pr_warn("ES insert assertion failed for " "inode: %lu we can find an extent " "at block [%d/%d/%llu/%c], but we " "want to add a delayed/hole extent " "[%d/%d/%llu/%x]\n", inode->i_ino, ee_block, ee_len, ee_start, ee_status ? 'u' : 'w', es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); } goto out; } /* * We don't check ee_block == es->es_lblk, etc. because es * might be a part of whole extent, vice versa. */ if (es->es_lblk < ee_block || ext4_es_pblock(es) != ee_start + es->es_lblk - ee_block) { pr_warn("ES insert assertion failed for inode: %lu " "ex_status [%d/%d/%llu/%c] != " "es_status [%d/%d/%llu/%c]\n", inode->i_ino, ee_block, ee_len, ee_start, ee_status ? 'u' : 'w', es->es_lblk, es->es_len, ext4_es_pblock(es), es_status ? 'u' : 'w'); goto out; } if (ee_status ^ es_status) { pr_warn("ES insert assertion failed for inode: %lu " "ex_status [%d/%d/%llu/%c] != " "es_status [%d/%d/%llu/%c]\n", inode->i_ino, ee_block, ee_len, ee_start, ee_status ? 'u' : 'w', es->es_lblk, es->es_len, ext4_es_pblock(es), es_status ? 'u' : 'w'); } } else { /* * We can't find an extent on disk. So we need to make sure * that we don't want to add an written/unwritten extent. */ if (!ext4_es_is_delayed(es) && !ext4_es_is_hole(es)) { pr_warn("ES insert assertion failed for inode: %lu " "can't find an extent at block %d but we want " "to add a written/unwritten extent " "[%d/%d/%llu/%x]\n", inode->i_ino, es->es_lblk, es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); } } out: ext4_free_ext_path(path); } static void ext4_es_insert_extent_ind_check(struct inode *inode, struct extent_status *es) { struct ext4_map_blocks map; int retval; /* * Here we call ext4_ind_map_blocks to lookup a block mapping because * 'Indirect' structure is defined in indirect.c. So we couldn't * access direct/indirect tree from outside. It is too dirty to define * this function in indirect.c file. */ map.m_lblk = es->es_lblk; map.m_len = es->es_len; retval = ext4_ind_map_blocks(NULL, inode, &map, 0); if (retval > 0) { if (ext4_es_is_delayed(es) || ext4_es_is_hole(es)) { /* * We want to add a delayed/hole extent but this * block has been allocated. */ pr_warn("ES insert assertion failed for inode: %lu " "We can find blocks but we want to add a " "delayed/hole extent [%d/%d/%llu/%x]\n", inode->i_ino, es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); return; } else if (ext4_es_is_written(es)) { if (retval != es->es_len) { pr_warn("ES insert assertion failed for " "inode: %lu retval %d != es_len %d\n", inode->i_ino, retval, es->es_len); return; } if (map.m_pblk != ext4_es_pblock(es)) { pr_warn("ES insert assertion failed for " "inode: %lu m_pblk %llu != " "es_pblk %llu\n", inode->i_ino, map.m_pblk, ext4_es_pblock(es)); return; } } else { /* * We don't need to check unwritten extent because * indirect-based file doesn't have it. */ BUG(); } } else if (retval == 0) { if (ext4_es_is_written(es)) { pr_warn("ES insert assertion failed for inode: %lu " "We can't find the block but we want to add " "a written extent [%d/%d/%llu/%x]\n", inode->i_ino, es->es_lblk, es->es_len, ext4_es_pblock(es), ext4_es_status(es)); return; } } } static inline void ext4_es_insert_extent_check(struct inode *inode, struct extent_status *es) { /* * We don't need to worry about the race condition because * caller takes i_data_sem locking. */ BUG_ON(!rwsem_is_locked(&EXT4_I(inode)->i_data_sem)); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) ext4_es_insert_extent_ext_check(inode, es); else ext4_es_insert_extent_ind_check(inode, es); } #else static inline void ext4_es_insert_extent_check(struct inode *inode, struct extent_status *es) { } #endif static int __es_insert_extent(struct inode *inode, struct extent_status *newes, struct extent_status *prealloc) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct rb_node **p = &tree->root.rb_node; struct rb_node *parent = NULL; struct extent_status *es; while (*p) { parent = *p; es = rb_entry(parent, struct extent_status, rb_node); if (newes->es_lblk < es->es_lblk) { if (ext4_es_can_be_merged(newes, es)) { /* * Here we can modify es_lblk directly * because it isn't overlapped. */ es->es_lblk = newes->es_lblk; es->es_len += newes->es_len; if (ext4_es_is_written(es) || ext4_es_is_unwritten(es)) ext4_es_store_pblock(es, newes->es_pblk); es = ext4_es_try_to_merge_left(inode, es); goto out; } p = &(*p)->rb_left; } else if (newes->es_lblk > ext4_es_end(es)) { if (ext4_es_can_be_merged(es, newes)) { es->es_len += newes->es_len; es = ext4_es_try_to_merge_right(inode, es); goto out; } p = &(*p)->rb_right; } else { BUG(); return -EINVAL; } } if (prealloc) es = prealloc; else es = __es_alloc_extent(false); if (!es) return -ENOMEM; ext4_es_init_extent(inode, es, newes->es_lblk, newes->es_len, newes->es_pblk); rb_link_node(&es->rb_node, parent, p); rb_insert_color(&es->rb_node, &tree->root); out: tree->cache_es = es; return 0; } /* * ext4_es_insert_extent() adds information to an inode's extent * status tree. */ void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk, unsigned int status) { struct extent_status newes; ext4_lblk_t end = lblk + len - 1; int err1 = 0, err2 = 0, err3 = 0; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct extent_status *es1 = NULL; struct extent_status *es2 = NULL; struct pending_reservation *pr = NULL; bool revise_pending = false; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; es_debug("add [%u/%u) %llu %x to extent status tree of inode %lu\n", lblk, len, pblk, status, inode->i_ino); if (!len) return; BUG_ON(end < lblk); if ((status & EXTENT_STATUS_DELAYED) && (status & EXTENT_STATUS_WRITTEN)) { ext4_warning(inode->i_sb, "Inserting extent [%u/%u] as " " delayed and written which can potentially " " cause data loss.", lblk, len); WARN_ON(1); } newes.es_lblk = lblk; newes.es_len = len; ext4_es_store_pblock_status(&newes, pblk, status); trace_ext4_es_insert_extent(inode, &newes); ext4_es_insert_extent_check(inode, &newes); revise_pending = sbi->s_cluster_ratio > 1 && test_opt(inode->i_sb, DELALLOC) && (status & (EXTENT_STATUS_WRITTEN | EXTENT_STATUS_UNWRITTEN)); retry: if (err1 && !es1) es1 = __es_alloc_extent(true); if ((err1 || err2) && !es2) es2 = __es_alloc_extent(true); if ((err1 || err2 || err3) && revise_pending && !pr) pr = __alloc_pending(true); write_lock(&EXT4_I(inode)->i_es_lock); err1 = __es_remove_extent(inode, lblk, end, NULL, es1); if (err1 != 0) goto error; /* Free preallocated extent if it didn't get used. */ if (es1) { if (!es1->es_len) __es_free_extent(es1); es1 = NULL; } err2 = __es_insert_extent(inode, &newes, es2); if (err2 == -ENOMEM && !ext4_es_must_keep(&newes)) err2 = 0; if (err2 != 0) goto error; /* Free preallocated extent if it didn't get used. */ if (es2) { if (!es2->es_len) __es_free_extent(es2); es2 = NULL; } if (revise_pending) { err3 = __revise_pending(inode, lblk, len, &pr); if (err3 != 0) goto error; if (pr) { __free_pending(pr); pr = NULL; } } error: write_unlock(&EXT4_I(inode)->i_es_lock); if (err1 || err2 || err3) goto retry; ext4_es_print_tree(inode); return; } /* * ext4_es_cache_extent() inserts information into the extent status * tree if and only if there isn't information about the range in * question already. */ void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, ext4_fsblk_t pblk, unsigned int status) { struct extent_status *es; struct extent_status newes; ext4_lblk_t end = lblk + len - 1; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; newes.es_lblk = lblk; newes.es_len = len; ext4_es_store_pblock_status(&newes, pblk, status); trace_ext4_es_cache_extent(inode, &newes); if (!len) return; BUG_ON(end < lblk); write_lock(&EXT4_I(inode)->i_es_lock); es = __es_tree_search(&EXT4_I(inode)->i_es_tree.root, lblk); if (!es || es->es_lblk > end) __es_insert_extent(inode, &newes, NULL); write_unlock(&EXT4_I(inode)->i_es_lock); } /* * ext4_es_lookup_extent() looks up an extent in extent status tree. * * ext4_es_lookup_extent is called by ext4_map_blocks/ext4_da_map_blocks. * * Return: 1 on found, 0 on not */ int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t *next_lblk, struct extent_status *es) { struct ext4_es_tree *tree; struct ext4_es_stats *stats; struct extent_status *es1 = NULL; struct rb_node *node; int found = 0; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return 0; trace_ext4_es_lookup_extent_enter(inode, lblk); es_debug("lookup extent in block %u\n", lblk); tree = &EXT4_I(inode)->i_es_tree; read_lock(&EXT4_I(inode)->i_es_lock); /* find extent in cache firstly */ es->es_lblk = es->es_len = es->es_pblk = 0; es1 = READ_ONCE(tree->cache_es); if (es1 && in_range(lblk, es1->es_lblk, es1->es_len)) { es_debug("%u cached by [%u/%u)\n", lblk, es1->es_lblk, es1->es_len); found = 1; goto out; } node = tree->root.rb_node; while (node) { es1 = rb_entry(node, struct extent_status, rb_node); if (lblk < es1->es_lblk) node = node->rb_left; else if (lblk > ext4_es_end(es1)) node = node->rb_right; else { found = 1; break; } } out: stats = &EXT4_SB(inode->i_sb)->s_es_stats; if (found) { BUG_ON(!es1); es->es_lblk = es1->es_lblk; es->es_len = es1->es_len; es->es_pblk = es1->es_pblk; if (!ext4_es_is_referenced(es1)) ext4_es_set_referenced(es1); percpu_counter_inc(&stats->es_stats_cache_hits); if (next_lblk) { node = rb_next(&es1->rb_node); if (node) { es1 = rb_entry(node, struct extent_status, rb_node); *next_lblk = es1->es_lblk; } else *next_lblk = 0; } } else { percpu_counter_inc(&stats->es_stats_cache_misses); } read_unlock(&EXT4_I(inode)->i_es_lock); trace_ext4_es_lookup_extent_exit(inode, es, found); return found; } struct rsvd_count { int ndelonly; bool first_do_lblk_found; ext4_lblk_t first_do_lblk; ext4_lblk_t last_do_lblk; struct extent_status *left_es; bool partial; ext4_lblk_t lclu; }; /* * init_rsvd - initialize reserved count data before removing block range * in file from extent status tree * * @inode - file containing range * @lblk - first block in range * @es - pointer to first extent in range * @rc - pointer to reserved count data * * Assumes es is not NULL */ static void init_rsvd(struct inode *inode, ext4_lblk_t lblk, struct extent_status *es, struct rsvd_count *rc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct rb_node *node; rc->ndelonly = 0; /* * for bigalloc, note the first delonly block in the range has not * been found, record the extent containing the block to the left of * the region to be removed, if any, and note that there's no partial * cluster to track */ if (sbi->s_cluster_ratio > 1) { rc->first_do_lblk_found = false; if (lblk > es->es_lblk) { rc->left_es = es; } else { node = rb_prev(&es->rb_node); rc->left_es = node ? rb_entry(node, struct extent_status, rb_node) : NULL; } rc->partial = false; } } /* * count_rsvd - count the clusters containing delayed and not unwritten * (delonly) blocks in a range within an extent and add to * the running tally in rsvd_count * * @inode - file containing extent * @lblk - first block in range * @len - length of range in blocks * @es - pointer to extent containing clusters to be counted * @rc - pointer to reserved count data * * Tracks partial clusters found at the beginning and end of extents so * they aren't overcounted when they span adjacent extents */ static void count_rsvd(struct inode *inode, ext4_lblk_t lblk, long len, struct extent_status *es, struct rsvd_count *rc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t i, end, nclu; if (!ext4_es_is_delonly(es)) return; WARN_ON(len <= 0); if (sbi->s_cluster_ratio == 1) { rc->ndelonly += (int) len; return; } /* bigalloc */ i = (lblk < es->es_lblk) ? es->es_lblk : lblk; end = lblk + (ext4_lblk_t) len - 1; end = (end > ext4_es_end(es)) ? ext4_es_end(es) : end; /* record the first block of the first delonly extent seen */ if (!rc->first_do_lblk_found) { rc->first_do_lblk = i; rc->first_do_lblk_found = true; } /* update the last lblk in the region seen so far */ rc->last_do_lblk = end; /* * if we're tracking a partial cluster and the current extent * doesn't start with it, count it and stop tracking */ if (rc->partial && (rc->lclu != EXT4_B2C(sbi, i))) { rc->ndelonly++; rc->partial = false; } /* * if the first cluster doesn't start on a cluster boundary but * ends on one, count it */ if (EXT4_LBLK_COFF(sbi, i) != 0) { if (end >= EXT4_LBLK_CFILL(sbi, i)) { rc->ndelonly++; rc->partial = false; i = EXT4_LBLK_CFILL(sbi, i) + 1; } } /* * if the current cluster starts on a cluster boundary, count the * number of whole delonly clusters in the extent */ if ((i + sbi->s_cluster_ratio - 1) <= end) { nclu = (end - i + 1) >> sbi->s_cluster_bits; rc->ndelonly += nclu; i += nclu << sbi->s_cluster_bits; } /* * start tracking a partial cluster if there's a partial at the end * of the current extent and we're not already tracking one */ if (!rc->partial && i <= end) { rc->partial = true; rc->lclu = EXT4_B2C(sbi, i); } } /* * __pr_tree_search - search for a pending cluster reservation * * @root - root of pending reservation tree * @lclu - logical cluster to search for * * Returns the pending reservation for the cluster identified by @lclu * if found. If not, returns a reservation for the next cluster if any, * and if not, returns NULL. */ static struct pending_reservation *__pr_tree_search(struct rb_root *root, ext4_lblk_t lclu) { struct rb_node *node = root->rb_node; struct pending_reservation *pr = NULL; while (node) { pr = rb_entry(node, struct pending_reservation, rb_node); if (lclu < pr->lclu) node = node->rb_left; else if (lclu > pr->lclu) node = node->rb_right; else return pr; } if (pr && lclu < pr->lclu) return pr; if (pr && lclu > pr->lclu) { node = rb_next(&pr->rb_node); return node ? rb_entry(node, struct pending_reservation, rb_node) : NULL; } return NULL; } /* * get_rsvd - calculates and returns the number of cluster reservations to be * released when removing a block range from the extent status tree * and releases any pending reservations within the range * * @inode - file containing block range * @end - last block in range * @right_es - pointer to extent containing next block beyond end or NULL * @rc - pointer to reserved count data * * The number of reservations to be released is equal to the number of * clusters containing delayed and not unwritten (delonly) blocks within * the range, minus the number of clusters still containing delonly blocks * at the ends of the range, and minus the number of pending reservations * within the range. */ static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end, struct extent_status *right_es, struct rsvd_count *rc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct pending_reservation *pr; struct ext4_pending_tree *tree = &EXT4_I(inode)->i_pending_tree; struct rb_node *node; ext4_lblk_t first_lclu, last_lclu; bool left_delonly, right_delonly, count_pending; struct extent_status *es; if (sbi->s_cluster_ratio > 1) { /* count any remaining partial cluster */ if (rc->partial) rc->ndelonly++; if (rc->ndelonly == 0) return 0; first_lclu = EXT4_B2C(sbi, rc->first_do_lblk); last_lclu = EXT4_B2C(sbi, rc->last_do_lblk); /* * decrease the delonly count by the number of clusters at the * ends of the range that still contain delonly blocks - * these clusters still need to be reserved */ left_delonly = right_delonly = false; es = rc->left_es; while (es && ext4_es_end(es) >= EXT4_LBLK_CMASK(sbi, rc->first_do_lblk)) { if (ext4_es_is_delonly(es)) { rc->ndelonly--; left_delonly = true; break; } node = rb_prev(&es->rb_node); if (!node) break; es = rb_entry(node, struct extent_status, rb_node); } if (right_es && (!left_delonly || first_lclu != last_lclu)) { if (end < ext4_es_end(right_es)) { es = right_es; } else { node = rb_next(&right_es->rb_node); es = node ? rb_entry(node, struct extent_status, rb_node) : NULL; } while (es && es->es_lblk <= EXT4_LBLK_CFILL(sbi, rc->last_do_lblk)) { if (ext4_es_is_delonly(es)) { rc->ndelonly--; right_delonly = true; break; } node = rb_next(&es->rb_node); if (!node) break; es = rb_entry(node, struct extent_status, rb_node); } } /* * Determine the block range that should be searched for * pending reservations, if any. Clusters on the ends of the * original removed range containing delonly blocks are * excluded. They've already been accounted for and it's not * possible to determine if an associated pending reservation * should be released with the information available in the * extents status tree. */ if (first_lclu == last_lclu) { if (left_delonly | right_delonly) count_pending = false; else count_pending = true; } else { if (left_delonly) first_lclu++; if (right_delonly) last_lclu--; if (first_lclu <= last_lclu) count_pending = true; else count_pending = false; } /* * a pending reservation found between first_lclu and last_lclu * represents an allocated cluster that contained at least one * delonly block, so the delonly total must be reduced by one * for each pending reservation found and released */ if (count_pending) { pr = __pr_tree_search(&tree->root, first_lclu); while (pr && pr->lclu <= last_lclu) { rc->ndelonly--; node = rb_next(&pr->rb_node); rb_erase(&pr->rb_node, &tree->root); __free_pending(pr); if (!node) break; pr = rb_entry(node, struct pending_reservation, rb_node); } } } return rc->ndelonly; } /* * __es_remove_extent - removes block range from extent status tree * * @inode - file containing range * @lblk - first block in range * @end - last block in range * @reserved - number of cluster reservations released * @prealloc - pre-allocated es to avoid memory allocation failures * * If @reserved is not NULL and delayed allocation is enabled, counts * block/cluster reservations freed by removing range and if bigalloc * enabled cancels pending reservations as needed. Returns 0 on success, * error code on failure. */ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t end, int *reserved, struct extent_status *prealloc) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct rb_node *node; struct extent_status *es; struct extent_status orig_es; ext4_lblk_t len1, len2; ext4_fsblk_t block; int err = 0; bool count_reserved = true; struct rsvd_count rc; if (reserved == NULL || !test_opt(inode->i_sb, DELALLOC)) count_reserved = false; es = __es_tree_search(&tree->root, lblk); if (!es) goto out; if (es->es_lblk > end) goto out; /* Simply invalidate cache_es. */ tree->cache_es = NULL; if (count_reserved) init_rsvd(inode, lblk, es, &rc); orig_es.es_lblk = es->es_lblk; orig_es.es_len = es->es_len; orig_es.es_pblk = es->es_pblk; len1 = lblk > es->es_lblk ? lblk - es->es_lblk : 0; len2 = ext4_es_end(es) > end ? ext4_es_end(es) - end : 0; if (len1 > 0) es->es_len = len1; if (len2 > 0) { if (len1 > 0) { struct extent_status newes; newes.es_lblk = end + 1; newes.es_len = len2; block = 0x7FDEADBEEFULL; if (ext4_es_is_written(&orig_es) || ext4_es_is_unwritten(&orig_es)) block = ext4_es_pblock(&orig_es) + orig_es.es_len - len2; ext4_es_store_pblock_status(&newes, block, ext4_es_status(&orig_es)); err = __es_insert_extent(inode, &newes, prealloc); if (err) { if (!ext4_es_must_keep(&newes)) return 0; es->es_lblk = orig_es.es_lblk; es->es_len = orig_es.es_len; goto out; } } else { es->es_lblk = end + 1; es->es_len = len2; if (ext4_es_is_written(es) || ext4_es_is_unwritten(es)) { block = orig_es.es_pblk + orig_es.es_len - len2; ext4_es_store_pblock(es, block); } } if (count_reserved) count_rsvd(inode, orig_es.es_lblk + len1, orig_es.es_len - len1 - len2, &orig_es, &rc); goto out_get_reserved; } if (len1 > 0) { if (count_reserved) count_rsvd(inode, lblk, orig_es.es_len - len1, &orig_es, &rc); node = rb_next(&es->rb_node); if (node) es = rb_entry(node, struct extent_status, rb_node); else es = NULL; } while (es && ext4_es_end(es) <= end) { if (count_reserved) count_rsvd(inode, es->es_lblk, es->es_len, es, &rc); node = rb_next(&es->rb_node); rb_erase(&es->rb_node, &tree->root); ext4_es_free_extent(inode, es); if (!node) { es = NULL; break; } es = rb_entry(node, struct extent_status, rb_node); } if (es && es->es_lblk < end + 1) { ext4_lblk_t orig_len = es->es_len; len1 = ext4_es_end(es) - end; if (count_reserved) count_rsvd(inode, es->es_lblk, orig_len - len1, es, &rc); es->es_lblk = end + 1; es->es_len = len1; if (ext4_es_is_written(es) || ext4_es_is_unwritten(es)) { block = es->es_pblk + orig_len - len1; ext4_es_store_pblock(es, block); } } out_get_reserved: if (count_reserved) *reserved = get_rsvd(inode, end, es, &rc); out: return err; } /* * ext4_es_remove_extent - removes block range from extent status tree * * @inode - file containing range * @lblk - first block in range * @len - number of blocks to remove * * Reduces block/cluster reservation count and for bigalloc cancels pending * reservations as needed. Returns 0 on success, error code on failure. */ int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len) { ext4_lblk_t end; int err = 0; int reserved = 0; struct extent_status *es = NULL; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return 0; trace_ext4_es_remove_extent(inode, lblk, len); es_debug("remove [%u/%u) from extent status tree of inode %lu\n", lblk, len, inode->i_ino); if (!len) return err; end = lblk + len - 1; BUG_ON(end < lblk); retry: if (err && !es) es = __es_alloc_extent(true); /* * ext4_clear_inode() depends on us taking i_es_lock unconditionally * so that we are sure __es_shrink() is done with the inode before it * is reclaimed. */ write_lock(&EXT4_I(inode)->i_es_lock); err = __es_remove_extent(inode, lblk, end, &reserved, es); /* Free preallocated extent if it didn't get used. */ if (es) { if (!es->es_len) __es_free_extent(es); es = NULL; } write_unlock(&EXT4_I(inode)->i_es_lock); if (err) goto retry; ext4_es_print_tree(inode); ext4_da_release_space(inode, reserved); return 0; } static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, struct ext4_inode_info *locked_ei) { struct ext4_inode_info *ei; struct ext4_es_stats *es_stats; ktime_t start_time; u64 scan_time; int nr_to_walk; int nr_shrunk = 0; int retried = 0, nr_skipped = 0; es_stats = &sbi->s_es_stats; start_time = ktime_get(); retry: spin_lock(&sbi->s_es_lock); nr_to_walk = sbi->s_es_nr_inode; while (nr_to_walk-- > 0) { if (list_empty(&sbi->s_es_list)) { spin_unlock(&sbi->s_es_lock); goto out; } ei = list_first_entry(&sbi->s_es_list, struct ext4_inode_info, i_es_list); /* Move the inode to the tail */ list_move_tail(&ei->i_es_list, &sbi->s_es_list); /* * Normally we try hard to avoid shrinking precached inodes, * but we will as a last resort. */ if (!retried && ext4_test_inode_state(&ei->vfs_inode, EXT4_STATE_EXT_PRECACHED)) { nr_skipped++; continue; } if (ei == locked_ei || !write_trylock(&ei->i_es_lock)) { nr_skipped++; continue; } /* * Now we hold i_es_lock which protects us from inode reclaim * freeing inode under us */ spin_unlock(&sbi->s_es_lock); nr_shrunk += es_reclaim_extents(ei, &nr_to_scan); write_unlock(&ei->i_es_lock); if (nr_to_scan <= 0) goto out; spin_lock(&sbi->s_es_lock); } spin_unlock(&sbi->s_es_lock); /* * If we skipped any inodes, and we weren't able to make any * forward progress, try again to scan precached inodes. */ if ((nr_shrunk == 0) && nr_skipped && !retried) { retried++; goto retry; } if (locked_ei && nr_shrunk == 0) nr_shrunk = es_reclaim_extents(locked_ei, &nr_to_scan); out: scan_time = ktime_to_ns(ktime_sub(ktime_get(), start_time)); if (likely(es_stats->es_stats_scan_time)) es_stats->es_stats_scan_time = (scan_time + es_stats->es_stats_scan_time*3) / 4; else es_stats->es_stats_scan_time = scan_time; if (scan_time > es_stats->es_stats_max_scan_time) es_stats->es_stats_max_scan_time = scan_time; if (likely(es_stats->es_stats_shrunk)) es_stats->es_stats_shrunk = (nr_shrunk + es_stats->es_stats_shrunk*3) / 4; else es_stats->es_stats_shrunk = nr_shrunk; trace_ext4_es_shrink(sbi->s_sb, nr_shrunk, scan_time, nr_skipped, retried); return nr_shrunk; } static unsigned long ext4_es_count(struct shrinker *shrink, struct shrink_control *sc) { unsigned long nr; struct ext4_sb_info *sbi; sbi = container_of(shrink, struct ext4_sb_info, s_es_shrinker); nr = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt); trace_ext4_es_shrink_count(sbi->s_sb, sc->nr_to_scan, nr); return nr; } static unsigned long ext4_es_scan(struct shrinker *shrink, struct shrink_control *sc) { struct ext4_sb_info *sbi = container_of(shrink, struct ext4_sb_info, s_es_shrinker); int nr_to_scan = sc->nr_to_scan; int ret, nr_shrunk; ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt); trace_ext4_es_shrink_scan_enter(sbi->s_sb, nr_to_scan, ret); nr_shrunk = __es_shrink(sbi, nr_to_scan, NULL); ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt); trace_ext4_es_shrink_scan_exit(sbi->s_sb, nr_shrunk, ret); return nr_shrunk; } int ext4_seq_es_shrinker_info_show(struct seq_file *seq, void *v) { struct ext4_sb_info *sbi = EXT4_SB((struct super_block *) seq->private); struct ext4_es_stats *es_stats = &sbi->s_es_stats; struct ext4_inode_info *ei, *max = NULL; unsigned int inode_cnt = 0; if (v != SEQ_START_TOKEN) return 0; /* here we just find an inode that has the max nr. of objects */ spin_lock(&sbi->s_es_lock); list_for_each_entry(ei, &sbi->s_es_list, i_es_list) { inode_cnt++; if (max && max->i_es_all_nr < ei->i_es_all_nr) max = ei; else if (!max) max = ei; } spin_unlock(&sbi->s_es_lock); seq_printf(seq, "stats:\n %lld objects\n %lld reclaimable objects\n", percpu_counter_sum_positive(&es_stats->es_stats_all_cnt), percpu_counter_sum_positive(&es_stats->es_stats_shk_cnt)); seq_printf(seq, " %lld/%lld cache hits/misses\n", percpu_counter_sum_positive(&es_stats->es_stats_cache_hits), percpu_counter_sum_positive(&es_stats->es_stats_cache_misses)); if (inode_cnt) seq_printf(seq, " %d inodes on list\n", inode_cnt); seq_printf(seq, "average:\n %llu us scan time\n", div_u64(es_stats->es_stats_scan_time, 1000)); seq_printf(seq, " %lu shrunk objects\n", es_stats->es_stats_shrunk); if (inode_cnt) seq_printf(seq, "maximum:\n %lu inode (%u objects, %u reclaimable)\n" " %llu us max scan time\n", max->vfs_inode.i_ino, max->i_es_all_nr, max->i_es_shk_nr, div_u64(es_stats->es_stats_max_scan_time, 1000)); return 0; } int ext4_es_register_shrinker(struct ext4_sb_info *sbi) { int err; /* Make sure we have enough bits for physical block number */ BUILD_BUG_ON(ES_SHIFT < 48); INIT_LIST_HEAD(&sbi->s_es_list); sbi->s_es_nr_inode = 0; spin_lock_init(&sbi->s_es_lock); sbi->s_es_stats.es_stats_shrunk = 0; err = percpu_counter_init(&sbi->s_es_stats.es_stats_cache_hits, 0, GFP_KERNEL); if (err) return err; err = percpu_counter_init(&sbi->s_es_stats.es_stats_cache_misses, 0, GFP_KERNEL); if (err) goto err1; sbi->s_es_stats.es_stats_scan_time = 0; sbi->s_es_stats.es_stats_max_scan_time = 0; err = percpu_counter_init(&sbi->s_es_stats.es_stats_all_cnt, 0, GFP_KERNEL); if (err) goto err2; err = percpu_counter_init(&sbi->s_es_stats.es_stats_shk_cnt, 0, GFP_KERNEL); if (err) goto err3; sbi->s_es_shrinker.scan_objects = ext4_es_scan; sbi->s_es_shrinker.count_objects = ext4_es_count; sbi->s_es_shrinker.seeks = DEFAULT_SEEKS; err = register_shrinker(&sbi->s_es_shrinker, "ext4-es:%s", sbi->s_sb->s_id); if (err) goto err4; return 0; err4: percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt); err3: percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt); err2: percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_misses); err1: percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_hits); return err; } void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi) { percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_hits); percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_misses); percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt); percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt); unregister_shrinker(&sbi->s_es_shrinker); } /* * Shrink extents in given inode from ei->i_es_shrink_lblk till end. Scan at * most *nr_to_scan extents, update *nr_to_scan accordingly. * * Return 0 if we hit end of tree / interval, 1 if we exhausted nr_to_scan. * Increment *nr_shrunk by the number of reclaimed extents. Also update * ei->i_es_shrink_lblk to where we should continue scanning. */ static int es_do_reclaim_extents(struct ext4_inode_info *ei, ext4_lblk_t end, int *nr_to_scan, int *nr_shrunk) { struct inode *inode = &ei->vfs_inode; struct ext4_es_tree *tree = &ei->i_es_tree; struct extent_status *es; struct rb_node *node; es = __es_tree_search(&tree->root, ei->i_es_shrink_lblk); if (!es) goto out_wrap; while (*nr_to_scan > 0) { if (es->es_lblk > end) { ei->i_es_shrink_lblk = end + 1; return 0; } (*nr_to_scan)--; node = rb_next(&es->rb_node); if (ext4_es_must_keep(es)) goto next; if (ext4_es_is_referenced(es)) { ext4_es_clear_referenced(es); goto next; } rb_erase(&es->rb_node, &tree->root); ext4_es_free_extent(inode, es); (*nr_shrunk)++; next: if (!node) goto out_wrap; es = rb_entry(node, struct extent_status, rb_node); } ei->i_es_shrink_lblk = es->es_lblk; return 1; out_wrap: ei->i_es_shrink_lblk = 0; return 0; } static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan) { struct inode *inode = &ei->vfs_inode; int nr_shrunk = 0; ext4_lblk_t start = ei->i_es_shrink_lblk; static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); if (ei->i_es_shk_nr == 0) return 0; if (ext4_test_inode_state(inode, EXT4_STATE_EXT_PRECACHED) && __ratelimit(&_rs)) ext4_warning(inode->i_sb, "forced shrink of precached extents"); if (!es_do_reclaim_extents(ei, EXT_MAX_BLOCKS, nr_to_scan, &nr_shrunk) && start != 0) es_do_reclaim_extents(ei, start - 1, nr_to_scan, &nr_shrunk); ei->i_es_tree.cache_es = NULL; return nr_shrunk; } /* * Called to support EXT4_IOC_CLEAR_ES_CACHE. We can only remove * discretionary entries from the extent status cache. (Some entries * must be present for proper operations.) */ void ext4_clear_inode_es(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct extent_status *es; struct ext4_es_tree *tree; struct rb_node *node; write_lock(&ei->i_es_lock); tree = &EXT4_I(inode)->i_es_tree; tree->cache_es = NULL; node = rb_first(&tree->root); while (node) { es = rb_entry(node, struct extent_status, rb_node); node = rb_next(node); if (!ext4_es_must_keep(es)) { rb_erase(&es->rb_node, &tree->root); ext4_es_free_extent(inode, es); } } ext4_clear_inode_state(inode, EXT4_STATE_EXT_PRECACHED); write_unlock(&ei->i_es_lock); } #ifdef ES_DEBUG__ static void ext4_print_pending_tree(struct inode *inode) { struct ext4_pending_tree *tree; struct rb_node *node; struct pending_reservation *pr; printk(KERN_DEBUG "pending reservations for inode %lu:", inode->i_ino); tree = &EXT4_I(inode)->i_pending_tree; node = rb_first(&tree->root); while (node) { pr = rb_entry(node, struct pending_reservation, rb_node); printk(KERN_DEBUG " %u", pr->lclu); node = rb_next(node); } printk(KERN_DEBUG "\n"); } #else #define ext4_print_pending_tree(inode) #endif int __init ext4_init_pending(void) { ext4_pending_cachep = kmem_cache_create("ext4_pending_reservation", sizeof(struct pending_reservation), 0, (SLAB_RECLAIM_ACCOUNT), NULL); if (ext4_pending_cachep == NULL) return -ENOMEM; return 0; } void ext4_exit_pending(void) { kmem_cache_destroy(ext4_pending_cachep); } void ext4_init_pending_tree(struct ext4_pending_tree *tree) { tree->root = RB_ROOT; } /* * __get_pending - retrieve a pointer to a pending reservation * * @inode - file containing the pending cluster reservation * @lclu - logical cluster of interest * * Returns a pointer to a pending reservation if it's a member of * the set, and NULL if not. Must be called holding i_es_lock. */ static struct pending_reservation *__get_pending(struct inode *inode, ext4_lblk_t lclu) { struct ext4_pending_tree *tree; struct rb_node *node; struct pending_reservation *pr = NULL; tree = &EXT4_I(inode)->i_pending_tree; node = (&tree->root)->rb_node; while (node) { pr = rb_entry(node, struct pending_reservation, rb_node); if (lclu < pr->lclu) node = node->rb_left; else if (lclu > pr->lclu) node = node->rb_right; else if (lclu == pr->lclu) return pr; } return NULL; } /* * __insert_pending - adds a pending cluster reservation to the set of * pending reservations * * @inode - file containing the cluster * @lblk - logical block in the cluster to be added * @prealloc - preallocated pending entry * * Returns 0 on successful insertion and -ENOMEM on failure. If the * pending reservation is already in the set, returns successfully. */ static int __insert_pending(struct inode *inode, ext4_lblk_t lblk, struct pending_reservation **prealloc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_pending_tree *tree = &EXT4_I(inode)->i_pending_tree; struct rb_node **p = &tree->root.rb_node; struct rb_node *parent = NULL; struct pending_reservation *pr; ext4_lblk_t lclu; int ret = 0; lclu = EXT4_B2C(sbi, lblk); /* search to find parent for insertion */ while (*p) { parent = *p; pr = rb_entry(parent, struct pending_reservation, rb_node); if (lclu < pr->lclu) { p = &(*p)->rb_left; } else if (lclu > pr->lclu) { p = &(*p)->rb_right; } else { /* pending reservation already inserted */ goto out; } } if (likely(*prealloc == NULL)) { pr = __alloc_pending(false); if (!pr) { ret = -ENOMEM; goto out; } } else { pr = *prealloc; *prealloc = NULL; } pr->lclu = lclu; rb_link_node(&pr->rb_node, parent, p); rb_insert_color(&pr->rb_node, &tree->root); out: return ret; } /* * __remove_pending - removes a pending cluster reservation from the set * of pending reservations * * @inode - file containing the cluster * @lblk - logical block in the pending cluster reservation to be removed * * Returns successfully if pending reservation is not a member of the set. */ static void __remove_pending(struct inode *inode, ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct pending_reservation *pr; struct ext4_pending_tree *tree; pr = __get_pending(inode, EXT4_B2C(sbi, lblk)); if (pr != NULL) { tree = &EXT4_I(inode)->i_pending_tree; rb_erase(&pr->rb_node, &tree->root); __free_pending(pr); } } /* * ext4_remove_pending - removes a pending cluster reservation from the set * of pending reservations * * @inode - file containing the cluster * @lblk - logical block in the pending cluster reservation to be removed * * Locking for external use of __remove_pending. */ void ext4_remove_pending(struct inode *inode, ext4_lblk_t lblk) { struct ext4_inode_info *ei = EXT4_I(inode); write_lock(&ei->i_es_lock); __remove_pending(inode, lblk); write_unlock(&ei->i_es_lock); } /* * ext4_is_pending - determine whether a cluster has a pending reservation * on it * * @inode - file containing the cluster * @lblk - logical block in the cluster * * Returns true if there's a pending reservation for the cluster in the * set of pending reservations, and false if not. */ bool ext4_is_pending(struct inode *inode, ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); bool ret; read_lock(&ei->i_es_lock); ret = (bool)(__get_pending(inode, EXT4_B2C(sbi, lblk)) != NULL); read_unlock(&ei->i_es_lock); return ret; } /* * ext4_es_insert_delayed_block - adds a delayed block to the extents status * tree, adding a pending reservation where * needed * * @inode - file containing the newly added block * @lblk - logical block to be added * @allocated - indicates whether a physical cluster has been allocated for * the logical cluster that contains the block * * Returns 0 on success, negative error code on failure. */ int ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk, bool allocated) { struct extent_status newes; int err1 = 0, err2 = 0, err3 = 0; struct extent_status *es1 = NULL; struct extent_status *es2 = NULL; struct pending_reservation *pr = NULL; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return 0; es_debug("add [%u/1) delayed to extent status tree of inode %lu\n", lblk, inode->i_ino); newes.es_lblk = lblk; newes.es_len = 1; ext4_es_store_pblock_status(&newes, ~0, EXTENT_STATUS_DELAYED); trace_ext4_es_insert_delayed_block(inode, &newes, allocated); ext4_es_insert_extent_check(inode, &newes); retry: if (err1 && !es1) es1 = __es_alloc_extent(true); if ((err1 || err2) && !es2) es2 = __es_alloc_extent(true); if ((err1 || err2 || err3) && allocated && !pr) pr = __alloc_pending(true); write_lock(&EXT4_I(inode)->i_es_lock); err1 = __es_remove_extent(inode, lblk, lblk, NULL, es1); if (err1 != 0) goto error; /* Free preallocated extent if it didn't get used. */ if (es1) { if (!es1->es_len) __es_free_extent(es1); es1 = NULL; } err2 = __es_insert_extent(inode, &newes, es2); if (err2 != 0) goto error; /* Free preallocated extent if it didn't get used. */ if (es2) { if (!es2->es_len) __es_free_extent(es2); es2 = NULL; } if (allocated) { err3 = __insert_pending(inode, lblk, &pr); if (err3 != 0) goto error; if (pr) { __free_pending(pr); pr = NULL; } } error: write_unlock(&EXT4_I(inode)->i_es_lock); if (err1 || err2 || err3) goto retry; ext4_es_print_tree(inode); ext4_print_pending_tree(inode); return 0; } /* * __es_delayed_clu - count number of clusters containing blocks that * are delayed only * * @inode - file containing block range * @start - logical block defining start of range * @end - logical block defining end of range * * Returns the number of clusters containing only delayed (not delayed * and unwritten) blocks in the range specified by @start and @end. Any * cluster or part of a cluster within the range and containing a delayed * and not unwritten block within the range is counted as a whole cluster. */ static unsigned int __es_delayed_clu(struct inode *inode, ext4_lblk_t start, ext4_lblk_t end) { struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree; struct extent_status *es; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct rb_node *node; ext4_lblk_t first_lclu, last_lclu; unsigned long long last_counted_lclu; unsigned int n = 0; /* guaranteed to be unequal to any ext4_lblk_t value */ last_counted_lclu = ~0ULL; es = __es_tree_search(&tree->root, start); while (es && (es->es_lblk <= end)) { if (ext4_es_is_delonly(es)) { if (es->es_lblk <= start) first_lclu = EXT4_B2C(sbi, start); else first_lclu = EXT4_B2C(sbi, es->es_lblk); if (ext4_es_end(es) >= end) last_lclu = EXT4_B2C(sbi, end); else last_lclu = EXT4_B2C(sbi, ext4_es_end(es)); if (first_lclu == last_counted_lclu) n += last_lclu - first_lclu; else n += last_lclu - first_lclu + 1; last_counted_lclu = last_lclu; } node = rb_next(&es->rb_node); if (!node) break; es = rb_entry(node, struct extent_status, rb_node); } return n; } /* * ext4_es_delayed_clu - count number of clusters containing blocks that * are both delayed and unwritten * * @inode - file containing block range * @lblk - logical block defining start of range * @len - number of blocks in range * * Locking for external use of __es_delayed_clu(). */ unsigned int ext4_es_delayed_clu(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len) { struct ext4_inode_info *ei = EXT4_I(inode); ext4_lblk_t end; unsigned int n; if (len == 0) return 0; end = lblk + len - 1; WARN_ON(end < lblk); read_lock(&ei->i_es_lock); n = __es_delayed_clu(inode, lblk, end); read_unlock(&ei->i_es_lock); return n; } /* * __revise_pending - makes, cancels, or leaves unchanged pending cluster * reservations for a specified block range depending * upon the presence or absence of delayed blocks * outside the range within clusters at the ends of the * range * * @inode - file containing the range * @lblk - logical block defining the start of range * @len - length of range in blocks * @prealloc - preallocated pending entry * * Used after a newly allocated extent is added to the extents status tree. * Requires that the extents in the range have either written or unwritten * status. Must be called while holding i_es_lock. */ static int __revise_pending(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len, struct pending_reservation **prealloc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t end = lblk + len - 1; ext4_lblk_t first, last; bool f_del = false, l_del = false; int ret = 0; if (len == 0) return 0; /* * Two cases - block range within single cluster and block range * spanning two or more clusters. Note that a cluster belonging * to a range starting and/or ending on a cluster boundary is treated * as if it does not contain a delayed extent. The new range may * have allocated space for previously delayed blocks out to the * cluster boundary, requiring that any pre-existing pending * reservation be canceled. Because this code only looks at blocks * outside the range, it should revise pending reservations * correctly even if the extent represented by the range can't be * inserted in the extents status tree due to ENOSPC. */ if (EXT4_B2C(sbi, lblk) == EXT4_B2C(sbi, end)) { first = EXT4_LBLK_CMASK(sbi, lblk); if (first != lblk) f_del = __es_scan_range(inode, &ext4_es_is_delonly, first, lblk - 1); if (f_del) { ret = __insert_pending(inode, first, prealloc); if (ret < 0) goto out; } else { last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1; if (last != end) l_del = __es_scan_range(inode, &ext4_es_is_delonly, end + 1, last); if (l_del) { ret = __insert_pending(inode, last, prealloc); if (ret < 0) goto out; } else __remove_pending(inode, last); } } else { first = EXT4_LBLK_CMASK(sbi, lblk); if (first != lblk) f_del = __es_scan_range(inode, &ext4_es_is_delonly, first, lblk - 1); if (f_del) { ret = __insert_pending(inode, first, prealloc); if (ret < 0) goto out; } else __remove_pending(inode, first); last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1; if (last != end) l_del = __es_scan_range(inode, &ext4_es_is_delonly, end + 1, last); if (l_del) { ret = __insert_pending(inode, last, prealloc); if (ret < 0) goto out; } else __remove_pending(inode, last); } out: return ret; } |
| 51 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/userfaultfd_k.h * * Copyright (C) 2015 Red Hat, Inc. * */ #ifndef _LINUX_USERFAULTFD_K_H #define _LINUX_USERFAULTFD_K_H #ifdef CONFIG_USERFAULTFD #include <linux/userfaultfd.h> /* linux/include/uapi/linux/userfaultfd.h */ #include <linux/fcntl.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/swapops.h> #include <asm-generic/pgtable_uffd.h> #include <linux/hugetlb_inline.h> /* The set of all possible UFFD-related VM flags. */ #define __VM_UFFD_FLAGS (VM_UFFD_MISSING | VM_UFFD_WP | VM_UFFD_MINOR) /* * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining * new flags, since they might collide with O_* ones. We want * to re-use O_* flags that couldn't possibly have a meaning * from userfaultfd, in order to leave a free define-space for * shared O_* flags. */ #define UFFD_CLOEXEC O_CLOEXEC #define UFFD_NONBLOCK O_NONBLOCK #define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) #define UFFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS) /* * Start with fault_pending_wqh and fault_wqh so they're more likely * to be in the same cacheline. * * Locking order: * fd_wqh.lock * fault_pending_wqh.lock * fault_wqh.lock * event_wqh.lock * * To avoid deadlocks, IRQs must be disabled when taking any of the above locks, * since fd_wqh.lock is taken by aio_poll() while it's holding a lock that's * also taken in IRQ context. */ /* * ANDROID: CRC fix for commit f91e6b41dd11 ("userfaultfd: move userfaultfd_ctx * struct to header file") */ #ifndef __GENKSYMS__ struct userfaultfd_ctx { /* waitqueue head for the pending (i.e. not read) userfaults */ wait_queue_head_t fault_pending_wqh; /* waitqueue head for the userfaults */ wait_queue_head_t fault_wqh; /* waitqueue head for the pseudo fd to wakeup poll/read */ wait_queue_head_t fd_wqh; /* waitqueue head for events */ wait_queue_head_t event_wqh; /* a refile sequence protected by fault_pending_wqh lock */ seqcount_spinlock_t refile_seq; /* pseudo fd refcounting */ refcount_t refcount; /* userfaultfd syscall flags */ unsigned int flags; /* features requested from the userspace */ unsigned int features; /* released */ bool released; /* * Prevents userfaultfd operations (fill/move/wp) from happening while * some non-cooperative event(s) is taking place. Increments are done * in write-mode. Whereas, userfaultfd operations, which includes * reading mmap_changing, is done under read-mode. */ struct rw_semaphore map_changing_lock; /* memory mappings are changing because of non-cooperative event */ atomic_t mmap_changing; /* mm with one ore more vmas attached to this userfaultfd_ctx */ struct mm_struct *mm; ANDROID_KABI_RESERVE(1); }; #endif extern int sysctl_unprivileged_userfaultfd; extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason); /* * The mode of operation for __mcopy_atomic and its helpers. * * This is almost an implementation detail (mcopy_atomic below doesn't take this * as a parameter), but it's exposed here because memory-kind-specific * implementations (e.g. hugetlbfs) need to know the mode of operation. */ enum mcopy_atomic_mode { /* A normal copy_from_user into the destination range. */ MCOPY_ATOMIC_NORMAL, /* Don't copy; map the destination range to the zero page. */ MCOPY_ATOMIC_ZEROPAGE, /* Just install pte(s) with the existing page(s) in the page cache. */ MCOPY_ATOMIC_CONTINUE, }; extern int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, struct page *page, bool newly_allocated, bool wp_copy); extern ssize_t mcopy_atomic(struct userfaultfd_ctx *ctx, unsigned long dst_start, unsigned long src_start, unsigned long len, __u64 mode); extern ssize_t mfill_zeropage(struct userfaultfd_ctx *ctx, unsigned long dst_start, unsigned long len); extern ssize_t mcopy_continue(struct userfaultfd_ctx *ctx, unsigned long dst_start, unsigned long len); extern int mwriteprotect_range(struct userfaultfd_ctx *ctx, unsigned long start, unsigned long len, bool enable_wp); extern void uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *vma, unsigned long start, unsigned long len, bool enable_wp); /* move_pages */ void double_pt_lock(spinlock_t *ptl1, spinlock_t *ptl2); void double_pt_unlock(spinlock_t *ptl1, spinlock_t *ptl2); ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start, unsigned long src_start, unsigned long len, __u64 flags); int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, unsigned long dst_addr, unsigned long src_addr); /* mm helpers */ static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, struct vm_userfaultfd_ctx vm_ctx) { return vma->vm_userfaultfd_ctx.ctx == vm_ctx.ctx; } /* * Never enable huge pmd sharing on some uffd registered vmas: * * - VM_UFFD_WP VMAs, because write protect information is per pgtable entry. * * - VM_UFFD_MINOR VMAs, because otherwise we would never get minor faults for * VMAs which share huge pmds. (If you have two mappings to the same * underlying pages, and fault in the non-UFFD-registered one with a write, * with huge pmd sharing this would *also* setup the second UFFD-registered * mapping, and we'd not get minor faults.) */ static inline bool uffd_disable_huge_pmd_share(struct vm_area_struct *vma) { return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR); } /* * Don't do fault around for either WP or MINOR registered uffd range. For * MINOR registered range, fault around will be a total disaster and ptes can * be installed without notifications; for WP it should mostly be fine as long * as the fault around checks for pte_none() before the installation, however * to be super safe we just forbid it. */ static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) { return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR); } static inline bool userfaultfd_missing(struct vm_area_struct *vma) { return vma->vm_flags & VM_UFFD_MISSING; } static inline bool userfaultfd_wp(struct vm_area_struct *vma) { return vma->vm_flags & VM_UFFD_WP; } static inline bool userfaultfd_minor(struct vm_area_struct *vma) { return vma->vm_flags & VM_UFFD_MINOR; } static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma, pte_t pte) { return userfaultfd_wp(vma) && pte_uffd_wp(pte); } static inline bool userfaultfd_huge_pmd_wp(struct vm_area_struct *vma, pmd_t pmd) { return userfaultfd_wp(vma) && pmd_uffd_wp(pmd); } static inline bool userfaultfd_armed(struct vm_area_struct *vma) { return vma->vm_flags & __VM_UFFD_FLAGS; } static inline bool vma_can_userfault(struct vm_area_struct *vma, unsigned long vm_flags) { if ((vm_flags & VM_UFFD_MINOR) && (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma))) return false; #ifndef CONFIG_PTE_MARKER_UFFD_WP /* * If user requested uffd-wp but not enabled pte markers for * uffd-wp, then shmem & hugetlbfs are not supported but only * anonymous. */ if ((vm_flags & VM_UFFD_WP) && !vma_is_anonymous(vma)) return false; #endif return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) || vma_is_shmem(vma); } extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); extern void dup_userfaultfd_complete(struct list_head *); extern void mremap_userfaultfd_prep(struct vm_area_struct *, struct vm_userfaultfd_ctx *); extern void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *, unsigned long from, unsigned long to, unsigned long len); extern bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern int userfaultfd_unmap_prep(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *uf); extern void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf); #else /* CONFIG_USERFAULTFD */ /* mm helpers */ static inline vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) { return VM_FAULT_SIGBUS; } static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, struct vm_userfaultfd_ctx vm_ctx) { return true; } static inline bool userfaultfd_missing(struct vm_area_struct *vma) { return false; } static inline bool userfaultfd_wp(struct vm_area_struct *vma) { return false; } static inline bool userfaultfd_minor(struct vm_area_struct *vma) { return false; } static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma, pte_t pte) { return false; } static inline bool userfaultfd_huge_pmd_wp(struct vm_area_struct *vma, pmd_t pmd) { return false; } static inline bool userfaultfd_armed(struct vm_area_struct *vma) { return false; } static inline int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *l) { return 0; } static inline void dup_userfaultfd_complete(struct list_head *l) { } static inline void mremap_userfaultfd_prep(struct vm_area_struct *vma, struct vm_userfaultfd_ctx *ctx) { } static inline void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *ctx, unsigned long from, unsigned long to, unsigned long len) { } static inline bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end) { return true; } static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *uf) { return 0; } static inline void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf) { } static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) { return false; } #endif /* CONFIG_USERFAULTFD */ static inline bool pte_marker_entry_uffd_wp(swp_entry_t entry) { #ifdef CONFIG_PTE_MARKER_UFFD_WP return is_pte_marker_entry(entry) && (pte_marker_get(entry) & PTE_MARKER_UFFD_WP); #else return false; #endif } static inline bool pte_marker_uffd_wp(pte_t pte) { #ifdef CONFIG_PTE_MARKER_UFFD_WP swp_entry_t entry; if (!is_swap_pte(pte)) return false; entry = pte_to_swp_entry(pte); return pte_marker_entry_uffd_wp(entry); #else return false; #endif } /* * Returns true if this is a swap pte and was uffd-wp wr-protected in either * forms (pte marker or a normal swap pte), false otherwise. */ static inline bool pte_swp_uffd_wp_any(pte_t pte) { #ifdef CONFIG_PTE_MARKER_UFFD_WP if (!is_swap_pte(pte)) return false; if (pte_swp_uffd_wp(pte)) return true; if (pte_marker_uffd_wp(pte)) return true; #endif return false; } #endif /* _LINUX_USERFAULTFD_K_H */ |
| 253 253 253 254 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 | // SPDX-License-Identifier: GPL-2.0-only /* * This is the 1999 rewrite of IP Firewalling, aiming for kernel 2.3.x. * * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling * Copyright (C) 2000-2004 Netfilter Core Team <coreteam@netfilter.org> */ #include <linux/module.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <net/sock.h> #include <net/route.h> #include <linux/ip.h> #include <net/ip.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("iptables mangle table"); #define MANGLE_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | \ (1 << NF_INET_LOCAL_IN) | \ (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT) | \ (1 << NF_INET_POST_ROUTING)) static const struct xt_table packet_mangler = { .name = "mangle", .valid_hooks = MANGLE_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_MANGLE, }; static unsigned int ipt_mangle_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { unsigned int ret; const struct iphdr *iph; u_int8_t tos; __be32 saddr, daddr; u_int32_t mark; int err; /* Save things which could affect route */ mark = skb->mark; iph = ip_hdr(skb); saddr = iph->saddr; daddr = iph->daddr; tos = iph->tos; ret = ipt_do_table(priv, skb, state); /* Reroute for ANY change. */ if (ret != NF_DROP && ret != NF_STOLEN) { iph = ip_hdr(skb); if (iph->saddr != saddr || iph->daddr != daddr || skb->mark != mark || iph->tos != tos) { err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } } return ret; } /* The work comes in here from netfilter.c. */ static unsigned int iptable_mangle_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { if (state->hook == NF_INET_LOCAL_OUT) return ipt_mangle_out(priv, skb, state); return ipt_do_table(priv, skb, state); } static struct nf_hook_ops *mangle_ops __read_mostly; static int iptable_mangle_table_init(struct net *net) { struct ipt_replace *repl; int ret; repl = ipt_alloc_initial_table(&packet_mangler); if (repl == NULL) return -ENOMEM; ret = ipt_register_table(net, &packet_mangler, repl, mangle_ops); kfree(repl); return ret; } static void __net_exit iptable_mangle_net_pre_exit(struct net *net) { ipt_unregister_table_pre_exit(net, "mangle"); } static void __net_exit iptable_mangle_net_exit(struct net *net) { ipt_unregister_table_exit(net, "mangle"); } static struct pernet_operations iptable_mangle_net_ops = { .pre_exit = iptable_mangle_net_pre_exit, .exit = iptable_mangle_net_exit, }; static int __init iptable_mangle_init(void) { int ret = xt_register_template(&packet_mangler, iptable_mangle_table_init); if (ret < 0) return ret; mangle_ops = xt_hook_ops_alloc(&packet_mangler, iptable_mangle_hook); if (IS_ERR(mangle_ops)) { xt_unregister_template(&packet_mangler); ret = PTR_ERR(mangle_ops); return ret; } ret = register_pernet_subsys(&iptable_mangle_net_ops); if (ret < 0) { xt_unregister_template(&packet_mangler); kfree(mangle_ops); return ret; } return ret; } static void __exit iptable_mangle_fini(void) { unregister_pernet_subsys(&iptable_mangle_net_ops); xt_unregister_template(&packet_mangler); kfree(mangle_ops); } module_init(iptable_mangle_init); module_exit(iptable_mangle_fini); |
| 6 7 253 422 2 7 303 150 34 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_NETFILTER_H #define __LINUX_NETFILTER_H #include <linux/init.h> #include <linux/skbuff.h> #include <linux/net.h> #include <linux/if.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/wait.h> #include <linux/list.h> #include <linux/static_key.h> #include <linux/netfilter_defs.h> #include <linux/netdevice.h> #include <linux/sockptr.h> #include <linux/android_kabi.h> #include <net/net_namespace.h> static inline int NF_DROP_GETERR(int verdict) { return -(verdict >> NF_VERDICT_QBITS); } static inline int nf_inet_addr_cmp(const union nf_inet_addr *a1, const union nf_inet_addr *a2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul1 = (const unsigned long *)a1; const unsigned long *ul2 = (const unsigned long *)a2; return ((ul1[0] ^ ul2[0]) | (ul1[1] ^ ul2[1])) == 0UL; #else return a1->all[0] == a2->all[0] && a1->all[1] == a2->all[1] && a1->all[2] == a2->all[2] && a1->all[3] == a2->all[3]; #endif } static inline void nf_inet_addr_mask(const union nf_inet_addr *a1, union nf_inet_addr *result, const union nf_inet_addr *mask) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ua = (const unsigned long *)a1; unsigned long *ur = (unsigned long *)result; const unsigned long *um = (const unsigned long *)mask; ur[0] = ua[0] & um[0]; ur[1] = ua[1] & um[1]; #else result->all[0] = a1->all[0] & mask->all[0]; result->all[1] = a1->all[1] & mask->all[1]; result->all[2] = a1->all[2] & mask->all[2]; result->all[3] = a1->all[3] & mask->all[3]; #endif } int netfilter_init(void); struct sk_buff; struct nf_hook_ops; struct sock; struct nf_hook_state { u8 hook; u8 pf; struct net_device *in; struct net_device *out; struct sock *sk; struct net *net; int (*okfn)(struct net *, struct sock *, struct sk_buff *); }; typedef unsigned int nf_hookfn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); enum nf_hook_ops_type { NF_HOOK_OP_UNDEFINED, NF_HOOK_OP_NF_TABLES, }; struct nf_hook_ops { /* User fills in from here down. */ nf_hookfn *hook; struct net_device *dev; void *priv; u8 pf; enum nf_hook_ops_type hook_ops_type:8; unsigned int hooknum; /* Hooks are ordered in ascending priority. */ int priority; }; struct nf_hook_entry { nf_hookfn *hook; void *priv; }; struct nf_hook_entries_rcu_head { struct rcu_head head; void *allocation; }; struct nf_hook_entries { u16 num_hook_entries; /* padding */ struct nf_hook_entry hooks[]; /* trailer: pointers to original orig_ops of each hook, * followed by rcu_head and scratch space used for freeing * the structure via call_rcu. * * This is not part of struct nf_hook_entry since its only * needed in slow path (hook register/unregister): * const struct nf_hook_ops *orig_ops[] * * For the same reason, we store this at end -- its * only needed when a hook is deleted, not during * packet path processing: * struct nf_hook_entries_rcu_head head */ }; #ifdef CONFIG_NETFILTER static inline struct nf_hook_ops **nf_hook_entries_get_hook_ops(const struct nf_hook_entries *e) { unsigned int n = e->num_hook_entries; const void *hook_end; hook_end = &e->hooks[n]; /* this is *past* ->hooks[]! */ return (struct nf_hook_ops **)hook_end; } static inline int nf_hook_entry_hookfn(const struct nf_hook_entry *entry, struct sk_buff *skb, struct nf_hook_state *state) { return entry->hook(entry->priv, skb, state); } static inline void nf_hook_state_init(struct nf_hook_state *p, unsigned int hook, u_int8_t pf, struct net_device *indev, struct net_device *outdev, struct sock *sk, struct net *net, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { p->hook = hook; p->pf = pf; p->in = indev; p->out = outdev; p->sk = sk; p->net = net; p->okfn = okfn; } struct nf_sockopt_ops { struct list_head list; u_int8_t pf; /* Non-inclusive ranges: use 0/0/NULL to never get called. */ int set_optmin; int set_optmax; int (*set)(struct sock *sk, int optval, sockptr_t arg, unsigned int len); int get_optmin; int get_optmax; int (*get)(struct sock *sk, int optval, void __user *user, int *len); /* Use the module struct to lock set/get code in place */ struct module *owner; ANDROID_KABI_RESERVE(1); }; /* Function to register/unregister hook points. */ int nf_register_net_hook(struct net *net, const struct nf_hook_ops *ops); void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *ops); int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg, unsigned int n); void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg, unsigned int n); /* Functions to register get/setsockopt ranges (non-inclusive). You need to check permissions yourself! */ int nf_register_sockopt(struct nf_sockopt_ops *reg); void nf_unregister_sockopt(struct nf_sockopt_ops *reg); #ifdef CONFIG_JUMP_LABEL extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; #endif int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, const struct nf_hook_entries *e, unsigned int i); void nf_hook_slow_list(struct list_head *head, struct nf_hook_state *state, const struct nf_hook_entries *e); /** * nf_hook - call a netfilter hook * * Returns 1 if the hook has allowed the packet to pass. The function * okfn must be invoked by the caller in this case. Any other return * value indicates the packet has been consumed by the hook. */ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { struct nf_hook_entries *hook_head = NULL; int ret = 1; #ifdef CONFIG_JUMP_LABEL if (__builtin_constant_p(pf) && __builtin_constant_p(hook) && !static_key_false(&nf_hooks_needed[pf][hook])) return 1; #endif rcu_read_lock(); switch (pf) { case NFPROTO_IPV4: hook_head = rcu_dereference(net->nf.hooks_ipv4[hook]); break; case NFPROTO_IPV6: hook_head = rcu_dereference(net->nf.hooks_ipv6[hook]); break; case NFPROTO_ARP: #ifdef CONFIG_NETFILTER_FAMILY_ARP if (WARN_ON_ONCE(hook >= ARRAY_SIZE(net->nf.hooks_arp))) break; hook_head = rcu_dereference(net->nf.hooks_arp[hook]); #endif break; case NFPROTO_BRIDGE: #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE hook_head = rcu_dereference(get_nf_hooks_bridge(net)[hook]); #endif break; default: WARN_ON_ONCE(1); break; } if (hook_head) { struct nf_hook_state state; nf_hook_state_init(&state, hook, pf, indev, outdev, sk, net, okfn); ret = nf_hook_slow(skb, &state, hook_head, 0); } rcu_read_unlock(); return ret; } /* Activate hook; either okfn or kfree_skb called, unless a hook returns NF_STOLEN (in which case, it's up to the hook to deal with the consequences). Returns -ERRNO if packet dropped. Zero means queued, stolen or accepted. */ /* RR: > I don't want nf_hook to return anything because people might forget > about async and trust the return value to mean "packet was ok". AK: Just document it clearly, then you can expect some sense from kernel coders :) */ static inline int NF_HOOK_COND(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, int (*okfn)(struct net *, struct sock *, struct sk_buff *), bool cond) { int ret; if (!cond || ((ret = nf_hook(pf, hook, net, sk, skb, in, out, okfn)) == 1)) ret = okfn(net, sk, skb); return ret; } static inline int NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { int ret = nf_hook(pf, hook, net, sk, skb, in, out, okfn); if (ret == 1) ret = okfn(net, sk, skb); return ret; } static inline void NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct list_head *head, struct net_device *in, struct net_device *out, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { struct nf_hook_entries *hook_head = NULL; #ifdef CONFIG_JUMP_LABEL if (__builtin_constant_p(pf) && __builtin_constant_p(hook) && !static_key_false(&nf_hooks_needed[pf][hook])) return; #endif rcu_read_lock(); switch (pf) { case NFPROTO_IPV4: hook_head = rcu_dereference(net->nf.hooks_ipv4[hook]); break; case NFPROTO_IPV6: hook_head = rcu_dereference(net->nf.hooks_ipv6[hook]); break; default: WARN_ON_ONCE(1); break; } if (hook_head) { struct nf_hook_state state; nf_hook_state_init(&state, hook, pf, in, out, sk, net, okfn); nf_hook_slow_list(head, &state, hook_head); } rcu_read_unlock(); } /* Call setsockopt() */ int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, sockptr_t opt, unsigned int len); int nf_getsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt, int *len); struct flowi; struct nf_queue_entry; __sum16 nf_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol, unsigned short family); __sum16 nf_checksum_partial(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, unsigned int len, u_int8_t protocol, unsigned short family); int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict, unsigned short family); int nf_reroute(struct sk_buff *skb, struct nf_queue_entry *entry); #include <net/flow.h> struct nf_conn; enum nf_nat_manip_type; struct nlattr; enum ip_conntrack_dir; struct nf_nat_hook { int (*parse_nat_setup)(struct nf_conn *ct, enum nf_nat_manip_type manip, const struct nlattr *attr); void (*decode_session)(struct sk_buff *skb, struct flowi *fl); unsigned int (*manip_pkt)(struct sk_buff *skb, struct nf_conn *ct, enum nf_nat_manip_type mtype, enum ip_conntrack_dir dir); void (*remove_nat_bysrc)(struct nf_conn *ct); ANDROID_KABI_RESERVE(1); }; extern const struct nf_nat_hook __rcu *nf_nat_hook; static inline void nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) { #if IS_ENABLED(CONFIG_NF_NAT) const struct nf_nat_hook *nat_hook; rcu_read_lock(); nat_hook = rcu_dereference(nf_nat_hook); if (nat_hook && nat_hook->decode_session) nat_hook->decode_session(skb, fl); rcu_read_unlock(); #endif } #else /* !CONFIG_NETFILTER */ static inline int NF_HOOK_COND(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, int (*okfn)(struct net *, struct sock *, struct sk_buff *), bool cond) { return okfn(net, sk, skb); } static inline int NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { return okfn(net, sk, skb); } static inline void NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct list_head *head, struct net_device *in, struct net_device *out, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { /* nothing to do */ } static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { return 1; } struct flowi; static inline void nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) { } #endif /*CONFIG_NETFILTER*/ #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_zones_common.h> void nf_ct_attach(struct sk_buff *, const struct sk_buff *); void nf_ct_set_closing(struct nf_conntrack *nfct); struct nf_conntrack_tuple; bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, const struct sk_buff *skb); #else static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} static inline void nf_ct_set_closing(struct nf_conntrack *nfct) {} struct nf_conntrack_tuple; static inline bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, const struct sk_buff *skb) { return false; } #endif struct nf_conn; enum ip_conntrack_info; struct nf_ct_hook { int (*update)(struct net *net, struct sk_buff *skb); void (*destroy)(struct nf_conntrack *); bool (*get_tuple_skb)(struct nf_conntrack_tuple *, const struct sk_buff *); void (*attach)(struct sk_buff *nskb, const struct sk_buff *skb); void (*set_closing)(struct nf_conntrack *nfct); int (*confirm)(struct sk_buff *skb); ANDROID_KABI_RESERVE(1); }; extern const struct nf_ct_hook __rcu *nf_ct_hook; struct nlattr; struct nfnl_ct_hook { size_t (*build_size)(const struct nf_conn *ct); int (*build)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, u_int16_t ct_attr, u_int16_t ct_info_attr); int (*parse)(const struct nlattr *attr, struct nf_conn *ct); int (*attach_expect)(const struct nlattr *attr, struct nf_conn *ct, u32 portid, u32 report); void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, s32 off); ANDROID_KABI_RESERVE(1); }; extern const struct nfnl_ct_hook __rcu *nfnl_ct_hook; /** * nf_skb_duplicated - TEE target has sent a packet * * When a xtables target sends a packet, the OUTPUT and POSTROUTING * hooks are traversed again, i.e. nft and xtables are invoked recursively. * * This is used by xtables TEE target to prevent the duplicated skb from * being duplicated again. */ DECLARE_PER_CPU(bool, nf_skb_duplicated); /** * Contains bitmask of ctnetlink event subscribers, if any. * Can't be pernet due to NETLINK_LISTEN_ALL_NSID setsockopt flag. */ extern u8 nf_ctnetlink_has_listener; #endif /*__LINUX_NETFILTER_H*/ |
| 1 536 70 534 2413 1136 1136 2373 1388 1387 2147 1628 1628 2458 1677 1676 3145 3144 2279 1437 3164 3163 1767 2106 743 15 3 737 31 31 2561 1042 1922 259 247 249 559 559 1 11 11 723 723 723 1082 953 4889 158 2294 1549 645 1549 2963 4660 546 2 2 572 572 572 1256 802 572 2038 332 2 173 99 34 69 85 49 46 13 78 23 45 1 74 26 202 65 69 14 3 73 31 29 34 29 24 52 66 61 48 153 59 1 1 67 101 51 40 40 27 1 1 1 8 1 1 1 1 1 26 4 28 1 10 46 29 1 1 1 1 1 24 14 1 1 12 45 1 2 1 2 39 7 1 6 52 1 2 1 1 1 2 44 2572 2572 2574 2573 2574 1908 1 3 65 1845 128 1 1 1 1 1 1 1 5 1 1 1 1 1 1 1 2 1 1 1 1 2 100 1 15 31 8 8 17 4 1 12 16 31 1 28 15 13 2 27 17 1 16 16 98 95 13 13 1 1 1 10 1250 1250 1249 1 30 30 4 11359 1834 7272 3091 8967 293 771 1 1 1246 1248 1248 26 5 2 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2011-2015 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook */ #include <linux/kernel.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/bpf.h> #include <linux/bpf_perf_event.h> #include <linux/btf.h> #include <linux/filter.h> #include <linux/uaccess.h> #include <linux/ctype.h> #include <linux/kprobes.h> #include <linux/spinlock.h> #include <linux/syscalls.h> #include <linux/error-injection.h> #include <linux/btf_ids.h> #include <linux/bpf_lsm.h> #include <linux/fprobe.h> #include <linux/bsearch.h> #include <linux/sort.h> #include <linux/key.h> #include <linux/verification.h> #include <net/bpf_sk_storage.h> #include <uapi/linux/bpf.h> #include <uapi/linux/btf.h> #include <asm/tlb.h> #include "trace_probe.h" #include "trace.h" #define CREATE_TRACE_POINTS #include "bpf_trace.h" #define bpf_event_rcu_dereference(p) \ rcu_dereference_protected(p, lockdep_is_held(&bpf_event_mutex)) #ifdef CONFIG_MODULES struct bpf_trace_module { struct module *module; struct list_head list; }; static LIST_HEAD(bpf_trace_modules); static DEFINE_MUTEX(bpf_module_mutex); static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name) { struct bpf_raw_event_map *btp, *ret = NULL; struct bpf_trace_module *btm; unsigned int i; mutex_lock(&bpf_module_mutex); list_for_each_entry(btm, &bpf_trace_modules, list) { for (i = 0; i < btm->module->num_bpf_raw_events; ++i) { btp = &btm->module->bpf_raw_events[i]; if (!strcmp(btp->tp->name, name)) { if (try_module_get(btm->module)) ret = btp; goto out; } } } out: mutex_unlock(&bpf_module_mutex); return ret; } #else static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name) { return NULL; } #endif /* CONFIG_MODULES */ u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags, const struct btf **btf, s32 *btf_id); static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx); static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx); /** * trace_call_bpf - invoke BPF program * @call: tracepoint event * @ctx: opaque context pointer * * kprobe handlers execute BPF programs via this helper. * Can be used from static tracepoints in the future. * * Return: BPF programs always return an integer which is interpreted by * kprobe handler as: * 0 - return from kprobe (event is filtered out) * 1 - store kprobe event into ring buffer * Other values are reserved and currently alias to 1 */ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) { unsigned int ret; cant_sleep(); if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { /* * since some bpf program is already running on this cpu, * don't call into another bpf program (same or different) * and don't send kprobe event into ring-buffer, * so return zero here */ ret = 0; goto out; } /* * Instead of moving rcu_read_lock/rcu_dereference/rcu_read_unlock * to all call sites, we did a bpf_prog_array_valid() there to check * whether call->prog_array is empty or not, which is * a heuristic to speed up execution. * * If bpf_prog_array_valid() fetched prog_array was * non-NULL, we go into trace_call_bpf() and do the actual * proper rcu_dereference() under RCU lock. * If it turns out that prog_array is NULL then, we bail out. * For the opposite, if the bpf_prog_array_valid() fetched pointer * was NULL, you'll skip the prog_array with the risk of missing * out of events when it was updated in between this and the * rcu_dereference() which is accepted risk. */ rcu_read_lock(); ret = bpf_prog_run_array(rcu_dereference(call->prog_array), ctx, bpf_prog_run); rcu_read_unlock(); out: __this_cpu_dec(bpf_prog_active); return ret; } #ifdef CONFIG_BPF_KPROBE_OVERRIDE BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc) { regs_set_return_value(regs, rc); override_function_with_return(regs); return 0; } static const struct bpf_func_proto bpf_override_return_proto = { .func = bpf_override_return, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; #endif static __always_inline int bpf_probe_read_user_common(void *dst, u32 size, const void __user *unsafe_ptr) { int ret; ret = copy_from_user_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); return ret; } BPF_CALL_3(bpf_probe_read_user, void *, dst, u32, size, const void __user *, unsafe_ptr) { return bpf_probe_read_user_common(dst, size, unsafe_ptr); } const struct bpf_func_proto bpf_probe_read_user_proto = { .func = bpf_probe_read_user, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; static __always_inline int bpf_probe_read_user_str_common(void *dst, u32 size, const void __user *unsafe_ptr) { int ret; /* * NB: We rely on strncpy_from_user() not copying junk past the NUL * terminator into `dst`. * * strncpy_from_user() does long-sized strides in the fast path. If the * strncpy does not mask out the bytes after the NUL in `unsafe_ptr`, * then there could be junk after the NUL in `dst`. If user takes `dst` * and keys a hash map with it, then semantically identical strings can * occupy multiple entries in the map. */ ret = strncpy_from_user_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); return ret; } BPF_CALL_3(bpf_probe_read_user_str, void *, dst, u32, size, const void __user *, unsafe_ptr) { return bpf_probe_read_user_str_common(dst, size, unsafe_ptr); } const struct bpf_func_proto bpf_probe_read_user_str_proto = { .func = bpf_probe_read_user_str, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; static __always_inline int bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr) { int ret; ret = copy_from_kernel_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); return ret; } BPF_CALL_3(bpf_probe_read_kernel, void *, dst, u32, size, const void *, unsafe_ptr) { return bpf_probe_read_kernel_common(dst, size, unsafe_ptr); } const struct bpf_func_proto bpf_probe_read_kernel_proto = { .func = bpf_probe_read_kernel, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; static __always_inline int bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr) { int ret; /* * The strncpy_from_kernel_nofault() call will likely not fill the * entire buffer, but that's okay in this circumstance as we're probing * arbitrary memory anyway similar to bpf_probe_read_*() and might * as well probe the stack. Thus, memory is explicitly cleared * only in error case, so that improper users ignoring return * code altogether don't copy garbage; otherwise length of string * is returned that can be used for bpf_perf_event_output() et al. */ ret = strncpy_from_kernel_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); return ret; } BPF_CALL_3(bpf_probe_read_kernel_str, void *, dst, u32, size, const void *, unsafe_ptr) { return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr); } const struct bpf_func_proto bpf_probe_read_kernel_str_proto = { .func = bpf_probe_read_kernel_str, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE BPF_CALL_3(bpf_probe_read_compat, void *, dst, u32, size, const void *, unsafe_ptr) { if ((unsigned long)unsafe_ptr < TASK_SIZE) { return bpf_probe_read_user_common(dst, size, (__force void __user *)unsafe_ptr); } return bpf_probe_read_kernel_common(dst, size, unsafe_ptr); } static const struct bpf_func_proto bpf_probe_read_compat_proto = { .func = bpf_probe_read_compat, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_probe_read_compat_str, void *, dst, u32, size, const void *, unsafe_ptr) { if ((unsigned long)unsafe_ptr < TASK_SIZE) { return bpf_probe_read_user_str_common(dst, size, (__force void __user *)unsafe_ptr); } return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr); } static const struct bpf_func_proto bpf_probe_read_compat_str_proto = { .func = bpf_probe_read_compat_str, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; #endif /* CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE */ BPF_CALL_3(bpf_probe_write_user, void __user *, unsafe_ptr, const void *, src, u32, size) { /* * Ensure we're in user context which is safe for the helper to * run. This helper has no business in a kthread. * * access_ok() should prevent writing to non-user memory, but in * some situations (nommu, temporary switch, etc) access_ok() does * not provide enough validation, hence the check on KERNEL_DS. * * nmi_uaccess_okay() ensures the probe is not run in an interim * state, when the task or mm are switched. This is specifically * required to prevent the use of temporary mm. */ if (unlikely(in_interrupt() || current->flags & (PF_KTHREAD | PF_EXITING))) return -EPERM; if (unlikely(!nmi_uaccess_okay())) return -EPERM; return copy_to_user_nofault(unsafe_ptr, src, size); } static const struct bpf_func_proto bpf_probe_write_user_proto = { .func = bpf_probe_write_user, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; static const struct bpf_func_proto *bpf_get_probe_write_proto(void) { if (!capable(CAP_SYS_ADMIN)) return NULL; pr_warn_ratelimited("%s[%d] is installing a program with bpf_probe_write_user helper that may corrupt user memory!", current->comm, task_pid_nr(current)); return &bpf_probe_write_user_proto; } #define MAX_TRACE_PRINTK_VARARGS 3 #define BPF_TRACE_PRINTK_SIZE 1024 BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, u64, arg2, u64, arg3) { u64 args[MAX_TRACE_PRINTK_VARARGS] = { arg1, arg2, arg3 }; struct bpf_bprintf_data data = { .get_bin_args = true, .get_buf = true, }; int ret; ret = bpf_bprintf_prepare(fmt, fmt_size, args, MAX_TRACE_PRINTK_VARARGS, &data); if (ret < 0) return ret; ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt, data.bin_args); trace_bpf_trace_printk(data.buf); bpf_bprintf_cleanup(&data); return ret; } static const struct bpf_func_proto bpf_trace_printk_proto = { .func = bpf_trace_printk, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, }; static void __set_printk_clr_event(void) { /* * This program might be calling bpf_trace_printk, * so enable the associated bpf_trace/bpf_trace_printk event. * Repeat this each time as it is possible a user has * disabled bpf_trace_printk events. By loading a program * calling bpf_trace_printk() however the user has expressed * the intent to see such events. */ if (trace_set_clr_event("bpf_trace", "bpf_trace_printk", 1)) pr_warn_ratelimited("could not enable bpf_trace_printk events"); } const struct bpf_func_proto *bpf_get_trace_printk_proto(void) { __set_printk_clr_event(); return &bpf_trace_printk_proto; } BPF_CALL_4(bpf_trace_vprintk, char *, fmt, u32, fmt_size, const void *, args, u32, data_len) { struct bpf_bprintf_data data = { .get_bin_args = true, .get_buf = true, }; int ret, num_args; if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || (data_len && !args)) return -EINVAL; num_args = data_len / 8; ret = bpf_bprintf_prepare(fmt, fmt_size, args, num_args, &data); if (ret < 0) return ret; ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt, data.bin_args); trace_bpf_trace_printk(data.buf); bpf_bprintf_cleanup(&data); return ret; } static const struct bpf_func_proto bpf_trace_vprintk_proto = { .func = bpf_trace_vprintk, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE_OR_ZERO, }; const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void) { __set_printk_clr_event(); return &bpf_trace_vprintk_proto; } BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size, const void *, args, u32, data_len) { struct bpf_bprintf_data data = { .get_bin_args = true, }; int err, num_args; if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || (data_len && !args)) return -EINVAL; num_args = data_len / 8; err = bpf_bprintf_prepare(fmt, fmt_size, args, num_args, &data); if (err < 0) return err; seq_bprintf(m, fmt, data.bin_args); bpf_bprintf_cleanup(&data); return seq_has_overflowed(m) ? -EOVERFLOW : 0; } BTF_ID_LIST_SINGLE(btf_seq_file_ids, struct, seq_file) static const struct bpf_func_proto bpf_seq_printf_proto = { .func = bpf_seq_printf, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_seq_file_ids[0], .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_3(bpf_seq_write, struct seq_file *, m, const void *, data, u32, len) { return seq_write(m, data, len) ? -EOVERFLOW : 0; } static const struct bpf_func_proto bpf_seq_write_proto = { .func = bpf_seq_write, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_seq_file_ids[0], .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_4(bpf_seq_printf_btf, struct seq_file *, m, struct btf_ptr *, ptr, u32, btf_ptr_size, u64, flags) { const struct btf *btf; s32 btf_id; int ret; ret = bpf_btf_printf_prepare(ptr, btf_ptr_size, flags, &btf, &btf_id); if (ret) return ret; return btf_type_seq_show_flags(btf, btf_id, ptr->ptr, m, flags); } static const struct bpf_func_proto bpf_seq_printf_btf_proto = { .func = bpf_seq_printf_btf, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_seq_file_ids[0], .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; static __always_inline int get_map_perf_counter(struct bpf_map *map, u64 flags, u64 *value, u64 *enabled, u64 *running) { struct bpf_array *array = container_of(map, struct bpf_array, map); unsigned int cpu = smp_processor_id(); u64 index = flags & BPF_F_INDEX_MASK; struct bpf_event_entry *ee; if (unlikely(flags & ~(BPF_F_INDEX_MASK))) return -EINVAL; if (index == BPF_F_CURRENT_CPU) index = cpu; if (unlikely(index >= array->map.max_entries)) return -E2BIG; ee = READ_ONCE(array->ptrs[index]); if (!ee) return -ENOENT; return perf_event_read_local(ee->event, value, enabled, running); } BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) { u64 value = 0; int err; err = get_map_perf_counter(map, flags, &value, NULL, NULL); /* * this api is ugly since we miss [-22..-2] range of valid * counter values, but that's uapi */ if (err) return err; return value; } static const struct bpf_func_proto bpf_perf_event_read_proto = { .func = bpf_perf_event_read, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_perf_event_read_value, struct bpf_map *, map, u64, flags, struct bpf_perf_event_value *, buf, u32, size) { int err = -EINVAL; if (unlikely(size != sizeof(struct bpf_perf_event_value))) goto clear; err = get_map_perf_counter(map, flags, &buf->counter, &buf->enabled, &buf->running); if (unlikely(err)) goto clear; return 0; clear: memset(buf, 0, size); return err; } static const struct bpf_func_proto bpf_perf_event_read_value_proto = { .func = bpf_perf_event_read_value, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; static __always_inline u64 __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, u64 flags, struct perf_sample_data *sd) { struct bpf_array *array = container_of(map, struct bpf_array, map); unsigned int cpu = smp_processor_id(); u64 index = flags & BPF_F_INDEX_MASK; struct bpf_event_entry *ee; struct perf_event *event; if (index == BPF_F_CURRENT_CPU) index = cpu; if (unlikely(index >= array->map.max_entries)) return -E2BIG; ee = READ_ONCE(array->ptrs[index]); if (!ee) return -ENOENT; event = ee->event; if (unlikely(event->attr.type != PERF_TYPE_SOFTWARE || event->attr.config != PERF_COUNT_SW_BPF_OUTPUT)) return -EINVAL; if (unlikely(event->oncpu != cpu)) return -EOPNOTSUPP; return perf_event_output(event, sd, regs); } /* * Support executing tracepoints in normal, irq, and nmi context that each call * bpf_perf_event_output */ struct bpf_trace_sample_data { struct perf_sample_data sds[3]; }; static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_trace_sds); static DEFINE_PER_CPU(int, bpf_trace_nest_level); BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, u64, flags, void *, data, u64, size) { struct bpf_trace_sample_data *sds; struct perf_raw_record raw = { .frag = { .size = size, .data = data, }, }; struct perf_sample_data *sd; int nest_level, err; preempt_disable(); sds = this_cpu_ptr(&bpf_trace_sds); nest_level = this_cpu_inc_return(bpf_trace_nest_level); if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(sds->sds))) { err = -EBUSY; goto out; } sd = &sds->sds[nest_level - 1]; if (unlikely(flags & ~(BPF_F_INDEX_MASK))) { err = -EINVAL; goto out; } perf_sample_data_init(sd, 0, 0); sd->raw = &raw; sd->sample_flags |= PERF_SAMPLE_RAW; err = __bpf_perf_event_output(regs, map, flags, sd); out: this_cpu_dec(bpf_trace_nest_level); preempt_enable(); return err; } static const struct bpf_func_proto bpf_perf_event_output_proto = { .func = bpf_perf_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; static DEFINE_PER_CPU(int, bpf_event_output_nest_level); struct bpf_nested_pt_regs { struct pt_regs regs[3]; }; static DEFINE_PER_CPU(struct bpf_nested_pt_regs, bpf_pt_regs); static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_misc_sds); u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) { struct perf_raw_frag frag = { .copy = ctx_copy, .size = ctx_size, .data = ctx, }; struct perf_raw_record raw = { .frag = { { .next = ctx_size ? &frag : NULL, }, .size = meta_size, .data = meta, }, }; struct perf_sample_data *sd; struct pt_regs *regs; int nest_level; u64 ret; preempt_disable(); nest_level = this_cpu_inc_return(bpf_event_output_nest_level); if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(bpf_misc_sds.sds))) { ret = -EBUSY; goto out; } sd = this_cpu_ptr(&bpf_misc_sds.sds[nest_level - 1]); regs = this_cpu_ptr(&bpf_pt_regs.regs[nest_level - 1]); perf_fetch_caller_regs(regs); perf_sample_data_init(sd, 0, 0); sd->raw = &raw; sd->sample_flags |= PERF_SAMPLE_RAW; ret = __bpf_perf_event_output(regs, map, flags, sd); out: this_cpu_dec(bpf_event_output_nest_level); preempt_enable(); return ret; } BPF_CALL_0(bpf_get_current_task) { return (long) current; } const struct bpf_func_proto bpf_get_current_task_proto = { .func = bpf_get_current_task, .gpl_only = true, .ret_type = RET_INTEGER, }; BPF_CALL_0(bpf_get_current_task_btf) { return (unsigned long) current; } const struct bpf_func_proto bpf_get_current_task_btf_proto = { .func = bpf_get_current_task_btf, .gpl_only = true, .ret_type = RET_PTR_TO_BTF_ID, .ret_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], }; BPF_CALL_1(bpf_task_pt_regs, struct task_struct *, task) { return (unsigned long) task_pt_regs(task); } BTF_ID_LIST(bpf_task_pt_regs_ids) BTF_ID(struct, pt_regs) const struct bpf_func_proto bpf_task_pt_regs_proto = { .func = bpf_task_pt_regs, .gpl_only = true, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], .ret_type = RET_PTR_TO_BTF_ID, .ret_btf_id = &bpf_task_pt_regs_ids[0], }; BPF_CALL_2(bpf_current_task_under_cgroup, struct bpf_map *, map, u32, idx) { struct bpf_array *array = container_of(map, struct bpf_array, map); struct cgroup *cgrp; if (unlikely(idx >= array->map.max_entries)) return -E2BIG; cgrp = READ_ONCE(array->ptrs[idx]); if (unlikely(!cgrp)) return -EAGAIN; return task_under_cgroup_hierarchy(current, cgrp); } static const struct bpf_func_proto bpf_current_task_under_cgroup_proto = { .func = bpf_current_task_under_cgroup, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, }; struct send_signal_irq_work { struct irq_work irq_work; struct task_struct *task; u32 sig; enum pid_type type; }; static DEFINE_PER_CPU(struct send_signal_irq_work, send_signal_work); static void do_bpf_send_signal(struct irq_work *entry) { struct send_signal_irq_work *work; work = container_of(entry, struct send_signal_irq_work, irq_work); group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, work->type); put_task_struct(work->task); } static int bpf_send_signal_common(u32 sig, enum pid_type type) { struct send_signal_irq_work *work = NULL; /* Similar to bpf_probe_write_user, task needs to be * in a sound condition and kernel memory access be * permitted in order to send signal to the current * task. */ if (unlikely(current->flags & (PF_KTHREAD | PF_EXITING))) return -EPERM; if (unlikely(!nmi_uaccess_okay())) return -EPERM; /* Task should not be pid=1 to avoid kernel panic. */ if (unlikely(is_global_init(current))) return -EPERM; if (irqs_disabled()) { /* Do an early check on signal validity. Otherwise, * the error is lost in deferred irq_work. */ if (unlikely(!valid_signal(sig))) return -EINVAL; work = this_cpu_ptr(&send_signal_work); if (irq_work_is_busy(&work->irq_work)) return -EBUSY; /* Add the current task, which is the target of sending signal, * to the irq_work. The current task may change when queued * irq works get executed. */ work->task = get_task_struct(current); work->sig = sig; work->type = type; irq_work_queue(&work->irq_work); return 0; } return group_send_sig_info(sig, SEND_SIG_PRIV, current, type); } BPF_CALL_1(bpf_send_signal, u32, sig) { return bpf_send_signal_common(sig, PIDTYPE_TGID); } static const struct bpf_func_proto bpf_send_signal_proto = { .func = bpf_send_signal, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_send_signal_thread, u32, sig) { return bpf_send_signal_common(sig, PIDTYPE_PID); } static const struct bpf_func_proto bpf_send_signal_thread_proto = { .func = bpf_send_signal_thread, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_d_path, struct path *, path, char *, buf, u32, sz) { struct path copy; long len; char *p; if (!sz) return 0; /* * The path pointer is verified as trusted and safe to use, * but let's double check it's valid anyway to workaround * potentially broken verifier. */ len = copy_from_kernel_nofault(©, path, sizeof(*path)); if (len < 0) return len; p = d_path(©, buf, sz); if (IS_ERR(p)) { len = PTR_ERR(p); } else { len = buf + sz - p; memmove(buf, p, len); } return len; } BTF_SET_START(btf_allowlist_d_path) #ifdef CONFIG_SECURITY BTF_ID(func, security_file_permission) BTF_ID(func, security_inode_getattr) BTF_ID(func, security_file_open) #endif #ifdef CONFIG_SECURITY_PATH BTF_ID(func, security_path_truncate) #endif BTF_ID(func, vfs_truncate) BTF_ID(func, vfs_fallocate) BTF_ID(func, dentry_open) BTF_ID(func, vfs_getattr) BTF_ID(func, filp_close) BTF_SET_END(btf_allowlist_d_path) static bool bpf_d_path_allowed(const struct bpf_prog *prog) { if (prog->type == BPF_PROG_TYPE_TRACING && prog->expected_attach_type == BPF_TRACE_ITER) return true; if (prog->type == BPF_PROG_TYPE_LSM) return bpf_lsm_is_sleepable_hook(prog->aux->attach_btf_id); return btf_id_set_contains(&btf_allowlist_d_path, prog->aux->attach_btf_id); } BTF_ID_LIST_SINGLE(bpf_d_path_btf_ids, struct, path) static const struct bpf_func_proto bpf_d_path_proto = { .func = bpf_d_path, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_d_path_btf_ids[0], .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .allowed = bpf_d_path_allowed, }; #define BTF_F_ALL (BTF_F_COMPACT | BTF_F_NONAME | \ BTF_F_PTR_RAW | BTF_F_ZERO) static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags, const struct btf **btf, s32 *btf_id) { const struct btf_type *t; if (unlikely(flags & ~(BTF_F_ALL))) return -EINVAL; if (btf_ptr_size != sizeof(struct btf_ptr)) return -EINVAL; *btf = bpf_get_btf_vmlinux(); if (IS_ERR_OR_NULL(*btf)) return IS_ERR(*btf) ? PTR_ERR(*btf) : -EINVAL; if (ptr->type_id > 0) *btf_id = ptr->type_id; else return -EINVAL; if (*btf_id > 0) t = btf_type_by_id(*btf, *btf_id); if (*btf_id <= 0 || !t) return -ENOENT; return 0; } BPF_CALL_5(bpf_snprintf_btf, char *, str, u32, str_size, struct btf_ptr *, ptr, u32, btf_ptr_size, u64, flags) { const struct btf *btf; s32 btf_id; int ret; ret = bpf_btf_printf_prepare(ptr, btf_ptr_size, flags, &btf, &btf_id); if (ret) return ret; return btf_type_snprintf_show(btf, btf_id, ptr->ptr, str, str_size, flags); } const struct bpf_func_proto bpf_snprintf_btf_proto = { .func = bpf_snprintf_btf, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_get_func_ip_tracing, void *, ctx) { /* This helper call is inlined by verifier. */ return ((u64 *)ctx)[-2]; } static const struct bpf_func_proto bpf_get_func_ip_proto_tracing = { .func = bpf_get_func_ip_tracing, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; #ifdef CONFIG_X86_KERNEL_IBT static unsigned long get_entry_ip(unsigned long fentry_ip) { u32 instr; /* Being extra safe in here in case entry ip is on the page-edge. */ if (get_kernel_nofault(instr, (u32 *) fentry_ip - 1)) return fentry_ip; if (is_endbr(instr)) fentry_ip -= ENDBR_INSN_SIZE; return fentry_ip; } #else #define get_entry_ip(fentry_ip) fentry_ip #endif BPF_CALL_1(bpf_get_func_ip_kprobe, struct pt_regs *, regs) { struct kprobe *kp = kprobe_running(); if (!kp || !(kp->flags & KPROBE_FLAG_ON_FUNC_ENTRY)) return 0; return get_entry_ip((uintptr_t)kp->addr); } static const struct bpf_func_proto bpf_get_func_ip_proto_kprobe = { .func = bpf_get_func_ip_kprobe, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_func_ip_kprobe_multi, struct pt_regs *, regs) { return bpf_kprobe_multi_entry_ip(current->bpf_ctx); } static const struct bpf_func_proto bpf_get_func_ip_proto_kprobe_multi = { .func = bpf_get_func_ip_kprobe_multi, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_attach_cookie_kprobe_multi, struct pt_regs *, regs) { return bpf_kprobe_multi_cookie(current->bpf_ctx); } static const struct bpf_func_proto bpf_get_attach_cookie_proto_kmulti = { .func = bpf_get_attach_cookie_kprobe_multi, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_attach_cookie_trace, void *, ctx) { struct bpf_trace_run_ctx *run_ctx; run_ctx = container_of(current->bpf_ctx, struct bpf_trace_run_ctx, run_ctx); return run_ctx->bpf_cookie; } static const struct bpf_func_proto bpf_get_attach_cookie_proto_trace = { .func = bpf_get_attach_cookie_trace, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_attach_cookie_pe, struct bpf_perf_event_data_kern *, ctx) { return ctx->event->bpf_cookie; } static const struct bpf_func_proto bpf_get_attach_cookie_proto_pe = { .func = bpf_get_attach_cookie_pe, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_attach_cookie_tracing, void *, ctx) { struct bpf_trace_run_ctx *run_ctx; run_ctx = container_of(current->bpf_ctx, struct bpf_trace_run_ctx, run_ctx); return run_ctx->bpf_cookie; } static const struct bpf_func_proto bpf_get_attach_cookie_proto_tracing = { .func = bpf_get_attach_cookie_tracing, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_3(bpf_get_branch_snapshot, void *, buf, u32, size, u64, flags) { #ifndef CONFIG_X86 return -ENOENT; #else static const u32 br_entry_size = sizeof(struct perf_branch_entry); u32 entry_cnt = size / br_entry_size; entry_cnt = static_call(perf_snapshot_branch_stack)(buf, entry_cnt); if (unlikely(flags)) return -EINVAL; if (!entry_cnt) return -ENOENT; return entry_cnt * br_entry_size; #endif } static const struct bpf_func_proto bpf_get_branch_snapshot_proto = { .func = bpf_get_branch_snapshot, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_3(get_func_arg, void *, ctx, u32, n, u64 *, value) { /* This helper call is inlined by verifier. */ u64 nr_args = ((u64 *)ctx)[-1]; if ((u64) n >= nr_args) return -EINVAL; *value = ((u64 *)ctx)[n]; return 0; } static const struct bpf_func_proto bpf_get_func_arg_proto = { .func = get_func_arg, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_LONG, }; BPF_CALL_2(get_func_ret, void *, ctx, u64 *, value) { /* This helper call is inlined by verifier. */ u64 nr_args = ((u64 *)ctx)[-1]; *value = ((u64 *)ctx)[nr_args]; return 0; } static const struct bpf_func_proto bpf_get_func_ret_proto = { .func = get_func_ret, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_LONG, }; BPF_CALL_1(get_func_arg_cnt, void *, ctx) { /* This helper call is inlined by verifier. */ return ((u64 *)ctx)[-1]; } static const struct bpf_func_proto bpf_get_func_arg_cnt_proto = { .func = get_func_arg_cnt, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; #ifdef CONFIG_KEYS __diag_push(); __diag_ignore_all("-Wmissing-prototypes", "kfuncs which will be used in BPF programs"); /** * bpf_lookup_user_key - lookup a key by its serial * @serial: key handle serial number * @flags: lookup-specific flags * * Search a key with a given *serial* and the provided *flags*. * If found, increment the reference count of the key by one, and * return it in the bpf_key structure. * * The bpf_key structure must be passed to bpf_key_put() when done * with it, so that the key reference count is decremented and the * bpf_key structure is freed. * * Permission checks are deferred to the time the key is used by * one of the available key-specific kfuncs. * * Set *flags* with KEY_LOOKUP_CREATE, to attempt creating a requested * special keyring (e.g. session keyring), if it doesn't yet exist. * Set *flags* with KEY_LOOKUP_PARTIAL, to lookup a key without waiting * for the key construction, and to retrieve uninstantiated keys (keys * without data attached to them). * * Return: a bpf_key pointer with a valid key pointer if the key is found, a * NULL pointer otherwise. */ struct bpf_key *bpf_lookup_user_key(u32 serial, u64 flags) { key_ref_t key_ref; struct bpf_key *bkey; if (flags & ~KEY_LOOKUP_ALL) return NULL; /* * Permission check is deferred until the key is used, as the * intent of the caller is unknown here. */ key_ref = lookup_user_key(serial, flags, KEY_DEFER_PERM_CHECK); if (IS_ERR(key_ref)) return NULL; bkey = kmalloc(sizeof(*bkey), GFP_KERNEL); if (!bkey) { key_put(key_ref_to_ptr(key_ref)); return NULL; } bkey->key = key_ref_to_ptr(key_ref); bkey->has_ref = true; return bkey; } /** * bpf_lookup_system_key - lookup a key by a system-defined ID * @id: key ID * * Obtain a bpf_key structure with a key pointer set to the passed key ID. * The key pointer is marked as invalid, to prevent bpf_key_put() from * attempting to decrement the key reference count on that pointer. The key * pointer set in such way is currently understood only by * verify_pkcs7_signature(). * * Set *id* to one of the values defined in include/linux/verification.h: * 0 for the primary keyring (immutable keyring of system keys); * VERIFY_USE_SECONDARY_KEYRING for both the primary and secondary keyring * (where keys can be added only if they are vouched for by existing keys * in those keyrings); VERIFY_USE_PLATFORM_KEYRING for the platform * keyring (primarily used by the integrity subsystem to verify a kexec'ed * kerned image and, possibly, the initramfs signature). * * Return: a bpf_key pointer with an invalid key pointer set from the * pre-determined ID on success, a NULL pointer otherwise */ struct bpf_key *bpf_lookup_system_key(u64 id) { struct bpf_key *bkey; if (system_keyring_id_check(id) < 0) return NULL; bkey = kmalloc(sizeof(*bkey), GFP_ATOMIC); if (!bkey) return NULL; bkey->key = (struct key *)(unsigned long)id; bkey->has_ref = false; return bkey; } /** * bpf_key_put - decrement key reference count if key is valid and free bpf_key * @bkey: bpf_key structure * * Decrement the reference count of the key inside *bkey*, if the pointer * is valid, and free *bkey*. */ void bpf_key_put(struct bpf_key *bkey) { if (bkey->has_ref) key_put(bkey->key); kfree(bkey); } #ifdef CONFIG_SYSTEM_DATA_VERIFICATION /** * bpf_verify_pkcs7_signature - verify a PKCS#7 signature * @data_ptr: data to verify * @sig_ptr: signature of the data * @trusted_keyring: keyring with keys trusted for signature verification * * Verify the PKCS#7 signature *sig_ptr* against the supplied *data_ptr* * with keys in a keyring referenced by *trusted_keyring*. * * Return: 0 on success, a negative value on error. */ int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr, struct bpf_dynptr_kern *sig_ptr, struct bpf_key *trusted_keyring) { int ret; if (trusted_keyring->has_ref) { /* * Do the permission check deferred in bpf_lookup_user_key(). * See bpf_lookup_user_key() for more details. * * A call to key_task_permission() here would be redundant, as * it is already done by keyring_search() called by * find_asymmetric_key(). */ ret = key_validate(trusted_keyring->key); if (ret < 0) return ret; } return verify_pkcs7_signature(data_ptr->data, bpf_dynptr_get_size(data_ptr), sig_ptr->data, bpf_dynptr_get_size(sig_ptr), trusted_keyring->key, VERIFYING_UNSPECIFIED_SIGNATURE, NULL, NULL); } #endif /* CONFIG_SYSTEM_DATA_VERIFICATION */ __diag_pop(); BTF_SET8_START(key_sig_kfunc_set) BTF_ID_FLAGS(func, bpf_lookup_user_key, KF_ACQUIRE | KF_RET_NULL | KF_SLEEPABLE) BTF_ID_FLAGS(func, bpf_lookup_system_key, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_key_put, KF_RELEASE) #ifdef CONFIG_SYSTEM_DATA_VERIFICATION BTF_ID_FLAGS(func, bpf_verify_pkcs7_signature, KF_SLEEPABLE) #endif BTF_SET8_END(key_sig_kfunc_set) static const struct btf_kfunc_id_set bpf_key_sig_kfunc_set = { .owner = THIS_MODULE, .set = &key_sig_kfunc_set, }; static int __init bpf_key_sig_kfuncs_init(void) { return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_key_sig_kfunc_set); } late_initcall(bpf_key_sig_kfuncs_init); #endif /* CONFIG_KEYS */ static const struct bpf_func_proto * bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_map_lookup_elem: return &bpf_map_lookup_elem_proto; case BPF_FUNC_map_update_elem: return &bpf_map_update_elem_proto; case BPF_FUNC_map_delete_elem: return &bpf_map_delete_elem_proto; case BPF_FUNC_map_push_elem: return &bpf_map_push_elem_proto; case BPF_FUNC_map_pop_elem: return &bpf_map_pop_elem_proto; case BPF_FUNC_map_peek_elem: return &bpf_map_peek_elem_proto; case BPF_FUNC_map_lookup_percpu_elem: return &bpf_map_lookup_percpu_elem_proto; case BPF_FUNC_ktime_get_ns: return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; case BPF_FUNC_tail_call: return &bpf_tail_call_proto; case BPF_FUNC_get_current_pid_tgid: return &bpf_get_current_pid_tgid_proto; case BPF_FUNC_get_current_task: return &bpf_get_current_task_proto; case BPF_FUNC_get_current_task_btf: return &bpf_get_current_task_btf_proto; case BPF_FUNC_task_pt_regs: return &bpf_task_pt_regs_proto; case BPF_FUNC_get_current_uid_gid: return &bpf_get_current_uid_gid_proto; case BPF_FUNC_get_current_comm: return &bpf_get_current_comm_proto; case BPF_FUNC_trace_printk: return bpf_get_trace_printk_proto(); case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; case BPF_FUNC_get_numa_node_id: return &bpf_get_numa_node_id_proto; case BPF_FUNC_perf_event_read: return &bpf_perf_event_read_proto; case BPF_FUNC_current_task_under_cgroup: return &bpf_current_task_under_cgroup_proto; case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; case BPF_FUNC_probe_write_user: return security_locked_down(LOCKDOWN_BPF_WRITE_USER) < 0 ? NULL : bpf_get_probe_write_proto(); case BPF_FUNC_probe_read_user: return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_kernel_proto; case BPF_FUNC_probe_read_user_str: return &bpf_probe_read_user_str_proto; case BPF_FUNC_probe_read_kernel_str: return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_kernel_str_proto; #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE case BPF_FUNC_probe_read: return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_compat_proto; case BPF_FUNC_probe_read_str: return security_locked_down(LOCKDOWN_BPF_READ_KERNEL) < 0 ? NULL : &bpf_probe_read_compat_str_proto; #endif #ifdef CONFIG_CGROUPS case BPF_FUNC_get_current_cgroup_id: return &bpf_get_current_cgroup_id_proto; case BPF_FUNC_get_current_ancestor_cgroup_id: return &bpf_get_current_ancestor_cgroup_id_proto; #endif case BPF_FUNC_send_signal: return &bpf_send_signal_proto; case BPF_FUNC_send_signal_thread: return &bpf_send_signal_thread_proto; case BPF_FUNC_perf_event_read_value: return &bpf_perf_event_read_value_proto; case BPF_FUNC_get_ns_current_pid_tgid: return &bpf_get_ns_current_pid_tgid_proto; case BPF_FUNC_ringbuf_output: return &bpf_ringbuf_output_proto; case BPF_FUNC_ringbuf_reserve: return &bpf_ringbuf_reserve_proto; case BPF_FUNC_ringbuf_submit: return &bpf_ringbuf_submit_proto; case BPF_FUNC_ringbuf_discard: return &bpf_ringbuf_discard_proto; case BPF_FUNC_ringbuf_query: return &bpf_ringbuf_query_proto; case BPF_FUNC_jiffies64: return &bpf_jiffies64_proto; case BPF_FUNC_get_task_stack: return &bpf_get_task_stack_proto; case BPF_FUNC_copy_from_user: return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL; case BPF_FUNC_copy_from_user_task: return prog->aux->sleepable ? &bpf_copy_from_user_task_proto : NULL; case BPF_FUNC_snprintf_btf: return &bpf_snprintf_btf_proto; case BPF_FUNC_per_cpu_ptr: return &bpf_per_cpu_ptr_proto; case BPF_FUNC_this_cpu_ptr: return &bpf_this_cpu_ptr_proto; case BPF_FUNC_task_storage_get: return &bpf_task_storage_get_proto; case BPF_FUNC_task_storage_delete: return &bpf_task_storage_delete_proto; case BPF_FUNC_for_each_map_elem: return &bpf_for_each_map_elem_proto; case BPF_FUNC_snprintf: return &bpf_snprintf_proto; case BPF_FUNC_get_func_ip: return &bpf_get_func_ip_proto_tracing; case BPF_FUNC_get_branch_snapshot: return &bpf_get_branch_snapshot_proto; case BPF_FUNC_find_vma: return &bpf_find_vma_proto; case BPF_FUNC_trace_vprintk: return bpf_get_trace_vprintk_proto(); default: return bpf_base_func_proto(func_id); } } static const struct bpf_func_proto * kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_perf_event_output_proto; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto; case BPF_FUNC_get_stack: return &bpf_get_stack_proto; #ifdef CONFIG_BPF_KPROBE_OVERRIDE case BPF_FUNC_override_return: return &bpf_override_return_proto; #endif case BPF_FUNC_get_func_ip: return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI ? &bpf_get_func_ip_proto_kprobe_multi : &bpf_get_func_ip_proto_kprobe; case BPF_FUNC_get_attach_cookie: return prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI ? &bpf_get_attach_cookie_proto_kmulti : &bpf_get_attach_cookie_proto_trace; default: return bpf_tracing_func_proto(func_id, prog); } } /* bpf+kprobe programs can access fields of 'struct pt_regs' */ static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (off < 0 || off >= sizeof(struct pt_regs)) return false; if (type != BPF_READ) return false; if (off % size != 0) return false; /* * Assertion for 32 bit to make sure last 8 byte access * (BPF_DW) to the last 4 byte member is disallowed. */ if (off + size > sizeof(struct pt_regs)) return false; return true; } const struct bpf_verifier_ops kprobe_verifier_ops = { .get_func_proto = kprobe_prog_func_proto, .is_valid_access = kprobe_prog_is_valid_access, }; const struct bpf_prog_ops kprobe_prog_ops = { }; BPF_CALL_5(bpf_perf_event_output_tp, void *, tp_buff, struct bpf_map *, map, u64, flags, void *, data, u64, size) { struct pt_regs *regs = *(struct pt_regs **)tp_buff; /* * r1 points to perf tracepoint buffer where first 8 bytes are hidden * from bpf program and contain a pointer to 'struct pt_regs'. Fetch it * from there and call the same bpf_perf_event_output() helper inline. */ return ____bpf_perf_event_output(regs, map, flags, data, size); } static const struct bpf_func_proto bpf_perf_event_output_proto_tp = { .func = bpf_perf_event_output_tp, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_3(bpf_get_stackid_tp, void *, tp_buff, struct bpf_map *, map, u64, flags) { struct pt_regs *regs = *(struct pt_regs **)tp_buff; /* * Same comment as in bpf_perf_event_output_tp(), only that this time * the other helper's function body cannot be inlined due to being * external, thus we need to call raw helper function. */ return bpf_get_stackid((unsigned long) regs, (unsigned long) map, flags, 0, 0); } static const struct bpf_func_proto bpf_get_stackid_proto_tp = { .func = bpf_get_stackid_tp, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_get_stack_tp, void *, tp_buff, void *, buf, u32, size, u64, flags) { struct pt_regs *regs = *(struct pt_regs **)tp_buff; return bpf_get_stack((unsigned long) regs, (unsigned long) buf, (unsigned long) size, flags, 0); } static const struct bpf_func_proto bpf_get_stack_proto_tp = { .func = bpf_get_stack_tp, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; static const struct bpf_func_proto * tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_perf_event_output_proto_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_tp; case BPF_FUNC_get_stack: return &bpf_get_stack_proto_tp; case BPF_FUNC_get_attach_cookie: return &bpf_get_attach_cookie_proto_trace; default: return bpf_tracing_func_proto(func_id, prog); } } static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE) return false; if (type != BPF_READ) return false; if (off % size != 0) return false; BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(__u64)); return true; } const struct bpf_verifier_ops tracepoint_verifier_ops = { .get_func_proto = tp_prog_func_proto, .is_valid_access = tp_prog_is_valid_access, }; const struct bpf_prog_ops tracepoint_prog_ops = { }; BPF_CALL_3(bpf_perf_prog_read_value, struct bpf_perf_event_data_kern *, ctx, struct bpf_perf_event_value *, buf, u32, size) { int err = -EINVAL; if (unlikely(size != sizeof(struct bpf_perf_event_value))) goto clear; err = perf_event_read_local(ctx->event, &buf->counter, &buf->enabled, &buf->running); if (unlikely(err)) goto clear; return 0; clear: memset(buf, 0, size); return err; } static const struct bpf_func_proto bpf_perf_prog_read_value_proto = { .func = bpf_perf_prog_read_value, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE, }; BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx, void *, buf, u32, size, u64, flags) { static const u32 br_entry_size = sizeof(struct perf_branch_entry); struct perf_branch_stack *br_stack = ctx->data->br_stack; u32 to_copy; if (unlikely(flags & ~BPF_F_GET_BRANCH_RECORDS_SIZE)) return -EINVAL; if (unlikely(!(ctx->data->sample_flags & PERF_SAMPLE_BRANCH_STACK))) return -ENOENT; if (unlikely(!br_stack)) return -ENOENT; if (flags & BPF_F_GET_BRANCH_RECORDS_SIZE) return br_stack->nr * br_entry_size; if (!buf || (size % br_entry_size != 0)) return -EINVAL; to_copy = min_t(u32, br_stack->nr * br_entry_size, size); memcpy(buf, br_stack->entries, to_copy); return to_copy; } static const struct bpf_func_proto bpf_read_branch_records_proto = { .func = bpf_read_branch_records, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM_OR_NULL, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; static const struct bpf_func_proto * pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_perf_event_output_proto_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_pe; case BPF_FUNC_get_stack: return &bpf_get_stack_proto_pe; case BPF_FUNC_perf_prog_read_value: return &bpf_perf_prog_read_value_proto; case BPF_FUNC_read_branch_records: return &bpf_read_branch_records_proto; case BPF_FUNC_get_attach_cookie: return &bpf_get_attach_cookie_proto_pe; default: return bpf_tracing_func_proto(func_id, prog); } } /* * bpf_raw_tp_regs are separate from bpf_pt_regs used from skb/xdp * to avoid potential recursive reuse issue when/if tracepoints are added * inside bpf_*_event_output, bpf_get_stackid and/or bpf_get_stack. * * Since raw tracepoints run despite bpf_prog_active, support concurrent usage * in normal, irq, and nmi context. */ struct bpf_raw_tp_regs { struct pt_regs regs[3]; }; static DEFINE_PER_CPU(struct bpf_raw_tp_regs, bpf_raw_tp_regs); static DEFINE_PER_CPU(int, bpf_raw_tp_nest_level); static struct pt_regs *get_bpf_raw_tp_regs(void) { struct bpf_raw_tp_regs *tp_regs = this_cpu_ptr(&bpf_raw_tp_regs); int nest_level = this_cpu_inc_return(bpf_raw_tp_nest_level); if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(tp_regs->regs))) { this_cpu_dec(bpf_raw_tp_nest_level); return ERR_PTR(-EBUSY); } return &tp_regs->regs[nest_level - 1]; } static void put_bpf_raw_tp_regs(void) { this_cpu_dec(bpf_raw_tp_nest_level); } BPF_CALL_5(bpf_perf_event_output_raw_tp, struct bpf_raw_tracepoint_args *, args, struct bpf_map *, map, u64, flags, void *, data, u64, size) { struct pt_regs *regs = get_bpf_raw_tp_regs(); int ret; if (IS_ERR(regs)) return PTR_ERR(regs); perf_fetch_caller_regs(regs); ret = ____bpf_perf_event_output(regs, map, flags, data, size); put_bpf_raw_tp_regs(); return ret; } static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = { .func = bpf_perf_event_output_raw_tp, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; extern const struct bpf_func_proto bpf_skb_output_proto; extern const struct bpf_func_proto bpf_xdp_output_proto; extern const struct bpf_func_proto bpf_xdp_get_buff_len_trace_proto; BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args, struct bpf_map *, map, u64, flags) { struct pt_regs *regs = get_bpf_raw_tp_regs(); int ret; if (IS_ERR(regs)) return PTR_ERR(regs); perf_fetch_caller_regs(regs); /* similar to bpf_perf_event_output_tp, but pt_regs fetched differently */ ret = bpf_get_stackid((unsigned long) regs, (unsigned long) map, flags, 0, 0); put_bpf_raw_tp_regs(); return ret; } static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = { .func = bpf_get_stackid_raw_tp, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_get_stack_raw_tp, struct bpf_raw_tracepoint_args *, args, void *, buf, u32, size, u64, flags) { struct pt_regs *regs = get_bpf_raw_tp_regs(); int ret; if (IS_ERR(regs)) return PTR_ERR(regs); perf_fetch_caller_regs(regs); ret = bpf_get_stack((unsigned long) regs, (unsigned long) buf, (unsigned long) size, flags, 0); put_bpf_raw_tp_regs(); return ret; } static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = { .func = bpf_get_stack_raw_tp, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; static const struct bpf_func_proto * raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_perf_event_output_proto_raw_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_raw_tp; case BPF_FUNC_get_stack: return &bpf_get_stack_proto_raw_tp; default: return bpf_tracing_func_proto(func_id, prog); } } const struct bpf_func_proto * tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *fn; switch (func_id) { #ifdef CONFIG_NET case BPF_FUNC_skb_output: return &bpf_skb_output_proto; case BPF_FUNC_xdp_output: return &bpf_xdp_output_proto; case BPF_FUNC_skc_to_tcp6_sock: return &bpf_skc_to_tcp6_sock_proto; case BPF_FUNC_skc_to_tcp_sock: return &bpf_skc_to_tcp_sock_proto; case BPF_FUNC_skc_to_tcp_timewait_sock: return &bpf_skc_to_tcp_timewait_sock_proto; case BPF_FUNC_skc_to_tcp_request_sock: return &bpf_skc_to_tcp_request_sock_proto; case BPF_FUNC_skc_to_udp6_sock: return &bpf_skc_to_udp6_sock_proto; case BPF_FUNC_skc_to_unix_sock: return &bpf_skc_to_unix_sock_proto; case BPF_FUNC_skc_to_mptcp_sock: return &bpf_skc_to_mptcp_sock_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_tracing_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_tracing_proto; case BPF_FUNC_sock_from_file: return &bpf_sock_from_file_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_ptr_cookie_proto; case BPF_FUNC_xdp_get_buff_len: return &bpf_xdp_get_buff_len_trace_proto; #endif case BPF_FUNC_seq_printf: return prog->expected_attach_type == BPF_TRACE_ITER ? &bpf_seq_printf_proto : NULL; case BPF_FUNC_seq_write: return prog->expected_attach_type == BPF_TRACE_ITER ? &bpf_seq_write_proto : NULL; case BPF_FUNC_seq_printf_btf: return prog->expected_attach_type == BPF_TRACE_ITER ? &bpf_seq_printf_btf_proto : NULL; case BPF_FUNC_d_path: return &bpf_d_path_proto; case BPF_FUNC_get_func_arg: return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_proto : NULL; case BPF_FUNC_get_func_ret: return bpf_prog_has_trampoline(prog) ? &bpf_get_func_ret_proto : NULL; case BPF_FUNC_get_func_arg_cnt: return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_cnt_proto : NULL; case BPF_FUNC_get_attach_cookie: return bpf_prog_has_trampoline(prog) ? &bpf_get_attach_cookie_proto_tracing : NULL; default: fn = raw_tp_prog_func_proto(func_id, prog); if (!fn && prog->expected_attach_type == BPF_TRACE_ITER) fn = bpf_iter_get_func_proto(func_id, prog); return fn; } } static bool raw_tp_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { return bpf_tracing_ctx_access(off, size, type); } static bool tracing_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { return bpf_tracing_btf_ctx_access(off, size, type, prog, info); } int __weak bpf_prog_test_run_tracing(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } const struct bpf_verifier_ops raw_tracepoint_verifier_ops = { .get_func_proto = raw_tp_prog_func_proto, .is_valid_access = raw_tp_prog_is_valid_access, }; const struct bpf_prog_ops raw_tracepoint_prog_ops = { #ifdef CONFIG_NET .test_run = bpf_prog_test_run_raw_tp, #endif }; const struct bpf_verifier_ops tracing_verifier_ops = { .get_func_proto = tracing_prog_func_proto, .is_valid_access = tracing_prog_is_valid_access, }; const struct bpf_prog_ops tracing_prog_ops = { .test_run = bpf_prog_test_run_tracing, }; static bool raw_tp_writable_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (off == 0) { if (size != sizeof(u64) || type != BPF_READ) return false; info->reg_type = PTR_TO_TP_BUFFER; } return raw_tp_prog_is_valid_access(off, size, type, prog, info); } const struct bpf_verifier_ops raw_tracepoint_writable_verifier_ops = { .get_func_proto = raw_tp_prog_func_proto, .is_valid_access = raw_tp_writable_prog_is_valid_access, }; const struct bpf_prog_ops raw_tracepoint_writable_prog_ops = { }; static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_u64 = sizeof(u64); if (off < 0 || off >= sizeof(struct bpf_perf_event_data)) return false; if (type != BPF_READ) return false; if (off % size != 0) { if (sizeof(unsigned long) != 4) return false; if (size != 8) return false; if (off % size != 4) return false; } switch (off) { case bpf_ctx_range(struct bpf_perf_event_data, sample_period): bpf_ctx_record_field_size(info, size_u64); if (!bpf_ctx_narrow_access_ok(off, size, size_u64)) return false; break; case bpf_ctx_range(struct bpf_perf_event_data, addr): bpf_ctx_record_field_size(info, size_u64); if (!bpf_ctx_narrow_access_ok(off, size, size_u64)) return false; break; default: if (size != sizeof(long)) return false; } return true; } static u32 pe_prog_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct bpf_perf_event_data, sample_period): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern, data), si->dst_reg, si->src_reg, offsetof(struct bpf_perf_event_data_kern, data)); *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, bpf_target_off(struct perf_sample_data, period, 8, target_size)); break; case offsetof(struct bpf_perf_event_data, addr): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern, data), si->dst_reg, si->src_reg, offsetof(struct bpf_perf_event_data_kern, data)); *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, bpf_target_off(struct perf_sample_data, addr, 8, target_size)); break; default: *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern, regs), si->dst_reg, si->src_reg, offsetof(struct bpf_perf_event_data_kern, regs)); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(long), si->dst_reg, si->dst_reg, si->off); break; } return insn - insn_buf; } const struct bpf_verifier_ops perf_event_verifier_ops = { .get_func_proto = pe_prog_func_proto, .is_valid_access = pe_prog_is_valid_access, .convert_ctx_access = pe_prog_convert_ctx_access, }; const struct bpf_prog_ops perf_event_prog_ops = { }; static DEFINE_MUTEX(bpf_event_mutex); #define BPF_TRACE_MAX_PROGS 64 int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie) { struct bpf_prog_array *old_array; struct bpf_prog_array *new_array; int ret = -EEXIST; /* * Kprobe override only works if they are on the function entry, * and only if they are on the opt-in list. */ if (prog->kprobe_override && (!trace_kprobe_on_func_entry(event->tp_event) || !trace_kprobe_error_injectable(event->tp_event))) return -EINVAL; mutex_lock(&bpf_event_mutex); if (event->prog) goto unlock; old_array = bpf_event_rcu_dereference(event->tp_event->prog_array); if (old_array && bpf_prog_array_length(old_array) >= BPF_TRACE_MAX_PROGS) { ret = -E2BIG; goto unlock; } ret = bpf_prog_array_copy(old_array, NULL, prog, bpf_cookie, &new_array); if (ret < 0) goto unlock; /* set the new array to event->tp_event and set event->prog */ event->prog = prog; event->bpf_cookie = bpf_cookie; rcu_assign_pointer(event->tp_event->prog_array, new_array); bpf_prog_array_free_sleepable(old_array); unlock: mutex_unlock(&bpf_event_mutex); return ret; } void perf_event_detach_bpf_prog(struct perf_event *event) { struct bpf_prog_array *old_array; struct bpf_prog_array *new_array; int ret; mutex_lock(&bpf_event_mutex); if (!event->prog) goto unlock; old_array = bpf_event_rcu_dereference(event->tp_event->prog_array); if (!old_array) goto put; ret = bpf_prog_array_copy(old_array, event->prog, NULL, 0, &new_array); if (ret < 0) { bpf_prog_array_delete_safe(old_array, event->prog); } else { rcu_assign_pointer(event->tp_event->prog_array, new_array); bpf_prog_array_free_sleepable(old_array); } put: /* * It could be that the bpf_prog is not sleepable (and will be freed * via normal RCU), but is called from a point that supports sleepable * programs and uses tasks-trace-RCU. */ synchronize_rcu_tasks_trace(); bpf_prog_put(event->prog); event->prog = NULL; unlock: mutex_unlock(&bpf_event_mutex); } int perf_event_query_prog_array(struct perf_event *event, void __user *info) { struct perf_event_query_bpf __user *uquery = info; struct perf_event_query_bpf query = {}; struct bpf_prog_array *progs; u32 *ids, prog_cnt, ids_len; int ret; if (!perfmon_capable()) return -EPERM; if (event->attr.type != PERF_TYPE_TRACEPOINT) return -EINVAL; if (copy_from_user(&query, uquery, sizeof(query))) return -EFAULT; ids_len = query.ids_len; if (ids_len > BPF_TRACE_MAX_PROGS) return -E2BIG; ids = kcalloc(ids_len, sizeof(u32), GFP_USER | __GFP_NOWARN); if (!ids) return -ENOMEM; /* * The above kcalloc returns ZERO_SIZE_PTR when ids_len = 0, which * is required when user only wants to check for uquery->prog_cnt. * There is no need to check for it since the case is handled * gracefully in bpf_prog_array_copy_info. */ mutex_lock(&bpf_event_mutex); progs = bpf_event_rcu_dereference(event->tp_event->prog_array); ret = bpf_prog_array_copy_info(progs, ids, ids_len, &prog_cnt); mutex_unlock(&bpf_event_mutex); if (copy_to_user(&uquery->prog_cnt, &prog_cnt, sizeof(prog_cnt)) || copy_to_user(uquery->ids, ids, ids_len * sizeof(u32))) ret = -EFAULT; kfree(ids); return ret; } extern struct bpf_raw_event_map __start__bpf_raw_tp[]; extern struct bpf_raw_event_map __stop__bpf_raw_tp[]; struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name) { struct bpf_raw_event_map *btp = __start__bpf_raw_tp; for (; btp < __stop__bpf_raw_tp; btp++) { if (!strcmp(btp->tp->name, name)) return btp; } return bpf_get_raw_tracepoint_module(name); } void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp) { struct module *mod; preempt_disable(); mod = __module_address((unsigned long)btp); module_put(mod); preempt_enable(); } static __always_inline void __bpf_trace_run(struct bpf_prog *prog, u64 *args) { cant_sleep(); if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) { bpf_prog_inc_misses_counter(prog); goto out; } rcu_read_lock(); (void) bpf_prog_run(prog, args); rcu_read_unlock(); out: this_cpu_dec(*(prog->active)); } #define UNPACK(...) __VA_ARGS__ #define REPEAT_1(FN, DL, X, ...) FN(X) #define REPEAT_2(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_1(FN, DL, __VA_ARGS__) #define REPEAT_3(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_2(FN, DL, __VA_ARGS__) #define REPEAT_4(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_3(FN, DL, __VA_ARGS__) #define REPEAT_5(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_4(FN, DL, __VA_ARGS__) #define REPEAT_6(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_5(FN, DL, __VA_ARGS__) #define REPEAT_7(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_6(FN, DL, __VA_ARGS__) #define REPEAT_8(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_7(FN, DL, __VA_ARGS__) #define REPEAT_9(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_8(FN, DL, __VA_ARGS__) #define REPEAT_10(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_9(FN, DL, __VA_ARGS__) #define REPEAT_11(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_10(FN, DL, __VA_ARGS__) #define REPEAT_12(FN, DL, X, ...) FN(X) UNPACK DL REPEAT_11(FN, DL, __VA_ARGS__) #define REPEAT(X, FN, DL, ...) REPEAT_##X(FN, DL, __VA_ARGS__) #define SARG(X) u64 arg##X #define COPY(X) args[X] = arg##X #define __DL_COM (,) #define __DL_SEM (;) #define __SEQ_0_11 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11 #define BPF_TRACE_DEFN_x(x) \ void bpf_trace_run##x(struct bpf_prog *prog, \ REPEAT(x, SARG, __DL_COM, __SEQ_0_11)) \ { \ u64 args[x]; \ REPEAT(x, COPY, __DL_SEM, __SEQ_0_11); \ __bpf_trace_run(prog, args); \ } \ EXPORT_SYMBOL_GPL(bpf_trace_run##x) BPF_TRACE_DEFN_x(1); BPF_TRACE_DEFN_x(2); BPF_TRACE_DEFN_x(3); BPF_TRACE_DEFN_x(4); BPF_TRACE_DEFN_x(5); BPF_TRACE_DEFN_x(6); BPF_TRACE_DEFN_x(7); BPF_TRACE_DEFN_x(8); BPF_TRACE_DEFN_x(9); BPF_TRACE_DEFN_x(10); BPF_TRACE_DEFN_x(11); BPF_TRACE_DEFN_x(12); static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog) { struct tracepoint *tp = btp->tp; /* * check that program doesn't access arguments beyond what's * available in this tracepoint */ if (prog->aux->max_ctx_offset > btp->num_args * sizeof(u64)) return -EINVAL; if (prog->aux->max_tp_access > btp->writable_size) return -EINVAL; return tracepoint_probe_register_may_exist(tp, (void *)btp->bpf_func, prog); } int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog) { return __bpf_probe_register(btp, prog); } int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog) { return tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog); } int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, u64 *probe_offset, u64 *probe_addr) { bool is_tracepoint, is_syscall_tp; struct bpf_prog *prog; int flags, err = 0; prog = event->prog; if (!prog) return -ENOENT; /* not supporting BPF_PROG_TYPE_PERF_EVENT yet */ if (prog->type == BPF_PROG_TYPE_PERF_EVENT) return -EOPNOTSUPP; *prog_id = prog->aux->id; flags = event->tp_event->flags; is_tracepoint = flags & TRACE_EVENT_FL_TRACEPOINT; is_syscall_tp = is_syscall_trace_event(event->tp_event); if (is_tracepoint || is_syscall_tp) { *buf = is_tracepoint ? event->tp_event->tp->name : event->tp_event->name; *fd_type = BPF_FD_TYPE_TRACEPOINT; *probe_offset = 0x0; *probe_addr = 0x0; } else { /* kprobe/uprobe */ err = -EOPNOTSUPP; #ifdef CONFIG_KPROBE_EVENTS if (flags & TRACE_EVENT_FL_KPROBE) err = bpf_get_kprobe_info(event, fd_type, buf, probe_offset, probe_addr, event->attr.type == PERF_TYPE_TRACEPOINT); #endif #ifdef CONFIG_UPROBE_EVENTS if (flags & TRACE_EVENT_FL_UPROBE) err = bpf_get_uprobe_info(event, fd_type, buf, probe_offset, probe_addr, event->attr.type == PERF_TYPE_TRACEPOINT); #endif } return err; } static int __init send_signal_irq_work_init(void) { int cpu; struct send_signal_irq_work *work; for_each_possible_cpu(cpu) { work = per_cpu_ptr(&send_signal_work, cpu); init_irq_work(&work->irq_work, do_bpf_send_signal); } return 0; } subsys_initcall(send_signal_irq_work_init); #ifdef CONFIG_MODULES static int bpf_event_notify(struct notifier_block *nb, unsigned long op, void *module) { struct bpf_trace_module *btm, *tmp; struct module *mod = module; int ret = 0; if (mod->num_bpf_raw_events == 0 || (op != MODULE_STATE_COMING && op != MODULE_STATE_GOING)) goto out; mutex_lock(&bpf_module_mutex); switch (op) { case MODULE_STATE_COMING: btm = kzalloc(sizeof(*btm), GFP_KERNEL); if (btm) { btm->module = module; list_add(&btm->list, &bpf_trace_modules); } else { ret = -ENOMEM; } break; case MODULE_STATE_GOING: list_for_each_entry_safe(btm, tmp, &bpf_trace_modules, list) { if (btm->module == module) { list_del(&btm->list); kfree(btm); break; } } break; } mutex_unlock(&bpf_module_mutex); out: return notifier_from_errno(ret); } static struct notifier_block bpf_module_nb = { .notifier_call = bpf_event_notify, }; static int __init bpf_event_init(void) { register_module_notifier(&bpf_module_nb); return 0; } fs_initcall(bpf_event_init); #endif /* CONFIG_MODULES */ #ifdef CONFIG_FPROBE struct bpf_kprobe_multi_link { struct bpf_link link; struct fprobe fp; unsigned long *addrs; u64 *cookies; u32 cnt; }; struct bpf_kprobe_multi_run_ctx { struct bpf_run_ctx run_ctx; struct bpf_kprobe_multi_link *link; unsigned long entry_ip; }; struct user_syms { const char **syms; char *buf; }; static int copy_user_syms(struct user_syms *us, unsigned long __user *usyms, u32 cnt) { unsigned long __user usymbol; const char **syms = NULL; char *buf = NULL, *p; int err = -ENOMEM; unsigned int i; syms = kvmalloc_array(cnt, sizeof(*syms), GFP_KERNEL); if (!syms) goto error; buf = kvmalloc_array(cnt, KSYM_NAME_LEN, GFP_KERNEL); if (!buf) goto error; for (p = buf, i = 0; i < cnt; i++) { if (__get_user(usymbol, usyms + i)) { err = -EFAULT; goto error; } err = strncpy_from_user(p, (const char __user *) usymbol, KSYM_NAME_LEN); if (err == KSYM_NAME_LEN) err = -E2BIG; if (err < 0) goto error; syms[i] = p; p += err + 1; } us->syms = syms; us->buf = buf; return 0; error: if (err) { kvfree(syms); kvfree(buf); } return err; } static void free_user_syms(struct user_syms *us) { kvfree(us->syms); kvfree(us->buf); } static void bpf_kprobe_multi_link_release(struct bpf_link *link) { struct bpf_kprobe_multi_link *kmulti_link; kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link); unregister_fprobe(&kmulti_link->fp); } static void bpf_kprobe_multi_link_dealloc(struct bpf_link *link) { struct bpf_kprobe_multi_link *kmulti_link; kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link); kvfree(kmulti_link->addrs); kvfree(kmulti_link->cookies); kfree(kmulti_link); } static const struct bpf_link_ops bpf_kprobe_multi_link_lops = { .release = bpf_kprobe_multi_link_release, .dealloc = bpf_kprobe_multi_link_dealloc, }; static void bpf_kprobe_multi_cookie_swap(void *a, void *b, int size, const void *priv) { const struct bpf_kprobe_multi_link *link = priv; unsigned long *addr_a = a, *addr_b = b; u64 *cookie_a, *cookie_b; cookie_a = link->cookies + (addr_a - link->addrs); cookie_b = link->cookies + (addr_b - link->addrs); /* swap addr_a/addr_b and cookie_a/cookie_b values */ swap(*addr_a, *addr_b); swap(*cookie_a, *cookie_b); } static int __bpf_kprobe_multi_cookie_cmp(const void *a, const void *b) { const unsigned long *addr_a = a, *addr_b = b; if (*addr_a == *addr_b) return 0; return *addr_a < *addr_b ? -1 : 1; } static int bpf_kprobe_multi_cookie_cmp(const void *a, const void *b, const void *priv) { return __bpf_kprobe_multi_cookie_cmp(a, b); } static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx) { struct bpf_kprobe_multi_run_ctx *run_ctx; struct bpf_kprobe_multi_link *link; u64 *cookie, entry_ip; unsigned long *addr; if (WARN_ON_ONCE(!ctx)) return 0; run_ctx = container_of(current->bpf_ctx, struct bpf_kprobe_multi_run_ctx, run_ctx); link = run_ctx->link; if (!link->cookies) return 0; entry_ip = run_ctx->entry_ip; addr = bsearch(&entry_ip, link->addrs, link->cnt, sizeof(entry_ip), __bpf_kprobe_multi_cookie_cmp); if (!addr) return 0; cookie = link->cookies + (addr - link->addrs); return *cookie; } static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx) { struct bpf_kprobe_multi_run_ctx *run_ctx; run_ctx = container_of(current->bpf_ctx, struct bpf_kprobe_multi_run_ctx, run_ctx); return run_ctx->entry_ip; } static int kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, unsigned long entry_ip, struct pt_regs *regs) { struct bpf_kprobe_multi_run_ctx run_ctx = { .link = link, .entry_ip = entry_ip, }; struct bpf_run_ctx *old_run_ctx; int err; if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { err = 0; goto out; } migrate_disable(); rcu_read_lock(); old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); err = bpf_prog_run(link->link.prog, regs); bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); migrate_enable(); out: __this_cpu_dec(bpf_prog_active); return err; } static void kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip, struct pt_regs *regs, void *data) { struct bpf_kprobe_multi_link *link; link = container_of(fp, struct bpf_kprobe_multi_link, fp); kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs); } static int symbols_cmp_r(const void *a, const void *b, const void *priv) { const char **str_a = (const char **) a; const char **str_b = (const char **) b; return strcmp(*str_a, *str_b); } struct multi_symbols_sort { const char **funcs; u64 *cookies; }; static void symbols_swap_r(void *a, void *b, int size, const void *priv) { const struct multi_symbols_sort *data = priv; const char **name_a = a, **name_b = b; swap(*name_a, *name_b); /* If defined, swap also related cookies. */ if (data->cookies) { u64 *cookie_a, *cookie_b; cookie_a = data->cookies + (name_a - data->funcs); cookie_b = data->cookies + (name_b - data->funcs); swap(*cookie_a, *cookie_b); } } static int addrs_check_error_injection_list(unsigned long *addrs, u32 cnt) { u32 i; for (i = 0; i < cnt; i++) { if (!within_error_injection_list(addrs[i])) return -EINVAL; } return 0; } int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct bpf_kprobe_multi_link *link = NULL; struct bpf_link_primer link_primer; void __user *ucookies; unsigned long *addrs; u32 flags, cnt, size; void __user *uaddrs; u64 *cookies = NULL; void __user *usyms; int err; /* no support for 32bit archs yet */ if (sizeof(u64) != sizeof(void *)) return -EOPNOTSUPP; if (prog->expected_attach_type != BPF_TRACE_KPROBE_MULTI) return -EINVAL; flags = attr->link_create.kprobe_multi.flags; if (flags & ~BPF_F_KPROBE_MULTI_RETURN) return -EINVAL; uaddrs = u64_to_user_ptr(attr->link_create.kprobe_multi.addrs); usyms = u64_to_user_ptr(attr->link_create.kprobe_multi.syms); if (!!uaddrs == !!usyms) return -EINVAL; cnt = attr->link_create.kprobe_multi.cnt; if (!cnt) return -EINVAL; size = cnt * sizeof(*addrs); addrs = kvmalloc_array(cnt, sizeof(*addrs), GFP_KERNEL); if (!addrs) return -ENOMEM; ucookies = u64_to_user_ptr(attr->link_create.kprobe_multi.cookies); if (ucookies) { cookies = kvmalloc_array(cnt, sizeof(*addrs), GFP_KERNEL); if (!cookies) { err = -ENOMEM; goto error; } if (copy_from_user(cookies, ucookies, size)) { err = -EFAULT; goto error; } } if (uaddrs) { if (copy_from_user(addrs, uaddrs, size)) { err = -EFAULT; goto error; } } else { struct multi_symbols_sort data = { .cookies = cookies, }; struct user_syms us; err = copy_user_syms(&us, usyms, cnt); if (err) goto error; if (cookies) data.funcs = us.syms; sort_r(us.syms, cnt, sizeof(*us.syms), symbols_cmp_r, symbols_swap_r, &data); err = ftrace_lookup_symbols(us.syms, cnt, addrs); free_user_syms(&us); if (err) goto error; } if (prog->kprobe_override && addrs_check_error_injection_list(addrs, cnt)) { err = -EINVAL; goto error; } link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) { err = -ENOMEM; goto error; } bpf_link_init(&link->link, BPF_LINK_TYPE_KPROBE_MULTI, &bpf_kprobe_multi_link_lops, prog); err = bpf_link_prime(&link->link, &link_primer); if (err) goto error; if (flags & BPF_F_KPROBE_MULTI_RETURN) link->fp.exit_handler = kprobe_multi_link_handler; else link->fp.entry_handler = kprobe_multi_link_handler; link->addrs = addrs; link->cookies = cookies; link->cnt = cnt; if (cookies) { /* * Sorting addresses will trigger sorting cookies as well * (check bpf_kprobe_multi_cookie_swap). This way we can * find cookie based on the address in bpf_get_attach_cookie * helper. */ sort_r(addrs, cnt, sizeof(*addrs), bpf_kprobe_multi_cookie_cmp, bpf_kprobe_multi_cookie_swap, link); } err = register_fprobe_ips(&link->fp, addrs, cnt); if (err) { bpf_link_cleanup(&link_primer); return err; } return bpf_link_settle(&link_primer); error: kfree(link); kvfree(addrs); kvfree(cookies); return err; } #else /* !CONFIG_FPROBE */ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EOPNOTSUPP; } static u64 bpf_kprobe_multi_cookie(struct bpf_run_ctx *ctx) { return 0; } static u64 bpf_kprobe_multi_entry_ip(struct bpf_run_ctx *ctx) { return 0; } #endif |
| 333 102 620 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 | #undef TRACE_SYSTEM #define TRACE_SYSTEM neigh #if !defined(_TRACE_NEIGH_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NEIGH_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/tracepoint.h> #include <net/neighbour.h> #define neigh_state_str(state) \ __print_symbolic(state, \ { NUD_INCOMPLETE, "incomplete" }, \ { NUD_REACHABLE, "reachable" }, \ { NUD_STALE, "stale" }, \ { NUD_DELAY, "delay" }, \ { NUD_PROBE, "probe" }, \ { NUD_FAILED, "failed" }, \ { NUD_NOARP, "noarp" }, \ { NUD_PERMANENT, "permanent"}) TRACE_EVENT(neigh_create, TP_PROTO(struct neigh_table *tbl, struct net_device *dev, const void *pkey, const struct neighbour *n, bool exempt_from_gc), TP_ARGS(tbl, dev, pkey, n, exempt_from_gc), TP_STRUCT__entry( __field(u32, family) __string(dev, dev ? dev->name : "NULL") __field(int, entries) __field(u8, created) __field(u8, gc_exempt) __array(u8, primary_key4, 4) __array(u8, primary_key6, 16) ), TP_fast_assign( __be32 *p32; __entry->family = tbl->family; __assign_str(dev, (dev ? dev->name : "NULL")); __entry->entries = atomic_read(&tbl->gc_entries); __entry->created = n != NULL; __entry->gc_exempt = exempt_from_gc; p32 = (__be32 *)__entry->primary_key4; if (tbl->family == AF_INET) *p32 = *(__be32 *)pkey; else *p32 = 0; #if IS_ENABLED(CONFIG_IPV6) if (tbl->family == AF_INET6) { struct in6_addr *pin6; pin6 = (struct in6_addr *)__entry->primary_key6; *pin6 = *(struct in6_addr *)pkey; } #endif ), TP_printk("family %d dev %s entries %d primary_key4 %pI4 primary_key6 %pI6c created %d gc_exempt %d", __entry->family, __get_str(dev), __entry->entries, __entry->primary_key4, __entry->primary_key6, __entry->created, __entry->gc_exempt) ); TRACE_EVENT(neigh_update, TP_PROTO(struct neighbour *n, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid), TP_ARGS(n, lladdr, new, flags, nlmsg_pid), TP_STRUCT__entry( __field(u32, family) __string(dev, (n->dev ? n->dev->name : "NULL")) __array(u8, lladdr, MAX_ADDR_LEN) __field(u8, lladdr_len) __field(u8, flags) __field(u8, nud_state) __field(u8, type) __field(u8, dead) __field(int, refcnt) __array(__u8, primary_key4, 4) __array(__u8, primary_key6, 16) __field(unsigned long, confirmed) __field(unsigned long, updated) __field(unsigned long, used) __array(u8, new_lladdr, MAX_ADDR_LEN) __field(u8, new_state) __field(u32, update_flags) __field(u32, pid) ), TP_fast_assign( int lladdr_len = (n->dev ? n->dev->addr_len : MAX_ADDR_LEN); struct in6_addr *pin6; __be32 *p32; __entry->family = n->tbl->family; __assign_str(dev, (n->dev ? n->dev->name : "NULL")); __entry->lladdr_len = lladdr_len; memcpy(__entry->lladdr, n->ha, lladdr_len); __entry->flags = n->flags; __entry->nud_state = n->nud_state; __entry->type = n->type; __entry->dead = n->dead; __entry->refcnt = refcount_read(&n->refcnt); pin6 = (struct in6_addr *)__entry->primary_key6; p32 = (__be32 *)__entry->primary_key4; if (n->tbl->family == AF_INET) *p32 = *(__be32 *)n->primary_key; else *p32 = 0; #if IS_ENABLED(CONFIG_IPV6) if (n->tbl->family == AF_INET6) { pin6 = (struct in6_addr *)__entry->primary_key6; *pin6 = *(struct in6_addr *)n->primary_key; } else #endif { ipv6_addr_set_v4mapped(*p32, pin6); } __entry->confirmed = n->confirmed; __entry->updated = n->up |