| 8 4 9 9 9 4 4 4 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _XFRM_HASH_H #define _XFRM_HASH_H #include <linux/xfrm.h> #include <linux/socket.h> #include <linux/jhash.h> static inline unsigned int __xfrm4_addr_hash(const xfrm_address_t *addr) { return ntohl(addr->a4); } static inline unsigned int __xfrm6_addr_hash(const xfrm_address_t *addr) { return jhash2((__force u32 *)addr->a6, 4, 0); } static inline unsigned int __xfrm4_daddr_saddr_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr) { u32 sum = (__force u32)daddr->a4 + (__force u32)saddr->a4; return ntohl((__force __be32)sum); } static inline unsigned int __xfrm6_daddr_saddr_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr) { return __xfrm6_addr_hash(daddr) ^ __xfrm6_addr_hash(saddr); } static inline u32 __bits2mask32(__u8 bits) { u32 mask32 = 0xffffffff; if (bits == 0) mask32 = 0; else if (bits < 32) mask32 <<= (32 - bits); return mask32; } static inline unsigned int __xfrm4_dpref_spref_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr, __u8 dbits, __u8 sbits) { return jhash_2words(ntohl(daddr->a4) & __bits2mask32(dbits), ntohl(saddr->a4) & __bits2mask32(sbits), 0); } static inline unsigned int __xfrm6_pref_hash(const xfrm_address_t *addr, __u8 prefixlen) { unsigned int pdw; unsigned int pbi; u32 initval = 0; pdw = prefixlen >> 5; /* num of whole u32 in prefix */ pbi = prefixlen & 0x1f; /* num of bits in incomplete u32 in prefix */ if (pbi) { __be32 mask; mask = htonl((0xffffffff) << (32 - pbi)); initval = (__force u32)(addr->a6[pdw] & mask); } return jhash2((__force u32 *)addr->a6, pdw, initval); } static inline unsigned int __xfrm6_dpref_spref_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr, __u8 dbits, __u8 sbits) { return __xfrm6_pref_hash(daddr, dbits) ^ __xfrm6_pref_hash(saddr, sbits); } static inline unsigned int __xfrm_dst_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr, u32 reqid, unsigned short family, unsigned int hmask) { unsigned int h = family ^ reqid; switch (family) { case AF_INET: h ^= __xfrm4_daddr_saddr_hash(daddr, saddr); break; case AF_INET6: h ^= __xfrm6_daddr_saddr_hash(daddr, saddr); break; } return (h ^ (h >> 16)) & hmask; } static inline unsigned int __xfrm_src_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family, unsigned int hmask) { unsigned int h = family; switch (family) { case AF_INET: h ^= __xfrm4_daddr_saddr_hash(daddr, saddr); break; case AF_INET6: h ^= __xfrm6_daddr_saddr_hash(daddr, saddr); break; } return (h ^ (h >> 16)) & hmask; } static inline unsigned int __xfrm_spi_hash(const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family, unsigned int hmask) { unsigned int h = (__force u32)spi ^ proto; switch (family) { case AF_INET: h ^= __xfrm4_addr_hash(daddr); break; case AF_INET6: h ^= __xfrm6_addr_hash(daddr); break; } return (h ^ (h >> 10) ^ (h >> 20)) & hmask; } static inline unsigned int __xfrm_seq_hash(u32 seq, unsigned int hmask) { unsigned int h = seq; return (h ^ (h >> 10) ^ (h >> 20)) & hmask; } static inline unsigned int __idx_hash(u32 index, unsigned int hmask) { return (index ^ (index >> 8)) & hmask; } static inline unsigned int __sel_hash(const struct xfrm_selector *sel, unsigned short family, unsigned int hmask, u8 dbits, u8 sbits) { const xfrm_address_t *daddr = &sel->daddr; const xfrm_address_t *saddr = &sel->saddr; unsigned int h = 0; switch (family) { case AF_INET: if (sel->prefixlen_d < dbits || sel->prefixlen_s < sbits) return hmask + 1; h = __xfrm4_dpref_spref_hash(daddr, saddr, dbits, sbits); break; case AF_INET6: if (sel->prefixlen_d < dbits || sel->prefixlen_s < sbits) return hmask + 1; h = __xfrm6_dpref_spref_hash(daddr, saddr, dbits, sbits); break; } h ^= (h >> 16); return h & hmask; } static inline unsigned int __addr_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family, unsigned int hmask, u8 dbits, u8 sbits) { unsigned int h = 0; switch (family) { case AF_INET: h = __xfrm4_dpref_spref_hash(daddr, saddr, dbits, sbits); break; case AF_INET6: h = __xfrm6_dpref_spref_hash(daddr, saddr, dbits, sbits); break; } h ^= (h >> 16); return h & hmask; } struct hlist_head *xfrm_hash_alloc(unsigned int sz); void xfrm_hash_free(struct hlist_head *n, unsigned int sz); #endif /* _XFRM_HASH_H */ |
| 18 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the UDP protocol. * * Version: @(#)udp.h 1.0.2 04/28/93 * * Author: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _LINUX_UDP_H #define _LINUX_UDP_H #include <net/inet_sock.h> #include <linux/skbuff.h> #include <net/netns/hash.h> #include <uapi/linux/udp.h> static inline struct udphdr *udp_hdr(const struct sk_buff *skb) { return (struct udphdr *)skb_transport_header(skb); } #define UDP_HTABLE_SIZE_MIN (CONFIG_BASE_SMALL ? 128 : 256) static inline u32 udp_hashfn(const struct net *net, u32 num, u32 mask) { return (num + net_hash_mix(net)) & mask; } struct udp_sock { /* inet_sock has to be the first member */ struct inet_sock inet; #define udp_port_hash inet.sk.__sk_common.skc_u16hashes[0] #define udp_portaddr_hash inet.sk.__sk_common.skc_u16hashes[1] #define udp_portaddr_node inet.sk.__sk_common.skc_portaddr_node int pending; /* Any pending frames ? */ unsigned int corkflag; /* Cork is required */ __u8 encap_type; /* Is this an Encapsulation socket? */ unsigned char no_check6_tx:1,/* Send zero UDP6 checksums on TX? */ no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */ encap_enabled:1, /* This socket enabled encap * processing; UDP tunnels and * different encapsulation layer set * this */ gro_enabled:1, /* Request GRO aggregation */ accept_udp_l4:1, accept_udp_fraglist:1; /* * Following member retains the information to create a UDP header * when the socket is uncorked. */ __u16 len; /* total length of pending frames */ __u16 gso_size; /* * Fields specific to UDP-Lite. */ __u16 pcslen; __u16 pcrlen; /* indicator bits used by pcflag: */ #define UDPLITE_BIT 0x1 /* set by udplite proto init function */ #define UDPLITE_SEND_CC 0x2 /* set via udplite setsockopt */ #define UDPLITE_RECV_CC 0x4 /* set via udplite setsocktopt */ __u8 pcflag; /* marks socket as UDP-Lite if > 0 */ __u8 unused[3]; /* * For encapsulation sockets. */ int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); void (*encap_err_rcv)(struct sock *sk, struct sk_buff *skb, unsigned int udp_offset); int (*encap_err_lookup)(struct sock *sk, struct sk_buff *skb); void (*encap_destroy)(struct sock *sk); /* GRO functions for UDP socket */ struct sk_buff * (*gro_receive)(struct sock *sk, struct list_head *head, struct sk_buff *skb); int (*gro_complete)(struct sock *sk, struct sk_buff *skb, int nhoff); /* udp_recvmsg try to use this before splicing sk_receive_queue */ struct sk_buff_head reader_queue ____cacheline_aligned_in_smp; /* This field is dirtied by udp_recvmsg() */ int forward_deficit; }; #define UDP_MAX_SEGMENTS (1 << 7UL) static inline struct udp_sock *udp_sk(const struct sock *sk) { return (struct udp_sock *)sk; } static inline void udp_set_no_check6_tx(struct sock *sk, bool val) { udp_sk(sk)->no_check6_tx = val; } static inline void udp_set_no_check6_rx(struct sock *sk, bool val) { udp_sk(sk)->no_check6_rx = val; } static inline bool udp_get_no_check6_tx(struct sock *sk) { return udp_sk(sk)->no_check6_tx; } static inline bool udp_get_no_check6_rx(struct sock *sk) { return udp_sk(sk)->no_check6_rx; } static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { int gso_size; if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) { gso_size = skb_shinfo(skb)->gso_size; put_cmsg(msg, SOL_UDP, UDP_GRO, sizeof(gso_size), &gso_size); } } DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key); #if IS_ENABLED(CONFIG_IPV6) DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); #endif static inline bool udp_encap_needed(void) { if (static_branch_unlikely(&udp_encap_needed_key)) return true; #if IS_ENABLED(CONFIG_IPV6) if (static_branch_unlikely(&udpv6_encap_needed_key)) return true; #endif return false; } static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) { if (!skb_is_gso(skb)) return false; if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && !udp_sk(sk)->accept_udp_l4) return true; if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST && !udp_sk(sk)->accept_udp_fraglist) return true; /* GSO packets lacking the SKB_GSO_UDP_TUNNEL/_CSUM bits might still * land in a tunnel as the socket check in udp_gro_receive cannot be * foolproof. */ if (udp_encap_needed() && READ_ONCE(udp_sk(sk)->encap_rcv) && !(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM))) return true; return false; } static inline void udp_allow_gso(struct sock *sk) { udp_sk(sk)->accept_udp_l4 = 1; udp_sk(sk)->accept_udp_fraglist = 1; } #define udp_portaddr_for_each_entry(__sk, list) \ hlist_for_each_entry(__sk, list, __sk_common.skc_portaddr_node) #define udp_portaddr_for_each_entry_rcu(__sk, list) \ hlist_for_each_entry_rcu(__sk, list, __sk_common.skc_portaddr_node) #define IS_UDPLITE(__sk) (__sk->sk_protocol == IPPROTO_UDPLITE) #endif /* _LINUX_UDP_H */ |
| 5 5 5 7 1 1 5 4 3 3 3 1 1 1 23 10 12 1 2 2 2 109 106 2 1 11 8 3 7 7 7 18 11 7 23 23 87 64 23 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/fcntl.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/syscalls.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/sched/task.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/capability.h> #include <linux/dnotify.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/pipe_fs_i.h> #include <linux/security.h> #include <linux/ptrace.h> #include <linux/signal.h> #include <linux/rcupdate.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/memfd.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/poll.h> #include <asm/siginfo.h> #include <linux/uaccess.h> #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME) static int setfl(int fd, struct file * filp, unsigned long arg) { struct inode * inode = file_inode(filp); int error = 0; /* * O_APPEND cannot be cleared if the file is marked as append-only * and the file is open for write. */ if (((arg ^ filp->f_flags) & O_APPEND) && IS_APPEND(inode)) return -EPERM; /* O_NOATIME can only be set by the owner or superuser */ if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME)) if (!inode_owner_or_capable(file_mnt_user_ns(filp), inode)) return -EPERM; /* required for strict SunOS emulation */ if (O_NONBLOCK != O_NDELAY) if (arg & O_NDELAY) arg |= O_NONBLOCK; /* Pipe packetized mode is controlled by O_DIRECT flag */ if (!S_ISFIFO(inode->i_mode) && (arg & O_DIRECT) && !(filp->f_mode & FMODE_CAN_ODIRECT)) return -EINVAL; if (filp->f_op->check_flags) error = filp->f_op->check_flags(arg); if (error) return error; /* * ->fasync() is responsible for setting the FASYNC bit. */ if (((arg ^ filp->f_flags) & FASYNC) && filp->f_op->fasync) { error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0); if (error < 0) goto out; if (error > 0) error = 0; } spin_lock(&filp->f_lock); filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK); filp->f_iocb_flags = iocb_flags(filp); spin_unlock(&filp->f_lock); out: return error; } void __f_setown(struct file *filp, struct pid *pid, enum pid_type type, int force) { write_lock_irq(&filp->f_owner.lock); if (force || !filp->f_owner.pid) { put_pid(filp->f_owner.pid); filp->f_owner.pid = get_pid(pid); filp->f_owner.pid_type = type; if (pid) { const struct cred *cred = current_cred(); security_file_set_fowner(filp); filp->f_owner.uid = cred->uid; filp->f_owner.euid = cred->euid; } } write_unlock_irq(&filp->f_owner.lock); } EXPORT_SYMBOL(__f_setown); int f_setown(struct file *filp, unsigned long arg, int force) { enum pid_type type; struct pid *pid = NULL; int who = arg, ret = 0; type = PIDTYPE_TGID; if (who < 0) { /* avoid overflow below */ if (who == INT_MIN) return -EINVAL; type = PIDTYPE_PGID; who = -who; } rcu_read_lock(); if (who) { pid = find_vpid(who); if (!pid) ret = -ESRCH; } if (!ret) __f_setown(filp, pid, type, force); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(f_setown); void f_delown(struct file *filp) { __f_setown(filp, NULL, PIDTYPE_TGID, 1); } pid_t f_getown(struct file *filp) { pid_t pid = 0; read_lock_irq(&filp->f_owner.lock); rcu_read_lock(); if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) { pid = pid_vnr(filp->f_owner.pid); if (filp->f_owner.pid_type == PIDTYPE_PGID) pid = -pid; } rcu_read_unlock(); read_unlock_irq(&filp->f_owner.lock); return pid; } static int f_setown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner; struct pid *pid; int type; int ret; ret = copy_from_user(&owner, owner_p, sizeof(owner)); if (ret) return -EFAULT; switch (owner.type) { case F_OWNER_TID: type = PIDTYPE_PID; break; case F_OWNER_PID: type = PIDTYPE_TGID; break; case F_OWNER_PGRP: type = PIDTYPE_PGID; break; default: return -EINVAL; } rcu_read_lock(); pid = find_vpid(owner.pid); if (owner.pid && !pid) ret = -ESRCH; else __f_setown(filp, pid, type, 1); rcu_read_unlock(); return ret; } static int f_getown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner = {}; int ret = 0; read_lock_irq(&filp->f_owner.lock); rcu_read_lock(); if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) owner.pid = pid_vnr(filp->f_owner.pid); rcu_read_unlock(); switch (filp->f_owner.pid_type) { case PIDTYPE_PID: owner.type = F_OWNER_TID; break; case PIDTYPE_TGID: owner.type = F_OWNER_PID; break; case PIDTYPE_PGID: owner.type = F_OWNER_PGRP; break; default: WARN_ON(1); ret = -EINVAL; break; } read_unlock_irq(&filp->f_owner.lock); if (!ret) { ret = copy_to_user(owner_p, &owner, sizeof(owner)); if (ret) ret = -EFAULT; } return ret; } #ifdef CONFIG_CHECKPOINT_RESTORE static int f_getowner_uids(struct file *filp, unsigned long arg) { struct user_namespace *user_ns = current_user_ns(); uid_t __user *dst = (void __user *)arg; uid_t src[2]; int err; read_lock_irq(&filp->f_owner.lock); src[0] = from_kuid(user_ns, filp->f_owner.uid); src[1] = from_kuid(user_ns, filp->f_owner.euid); read_unlock_irq(&filp->f_owner.lock); err = put_user(src[0], &dst[0]); err |= put_user(src[1], &dst[1]); return err; } #else static int f_getowner_uids(struct file *filp, unsigned long arg) { return -EINVAL; } #endif static bool rw_hint_valid(u64 hint) { switch (hint) { case RWH_WRITE_LIFE_NOT_SET: case RWH_WRITE_LIFE_NONE: case RWH_WRITE_LIFE_SHORT: case RWH_WRITE_LIFE_MEDIUM: case RWH_WRITE_LIFE_LONG: case RWH_WRITE_LIFE_EXTREME: return true; default: return false; } } static long fcntl_rw_hint(struct file *file, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(file); u64 __user *argp = (u64 __user *)arg; u64 hint; switch (cmd) { case F_GET_RW_HINT: hint = inode->i_write_hint; if (copy_to_user(argp, &hint, sizeof(*argp))) return -EFAULT; return 0; case F_SET_RW_HINT: if (copy_from_user(&hint, argp, sizeof(hint))) return -EFAULT; if (!rw_hint_valid(hint)) return -EINVAL; inode_lock(inode); inode->i_write_hint = hint; inode_unlock(inode); return 0; default: return -EINVAL; } } static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, struct file *filp) { void __user *argp = (void __user *)arg; struct flock flock; long err = -EINVAL; switch (cmd) { case F_DUPFD: err = f_dupfd(arg, filp, 0); break; case F_DUPFD_CLOEXEC: err = f_dupfd(arg, filp, O_CLOEXEC); break; case F_GETFD: err = get_close_on_exec(fd) ? FD_CLOEXEC : 0; break; case F_SETFD: err = 0; set_close_on_exec(fd, arg & FD_CLOEXEC); break; case F_GETFL: err = filp->f_flags; break; case F_SETFL: err = setfl(fd, filp, arg); break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_GETLK: #endif case F_GETLK: if (copy_from_user(&flock, argp, sizeof(flock))) return -EFAULT; err = fcntl_getlk(filp, cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) return -EFAULT; break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_SETLK: case F_OFD_SETLKW: fallthrough; #endif case F_SETLK: case F_SETLKW: if (copy_from_user(&flock, argp, sizeof(flock))) return -EFAULT; err = fcntl_setlk(fd, filp, cmd, &flock); break; case F_GETOWN: /* * XXX If f_owner is a process group, the * negative return value will get converted * into an error. Oops. If we keep the * current syscall conventions, the only way * to fix this will be in libc. */ err = f_getown(filp); force_successful_syscall_return(); break; case F_SETOWN: err = f_setown(filp, arg, 1); break; case F_GETOWN_EX: err = f_getown_ex(filp, arg); break; case F_SETOWN_EX: err = f_setown_ex(filp, arg); break; case F_GETOWNER_UIDS: err = f_getowner_uids(filp, arg); break; case F_GETSIG: err = filp->f_owner.signum; break; case F_SETSIG: /* arg == 0 restores default behaviour. */ if (!valid_signal(arg)) { break; } err = 0; filp->f_owner.signum = arg; break; case F_GETLEASE: err = fcntl_getlease(filp); break; case F_SETLEASE: err = fcntl_setlease(fd, filp, arg); break; case F_NOTIFY: err = fcntl_dirnotify(fd, filp, arg); break; case F_SETPIPE_SZ: case F_GETPIPE_SZ: err = pipe_fcntl(filp, cmd, arg); break; case F_ADD_SEALS: case F_GET_SEALS: err = memfd_fcntl(filp, cmd, arg); break; case F_GET_RW_HINT: case F_SET_RW_HINT: err = fcntl_rw_hint(filp, cmd, arg); break; default: break; } return err; } static int check_fcntl_cmd(unsigned cmd) { switch (cmd) { case F_DUPFD: case F_DUPFD_CLOEXEC: case F_GETFD: case F_SETFD: case F_GETFL: return 1; } return 0; } SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { struct fd f = fdget_raw(fd); long err = -EBADF; if (!f.file) goto out; if (unlikely(f.file->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out1; } err = security_file_fcntl(f.file, cmd, arg); if (!err) err = do_fcntl(fd, cmd, arg, f.file); out1: fdput(f); out: return err; } #if BITS_PER_LONG == 32 SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { void __user *argp = (void __user *)arg; struct fd f = fdget_raw(fd); struct flock64 flock; long err = -EBADF; if (!f.file) goto out; if (unlikely(f.file->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out1; } err = security_file_fcntl(f.file, cmd, arg); if (err) goto out1; switch (cmd) { case F_GETLK64: case F_OFD_GETLK: err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; err = fcntl_getlk64(f.file, cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) err = -EFAULT; break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; err = fcntl_setlk64(fd, f.file, cmd, &flock); break; default: err = do_fcntl(fd, cmd, arg, f.file); break; } out1: fdput(f); out: return err; } #endif #ifdef CONFIG_COMPAT /* careful - don't use anywhere else */ #define copy_flock_fields(dst, src) \ (dst)->l_type = (src)->l_type; \ (dst)->l_whence = (src)->l_whence; \ (dst)->l_start = (src)->l_start; \ (dst)->l_len = (src)->l_len; \ (dst)->l_pid = (src)->l_pid; static int get_compat_flock(struct flock *kfl, const struct compat_flock __user *ufl) { struct compat_flock fl; if (copy_from_user(&fl, ufl, sizeof(struct compat_flock))) return -EFAULT; copy_flock_fields(kfl, &fl); return 0; } static int get_compat_flock64(struct flock *kfl, const struct compat_flock64 __user *ufl) { struct compat_flock64 fl; if (copy_from_user(&fl, ufl, sizeof(struct compat_flock64))) return -EFAULT; copy_flock_fields(kfl, &fl); return 0; } static int put_compat_flock(const struct flock *kfl, struct compat_flock __user *ufl) { struct compat_flock fl; memset(&fl, 0, sizeof(struct compat_flock)); copy_flock_fields(&fl, kfl); if (copy_to_user(ufl, &fl, sizeof(struct compat_flock))) return -EFAULT; return 0; } static int put_compat_flock64(const struct flock *kfl, struct compat_flock64 __user *ufl) { struct compat_flock64 fl; BUILD_BUG_ON(sizeof(kfl->l_start) > sizeof(ufl->l_start)); BUILD_BUG_ON(sizeof(kfl->l_len) > sizeof(ufl->l_len)); memset(&fl, 0, sizeof(struct compat_flock64)); copy_flock_fields(&fl, kfl); if (copy_to_user(ufl, &fl, sizeof(struct compat_flock64))) return -EFAULT; return 0; } #undef copy_flock_fields static unsigned int convert_fcntl_cmd(unsigned int cmd) { switch (cmd) { case F_GETLK64: return F_GETLK; case F_SETLK64: return F_SETLK; case F_SETLKW64: return F_SETLKW; } return cmd; } /* * GETLK was successful and we need to return the data, but it needs to fit in * the compat structure. * l_start shouldn't be too big, unless the original start + end is greater than * COMPAT_OFF_T_MAX, in which case the app was asking for trouble, so we return * -EOVERFLOW in that case. l_len could be too big, in which case we just * truncate it, and only allow the app to see that part of the conflicting lock * that might make sense to it anyway */ static int fixup_compat_flock(struct flock *flock) { if (flock->l_start > COMPAT_OFF_T_MAX) return -EOVERFLOW; if (flock->l_len > COMPAT_OFF_T_MAX) flock->l_len = COMPAT_OFF_T_MAX; return 0; } static long do_compat_fcntl64(unsigned int fd, unsigned int cmd, compat_ulong_t arg) { struct fd f = fdget_raw(fd); struct flock flock; long err = -EBADF; if (!f.file) return err; if (unlikely(f.file->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out_put; } err = security_file_fcntl(f.file, cmd, arg); if (err) goto out_put; switch (cmd) { case F_GETLK: err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock); if (err) break; err = fixup_compat_flock(&flock); if (!err) err = put_compat_flock(&flock, compat_ptr(arg)); break; case F_GETLK64: case F_OFD_GETLK: err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock); if (!err) err = put_compat_flock64(&flock, compat_ptr(arg)); break; case F_SETLK: case F_SETLKW: err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock); break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock); break; default: err = do_fcntl(fd, cmd, arg, f.file); break; } out_put: fdput(f); return err; } COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { return do_compat_fcntl64(fd, cmd, arg); } COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { switch (cmd) { case F_GETLK64: case F_SETLK64: case F_SETLKW64: case F_OFD_GETLK: case F_OFD_SETLK: case F_OFD_SETLKW: return -EINVAL; } return do_compat_fcntl64(fd, cmd, arg); } #endif /* Table to convert sigio signal codes into poll band bitmaps */ static const __poll_t band_table[NSIGPOLL] = { EPOLLIN | EPOLLRDNORM, /* POLL_IN */ EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND, /* POLL_OUT */ EPOLLIN | EPOLLRDNORM | EPOLLMSG, /* POLL_MSG */ EPOLLERR, /* POLL_ERR */ EPOLLPRI | EPOLLRDBAND, /* POLL_PRI */ EPOLLHUP | EPOLLERR /* POLL_HUP */ }; static inline int sigio_perm(struct task_struct *p, struct fown_struct *fown, int sig) { const struct cred *cred; int ret; rcu_read_lock(); cred = __task_cred(p); ret = ((uid_eq(fown->euid, GLOBAL_ROOT_UID) || uid_eq(fown->euid, cred->suid) || uid_eq(fown->euid, cred->uid) || uid_eq(fown->uid, cred->suid) || uid_eq(fown->uid, cred->uid)) && !security_file_send_sigiotask(p, fown, sig)); rcu_read_unlock(); return ret; } static void send_sigio_to_task(struct task_struct *p, struct fown_struct *fown, int fd, int reason, enum pid_type type) { /* * F_SETSIG can change ->signum lockless in parallel, make * sure we read it once and use the same value throughout. */ int signum = READ_ONCE(fown->signum); if (!sigio_perm(p, fown, signum)) return; switch (signum) { default: { kernel_siginfo_t si; /* Queue a rt signal with the appropriate fd as its value. We use SI_SIGIO as the source, not SI_KERNEL, since kernel signals always get delivered even if we can't queue. Failure to queue in this case _should_ be reported; we fall back to SIGIO in that case. --sct */ clear_siginfo(&si); si.si_signo = signum; si.si_errno = 0; si.si_code = reason; /* * Posix definies POLL_IN and friends to be signal * specific si_codes for SIG_POLL. Linux extended * these si_codes to other signals in a way that is * ambiguous if other signals also have signal * specific si_codes. In that case use SI_SIGIO instead * to remove the ambiguity. */ if ((signum != SIGPOLL) && sig_specific_sicodes(signum)) si.si_code = SI_SIGIO; /* Make sure we are called with one of the POLL_* reasons, otherwise we could leak kernel stack into userspace. */ BUG_ON((reason < POLL_IN) || ((reason - POLL_IN) >= NSIGPOLL)); if (reason - POLL_IN >= NSIGPOLL) si.si_band = ~0L; else si.si_band = mangle_poll(band_table[reason - POLL_IN]); si.si_fd = fd; if (!do_send_sig_info(signum, &si, p, type)) break; } fallthrough; /* fall back on the old plain SIGIO signal */ case 0: do_send_sig_info(SIGIO, SEND_SIG_PRIV, p, type); } } void send_sigio(struct fown_struct *fown, int fd, int band) { struct task_struct *p; enum pid_type type; unsigned long flags; struct pid *pid; read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; if (type <= PIDTYPE_TGID) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) send_sigio_to_task(p, fown, fd, band, type); rcu_read_unlock(); } else { read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigio_to_task(p, fown, fd, band, type); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); } out_unlock_fown: read_unlock_irqrestore(&fown->lock, flags); } static void send_sigurg_to_task(struct task_struct *p, struct fown_struct *fown, enum pid_type type) { if (sigio_perm(p, fown, SIGURG)) do_send_sig_info(SIGURG, SEND_SIG_PRIV, p, type); } int send_sigurg(struct fown_struct *fown) { struct task_struct *p; enum pid_type type; struct pid *pid; unsigned long flags; int ret = 0; read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; ret = 1; if (type <= PIDTYPE_TGID) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) send_sigurg_to_task(p, fown, type); rcu_read_unlock(); } else { read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigurg_to_task(p, fown, type); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); } out_unlock_fown: read_unlock_irqrestore(&fown->lock, flags); return ret; } static DEFINE_SPINLOCK(fasync_lock); static struct kmem_cache *fasync_cache __read_mostly; static void fasync_free_rcu(struct rcu_head *head) { kmem_cache_free(fasync_cache, container_of(head, struct fasync_struct, fa_rcu)); } /* * Remove a fasync entry. If successfully removed, return * positive and clear the FASYNC flag. If no entry exists, * do nothing and return 0. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". * */ int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *fa, **fp; int result = 0; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; write_lock_irq(&fa->fa_lock); fa->fa_file = NULL; write_unlock_irq(&fa->fa_lock); *fp = fa->fa_next; call_rcu(&fa->fa_rcu, fasync_free_rcu); filp->f_flags &= ~FASYNC; result = 1; break; } spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return result; } struct fasync_struct *fasync_alloc(void) { return kmem_cache_alloc(fasync_cache, GFP_KERNEL); } /* * NOTE! This can be used only for unused fasync entries: * entries that actually got inserted on the fasync list * need to be released by rcu - see fasync_remove_entry. */ void fasync_free(struct fasync_struct *new) { kmem_cache_free(fasync_cache, new); } /* * Insert a new entry into the fasync list. Return the pointer to the * old one if we didn't use the new one. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". */ struct fasync_struct *fasync_insert_entry(int fd, struct file *filp, struct fasync_struct **fapp, struct fasync_struct *new) { struct fasync_struct *fa, **fp; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; write_lock_irq(&fa->fa_lock); fa->fa_fd = fd; write_unlock_irq(&fa->fa_lock); goto out; } rwlock_init(&new->fa_lock); new->magic = FASYNC_MAGIC; new->fa_file = filp; new->fa_fd = fd; new->fa_next = *fapp; rcu_assign_pointer(*fapp, new); filp->f_flags |= FASYNC; out: spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return fa; } /* * Add a fasync entry. Return negative on error, positive if * added, and zero if did nothing but change an existing one. */ static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *new; new = fasync_alloc(); if (!new) return -ENOMEM; /* * fasync_insert_entry() returns the old (update) entry if * it existed. * * So free the (unused) new entry and return 0 to let the * caller know that we didn't add any new fasync entries. */ if (fasync_insert_entry(fd, filp, fapp, new)) { fasync_free(new); return 0; } return 1; } /* * fasync_helper() is used by almost all character device drivers * to set up the fasync queue, and for regular files by the file * lease code. It returns negative on error, 0 if it did no changes * and positive if it added/deleted the entry. */ int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fapp) { if (!on) return fasync_remove_entry(filp, fapp); return fasync_add_entry(fd, filp, fapp); } EXPORT_SYMBOL(fasync_helper); /* * rcu_read_lock() is held */ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band) { while (fa) { struct fown_struct *fown; unsigned long flags; if (fa->magic != FASYNC_MAGIC) { printk(KERN_ERR "kill_fasync: bad magic number in " "fasync_struct!\n"); return; } read_lock_irqsave(&fa->fa_lock, flags); if (fa->fa_file) { fown = &fa->fa_file->f_owner; /* Don't send SIGURG to processes which have not set a queued signum: SIGURG has its own default signalling mechanism. */ if (!(sig == SIGURG && fown->signum == 0)) send_sigio(fown, fa->fa_fd, band); } read_unlock_irqrestore(&fa->fa_lock, flags); fa = rcu_dereference(fa->fa_next); } } void kill_fasync(struct fasync_struct **fp, int sig, int band) { /* First a quick test without locking: usually * the list is empty. */ if (*fp) { rcu_read_lock(); kill_fasync_rcu(rcu_dereference(*fp), sig, band); rcu_read_unlock(); } } EXPORT_SYMBOL(kill_fasync); static int __init fcntl_init(void) { /* * Please add new bits here to ensure allocation uniqueness. * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY * is defined as O_NONBLOCK on some platforms and not on others. */ BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( (VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) | __FMODE_EXEC | __FMODE_NONOTIFY)); fasync_cache = kmem_cache_create("fasync_cache", sizeof(struct fasync_struct), 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); return 0; } module_init(fcntl_init) |
| 5038 5037 5035 5040 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 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-or-later /* * The "hash function" used as the core of the ChaCha stream cipher (RFC7539) * * Copyright (C) 2015 Martin Willi */ #include <linux/bug.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/bitops.h> #include <linux/string.h> #include <asm/unaligned.h> #include <crypto/chacha.h> static void chacha_permute(u32 *x, int nrounds) { int i; /* whitelist the allowed round counts */ WARN_ON_ONCE(nrounds != 20 && nrounds != 12); for (i = 0; i < nrounds; i += 2) { x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 16); x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 16); x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 16); x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 16); x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 12); x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 12); x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 12); x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 12); x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 8); x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 8); x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 8); x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 8); x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 7); x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 7); x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 7); x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 7); x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 16); x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 16); x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 16); x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 16); x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 12); x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 12); x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 12); x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 12); x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 8); x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 8); x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 8); x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 8); x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 7); x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 7); x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 7); x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 7); } } /** * chacha_block_generic - generate one keystream block and increment block counter * @state: input state matrix (16 32-bit words) * @stream: output keystream block (64 bytes) * @nrounds: number of rounds (20 or 12; 20 is recommended) * * This is the ChaCha core, a function from 64-byte strings to 64-byte strings. * The caller has already converted the endianness of the input. This function * also handles incrementing the block counter in the input matrix. */ void chacha_block_generic(u32 *state, u8 *stream, int nrounds) { u32 x[16]; int i; memcpy(x, state, 64); chacha_permute(x, nrounds); for (i = 0; i < ARRAY_SIZE(x); i++) put_unaligned_le32(x[i] + state[i], &stream[i * sizeof(u32)]); state[12]++; } EXPORT_SYMBOL(chacha_block_generic); /** * hchacha_block_generic - abbreviated ChaCha core, for XChaCha * @state: input state matrix (16 32-bit words) * @stream: output (8 32-bit words) * @nrounds: number of rounds (20 or 12; 20 is recommended) * * HChaCha is the ChaCha equivalent of HSalsa and is an intermediate step * towards XChaCha (see https://cr.yp.to/snuffle/xsalsa-20081128.pdf). HChaCha * skips the final addition of the initial state, and outputs only certain words * of the state. It should not be used for streaming directly. */ void hchacha_block_generic(const u32 *state, u32 *stream, int nrounds) { u32 x[16]; memcpy(x, state, 64); chacha_permute(x, nrounds); memcpy(&stream[0], &x[0], 16); memcpy(&stream[4], &x[12], 16); } EXPORT_SYMBOL(hchacha_block_generic); |
| 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 | /* 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 |
| 9411 9399 9402 9413 9404 9404 9404 7872 7873 7881 7876 7868 2936 2936 7875 7873 9396 9407 9401 9395 9402 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 | // SPDX-License-Identifier: GPL-2.0-or-later /* * lib/plist.c * * Descending-priority-sorted double-linked list * * (C) 2002-2003 Intel Corp * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>. * * 2001-2005 (c) MontaVista Software, Inc. * Daniel Walker <dwalker@mvista.com> * * (C) 2005 Thomas Gleixner <tglx@linutronix.de> * * Simplifications of the original code by * Oleg Nesterov <oleg@tv-sign.ru> * * Based on simple lists (include/linux/list.h). * * This file contains the add / del functions which are considered to * be too large to inline. See include/linux/plist.h for further * information. */ #include <linux/bug.h> #include <linux/plist.h> #ifdef CONFIG_DEBUG_PLIST static struct plist_head test_head; static void plist_check_prev_next(struct list_head *t, struct list_head *p, struct list_head *n) { WARN(n->prev != p || p->next != n, "top: %p, n: %p, p: %p\n" "prev: %p, n: %p, p: %p\n" "next: %p, n: %p, p: %p\n", t, t->next, t->prev, p, p->next, p->prev, n, n->next, n->prev); } static void plist_check_list(struct list_head *top) { struct list_head *prev = top, *next = top->next; plist_check_prev_next(top, prev, next); while (next != top) { prev = next; next = prev->next; plist_check_prev_next(top, prev, next); } } static void plist_check_head(struct plist_head *head) { if (!plist_head_empty(head)) plist_check_list(&plist_first(head)->prio_list); plist_check_list(&head->node_list); } #else # define plist_check_head(h) do { } while (0) #endif /** * plist_add - add @node to @head * * @node: &struct plist_node pointer * @head: &struct plist_head pointer */ void plist_add(struct plist_node *node, struct plist_head *head) { struct plist_node *first, *iter, *prev = NULL; struct list_head *node_next = &head->node_list; plist_check_head(head); WARN_ON(!plist_node_empty(node)); WARN_ON(!list_empty(&node->prio_list)); if (plist_head_empty(head)) goto ins_node; first = iter = plist_first(head); do { if (node->prio < iter->prio) { node_next = &iter->node_list; break; } prev = iter; iter = list_entry(iter->prio_list.next, struct plist_node, prio_list); } while (iter != first); if (!prev || prev->prio != node->prio) list_add_tail(&node->prio_list, &iter->prio_list); ins_node: list_add_tail(&node->node_list, node_next); plist_check_head(head); } /** * plist_del - Remove a @node from plist. * * @node: &struct plist_node pointer - entry to be removed * @head: &struct plist_head pointer - list head */ void plist_del(struct plist_node *node, struct plist_head *head) { plist_check_head(head); if (!list_empty(&node->prio_list)) { if (node->node_list.next != &head->node_list) { struct plist_node *next; next = list_entry(node->node_list.next, struct plist_node, node_list); /* add the next plist_node into prio_list */ if (list_empty(&next->prio_list)) list_add(&next->prio_list, &node->prio_list); } list_del_init(&node->prio_list); } list_del_init(&node->node_list); plist_check_head(head); } /** * plist_requeue - Requeue @node at end of same-prio entries. * * This is essentially an optimized plist_del() followed by * plist_add(). It moves an entry already in the plist to * after any other same-priority entries. * * @node: &struct plist_node pointer - entry to be moved * @head: &struct plist_head pointer - list head */ void plist_requeue(struct plist_node *node, struct plist_head *head) { struct plist_node *iter; struct list_head *node_next = &head->node_list; plist_check_head(head); BUG_ON(plist_head_empty(head)); BUG_ON(plist_node_empty(node)); if (node == plist_last(head)) return; iter = plist_next(node); if (node->prio != iter->prio) return; plist_del(node, head); plist_for_each_continue(iter, head) { if (node->prio != iter->prio) { node_next = &iter->node_list; break; } } list_add_tail(&node->node_list, node_next); plist_check_head(head); } #ifdef CONFIG_DEBUG_PLIST #include <linux/sched.h> #include <linux/sched/clock.h> #include <linux/module.h> #include <linux/init.h> static struct plist_node __initdata test_node[241]; static void __init plist_test_check(int nr_expect) { struct plist_node *first, *prio_pos, *node_pos; if (plist_head_empty(&test_head)) { BUG_ON(nr_expect != 0); return; } prio_pos = first = plist_first(&test_head); plist_for_each(node_pos, &test_head) { if (nr_expect-- < 0) break; if (node_pos == first) continue; if (node_pos->prio == prio_pos->prio) { BUG_ON(!list_empty(&node_pos->prio_list)); continue; } BUG_ON(prio_pos->prio > node_pos->prio); BUG_ON(prio_pos->prio_list.next != &node_pos->prio_list); prio_pos = node_pos; } BUG_ON(nr_expect != 0); BUG_ON(prio_pos->prio_list.next != &first->prio_list); } static void __init plist_test_requeue(struct plist_node *node) { plist_requeue(node, &test_head); if (node != plist_last(&test_head)) BUG_ON(node->prio == plist_next(node)->prio); } static int __init plist_test(void) { int nr_expect = 0, i, loop; unsigned int r = local_clock(); printk(KERN_DEBUG "start plist test\n"); plist_head_init(&test_head); for (i = 0; i < ARRAY_SIZE(test_node); i++) plist_node_init(test_node + i, 0); for (loop = 0; loop < 1000; loop++) { r = r * 193939 % 47629; i = r % ARRAY_SIZE(test_node); if (plist_node_empty(test_node + i)) { r = r * 193939 % 47629; test_node[i].prio = r % 99; plist_add(test_node + i, &test_head); nr_expect++; } else { plist_del(test_node + i, &test_head); nr_expect--; } plist_test_check(nr_expect); if (!plist_node_empty(test_node + i)) { plist_test_requeue(test_node + i); plist_test_check(nr_expect); } } for (i = 0; i < ARRAY_SIZE(test_node); i++) { if (plist_node_empty(test_node + i)) continue; plist_del(test_node + i, &test_head); nr_expect--; plist_test_check(nr_expect); } printk(KERN_DEBUG "end plist test\n"); return 0; } module_init(plist_test); #endif |
| 4 4 4 2 2 4 2 2 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 | // SPDX-License-Identifier: GPL-2.0-only #include "netlink.h" #include "common.h" #include "bitset.h" /* LINKMODES_GET */ struct linkmodes_req_info { struct ethnl_req_info base; }; struct linkmodes_reply_data { struct ethnl_reply_data base; struct ethtool_link_ksettings ksettings; struct ethtool_link_settings *lsettings; bool peer_empty; }; #define LINKMODES_REPDATA(__reply_base) \ container_of(__reply_base, struct linkmodes_reply_data, base) const struct nla_policy ethnl_linkmodes_get_policy[] = { [ETHTOOL_A_LINKMODES_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; static int linkmodes_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, struct genl_info *info) { struct linkmodes_reply_data *data = LINKMODES_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"); goto out; } if (!dev->ethtool_ops->cap_link_lanes_supported) data->ksettings.lanes = 0; data->peer_empty = bitmap_empty(data->ksettings.link_modes.lp_advertising, __ETHTOOL_LINK_MODE_MASK_NBITS); out: ethnl_ops_complete(dev); return ret; } static int linkmodes_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct linkmodes_reply_data *data = LINKMODES_REPDATA(reply_base); const struct ethtool_link_ksettings *ksettings = &data->ksettings; const struct ethtool_link_settings *lsettings = &ksettings->base; bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; int len, ret; len = nla_total_size(sizeof(u8)) /* LINKMODES_AUTONEG */ + nla_total_size(sizeof(u32)) /* LINKMODES_SPEED */ + nla_total_size(sizeof(u32)) /* LINKMODES_LANES */ + nla_total_size(sizeof(u8)) /* LINKMODES_DUPLEX */ + nla_total_size(sizeof(u8)) /* LINKMODES_RATE_MATCHING */ + 0; ret = ethnl_bitset_size(ksettings->link_modes.advertising, ksettings->link_modes.supported, __ETHTOOL_LINK_MODE_MASK_NBITS, link_mode_names, compact); if (ret < 0) return ret; len += ret; if (!data->peer_empty) { ret = ethnl_bitset_size(ksettings->link_modes.lp_advertising, NULL, __ETHTOOL_LINK_MODE_MASK_NBITS, link_mode_names, compact); if (ret < 0) return ret; len += ret; } if (lsettings->master_slave_cfg != MASTER_SLAVE_CFG_UNSUPPORTED) len += nla_total_size(sizeof(u8)); if (lsettings->master_slave_state != MASTER_SLAVE_STATE_UNSUPPORTED) len += nla_total_size(sizeof(u8)); return len; } static int linkmodes_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct linkmodes_reply_data *data = LINKMODES_REPDATA(reply_base); const struct ethtool_link_ksettings *ksettings = &data->ksettings; const struct ethtool_link_settings *lsettings = &ksettings->base; bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; int ret; if (nla_put_u8(skb, ETHTOOL_A_LINKMODES_AUTONEG, lsettings->autoneg)) return -EMSGSIZE; ret = ethnl_put_bitset(skb, ETHTOOL_A_LINKMODES_OURS, ksettings->link_modes.advertising, ksettings->link_modes.supported, __ETHTOOL_LINK_MODE_MASK_NBITS, link_mode_names, compact); if (ret < 0) return -EMSGSIZE; if (!data->peer_empty) { ret = ethnl_put_bitset(skb, ETHTOOL_A_LINKMODES_PEER, ksettings->link_modes.lp_advertising, NULL, __ETHTOOL_LINK_MODE_MASK_NBITS, link_mode_names, compact); if (ret < 0) return -EMSGSIZE; } if (nla_put_u32(skb, ETHTOOL_A_LINKMODES_SPEED, lsettings->speed) || nla_put_u8(skb, ETHTOOL_A_LINKMODES_DUPLEX, lsettings->duplex)) return -EMSGSIZE; if (ksettings->lanes && nla_put_u32(skb, ETHTOOL_A_LINKMODES_LANES, ksettings->lanes)) return -EMSGSIZE; if (lsettings->master_slave_cfg != MASTER_SLAVE_CFG_UNSUPPORTED && nla_put_u8(skb, ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG, lsettings->master_slave_cfg)) return -EMSGSIZE; if (lsettings->master_slave_state != MASTER_SLAVE_STATE_UNSUPPORTED && nla_put_u8(skb, ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE, lsettings->master_slave_state)) return -EMSGSIZE; if (nla_put_u8(skb, ETHTOOL_A_LINKMODES_RATE_MATCHING, lsettings->rate_matching)) return -EMSGSIZE; return 0; } const struct ethnl_request_ops ethnl_linkmodes_request_ops = { .request_cmd = ETHTOOL_MSG_LINKMODES_GET, .reply_cmd = ETHTOOL_MSG_LINKMODES_GET_REPLY, .hdr_attr = ETHTOOL_A_LINKMODES_HEADER, .req_info_size = sizeof(struct linkmodes_req_info), .reply_data_size = sizeof(struct linkmodes_reply_data), .prepare_data = linkmodes_prepare_data, .reply_size = linkmodes_reply_size, .fill_reply = linkmodes_fill_reply, }; /* LINKMODES_SET */ const struct nla_policy ethnl_linkmodes_set_policy[] = { [ETHTOOL_A_LINKMODES_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_LINKMODES_AUTONEG] = { .type = NLA_U8 }, [ETHTOOL_A_LINKMODES_OURS] = { .type = NLA_NESTED }, [ETHTOOL_A_LINKMODES_SPEED] = { .type = NLA_U32 }, [ETHTOOL_A_LINKMODES_DUPLEX] = { .type = NLA_U8 }, [ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG] = { .type = NLA_U8 }, [ETHTOOL_A_LINKMODES_LANES] = NLA_POLICY_RANGE(NLA_U32, 1, 8), }; /* Set advertised link modes to all supported modes matching requested speed, * lanes and duplex values. Called when autonegotiation is on, speed, lanes or * duplex is requested but no link mode change. This is done in userspace with * ioctl() interface, move it into kernel for netlink. * Returns true if advertised modes bitmap was modified. */ static bool ethnl_auto_linkmodes(struct ethtool_link_ksettings *ksettings, bool req_speed, bool req_lanes, bool req_duplex) { unsigned long *advertising = ksettings->link_modes.advertising; unsigned long *supported = ksettings->link_modes.supported; DECLARE_BITMAP(old_adv, __ETHTOOL_LINK_MODE_MASK_NBITS); unsigned int i; bitmap_copy(old_adv, advertising, __ETHTOOL_LINK_MODE_MASK_NBITS); for (i = 0; i < __ETHTOOL_LINK_MODE_MASK_NBITS; i++) { const struct link_mode_info *info = &link_mode_params[i]; if (info->speed == SPEED_UNKNOWN) continue; if (test_bit(i, supported) && (!req_speed || info->speed == ksettings->base.speed) && (!req_lanes || info->lanes == ksettings->lanes) && (!req_duplex || info->duplex == ksettings->base.duplex)) set_bit(i, advertising); else clear_bit(i, advertising); } return !bitmap_equal(old_adv, advertising, __ETHTOOL_LINK_MODE_MASK_NBITS); } static bool ethnl_validate_master_slave_cfg(u8 cfg) { switch (cfg) { case MASTER_SLAVE_CFG_MASTER_PREFERRED: case MASTER_SLAVE_CFG_SLAVE_PREFERRED: case MASTER_SLAVE_CFG_MASTER_FORCE: case MASTER_SLAVE_CFG_SLAVE_FORCE: return true; } return false; } static int ethnl_check_linkmodes(struct genl_info *info, struct nlattr **tb) { const struct nlattr *master_slave_cfg, *lanes_cfg; master_slave_cfg = tb[ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG]; if (master_slave_cfg && !ethnl_validate_master_slave_cfg(nla_get_u8(master_slave_cfg))) { NL_SET_ERR_MSG_ATTR(info->extack, master_slave_cfg, "master/slave value is invalid"); return -EOPNOTSUPP; } lanes_cfg = tb[ETHTOOL_A_LINKMODES_LANES]; if (lanes_cfg && !is_power_of_2(nla_get_u32(lanes_cfg))) { NL_SET_ERR_MSG_ATTR(info->extack, lanes_cfg, "lanes value is invalid"); return -EINVAL; } return 0; } static int ethnl_update_linkmodes(struct genl_info *info, struct nlattr **tb, struct ethtool_link_ksettings *ksettings, bool *mod, const struct net_device *dev) { struct ethtool_link_settings *lsettings = &ksettings->base; bool req_speed, req_lanes, req_duplex; const struct nlattr *master_slave_cfg, *lanes_cfg; int ret; master_slave_cfg = tb[ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG]; if (master_slave_cfg) { if (lsettings->master_slave_cfg == MASTER_SLAVE_CFG_UNSUPPORTED) { NL_SET_ERR_MSG_ATTR(info->extack, master_slave_cfg, "master/slave configuration not supported by device"); return -EOPNOTSUPP; } } *mod = false; req_speed = tb[ETHTOOL_A_LINKMODES_SPEED]; req_lanes = tb[ETHTOOL_A_LINKMODES_LANES]; req_duplex = tb[ETHTOOL_A_LINKMODES_DUPLEX]; ethnl_update_u8(&lsettings->autoneg, tb[ETHTOOL_A_LINKMODES_AUTONEG], mod); lanes_cfg = tb[ETHTOOL_A_LINKMODES_LANES]; if (lanes_cfg) { /* If autoneg is off and lanes parameter is not supported by the * driver, return an error. */ if (!lsettings->autoneg && !dev->ethtool_ops->cap_link_lanes_supported) { NL_SET_ERR_MSG_ATTR(info->extack, lanes_cfg, "lanes configuration not supported by device"); return -EOPNOTSUPP; } } else if (!lsettings->autoneg && ksettings->lanes) { /* If autoneg is off and lanes parameter is not passed from user but * it was defined previously then set the lanes parameter to 0. */ ksettings->lanes = 0; *mod = true; } ret = ethnl_update_bitset(ksettings->link_modes.advertising, __ETHTOOL_LINK_MODE_MASK_NBITS, tb[ETHTOOL_A_LINKMODES_OURS], link_mode_names, info->extack, mod); if (ret < 0) return ret; ethnl_update_u32(&lsettings->speed, tb[ETHTOOL_A_LINKMODES_SPEED], mod); ethnl_update_u32(&ksettings->lanes, lanes_cfg, mod); ethnl_update_u8(&lsettings->duplex, tb[ETHTOOL_A_LINKMODES_DUPLEX], mod); ethnl_update_u8(&lsettings->master_slave_cfg, master_slave_cfg, mod); if (!tb[ETHTOOL_A_LINKMODES_OURS] && lsettings->autoneg && (req_speed || req_lanes || req_duplex) && ethnl_auto_linkmodes(ksettings, req_speed, req_lanes, req_duplex)) *mod = true; return 0; } int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info) { struct ethtool_link_ksettings ksettings = {}; struct ethnl_req_info req_info = {}; struct nlattr **tb = info->attrs; struct net_device *dev; bool mod = false; int ret; ret = ethnl_check_linkmodes(info, tb); if (ret < 0) return ret; ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_LINKMODES_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; } ret = ethnl_update_linkmodes(info, tb, &ksettings, &mod, dev); if (ret < 0) goto out_ops; if (mod) { 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_LINKMODES_NTF, NULL); } out_ops: ethnl_ops_complete(dev); out_rtnl: rtnl_unlock(); out_dev: ethnl_parse_header_dev_put(&req_info); return ret; } |
| 4 4 2 1 1 14 14 2 1 8 1003 1003 1003 1003 1003 999 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 | // 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"); |
| 207 207 207 140 140 140 207 207 128 204 206 206 207 206 207 207 206 206 207 207 207 207 52 52 52 52 218 208 83 83 83 1 71 11 71 218 11 208 208 39 32 44 207 16 11 218 207 207 207 207 206 207 207 207 207 207 207 206 207 207 206 207 207 207 207 207 207 207 206 207 207 207 206 207 207 207 207 207 207 206 210 210 210 207 207 207 207 207 206 206 207 207 207 207 207 169 1 38 207 207 207 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 output functions * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Based on linux/net/ipv4/ip_output.c * * Changes: * A.N.Kuznetsov : airthmetics in fragmentation. * extension headers are implemented. * route changes now work. * ip6_forward does not confuse sniffers. * etc. * * H. von Brand : Added missing #include <linux/string.h> * Imran Patel : frag id should be in NBO * Kazunori MIYAZAWA @USAGI * : add ip6_append_data and related functions * for datagram xmit */ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/in6.h> #include <linux/tcp.h> #include <linux/route.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/bpf-cgroup.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.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/addrconf.h> #include <net/rawv6.h> #include <net/icmp.h> #include <net/xfrm.h> #include <net/checksum.h> #include <linux/mroute6.h> #include <net/l3mdev.h> #include <net/lwtunnel.h> #include <net/ip_tunnels.h> static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; struct inet6_dev *idev = ip6_dst_idev(dst); unsigned int hh_len = LL_RESERVED_SPACE(dev); const struct in6_addr *daddr, *nexthop; struct ipv6hdr *hdr; struct neighbour *neigh; int ret; /* Be paranoid, rather than too clever. */ if (unlikely(hh_len > skb_headroom(skb)) && dev->header_ops) { /* Make sure idev stays alive */ rcu_read_lock(); skb = skb_expand_head(skb, hh_len); if (!skb) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); return -ENOMEM; } rcu_read_unlock(); } hdr = ipv6_hdr(skb); daddr = &hdr->daddr; if (ipv6_addr_is_multicast(daddr)) { if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(sk) && ((mroute6_is_socket(net, skb) && !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) || ipv6_chk_mcast_addr(dev, daddr, &hdr->saddr))) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); /* Do not check for IFF_ALLMULTI; multicast routing is not supported in any case. */ if (newskb) NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, newskb, NULL, newskb->dev, dev_loopback_xmit); if (hdr->hop_limit == 0) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return 0; } } IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, skb->len); if (IPV6_ADDR_MC_SCOPE(daddr) <= IPV6_ADDR_SCOPE_NODELOCAL && !(dev->flags & IFF_LOOPBACK)) { kfree_skb(skb); return 0; } } if (lwtunnel_xmit_redirect(dst->lwtstate)) { int res = lwtunnel_xmit(skb); if (res != LWTUNNEL_XMIT_CONTINUE) return res; } rcu_read_lock(); nexthop = rt6_nexthop((struct rt6_info *)dst, daddr); neigh = __ipv6_neigh_lookup_noref(dev, nexthop); if (unlikely(IS_ERR_OR_NULL(neigh))) { if (unlikely(!neigh)) neigh = __neigh_create(&nd_tbl, nexthop, dev, false); if (IS_ERR(neigh)) { rcu_read_unlock(); IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTNOROUTES); kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_CREATEFAIL); return -EINVAL; } } sock_confirm_neigh(skb, neigh); ret = neigh_output(neigh, skb, false); rcu_read_unlock(); return ret; } static int ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu) { struct sk_buff *segs, *nskb; netdev_features_t features; int ret = 0; /* Please see corresponding comment in ip_finish_output_gso * describing the cases where GSO segment length exceeds the * egress MTU. */ features = netif_skb_features(skb); segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) { kfree_skb(skb); return -ENOMEM; } consume_skb(skb); skb_list_walk_safe(segs, segs, nskb) { int err; skb_mark_not_on_list(segs); /* Last GSO segment can be smaller than gso_size (and MTU). * Adding a fragment header would produce an "atomic fragment", * which is considered harmful (RFC-8021). Avoid that. */ err = segs->len > mtu ? ip6_fragment(net, sk, segs, ip6_finish_output2) : ip6_finish_output2(net, sk, segs); if (err && ret == 0) ret = err; } return ret; } static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { unsigned int mtu; #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ if (skb_dst(skb)->xfrm) { IP6CB(skb)->flags |= IP6SKB_REROUTED; return dst_output(net, sk, skb); } #endif mtu = ip6_skb_dst_mtu(skb); if (skb_is_gso(skb) && !(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) && !skb_gso_validate_network_len(skb, mtu)) return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu); if ((skb->len > mtu && !skb_is_gso(skb)) || dst_allfrag(skb_dst(skb)) || (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size)) return ip6_fragment(net, sk, skb, ip6_finish_output2); else return ip6_finish_output2(net, sk, skb); } static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { int ret; ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); switch (ret) { case NET_XMIT_SUCCESS: case NET_XMIT_CN: return __ip6_finish_output(net, sk, skb) ? : ret; default: kfree_skb_reason(skb, SKB_DROP_REASON_BPF_CGROUP_EGRESS); return ret; } } int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev; struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; if (unlikely(!idev || READ_ONCE(idev->cnf.disable_ipv6))) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); kfree_skb_reason(skb, SKB_DROP_REASON_IPV6DISABLED); return 0; } return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, indev, dev, ip6_finish_output, !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } EXPORT_SYMBOL(ip6_output); bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np) { if (!np->autoflowlabel_set) return ip6_default_np_autolabel(net); else return np->autoflowlabel; } /* * xmit an sk_buff (used by TCP, SCTP and DCCP) * Note : socket lock is not held for SYNACK packets, but might be modified * by calls to skb_set_owner_w() and ipv6_local_error(), * which are using proper atomic operations or spinlocks. */ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, __u32 mark, struct ipv6_txoptions *opt, int tclass, u32 priority) { struct net *net = sock_net(sk); const struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *first_hop = &fl6->daddr; struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; struct inet6_dev *idev = ip6_dst_idev(dst); struct hop_jumbo_hdr *hop_jumbo; int hoplen = sizeof(*hop_jumbo); unsigned int head_room; struct ipv6hdr *hdr; u8 proto = fl6->flowi6_proto; int seg_len = skb->len; int hlimit = -1; u32 mtu; head_room = sizeof(struct ipv6hdr) + hoplen + LL_RESERVED_SPACE(dev); if (opt) head_room += opt->opt_nflen + opt->opt_flen; if (unlikely(head_room > skb_headroom(skb))) { /* Make sure idev stays alive */ rcu_read_lock(); skb = skb_expand_head(skb, head_room); if (!skb) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); return -ENOBUFS; } rcu_read_unlock(); } if (opt) { seg_len += opt->opt_nflen + opt->opt_flen; if (opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); if (opt->opt_nflen) ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop, &fl6->saddr); } if (unlikely(seg_len > IPV6_MAXPLEN)) { hop_jumbo = skb_push(skb, hoplen); hop_jumbo->nexthdr = proto; hop_jumbo->hdrlen = 0; hop_jumbo->tlv_type = IPV6_TLV_JUMBO; hop_jumbo->tlv_len = 4; hop_jumbo->jumbo_payload_len = htonl(seg_len + hoplen); proto = IPPROTO_HOPOPTS; seg_len = 0; IP6CB(skb)->flags |= IP6SKB_FAKEJUMBO; } skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); hdr = ipv6_hdr(skb); /* * Fill in the IPv6 header */ if (np) hlimit = np->hop_limit; if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, ip6_autoflowlabel(net, np), fl6)); hdr->payload_len = htons(seg_len); hdr->nexthdr = proto; hdr->hop_limit = hlimit; hdr->saddr = fl6->saddr; hdr->daddr = *first_hop; skb->protocol = htons(ETH_P_IPV6); skb->priority = priority; skb->mark = mark; mtu = dst_mtu(dst); if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) { IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip6_out((struct sock *)sk, skb); if (unlikely(!skb)) return 0; /* hooks should never assume socket lock is held. * we promote our socket to non const */ return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, (struct sock *)sk, skb, NULL, dev, dst_output); } skb->dev = dev; /* ipv6_local_error() does not require socket lock, * we promote our socket to non const */ ipv6_local_error((struct sock *)sk, EMSGSIZE, fl6, mtu); IP6_INC_STATS(net, idev, IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; } EXPORT_SYMBOL(ip6_xmit); static int ip6_call_ra_chain(struct sk_buff *skb, int sel) { struct ip6_ra_chain *ra; struct sock *last = NULL; read_lock(&ip6_ra_lock); for (ra = ip6_ra_chain; ra; ra = ra->next) { struct sock *sk = ra->sk; if (sk && ra->sel == sel && (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == skb->dev->ifindex)) { struct ipv6_pinfo *np = inet6_sk(sk); if (np && np->rtalert_isolate && !net_eq(sock_net(sk), dev_net(skb->dev))) { continue; } if (last) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) rawv6_rcv(last, skb2); } last = sk; } } if (last) { rawv6_rcv(last, skb); read_unlock(&ip6_ra_lock); return 1; } read_unlock(&ip6_ra_lock); return 0; } static int ip6_forward_proxy_check(struct sk_buff *skb) { struct ipv6hdr *hdr = ipv6_hdr(skb); u8 nexthdr = hdr->nexthdr; __be16 frag_off; int offset; if (ipv6_ext_hdr(nexthdr)) { offset = ipv6_skip_exthdr(skb, sizeof(*hdr), &nexthdr, &frag_off); if (offset < 0) return 0; } else offset = sizeof(struct ipv6hdr); if (nexthdr == IPPROTO_ICMPV6) { struct icmp6hdr *icmp6; if (!pskb_may_pull(skb, (skb_network_header(skb) + offset + 1 - skb->data))) return 0; icmp6 = (struct icmp6hdr *)(skb_network_header(skb) + offset); switch (icmp6->icmp6_type) { case NDISC_ROUTER_SOLICITATION: case NDISC_ROUTER_ADVERTISEMENT: case NDISC_NEIGHBOUR_SOLICITATION: case NDISC_NEIGHBOUR_ADVERTISEMENT: case NDISC_REDIRECT: /* For reaction involving unicast neighbor discovery * message destined to the proxied address, pass it to * input function. */ return 1; default: break; } } /* * The proxying router can't forward traffic sent to a link-local * address, so signal the sender and discard the packet. This * behavior is clarified by the MIPv6 specification. */ if (ipv6_addr_type(&hdr->daddr) & IPV6_ADDR_LINKLOCAL) { dst_link_failure(skb); return -1; } return 0; } static inline int ip6_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS); __IP6_ADD_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len); #ifdef CONFIG_NET_SWITCHDEV if (skb->offload_l3_fwd_mark) { consume_skb(skb); return 0; } #endif skb_clear_tstamp(skb); return dst_output(net, sk, skb); } static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) { if (skb->len <= mtu) return false; /* ipv6 conntrack defrag sets max_frag_size + ignore_df */ if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu) return true; if (skb->ignore_df) return false; if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; } int ip6_forward(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct ipv6hdr *hdr = ipv6_hdr(skb); struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(dst->dev); struct inet6_dev *idev; SKB_DR(reason); u32 mtu; idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif)); if (net->ipv6.devconf_all->forwarding == 0) goto error; if (skb->pkt_type != PACKET_HOST) goto drop; if (unlikely(skb->sk)) goto drop; if (skb_warn_if_lro(skb)) goto drop; if (!net->ipv6.devconf_all->disable_policy && (!idev || !idev->cnf.disable_policy) && !xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } skb_forward_csum(skb); /* * We DO NOT make any processing on * RA packets, pushing them to user level AS IS * without ane WARRANTY that application will be able * to interpret them. The reason is that we * cannot make anything clever here. * * We are not end-node, so that if packet contains * AH/ESP, we cannot make anything. * Defragmentation also would be mistake, RA packets * cannot be fragmented, because there is no warranty * that different fragments will go along one path. --ANK */ if (unlikely(opt->flags & IP6SKB_ROUTERALERT)) { if (ip6_call_ra_chain(skb, ntohs(opt->ra))) return 0; } /* * check and decrement ttl */ if (hdr->hop_limit <= 1) { icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR); return -ETIMEDOUT; } /* XXX: idev->cnf.proxy_ndp? */ if (net->ipv6.devconf_all->proxy_ndp && pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) { int proxied = ip6_forward_proxy_check(skb); if (proxied > 0) { /* It's tempting to decrease the hop limit * here by 1, as we do at the end of the * function too. * * But that would be incorrect, as proxying is * not forwarding. The ip6_input function * will handle this packet locally, and it * depends on the hop limit being unchanged. * * One example is the NDP hop limit, that * always has to stay 255, but other would be * similar checks around RA packets, where the * user can even change the desired limit. */ return ip6_input(skb); } else if (proxied < 0) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } } if (!xfrm6_route_forward(skb)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); SKB_DR_SET(reason, XFRM_POLICY); goto drop; } dst = skb_dst(skb); /* IPv6 specs say nothing about it, but it is clear that we cannot send redirects to source routed frames. We don't send redirects to frames decapsulated from IPsec. */ if (IP6CB(skb)->iif == dst->dev->ifindex && opt->srcrt == 0 && !skb_sec_path(skb)) { struct in6_addr *target = NULL; struct inet_peer *peer; struct rt6_info *rt; /* * incoming and outgoing devices are the same * send a redirect. */ rt = (struct rt6_info *) dst; if (rt->rt6i_flags & RTF_GATEWAY) target = &rt->rt6i_gateway; else target = &hdr->daddr; rcu_read_lock(); peer = inet_getpeer_v6(net->ipv6.peers, &hdr->daddr); /* Limit redirects both by destination (here) and by source (inside ndisc_send_redirect) */ if (inet_peer_xrlim_allow(peer, 1*HZ)) ndisc_send_redirect(skb, target); rcu_read_unlock(); } else { int addrtype = ipv6_addr_type(&hdr->saddr); /* This check is security critical. */ if (addrtype == IPV6_ADDR_ANY || addrtype & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LOOPBACK)) goto error; if (addrtype & IPV6_ADDR_LINKLOCAL) { icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_NOT_NEIGHBOUR, 0); goto error; } } mtu = ip6_dst_mtu_maybe_forward(dst, true); if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; if (ip6_pkt_too_big(skb, mtu)) { /* Again, force OUTPUT device used as source address */ skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); __IP6_INC_STATS(net, idev, IPSTATS_MIB_INTOOBIGERRORS); __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_FRAGFAILS); kfree_skb_reason(skb, SKB_DROP_REASON_PKT_TOO_BIG); return -EMSGSIZE; } if (skb_cow(skb, dst->dev->hard_header_len)) { __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS); goto drop; } hdr = ipv6_hdr(skb); /* Mangling hops number delayed to point after skb COW */ hdr->hop_limit--; return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, net, NULL, skb, skb->dev, dst->dev, ip6_forward_finish); error: __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); SKB_DR_SET(reason, IP_INADDRERRORS); drop: kfree_skb_reason(skb, reason); return -EINVAL; } static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) { to->pkt_type = from->pkt_type; to->priority = from->priority; to->protocol = from->protocol; skb_dst_drop(to); skb_dst_set(to, dst_clone(skb_dst(from))); to->dev = from->dev; to->mark = from->mark; skb_copy_hash(to, from); #ifdef CONFIG_NET_SCHED to->tc_index = from->tc_index; #endif nf_copy(to, from); skb_ext_copy(to, from); skb_copy_secmark(to, from); } int ip6_fraglist_init(struct sk_buff *skb, unsigned int hlen, u8 *prevhdr, u8 nexthdr, __be32 frag_id, struct ip6_fraglist_iter *iter) { unsigned int first_len; struct frag_hdr *fh; /* BUILD HEADER */ *prevhdr = NEXTHDR_FRAGMENT; iter->tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC); if (!iter->tmp_hdr) return -ENOMEM; iter->frag = skb_shinfo(skb)->frag_list; skb_frag_list_init(skb); iter->offset = 0; iter->hlen = hlen; iter->frag_id = frag_id; iter->nexthdr = nexthdr; __skb_pull(skb, hlen); fh = __skb_push(skb, sizeof(struct frag_hdr)); __skb_push(skb, hlen); skb_reset_network_header(skb); memcpy(skb_network_header(skb), iter->tmp_hdr, hlen); fh->nexthdr = nexthdr; fh->reserved = 0; fh->frag_off = htons(IP6_MF); fh->identification = frag_id; first_len = skb_pagelen(skb); skb->data_len = first_len - skb_headlen(skb); skb->len = first_len; ipv6_hdr(skb)->payload_len = htons(first_len - sizeof(struct ipv6hdr)); return 0; } EXPORT_SYMBOL(ip6_fraglist_init); void ip6_fraglist_prepare(struct sk_buff *skb, struct ip6_fraglist_iter *iter) { struct sk_buff *frag = iter->frag; unsigned int hlen = iter->hlen; struct frag_hdr *fh; frag->ip_summed = CHECKSUM_NONE; skb_reset_transport_header(frag); fh = __skb_push(frag, sizeof(struct frag_hdr)); __skb_push(frag, hlen); skb_reset_network_header(frag); memcpy(skb_network_header(frag), iter->tmp_hdr, hlen); iter->offset += skb->len - hlen - sizeof(struct frag_hdr); fh->nexthdr = iter->nexthdr; fh->reserved = 0; fh->frag_off = htons(iter->offset); if (frag->next) fh->frag_off |= htons(IP6_MF); fh->identification = iter->frag_id; ipv6_hdr(frag)->payload_len = htons(frag->len - sizeof(struct ipv6hdr)); ip6_copy_metadata(frag, skb); } EXPORT_SYMBOL(ip6_fraglist_prepare); void ip6_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int mtu, unsigned short needed_tailroom, int hdr_room, u8 *prevhdr, u8 nexthdr, __be32 frag_id, struct ip6_frag_state *state) { state->prevhdr = prevhdr; state->nexthdr = nexthdr; state->frag_id = frag_id; state->hlen = hlen; state->mtu = mtu; state->left = skb->len - hlen; /* Space per frame */ state->ptr = hlen; /* Where to start from */ state->hroom = hdr_room; state->troom = needed_tailroom; state->offset = 0; } EXPORT_SYMBOL(ip6_frag_init); struct sk_buff *ip6_frag_next(struct sk_buff *skb, struct ip6_frag_state *state) { u8 *prevhdr = state->prevhdr, *fragnexthdr_offset; struct sk_buff *frag; struct frag_hdr *fh; unsigned int len; len = state->left; /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > state->mtu) len = state->mtu; /* IF: we are not sending up to and including the packet end then align the next start on an eight byte boundary */ if (len < state->left) len &= ~7; /* Allocate buffer */ frag = alloc_skb(len + state->hlen + sizeof(struct frag_hdr) + state->hroom + state->troom, GFP_ATOMIC); if (!frag) return ERR_PTR(-ENOMEM); /* * Set up data on packet */ ip6_copy_metadata(frag, skb); skb_reserve(frag, state->hroom); skb_put(frag, len + state->hlen + sizeof(struct frag_hdr)); skb_reset_network_header(frag); fh = (struct frag_hdr *)(skb_network_header(frag) + state->hlen); frag->transport_header = (frag->network_header + state->hlen + sizeof(struct frag_hdr)); /* * Charge the memory for the fragment to any owner * it might possess */ if (skb->sk) skb_set_owner_w(frag, skb->sk); /* * Copy the packet header into the new buffer. */ skb_copy_from_linear_data(skb, skb_network_header(frag), state->hlen); fragnexthdr_offset = skb_network_header(frag); fragnexthdr_offset += prevhdr - skb_network_header(skb); *fragnexthdr_offset = NEXTHDR_FRAGMENT; /* * Build fragment header. */ fh->nexthdr = state->nexthdr; fh->reserved = 0; fh->identification = state->frag_id; /* * Copy a block of the IP datagram. */ BUG_ON(skb_copy_bits(skb, state->ptr, skb_transport_header(frag), len)); state->left -= len; fh->frag_off = htons(state->offset); if (state->left > 0) fh->frag_off |= htons(IP6_MF); ipv6_hdr(frag)->payload_len = htons(frag->len - sizeof(struct ipv6hdr)); state->ptr += len; state->offset += len; return frag; } EXPORT_SYMBOL(ip6_frag_next); int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct sk_buff *frag; struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? inet6_sk(skb->sk) : NULL; bool mono_delivery_time = skb->mono_delivery_time; struct ip6_frag_state state; unsigned int mtu, hlen, nexthdr_offset; ktime_t tstamp = skb->tstamp; int hroom, err = 0; __be32 frag_id; u8 *prevhdr, nexthdr = 0; err = ip6_find_1stfragopt(skb, &prevhdr); if (err < 0) goto fail; hlen = err; nexthdr = *prevhdr; nexthdr_offset = prevhdr - skb_network_header(skb); mtu = ip6_skb_dst_mtu(skb); /* We must not fragment if the socket is set to force MTU discovery * or if the skb it not generated by a local socket. */ if (unlikely(!skb->ignore_df && skb->len > mtu)) goto fail_toobig; if (IP6CB(skb)->frag_max_size) { if (IP6CB(skb)->frag_max_size > mtu) goto fail_toobig; /* don't send fragments larger than what we received */ mtu = IP6CB(skb)->frag_max_size; if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; } if (np && np->frag_size < mtu) { if (np->frag_size) mtu = np->frag_size; } if (mtu < hlen + sizeof(struct frag_hdr) + 8) goto fail_toobig; mtu -= hlen + sizeof(struct frag_hdr); frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr, &ipv6_hdr(skb)->saddr); if (skb->ip_summed == CHECKSUM_PARTIAL && (err = skb_checksum_help(skb))) goto fail; prevhdr = skb_network_header(skb) + nexthdr_offset; hroom = LL_RESERVED_SPACE(rt->dst.dev); if (skb_has_frag_list(skb)) { unsigned int first_len = skb_pagelen(skb); struct ip6_fraglist_iter iter; struct sk_buff *frag2; if (first_len - hlen > mtu || ((first_len - hlen) & 7) || skb_cloned(skb) || skb_headroom(skb) < (hroom + sizeof(struct frag_hdr))) goto slow_path; skb_walk_frags(skb, frag) { /* Correct geometry. */ if (frag->len > mtu || ((frag->len & 7) && frag->next) || skb_headroom(frag) < (hlen + hroom + sizeof(struct frag_hdr))) goto slow_path_clean; /* Partially cloned skb? */ if (skb_shared(frag)) goto slow_path_clean; BUG_ON(frag->sk); if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; } skb->truesize -= frag->truesize; } err = ip6_fraglist_init(skb, hlen, prevhdr, nexthdr, frag_id, &iter); if (err < 0) goto fail; /* We prevent @rt from being freed. */ rcu_read_lock(); for (;;) { /* Prepare header of the next frame, * before previous one went down. */ if (iter.frag) ip6_fraglist_prepare(skb, &iter); skb_set_delivery_time(skb, tstamp, mono_delivery_time); err = output(net, sk, skb); if (!err) IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGCREATES); if (err || !iter.frag) break; skb = ip6_fraglist_next(&iter); } kfree(iter.tmp_hdr); if (err == 0) { IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGOKS); rcu_read_unlock(); return 0; } kfree_skb_list(iter.frag); IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGFAILS); rcu_read_unlock(); return err; slow_path_clean: skb_walk_frags(skb, frag2) { if (frag2 == frag) break; frag2->sk = NULL; frag2->destructor = NULL; skb->truesize += frag2->truesize; } } slow_path: /* * Fragment the datagram. */ ip6_frag_init(skb, hlen, mtu, rt->dst.dev->needed_tailroom, LL_RESERVED_SPACE(rt->dst.dev), prevhdr, nexthdr, frag_id, &state); /* * Keep copying data until we run out. */ while (state.left > 0) { frag = ip6_frag_next(skb, &state); if (IS_ERR(frag)) { err = PTR_ERR(frag); goto fail; } /* * Put this fragment into the sending queue. */ skb_set_delivery_time(frag, tstamp, mono_delivery_time); err = output(net, sk, frag); if (err) goto fail; IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGCREATES); } IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGOKS); consume_skb(skb); return err; fail_toobig: if (skb->sk && dst_allfrag(skb_dst(skb))) sk_gso_disable(skb->sk); icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); err = -EMSGSIZE; fail: IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return err; } static inline int ip6_rt_check(const struct rt6key *rt_key, const struct in6_addr *fl_addr, const struct in6_addr *addr_cache) { return (rt_key->plen != 128 || !ipv6_addr_equal(fl_addr, &rt_key->addr)) && (!addr_cache || !ipv6_addr_equal(fl_addr, addr_cache)); } static struct dst_entry *ip6_sk_dst_check(struct sock *sk, struct dst_entry *dst, const struct flowi6 *fl6) { struct ipv6_pinfo *np = inet6_sk(sk); struct rt6_info *rt; if (!dst) goto out; if (dst->ops->family != AF_INET6) { dst_release(dst); return NULL; } rt = (struct rt6_info *)dst; /* Yes, checking route validity in not connected * case is not very simple. Take into account, * that we do not support routing by source, TOS, * and MSG_DONTROUTE --ANK (980726) * * 1. ip6_rt_check(): If route was host route, * check that cached destination is current. * If it is network route, we still may * check its validity using saved pointer * to the last used address: daddr_cache. * We do not want to save whole address now, * (because main consumer of this service * is tcp, which has not this problem), * so that the last trick works only on connected * sockets. * 2. oif also should be the same. */ if (ip6_rt_check(&rt->rt6i_dst, &fl6->daddr, np->daddr_cache) || #ifdef CONFIG_IPV6_SUBTREES ip6_rt_check(&rt->rt6i_src, &fl6->saddr, np->saddr_cache) || #endif (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex)) { dst_release(dst); dst = NULL; } out: return dst; } static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6) { #ifdef CONFIG_IPV6_OPTIMISTIC_DAD struct neighbour *n; struct rt6_info *rt; #endif int err; int flags = 0; /* The correct way to handle this would be to do * ip6_route_get_saddr, and then ip6_route_output; however, * the route-specific preferred source forces the * ip6_route_output call _before_ ip6_route_get_saddr. * * In source specific routing (no src=any default route), * ip6_route_output will fail given src=any saddr, though, so * that's why we try it again later. */ if (ipv6_addr_any(&fl6->saddr)) { struct fib6_info *from; struct rt6_info *rt; *dst = ip6_route_output(net, sk, fl6); rt = (*dst)->error ? NULL : (struct rt6_info *)*dst; rcu_read_lock(); from = rt ? rcu_dereference(rt->from) : NULL; err = ip6_route_get_saddr(net, from, &fl6->daddr, sk ? inet6_sk(sk)->srcprefs : 0, fl6->flowi6_l3mdev, &fl6->saddr); rcu_read_unlock(); if (err) goto out_err_release; /* If we had an erroneous initial result, pretend it * never existed and let the SA-enabled version take * over. */ if ((*dst)->error) { dst_release(*dst); *dst = NULL; } if (fl6->flowi6_oif) flags |= RT6_LOOKUP_F_IFACE; } if (!*dst) *dst = ip6_route_output_flags(net, sk, fl6, flags); err = (*dst)->error; if (err) goto out_err_release; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD /* * Here if the dst entry we've looked up * has a neighbour entry that is in the INCOMPLETE * state and the src address from the flow is * marked as OPTIMISTIC, we release the found * dst entry and replace it instead with the * dst entry of the nexthop router */ rt = (struct rt6_info *) *dst; rcu_read_lock(); n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr)); err = n && !(READ_ONCE(n->nud_state) & NUD_VALID) ? -EINVAL : 0; rcu_read_unlock(); if (err) { struct inet6_ifaddr *ifp; struct flowi6 fl_gw6; int redirect; ifp = ipv6_get_ifaddr(net, &fl6->saddr, (*dst)->dev, 1); redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC); if (ifp) in6_ifa_put(ifp); if (redirect) { /* * We need to get the dst entry for the * default router instead */ dst_release(*dst); memcpy(&fl_gw6, fl6, sizeof(struct flowi6)); memset(&fl_gw6.daddr, 0, sizeof(struct in6_addr)); *dst = ip6_route_output(net, sk, &fl_gw6); err = (*dst)->error; if (err) goto out_err_release; } } #endif if (ipv6_addr_v4mapped(&fl6->saddr) && !(ipv6_addr_v4mapped(&fl6->daddr) || ipv6_addr_any(&fl6->daddr))) { err = -EAFNOSUPPORT; goto out_err_release; } return 0; out_err_release: dst_release(*dst); *dst = NULL; if (err == -ENETUNREACH) IP6_INC_STATS(net, NULL, IPSTATS_MIB_OUTNOROUTES); return err; } /** * ip6_dst_lookup - perform route lookup on flow * @net: Network namespace to perform lookup in * @sk: socket which provides route info * @dst: pointer to dst_entry * for result * @fl6: flow to lookup * * This function performs a route lookup on the given flow. * * It returns zero on success, or a standard errno code on error. */ int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6) { *dst = NULL; return ip6_dst_lookup_tail(net, sk, dst, fl6); } EXPORT_SYMBOL_GPL(ip6_dst_lookup); /** * ip6_dst_lookup_flow - perform route lookup on flow with ipsec * @net: Network namespace to perform lookup in * @sk: socket which provides route info * @fl6: flow to lookup * @final_dst: final destination address for ipsec lookup * * This function performs a route lookup on the given flow. * * It returns a valid dst pointer on success, or a pointer encoded * error code. */ struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst) { struct dst_entry *dst = NULL; int err; err = ip6_dst_lookup_tail(net, sk, &dst, fl6); if (err) return ERR_PTR(err); if (final_dst) fl6->daddr = *final_dst; return xfrm_lookup_route(net, dst, flowi6_to_flowi(fl6), sk, 0); } EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow); /** * ip6_sk_dst_lookup_flow - perform socket cached route lookup on flow * @sk: socket which provides the dst cache and route info * @fl6: flow to lookup * @final_dst: final destination address for ipsec lookup * @connected: whether @sk is connected or not * * This function performs a route lookup on the given flow with the * possibility of using the cached route in the socket if it is valid. * It will take the socket dst lock when operating on the dst cache. * As a result, this function can only be used in process context. * * In addition, for a connected socket, cache the dst in the socket * if the current cache is not valid. * * It returns a valid dst pointer on success, or a pointer encoded * error code. */ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst, bool connected) { struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie); dst = ip6_sk_dst_check(sk, dst, fl6); if (dst) return dst; dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_dst); if (connected && !IS_ERR(dst)) ip6_sk_dst_store_flow(sk, dst_clone(dst), fl6); return dst; } EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow); /** * ip6_dst_lookup_tunnel - perform route lookup on tunnel * @skb: Packet for which lookup is done * @dev: Tunnel device * @net: Network namespace of tunnel device * @sock: Socket which provides route info * @saddr: Memory to store the src ip address * @info: Tunnel information * @protocol: IP protocol * @use_cache: Flag to enable cache usage * This function performs a route lookup on a tunnel * * It returns a valid dst pointer and stores src address to be used in * tunnel in param saddr on success, else a pointer encoded error code. */ struct dst_entry *ip6_dst_lookup_tunnel(struct sk_buff *skb, struct net_device *dev, struct net *net, struct socket *sock, struct in6_addr *saddr, const struct ip_tunnel_info *info, u8 protocol, bool use_cache) { struct dst_entry *dst = NULL; #ifdef CONFIG_DST_CACHE struct dst_cache *dst_cache; #endif struct flowi6 fl6; __u8 prio; #ifdef CONFIG_DST_CACHE dst_cache = (struct dst_cache *)&info->dst_cache; if (use_cache) { dst = dst_cache_get_ip6(dst_cache, saddr); if (dst) return dst; } #endif memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_mark = skb->mark; fl6.flowi6_proto = protocol; fl6.daddr = info->key.u.ipv6.dst; fl6.saddr = info->key.u.ipv6.src; prio = info->key.tos; fl6.flowlabel = ip6_make_flowinfo(prio, info->key.label); dst = ipv6_stub->ipv6_dst_lookup_flow(net, sock->sk, &fl6, NULL); if (IS_ERR(dst)) { netdev_dbg(dev, "no route to %pI6\n", &fl6.daddr); return ERR_PTR(-ENETUNREACH); } if (dst->dev == dev) { /* is this necessary? */ netdev_dbg(dev, "circular route to %pI6\n", &fl6.daddr); dst_release(dst); return ERR_PTR(-ELOOP); } #ifdef CONFIG_DST_CACHE if (use_cache) dst_cache_set_ip6(dst_cache, dst, &fl6.saddr); #endif *saddr = fl6.saddr; return dst; } EXPORT_SYMBOL_GPL(ip6_dst_lookup_tunnel); static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src, gfp_t gfp) { return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL; } static inline struct ipv6_rt_hdr *ip6_rthdr_dup(struct ipv6_rt_hdr *src, gfp_t gfp) { return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL; } static void ip6_append_data_mtu(unsigned int *mtu, int *maxfraglen, unsigned int fragheaderlen, struct sk_buff *skb, struct rt6_info *rt, unsigned int orig_mtu) { if (!(rt->dst.flags & DST_XFRM_TUNNEL)) { if (!skb) { /* first fragment, reserve header_len */ *mtu = orig_mtu - rt->dst.header_len; } else { /* * this fragment is not first, the headers * space is regarded as data space. */ *mtu = orig_mtu; } *maxfraglen = ((*mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr); } } static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, struct inet6_cork *v6_cork, struct ipcm6_cookie *ipc6, struct rt6_info *rt) { struct ipv6_pinfo *np = inet6_sk(sk); unsigned int mtu; struct ipv6_txoptions *nopt, *opt = ipc6->opt; /* callers pass dst together with a reference, set it first so * ip6_cork_release() can put it down even in case of an error. */ cork->base.dst = &rt->dst; /* * setup for corking */ if (opt) { if (WARN_ON(v6_cork->opt)) return -EINVAL; nopt = v6_cork->opt = kzalloc(sizeof(*opt), sk->sk_allocation); if (unlikely(!nopt)) return -ENOBUFS; nopt->tot_len = sizeof(*opt); nopt->opt_flen = opt->opt_flen; nopt->opt_nflen = opt->opt_nflen; nopt->dst0opt = ip6_opt_dup(opt->dst0opt, sk->sk_allocation); if (opt->dst0opt && !nopt->dst0opt) return -ENOBUFS; nopt->dst1opt = ip6_opt_dup(opt->dst1opt, sk->sk_allocation); if (opt->dst1opt && !nopt->dst1opt) return -ENOBUFS; nopt->hopopt = ip6_opt_dup(opt->hopopt, sk->sk_allocation); if (opt->hopopt && !nopt->hopopt) return -ENOBUFS; nopt->srcrt = ip6_rthdr_dup(opt->srcrt, sk->sk_allocation); if (opt->srcrt && !nopt->srcrt) return -ENOBUFS; /* need source address above miyazawa*/ } v6_cork->hop_limit = ipc6->hlimit; v6_cork->tclass = ipc6->tclass; if (rt->dst.flags & DST_XFRM_TUNNEL) mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ? READ_ONCE(rt->dst.dev->mtu) : dst_mtu(&rt->dst); else mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ? READ_ONCE(rt->dst.dev->mtu) : dst_mtu(xfrm_dst_path(&rt->dst)); if (np->frag_size < mtu) { if (np->frag_size) mtu = np->frag_size; } cork->base.fragsize = mtu; cork->base.gso_size = ipc6->gso_size; cork->base.tx_flags = 0; cork->base.mark = ipc6->sockc.mark; sock_tx_timestamp(sk, ipc6->sockc.tsflags, &cork->base.tx_flags); if (dst_allfrag(xfrm_dst_path(&rt->dst))) cork->base.flags |= IPCORK_ALLFRAG; cork->base.length = 0; cork->base.transmit_time = ipc6->sockc.transmit_time; return 0; } static int __ip6_append_data(struct sock *sk, struct sk_buff_head *queue, struct inet_cork_full *cork_full, struct inet6_cork *v6_cork, struct page_frag *pfrag, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, size_t length, int transhdrlen, unsigned int flags, struct ipcm6_cookie *ipc6) { struct sk_buff *skb, *skb_prev = NULL; struct inet_cork *cork = &cork_full->base; struct flowi6 *fl6 = &cork_full->fl.u.ip6; unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu, pmtu; struct ubuf_info *uarg = NULL; int exthdrlen = 0; int dst_exthdrlen = 0; int hh_len; int copy; int err; int offset = 0; bool zc = false; u32 tskey = 0; struct rt6_info *rt = (struct rt6_info *)cork->dst; bool paged, hold_tskey, extra_uref = false; struct ipv6_txoptions *opt = v6_cork->opt; int csummode = CHECKSUM_NONE; unsigned int maxnonfragsize, headersize; unsigned int wmem_alloc_delta = 0; skb = skb_peek_tail(queue); if (!skb) { exthdrlen = opt ? opt->opt_flen : 0; dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len; } paged = !!cork->gso_size; mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize; orig_mtu = mtu; hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len + (opt ? opt->opt_nflen : 0); headersize = sizeof(struct ipv6hdr) + (opt ? opt->opt_flen + opt->opt_nflen : 0) + (dst_allfrag(&rt->dst) ? sizeof(struct frag_hdr) : 0) + rt->rt6i_nfheader_len; if (mtu <= fragheaderlen || ((mtu - fragheaderlen) & ~7) + fragheaderlen <= sizeof(struct frag_hdr)) goto emsgsize; maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr); /* as per RFC 7112 section 5, the entire IPv6 Header Chain must fit * the first fragment */ if (headersize + transhdrlen > mtu) goto emsgsize; if (cork->length + length > mtu - headersize && ipc6->dontfrag && (sk->sk_protocol == IPPROTO_UDP || sk->sk_protocol == IPPROTO_ICMPV6 || sk->sk_protocol == IPPROTO_RAW)) { ipv6_local_rxpmtu(sk, fl6, mtu - headersize + sizeof(struct ipv6hdr)); goto emsgsize; } if (ip6_sk_ignore_df(sk)) maxnonfragsize = sizeof(struct ipv6hdr) + IPV6_MAXPLEN; else maxnonfragsize = mtu; if (cork->length + length > maxnonfragsize - headersize) { emsgsize: pmtu = max_t(int, mtu - headersize + sizeof(struct ipv6hdr), 0); ipv6_local_error(sk, EMSGSIZE, fl6, pmtu); return -EMSGSIZE; } /* CHECKSUM_PARTIAL only with no extension headers and when * we are not going to fragment */ if (transhdrlen && sk->sk_protocol == IPPROTO_UDP && headersize == sizeof(struct ipv6hdr) && length <= mtu - headersize && (!(flags & MSG_MORE) || cork->gso_size) && rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) csummode = CHECKSUM_PARTIAL; if ((flags & MSG_ZEROCOPY) && length) { struct msghdr *msg = from; if (getfrag == ip_generic_getfrag && msg->msg_ubuf) { if (skb_zcopy(skb) && msg->msg_ubuf != skb_zcopy(skb)) return -EINVAL; /* Leave uarg NULL if can't zerocopy, callers should * be able to handle it. */ if ((rt->dst.dev->features & NETIF_F_SG) && csummode == CHECKSUM_PARTIAL) { paged = true; zc = true; uarg = msg->msg_ubuf; } } else if (sock_flag(sk, SOCK_ZEROCOPY)) { uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb)); if (!uarg) return -ENOBUFS; extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ if (rt->dst.dev->features & NETIF_F_SG && csummode == CHECKSUM_PARTIAL) { paged = true; zc = true; } else { uarg_to_msgzc(uarg)->zerocopy = 0; skb_zcopy_set(skb, uarg, &extra_uref); } } } hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP && READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID; if (hold_tskey) tskey = atomic_inc_return(&sk->sk_tskey) - 1; /* * Let's try using as much space as possible. * Use MTU if total length of the message fits into the MTU. * Otherwise, we need to reserve fragment header and * fragment alignment (= 8-15 octects, in total). * * Note that we may need to "move" the data from the tail * of the buffer to the new fragment when we split * the message. * * FIXME: It may be fragmented into multiple chunks * at once if non-fragmentable extension headers * are too large. * --yoshfuji */ cork->length += length; if (!skb) goto alloc_new_skb; while (length > 0) { /* Check if the remaining data fits into current packet. */ copy = (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len; if (copy < length) copy = maxfraglen - skb->len; if (copy <= 0) { char *data; unsigned int datalen; unsigned int fraglen; unsigned int fraggap; unsigned int alloclen, alloc_extra; unsigned int pagedlen; alloc_new_skb: /* There's no room in the current skb */ if (skb) fraggap = skb->len - maxfraglen; else fraggap = 0; /* update mtu and maxfraglen if necessary */ if (!skb || !skb_prev) ip6_append_data_mtu(&mtu, &maxfraglen, fragheaderlen, skb, rt, orig_mtu); skb_prev = skb; /* * If remaining data exceeds the mtu, * we know we need more fragment(s). */ datalen = length + fraggap; if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen) datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len; fraglen = datalen + fragheaderlen; pagedlen = 0; alloc_extra = hh_len; alloc_extra += dst_exthdrlen; alloc_extra += rt->dst.trailer_len; /* We just reserve space for fragment header. * Note: this may be overallocation if the message * (without MSG_MORE) fits into the MTU. */ alloc_extra += sizeof(struct frag_hdr); if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; else if (!paged && (fraglen + alloc_extra < SKB_MAX_ALLOC || !(rt->dst.dev->features & NETIF_F_SG))) alloclen = fraglen; else { alloclen = fragheaderlen + transhdrlen; pagedlen = datalen - transhdrlen; } alloclen += alloc_extra; if (datalen != length + fraggap) { /* * this is not the last fragment, the trailer * space is regarded as data space. */ datalen += rt->dst.trailer_len; } fraglen = datalen + fragheaderlen; copy = datalen - transhdrlen - fraggap - pagedlen; if (copy < 0) { err = -EINVAL; goto error; } if (transhdrlen) { skb = sock_alloc_send_skb(sk, alloclen, (flags & MSG_DONTWAIT), &err); } else { skb = NULL; if (refcount_read(&sk->sk_wmem_alloc) + wmem_alloc_delta <= 2 * sk->sk_sndbuf) skb = alloc_skb(alloclen, sk->sk_allocation); if (unlikely(!skb)) err = -ENOBUFS; } if (!skb) goto error; /* * Fill in the control structures */ skb->protocol = htons(ETH_P_IPV6); skb->ip_summed = csummode; skb->csum = 0; /* reserve for fragmentation and ipsec header */ skb_reserve(skb, hh_len + sizeof(struct frag_hdr) + dst_exthdrlen); /* * Find where to start putting bytes */ data = skb_put(skb, fraglen - pagedlen); skb_set_network_header(skb, exthdrlen); data += fragheaderlen; skb->transport_header = (skb->network_header + fragheaderlen); if (fraggap) { skb->csum = skb_copy_and_csum_bits( skb_prev, maxfraglen, data + transhdrlen, fraggap); skb_prev->csum = csum_sub(skb_prev->csum, skb->csum); data += fraggap; pskb_trim_unique(skb_prev, maxfraglen); } if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) { err = -EFAULT; kfree_skb(skb); goto error; } offset += copy; length -= copy + transhdrlen; transhdrlen = 0; exthdrlen = 0; dst_exthdrlen = 0; /* Only the initial fragment is time stamped */ skb_shinfo(skb)->tx_flags = cork->tx_flags; cork->tx_flags = 0; skb_shinfo(skb)->tskey = tskey; tskey = 0; skb_zcopy_set(skb, uarg, &extra_uref); if ((flags & MSG_CONFIRM) && !skb_prev) skb_set_dst_pending_confirm(skb, 1); /* * Put the packet on the pending queue */ if (!skb->destructor) { skb->destructor = sock_wfree; skb->sk = sk; wmem_alloc_delta += skb->truesize; } __skb_queue_tail(queue, skb); continue; } if (copy > length) copy = length; if (!(rt->dst.dev->features&NETIF_F_SG) && skb_tailroom(skb) >= copy) { unsigned int off; off = skb->len; if (getfrag(from, skb_put(skb, copy), offset, copy, off, skb) < 0) { __skb_trim(skb, off); err = -EFAULT; goto error; } } else if (!zc) { int i = skb_shinfo(skb)->nr_frags; err = -ENOMEM; if (!sk_page_frag_refill(sk, pfrag)) goto error; skb_zcopy_downgrade_managed(skb); if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { err = -EMSGSIZE; if (i == MAX_SKB_FRAGS) goto error; __skb_fill_page_desc(skb, i, pfrag->page, pfrag->offset, 0); skb_shinfo(skb)->nr_frags = ++i; get_page(pfrag->page); } copy = min_t(int, copy, pfrag->size - pfrag->offset); if (getfrag(from, page_address(pfrag->page) + pfrag->offset, offset, copy, skb->len, skb) < 0) goto error_efault; pfrag->offset += copy; skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); skb->len += copy; skb->data_len += copy; skb->truesize += copy; wmem_alloc_delta += copy; } else { err = skb_zerocopy_iter_dgram(skb, from, copy); if (err < 0) goto error; } offset += copy; length -= copy; } if (wmem_alloc_delta) refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); return 0; error_efault: err = -EFAULT; error: net_zcopy_put_abort(uarg, extra_uref); cork->length -= length; IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); if (hold_tskey) atomic_dec(&sk->sk_tskey); return err; } int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); int exthdrlen; int err; if (flags&MSG_PROBE) return 0; if (skb_queue_empty(&sk->sk_write_queue)) { /* * setup for corking */ dst_hold(&rt->dst); err = ip6_setup_cork(sk, &inet->cork, &np->cork, ipc6, rt); if (err) return err; inet->cork.fl.u.ip6 = *fl6; exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0); length += exthdrlen; transhdrlen += exthdrlen; } else { transhdrlen = 0; } return __ip6_append_data(sk, &sk->sk_write_queue, &inet->cork, &np->cork, sk_page_frag(sk), getfrag, from, length, transhdrlen, flags, ipc6); } EXPORT_SYMBOL_GPL(ip6_append_data); static void ip6_cork_steal_dst(struct sk_buff *skb, struct inet_cork_full *cork) { struct dst_entry *dst = cork->base.dst; cork->base.dst = NULL; cork->base.flags &= ~IPCORK_ALLFRAG; skb_dst_set(skb, dst); } static void ip6_cork_release(struct inet_cork_full *cork, struct inet6_cork *v6_cork) { if (v6_cork->opt) { struct ipv6_txoptions *opt = v6_cork->opt; kfree(opt->dst0opt); kfree(opt->dst1opt); kfree(opt->hopopt); kfree(opt->srcrt); kfree(opt); v6_cork->opt = NULL; } if (cork->base.dst) { dst_release(cork->base.dst); cork->base.dst = NULL; cork->base.flags &= ~IPCORK_ALLFRAG; } } struct sk_buff *__ip6_make_skb(struct sock *sk, struct sk_buff_head *queue, struct inet_cork_full *cork, struct inet6_cork *v6_cork) { struct sk_buff *skb, *tmp_skb; struct sk_buff **tail_skb; struct in6_addr *final_dst; struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); struct ipv6hdr *hdr; struct ipv6_txoptions *opt = v6_cork->opt; struct rt6_info *rt = (struct rt6_info *)cork->base.dst; struct flowi6 *fl6 = &cork->fl.u.ip6; unsigned char proto = fl6->flowi6_proto; skb = __skb_dequeue(queue); if (!skb) goto out; tail_skb = &(skb_shinfo(skb)->frag_list); /* move skb->data to ip header from ext header */ if (skb->data < skb_network_header(skb)) __skb_pull(skb, skb_network_offset(skb)); while ((tmp_skb = __skb_dequeue(queue)) != NULL) { __skb_pull(tmp_skb, skb_network_header_len(skb)); *tail_skb = tmp_skb; tail_skb = &(tmp_skb->next); skb->len += tmp_skb->len; skb->data_len += tmp_skb->len; skb->truesize += tmp_skb->truesize; tmp_skb->destructor = NULL; tmp_skb->sk = NULL; } /* Allow local fragmentation. */ skb->ignore_df = ip6_sk_ignore_df(sk); __skb_pull(skb, skb_network_header_len(skb)); final_dst = &fl6->daddr; if (opt && opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); if (opt && opt->opt_nflen) ipv6_push_nfrag_opts(skb, opt, &proto, &final_dst, &fl6->saddr); skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); hdr = ipv6_hdr(skb); ip6_flow_hdr(hdr, v6_cork->tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, ip6_autoflowlabel(net, np), fl6)); hdr->hop_limit = v6_cork->hop_limit; hdr->nexthdr = proto; hdr->saddr = fl6->saddr; hdr->daddr = *final_dst; skb->priority = sk->sk_priority; skb->mark = cork->base.mark; skb->tstamp = cork->base.transmit_time; ip6_cork_steal_dst(skb, cork); IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); u8 icmp6_type; if (sk->sk_socket->type == SOCK_RAW && !inet_sk(sk)->hdrincl) icmp6_type = fl6->fl6_icmp_type; else icmp6_type = icmp6_hdr(skb)->icmp6_type; ICMP6MSGOUT_INC_STATS(net, idev, icmp6_type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } ip6_cork_release(cork, v6_cork); out: return skb; } int ip6_send_skb(struct sk_buff *skb) { struct net *net = sock_net(skb->sk); struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); int err; rcu_read_lock(); err = ip6_local_out(net, skb->sk, skb); if (err) { if (err > 0) err = net_xmit_errno(err); if (err) IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); } rcu_read_unlock(); return err; } int ip6_push_pending_frames(struct sock *sk) { struct sk_buff *skb; skb = ip6_finish_skb(sk); if (!skb) return 0; return ip6_send_skb(skb); } EXPORT_SYMBOL_GPL(ip6_push_pending_frames); static void __ip6_flush_pending_frames(struct sock *sk, struct sk_buff_head *queue, struct inet_cork_full *cork, struct inet6_cork *v6_cork) { struct sk_buff *skb; while ((skb = __skb_dequeue_tail(queue)) != NULL) { if (skb_dst(skb)) IP6_INC_STATS(sock_net(sk), ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); } ip6_cork_release(cork, v6_cork); } void ip6_flush_pending_frames(struct sock *sk) { __ip6_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork, &inet6_sk(sk)->cork); } EXPORT_SYMBOL_GPL(ip6_flush_pending_frames); struct sk_buff *ip6_make_skb(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct rt6_info *rt, unsigned int flags, struct inet_cork_full *cork) { struct inet6_cork v6_cork; struct sk_buff_head queue; int exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0); int err; if (flags & MSG_PROBE) { dst_release(&rt->dst); return NULL; } __skb_queue_head_init(&queue); cork->base.flags = 0; cork->base.addr = 0; cork->base.opt = NULL; v6_cork.opt = NULL; err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt); if (err) { ip6_cork_release(cork, &v6_cork); return ERR_PTR(err); } if (ipc6->dontfrag < 0) ipc6->dontfrag = inet6_sk(sk)->dontfrag; err = __ip6_append_data(sk, &queue, cork, &v6_cork, ¤t->task_frag, getfrag, from, length + exthdrlen, transhdrlen + exthdrlen, flags, ipc6); if (err) { __ip6_flush_pending_frames(sk, &queue, cork, &v6_cork); return ERR_PTR(err); } return __ip6_make_skb(sk, &queue, cork, &v6_cork); } |
| 2928 2928 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swapfile.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * Swap reorganised 29.12.95, Stephen Tweedie */ #include <linux/blkdev.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/vmalloc.h> #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/shmem_fs.h> #include <linux/blk-cgroup.h> #include <linux/random.h> #include <linux/writeback.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/backing-dev.h> #include <linux/mutex.h> #include <linux/capability.h> #include <linux/syscalls.h> #include <linux/memcontrol.h> #include <linux/poll.h> #include <linux/oom.h> #include <linux/frontswap.h> #include <linux/swapfile.h> #include <linux/export.h> #include <linux/swap_slots.h> #include <linux/sort.h> #include <linux/completion.h> #include <asm/tlbflush.h> #include <linux/swapops.h> #include <linux/swap_cgroup.h> #include "swap.h" #include <trace/hooks/bl_hib.h> static bool swap_count_continued(struct swap_info_struct *, pgoff_t, unsigned char); static void free_swap_count_continuations(struct swap_info_struct *); static DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; atomic_long_t nr_swap_pages; /* * Some modules use swappable objects and may try to swap them out under * memory pressure (via the shrinker). Before doing so, they may wish to * check to see if any swap space is available. */ EXPORT_SYMBOL_GPL(nr_swap_pages); /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority = -1; unsigned long swapfile_maximum_size; #ifdef CONFIG_MIGRATION bool swap_migration_ad_supported; #endif /* CONFIG_MIGRATION */ static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; static const char Unused_offset[] = "Unused swap offset entry "; /* * all active swap_info_structs * protected with swap_lock, and ordered by priority. */ static PLIST_HEAD(swap_active_head); /* * all available (active, not full) swap_info_structs * protected with swap_avail_lock, ordered by priority. * This is used by folio_alloc_swap() instead of swap_active_head * because swap_active_head includes all swap_info_structs, * but folio_alloc_swap() doesn't need to look at full ones. * This uses its own lock instead of swap_lock because when a * swap_info_struct changes between not-full/full, it needs to * add/remove itself to/from this list, but the swap_info_struct->lock * is held and the locking order requires swap_lock to be taken * before any swap_info_struct->lock. */ static struct plist_head *swap_avail_heads; static DEFINE_SPINLOCK(swap_avail_lock); struct swap_info_struct *swap_info[MAX_SWAPFILES]; static DEFINE_MUTEX(swapon_mutex); static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait); /* Activity counter to indicate that a swapon or swapoff has occurred */ static atomic_t proc_poll_event = ATOMIC_INIT(0); atomic_t nr_rotate_swap = ATOMIC_INIT(0); static struct swap_info_struct *swap_type_to_swap_info(int type) { if (type >= MAX_SWAPFILES) return NULL; return READ_ONCE(swap_info[type]); /* rcu_dereference() */ } static inline unsigned char swap_count(unsigned char ent) { return ent & ~SWAP_HAS_CACHE; /* may include COUNT_CONTINUED flag */ } /* Reclaim the swap entry anyway if possible */ #define TTRS_ANYWAY 0x1 /* * Reclaim the swap entry if there are no more mappings of the * corresponding page */ #define TTRS_UNMAPPED 0x2 /* Reclaim the swap entry if swap is getting full*/ #define TTRS_FULL 0x4 /* returns 1 if swap entry is freed */ static int __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset, unsigned long flags) { swp_entry_t entry = swp_entry(si->type, offset); struct folio *folio; int ret = 0; folio = filemap_get_folio(swap_address_space(entry), offset); if (!folio) return 0; /* * When this function is called from scan_swap_map_slots() and it's * called by vmscan.c at reclaiming folios. So we hold a folio lock * here. We have to use trylock for avoiding deadlock. This is a special * case and you should use folio_free_swap() with explicit folio_lock() * in usual operations. */ if (folio_trylock(folio)) { if ((flags & TTRS_ANYWAY) || ((flags & TTRS_UNMAPPED) && !folio_mapped(folio)) || ((flags & TTRS_FULL) && mem_cgroup_swap_full(folio))) ret = folio_free_swap(folio); folio_unlock(folio); } folio_put(folio); return ret; } static inline struct swap_extent *first_se(struct swap_info_struct *sis) { struct rb_node *rb = rb_first(&sis->swap_extent_root); return rb_entry(rb, struct swap_extent, rb_node); } static inline struct swap_extent *next_se(struct swap_extent *se) { struct rb_node *rb = rb_next(&se->rb_node); return rb ? rb_entry(rb, struct swap_extent, rb_node) : NULL; } /* * swapon tell device that all the old swap contents can be discarded, * to allow the swap device to optimize its wear-levelling. */ static int discard_swap(struct swap_info_struct *si) { struct swap_extent *se; sector_t start_block; sector_t nr_blocks; int err = 0; /* Do not discard the swap header page! */ se = first_se(si); start_block = (se->start_block + 1) << (PAGE_SHIFT - 9); nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL); if (err) return err; cond_resched(); } for (se = next_se(se); se; se = next_se(se)) { start_block = se->start_block << (PAGE_SHIFT - 9); nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL); if (err) break; cond_resched(); } return err; /* That will often be -EOPNOTSUPP */ } static struct swap_extent * offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset) { struct swap_extent *se; struct rb_node *rb; rb = sis->swap_extent_root.rb_node; while (rb) { se = rb_entry(rb, struct swap_extent, rb_node); if (offset < se->start_page) rb = rb->rb_left; else if (offset >= se->start_page + se->nr_pages) rb = rb->rb_right; else return se; } /* It *must* be present */ BUG(); } sector_t swap_page_sector(struct page *page) { struct swap_info_struct *sis = page_swap_info(page); struct swap_extent *se; sector_t sector; pgoff_t offset; offset = __page_file_index(page); se = offset_to_swap_extent(sis, offset); sector = se->start_block + (offset - se->start_page); return sector << (PAGE_SHIFT - 9); } /* * swap allocation tell device that a cluster of swap can now be discarded, * to allow the swap device to optimize its wear-levelling. */ static void discard_swap_cluster(struct swap_info_struct *si, pgoff_t start_page, pgoff_t nr_pages) { struct swap_extent *se = offset_to_swap_extent(si, start_page); while (nr_pages) { pgoff_t offset = start_page - se->start_page; sector_t start_block = se->start_block + offset; sector_t nr_blocks = se->nr_pages - offset; if (nr_blocks > nr_pages) nr_blocks = nr_pages; start_page += nr_blocks; nr_pages -= nr_blocks; start_block <<= PAGE_SHIFT - 9; nr_blocks <<= PAGE_SHIFT - 9; if (blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_NOIO)) break; se = next_se(se); } } #ifdef CONFIG_THP_SWAP #define SWAPFILE_CLUSTER HPAGE_PMD_NR #define swap_entry_size(size) (size) #else #define SWAPFILE_CLUSTER 256 /* * Define swap_entry_size() as constant to let compiler to optimize * out some code if !CONFIG_THP_SWAP */ #define swap_entry_size(size) 1 #endif #define LATENCY_LIMIT 256 static inline void cluster_set_flag(struct swap_cluster_info *info, unsigned int flag) { info->flags = flag; } static inline unsigned int cluster_count(struct swap_cluster_info *info) { return info->data; } static inline void cluster_set_count(struct swap_cluster_info *info, unsigned int c) { info->data = c; } static inline void cluster_set_count_flag(struct swap_cluster_info *info, unsigned int c, unsigned int f) { info->flags = f; info->data = c; } static inline unsigned int cluster_next(struct swap_cluster_info *info) { return info->data; } static inline void cluster_set_next(struct swap_cluster_info *info, unsigned int n) { info->data = n; } static inline void cluster_set_next_flag(struct swap_cluster_info *info, unsigned int n, unsigned int f) { info->flags = f; info->data = n; } static inline bool cluster_is_free(struct swap_cluster_info *info) { return info->flags & CLUSTER_FLAG_FREE; } static inline bool cluster_is_null(struct swap_cluster_info *info) { return info->flags & CLUSTER_FLAG_NEXT_NULL; } static inline void cluster_set_null(struct swap_cluster_info *info) { info->flags = CLUSTER_FLAG_NEXT_NULL; info->data = 0; } static inline bool cluster_is_huge(struct swap_cluster_info *info) { if (IS_ENABLED(CONFIG_THP_SWAP)) return info->flags & CLUSTER_FLAG_HUGE; return false; } static inline void cluster_clear_huge(struct swap_cluster_info *info) { info->flags &= ~CLUSTER_FLAG_HUGE; } static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si, unsigned long offset) { struct swap_cluster_info *ci; ci = si->cluster_info; if (ci) { ci += offset / SWAPFILE_CLUSTER; spin_lock(&ci->lock); } return ci; } static inline void unlock_cluster(struct swap_cluster_info *ci) { if (ci) spin_unlock(&ci->lock); } /* * Determine the locking method in use for this device. Return * swap_cluster_info if SSD-style cluster-based locking is in place. */ static inline struct swap_cluster_info *lock_cluster_or_swap_info( struct swap_info_struct *si, unsigned long offset) { struct swap_cluster_info *ci; /* Try to use fine-grained SSD-style locking if available: */ ci = lock_cluster(si, offset); /* Otherwise, fall back to traditional, coarse locking: */ if (!ci) spin_lock(&si->lock); return ci; } static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si, struct swap_cluster_info *ci) { if (ci) unlock_cluster(ci); else spin_unlock(&si->lock); } static inline bool cluster_list_empty(struct swap_cluster_list *list) { return cluster_is_null(&list->head); } static inline unsigned int cluster_list_first(struct swap_cluster_list *list) { return cluster_next(&list->head); } static void cluster_list_init(struct swap_cluster_list *list) { cluster_set_null(&list->head); cluster_set_null(&list->tail); } static void cluster_list_add_tail(struct swap_cluster_list *list, struct swap_cluster_info *ci, unsigned int idx) { if (cluster_list_empty(list)) { cluster_set_next_flag(&list->head, idx, 0); cluster_set_next_flag(&list->tail, idx, 0); } else { struct swap_cluster_info *ci_tail; unsigned int tail = cluster_next(&list->tail); /* * Nested cluster lock, but both cluster locks are * only acquired when we held swap_info_struct->lock */ ci_tail = ci + tail; spin_lock_nested(&ci_tail->lock, SINGLE_DEPTH_NESTING); cluster_set_next(ci_tail, idx); spin_unlock(&ci_tail->lock); cluster_set_next_flag(&list->tail, idx, 0); } } static unsigned int cluster_list_del_first(struct swap_cluster_list *list, struct swap_cluster_info *ci) { unsigned int idx; idx = cluster_next(&list->head); if (cluster_next(&list->tail) == idx) { cluster_set_null(&list->head); cluster_set_null(&list->tail); } else cluster_set_next_flag(&list->head, cluster_next(&ci[idx]), 0); return idx; } /* Add a cluster to discard list and schedule it to do discard */ static void swap_cluster_schedule_discard(struct swap_info_struct *si, unsigned int idx) { /* * If scan_swap_map_slots() can't find a free cluster, it will check * si->swap_map directly. To make sure the discarding cluster isn't * taken by scan_swap_map_slots(), mark the swap entries bad (occupied). * It will be cleared after discard */ memset(si->swap_map + idx * SWAPFILE_CLUSTER, SWAP_MAP_BAD, SWAPFILE_CLUSTER); cluster_list_add_tail(&si->discard_clusters, si->cluster_info, idx); schedule_work(&si->discard_work); } static void __free_cluster(struct swap_info_struct *si, unsigned long idx) { struct swap_cluster_info *ci = si->cluster_info; cluster_set_flag(ci + idx, CLUSTER_FLAG_FREE); cluster_list_add_tail(&si->free_clusters, ci, idx); } /* * Doing discard actually. After a cluster discard is finished, the cluster * will be added to free cluster list. caller should hold si->lock. */ static void swap_do_scheduled_discard(struct swap_info_struct *si) { struct swap_cluster_info *info, *ci; unsigned int idx; info = si->cluster_info; while (!cluster_list_empty(&si->discard_clusters)) { idx = cluster_list_del_first(&si->discard_clusters, info); spin_unlock(&si->lock); discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, SWAPFILE_CLUSTER); spin_lock(&si->lock); ci = lock_cluster(si, idx * SWAPFILE_CLUSTER); __free_cluster(si, idx); memset(si->swap_map + idx * SWAPFILE_CLUSTER, 0, SWAPFILE_CLUSTER); unlock_cluster(ci); } } static void swap_discard_work(struct work_struct *work) { struct swap_info_struct *si; si = container_of(work, struct swap_info_struct, discard_work); spin_lock(&si->lock); swap_do_scheduled_discard(si); spin_unlock(&si->lock); } static void swap_users_ref_free(struct percpu_ref *ref) { struct swap_info_struct *si; si = container_of(ref, struct swap_info_struct, users); complete(&si->comp); } static void alloc_cluster(struct swap_info_struct *si, unsigned long idx) { struct swap_cluster_info *ci = si->cluster_info; VM_BUG_ON(cluster_list_first(&si->free_clusters) != idx); cluster_list_del_first(&si->free_clusters, ci); cluster_set_count_flag(ci + idx, 0, 0); } static void free_cluster(struct swap_info_struct *si, unsigned long idx) { struct swap_cluster_info *ci = si->cluster_info + idx; VM_BUG_ON(cluster_count(ci) != 0); /* * If the swap is discardable, prepare discard the cluster * instead of free it immediately. The cluster will be freed * after discard. */ if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) == (SWP_WRITEOK | SWP_PAGE_DISCARD)) { swap_cluster_schedule_discard(si, idx); return; } __free_cluster(si, idx); } /* * The cluster corresponding to page_nr will be used. The cluster will be * removed from free cluster list and its usage counter will be increased. */ static void inc_cluster_info_page(struct swap_info_struct *p, struct swap_cluster_info *cluster_info, unsigned long page_nr) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; if (!cluster_info) return; if (cluster_is_free(&cluster_info[idx])) alloc_cluster(p, idx); VM_BUG_ON(cluster_count(&cluster_info[idx]) >= SWAPFILE_CLUSTER); cluster_set_count(&cluster_info[idx], cluster_count(&cluster_info[idx]) + 1); } /* * The cluster corresponding to page_nr decreases one usage. If the usage * counter becomes 0, which means no page in the cluster is in using, we can * optionally discard the cluster and add it to free cluster list. */ static void dec_cluster_info_page(struct swap_info_struct *p, struct swap_cluster_info *cluster_info, unsigned long page_nr) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; if (!cluster_info) return; VM_BUG_ON(cluster_count(&cluster_info[idx]) == 0); cluster_set_count(&cluster_info[idx], cluster_count(&cluster_info[idx]) - 1); if (cluster_count(&cluster_info[idx]) == 0) free_cluster(p, idx); } /* * It's possible scan_swap_map_slots() uses a free cluster in the middle of free * cluster list. Avoiding such abuse to avoid list corruption. */ static bool scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si, unsigned long offset) { struct percpu_cluster *percpu_cluster; bool conflict; offset /= SWAPFILE_CLUSTER; conflict = !cluster_list_empty(&si->free_clusters) && offset != cluster_list_first(&si->free_clusters) && cluster_is_free(&si->cluster_info[offset]); if (!conflict) return false; percpu_cluster = this_cpu_ptr(si->percpu_cluster); cluster_set_null(&percpu_cluster->index); return true; } /* * Try to get a swap entry from current cpu's swap entry pool (a cluster). This * might involve allocating a new cluster for current CPU too. */ static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, unsigned long *offset, unsigned long *scan_base) { struct percpu_cluster *cluster; struct swap_cluster_info *ci; unsigned long tmp, max; new_cluster: cluster = this_cpu_ptr(si->percpu_cluster); if (cluster_is_null(&cluster->index)) { if (!cluster_list_empty(&si->free_clusters)) { cluster->index = si->free_clusters.head; cluster->next = cluster_next(&cluster->index) * SWAPFILE_CLUSTER; } else if (!cluster_list_empty(&si->discard_clusters)) { /* * we don't have free cluster but have some clusters in * discarding, do discard now and reclaim them, then * reread cluster_next_cpu since we dropped si->lock */ swap_do_scheduled_discard(si); *scan_base = this_cpu_read(*si->cluster_next_cpu); *offset = *scan_base; goto new_cluster; } else return false; } /* * Other CPUs can use our cluster if they can't find a free cluster, * check if there is still free entry in the cluster */ tmp = cluster->next; max = min_t(unsigned long, si->max, (cluster_next(&cluster->index) + 1) * SWAPFILE_CLUSTER); if (tmp < max) { ci = lock_cluster(si, tmp); while (tmp < max) { if (!si->swap_map[tmp]) break; tmp++; } unlock_cluster(ci); } if (tmp >= max) { cluster_set_null(&cluster->index); goto new_cluster; } cluster->next = tmp + 1; *offset = tmp; *scan_base = tmp; return true; } static void __del_from_avail_list(struct swap_info_struct *p) { int nid; assert_spin_locked(&p->lock); for_each_node(nid) plist_del(&p->avail_lists[nid], &swap_avail_heads[nid]); } static void del_from_avail_list(struct swap_info_struct *p) { spin_lock(&swap_avail_lock); __del_from_avail_list(p); spin_unlock(&swap_avail_lock); } static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned int end = offset + nr_entries - 1; if (offset == si->lowest_bit) si->lowest_bit += nr_entries; if (end == si->highest_bit) WRITE_ONCE(si->highest_bit, si->highest_bit - nr_entries); WRITE_ONCE(si->inuse_pages, si->inuse_pages + nr_entries); if (si->inuse_pages == si->pages) { si->lowest_bit = si->max; si->highest_bit = 0; del_from_avail_list(si); } } static void add_to_avail_list(struct swap_info_struct *p) { int nid; spin_lock(&swap_avail_lock); for_each_node(nid) { WARN_ON(!plist_node_empty(&p->avail_lists[nid])); plist_add(&p->avail_lists[nid], &swap_avail_heads[nid]); } spin_unlock(&swap_avail_lock); } static void swap_range_free(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned long begin = offset; unsigned long end = offset + nr_entries - 1; void (*swap_slot_free_notify)(struct block_device *, unsigned long); if (offset < si->lowest_bit) si->lowest_bit = offset; if (end > si->highest_bit) { bool was_full = !si->highest_bit; WRITE_ONCE(si->highest_bit, end); if (was_full && (si->flags & SWP_WRITEOK)) add_to_avail_list(si); } atomic_long_add(nr_entries, &nr_swap_pages); WRITE_ONCE(si->inuse_pages, si->inuse_pages - nr_entries); if (si->flags & SWP_BLKDEV) swap_slot_free_notify = si->bdev->bd_disk->fops->swap_slot_free_notify; else swap_slot_free_notify = NULL; while (offset <= end) { arch_swap_invalidate_page(si->type, offset); frontswap_invalidate_page(si->type, offset); if (swap_slot_free_notify) swap_slot_free_notify(si->bdev, offset); offset++; } clear_shadow_from_swap_cache(si->type, begin, end); } static void set_cluster_next(struct swap_info_struct *si, unsigned long next) { unsigned long prev; if (!(si->flags & SWP_SOLIDSTATE)) { si->cluster_next = next; return; } prev = this_cpu_read(*si->cluster_next_cpu); /* * Cross the swap address space size aligned trunk, choose * another trunk randomly to avoid lock contention on swap * address space if possible. */ if ((prev >> SWAP_ADDRESS_SPACE_SHIFT) != (next >> SWAP_ADDRESS_SPACE_SHIFT)) { /* No free swap slots available */ if (si->highest_bit <= si->lowest_bit) return; next = si->lowest_bit + prandom_u32_max(si->highest_bit - si->lowest_bit + 1); next = ALIGN_DOWN(next, SWAP_ADDRESS_SPACE_PAGES); next = max_t(unsigned int, next, si->lowest_bit); } this_cpu_write(*si->cluster_next_cpu, next); } static bool swap_offset_available_and_locked(struct swap_info_struct *si, unsigned long offset) { if (data_race(!si->swap_map[offset])) { spin_lock(&si->lock); return true; } if (vm_swap_full() && READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { spin_lock(&si->lock); return true; } return false; } static int scan_swap_map_slots(struct swap_info_struct *si, unsigned char usage, int nr, swp_entry_t slots[]) { struct swap_cluster_info *ci; unsigned long offset; unsigned long scan_base; unsigned long last_in_cluster = 0; int latency_ration = LATENCY_LIMIT; int n_ret = 0; bool scanned_many = false; /* * We try to cluster swap pages by allocating them sequentially * in swap. Once we've allocated SWAPFILE_CLUSTER pages this * way, however, we resort to first-free allocation, starting * a new cluster. This prevents us from scattering swap pages * all over the entire swap partition, so that we reduce * overall disk seek times between swap pages. -- sct * But we do now try to find an empty cluster. -Andrea * And we let swap pages go all over an SSD partition. Hugh */ si->flags += SWP_SCANNING; /* * Use percpu scan base for SSD to reduce lock contention on * cluster and swap cache. For HDD, sequential access is more * important. */ if (si->flags & SWP_SOLIDSTATE) scan_base = this_cpu_read(*si->cluster_next_cpu); else scan_base = si->cluster_next; offset = scan_base; /* SSD algorithm */ if (si->cluster_info) { if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) goto scan; } else if (unlikely(!si->cluster_nr--)) { if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) { si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } spin_unlock(&si->lock); /* * If seek is expensive, start searching for new cluster from * start of partition, to minimize the span of allocated swap. * If seek is cheap, that is the SWP_SOLIDSTATE si->cluster_info * case, just handled by scan_swap_map_try_ssd_cluster() above. */ scan_base = offset = si->lowest_bit; last_in_cluster = offset + SWAPFILE_CLUSTER - 1; /* Locate the first empty (unaligned) cluster */ for (; last_in_cluster <= si->highest_bit; offset++) { if (si->swap_map[offset]) last_in_cluster = offset + SWAPFILE_CLUSTER; else if (offset == last_in_cluster) { spin_lock(&si->lock); offset -= SWAPFILE_CLUSTER - 1; si->cluster_next = offset; si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; } } offset = scan_base; spin_lock(&si->lock); si->cluster_nr = SWAPFILE_CLUSTER - 1; } checks: if (si->cluster_info) { while (scan_swap_map_ssd_cluster_conflict(si, offset)) { /* take a break if we already got some slots */ if (n_ret) goto done; if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) goto scan; } } if (!(si->flags & SWP_WRITEOK)) goto no_page; if (!si->highest_bit) goto no_page; if (offset > si->highest_bit) scan_base = offset = si->lowest_bit; ci = lock_cluster(si, offset); /* reuse swap entry of cache-only swap if not busy. */ if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { int swap_was_freed; unlock_cluster(ci); spin_unlock(&si->lock); swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY); spin_lock(&si->lock); /* entry was freed successfully, try to use this again */ if (swap_was_freed) goto checks; goto scan; /* check next one */ } if (si->swap_map[offset]) { unlock_cluster(ci); if (!n_ret) goto scan; else goto done; } WRITE_ONCE(si->swap_map[offset], usage); inc_cluster_info_page(si, si->cluster_info, offset); unlock_cluster(ci); swap_range_alloc(si, offset, 1); slots[n_ret++] = swp_entry(si->type, offset); /* got enough slots or reach max slots? */ if ((n_ret == nr) || (offset >= si->highest_bit)) goto done; /* search for next available slot */ /* time to take a break? */ if (unlikely(--latency_ration < 0)) { if (n_ret) goto done; spin_unlock(&si->lock); cond_resched(); spin_lock(&si->lock); latency_ration = LATENCY_LIMIT; } /* try to get more slots in cluster */ if (si->cluster_info) { if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) goto checks; } else if (si->cluster_nr && !si->swap_map[++offset]) { /* non-ssd case, still more slots in cluster? */ --si->cluster_nr; goto checks; } /* * Even if there's no free clusters available (fragmented), * try to scan a little more quickly with lock held unless we * have scanned too many slots already. */ if (!scanned_many) { unsigned long scan_limit; if (offset < scan_base) scan_limit = scan_base; else scan_limit = si->highest_bit; for (; offset <= scan_limit && --latency_ration > 0; offset++) { if (!si->swap_map[offset]) goto checks; } } done: set_cluster_next(si, offset + 1); si->flags -= SWP_SCANNING; return n_ret; scan: spin_unlock(&si->lock); while (++offset <= READ_ONCE(si->highest_bit)) { if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; scanned_many = true; } if (swap_offset_available_and_locked(si, offset)) goto checks; } offset = si->lowest_bit; while (offset < scan_base) { if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; scanned_many = true; } if (swap_offset_available_and_locked(si, offset)) goto checks; offset++; } spin_lock(&si->lock); no_page: si->flags -= SWP_SCANNING; return n_ret; } static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot) { unsigned long idx; struct swap_cluster_info *ci; unsigned long offset; /* * Should not even be attempting cluster allocations when huge * page swap is disabled. Warn and fail the allocation. */ if (!IS_ENABLED(CONFIG_THP_SWAP)) { VM_WARN_ON_ONCE(1); return 0; } if (cluster_list_empty(&si->free_clusters)) return 0; idx = cluster_list_first(&si->free_clusters); offset = idx * SWAPFILE_CLUSTER; ci = lock_cluster(si, offset); alloc_cluster(si, idx); cluster_set_count_flag(ci, SWAPFILE_CLUSTER, CLUSTER_FLAG_HUGE); memset(si->swap_map + offset, SWAP_HAS_CACHE, SWAPFILE_CLUSTER); unlock_cluster(ci); swap_range_alloc(si, offset, SWAPFILE_CLUSTER); *slot = swp_entry(si->type, offset); return 1; } static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx) { unsigned long offset = idx * SWAPFILE_CLUSTER; struct swap_cluster_info *ci; ci = lock_cluster(si, offset); memset(si->swap_map + offset, 0, SWAPFILE_CLUSTER); cluster_set_count_flag(ci, 0, 0); free_cluster(si, idx); unlock_cluster(ci); swap_range_free(si, offset, SWAPFILE_CLUSTER); } int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size) { unsigned long size = swap_entry_size(entry_size); struct swap_info_struct *si, *next; long avail_pgs; int n_ret = 0; int node; /* Only single cluster request supported */ WARN_ON_ONCE(n_goal > 1 && size == SWAPFILE_CLUSTER); spin_lock(&swap_avail_lock); avail_pgs = atomic_long_read(&nr_swap_pages) / size; if (avail_pgs <= 0) { spin_unlock(&swap_avail_lock); goto noswap; } n_goal = min3((long)n_goal, (long)SWAP_BATCH, avail_pgs); atomic_long_sub(n_goal * size, &nr_swap_pages); start_over: node = numa_node_id(); plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) { /* requeue si to after same-priority siblings */ plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]); spin_unlock(&swap_avail_lock); spin_lock(&si->lock); if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) { spin_lock(&swap_avail_lock); if (plist_node_empty(&si->avail_lists[node])) { spin_unlock(&si->lock); goto nextsi; } WARN(!si->highest_bit, "swap_info %d in list but !highest_bit\n", si->type); WARN(!(si->flags & SWP_WRITEOK), "swap_info %d in list but !SWP_WRITEOK\n", si->type); __del_from_avail_list(si); spin_unlock(&si->lock); goto nextsi; } if (size == SWAPFILE_CLUSTER) { if (si->flags & SWP_BLKDEV) n_ret = swap_alloc_cluster(si, swp_entries); } else n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, n_goal, swp_entries); spin_unlock(&si->lock); if (n_ret || size == SWAPFILE_CLUSTER) goto check_out; pr_debug("scan_swap_map of si %d failed to find offset\n", si->type); cond_resched(); spin_lock(&swap_avail_lock); nextsi: /* * if we got here, it's likely that si was almost full before, * and since scan_swap_map_slots() can drop the si->lock, * multiple callers probably all tried to get a page from the * same si and it filled up before we could get one; or, the si * filled up between us dropping swap_avail_lock and taking * si->lock. Since we dropped the swap_avail_lock, the * swap_avail_head list may have been modified; so if next is * still in the swap_avail_head list then try it, otherwise * start over if we have not gotten any slots. */ if (plist_node_empty(&next->avail_lists[node])) goto start_over; } spin_unlock(&swap_avail_lock); check_out: if (n_ret < n_goal) atomic_long_add((long)(n_goal - n_ret) * size, &nr_swap_pages); noswap: return n_ret; } static struct swap_info_struct *_swap_info_get(swp_entry_t entry) { struct swap_info_struct *p; unsigned long offset; if (!entry.val) goto out; p = swp_swap_info(entry); if (!p) goto bad_nofile; if (data_race(!(p->flags & SWP_USED))) goto bad_device; offset = swp_offset(entry); if (offset >= p->max) goto bad_offset; if (data_race(!p->swap_map[swp_offset(entry)])) goto bad_free; return p; bad_free: pr_err("%s: %s%08lx\n", __func__, Unused_offset, entry.val); goto out; bad_offset: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); goto out; bad_device: pr_err("%s: %s%08lx\n", __func__, Unused_file, entry.val); goto out; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; } static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry, struct swap_info_struct *q) { struct swap_info_struct *p; p = _swap_info_get(entry); if (p != q) { if (q != NULL) spin_unlock(&q->lock); if (p != NULL) spin_lock(&p->lock); } return p; } static unsigned char __swap_entry_free_locked(struct swap_info_struct *p, unsigned long offset, unsigned char usage) { unsigned char count; unsigned char has_cache; count = p->swap_map[offset]; has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (usage == SWAP_HAS_CACHE) { VM_BUG_ON(!has_cache); has_cache = 0; } else if (count == SWAP_MAP_SHMEM) { /* * Or we could insist on shmem.c using a special * swap_shmem_free() and free_shmem_swap_and_cache()... */ count = 0; } else if ((count & ~COUNT_CONTINUED) <= SWAP_MAP_MAX) { if (count == COUNT_CONTINUED) { if (swap_count_continued(p, offset, count)) count = SWAP_MAP_MAX | COUNT_CONTINUED; else count = SWAP_MAP_MAX; } else count--; } usage = count | has_cache; if (usage) WRITE_ONCE(p->swap_map[offset], usage); else WRITE_ONCE(p->swap_map[offset], SWAP_HAS_CACHE); return usage; } /* * When we get a swap entry, if there aren't some other ways to * prevent swapoff, such as the folio in swap cache is locked, page * table lock is held, etc., the swap entry may become invalid because * of swapoff. Then, we need to enclose all swap related functions * with get_swap_device() and put_swap_device(), unless the swap * functions call get/put_swap_device() by themselves. * * Note that when only holding the PTL, swapoff might succeed immediately * after freeing a swap entry. Therefore, immediately after * __swap_entry_free(), the swap info might become stale and should not * be touched without a prior get_swap_device(). * * Check whether swap entry is valid in the swap device. If so, * return pointer to swap_info_struct, and keep the swap entry valid * via preventing the swap device from being swapoff, until * put_swap_device() is called. Otherwise return NULL. * * Notice that swapoff or swapoff+swapon can still happen before the * percpu_ref_tryget_live() in get_swap_device() or after the * percpu_ref_put() in put_swap_device() if there isn't any other way * to prevent swapoff. The caller must be prepared for that. For * example, the following situation is possible. * * CPU1 CPU2 * do_swap_page() * ... swapoff+swapon * __read_swap_cache_async() * swapcache_prepare() * __swap_duplicate() * // check swap_map * // verify PTE not changed * * In __swap_duplicate(), the swap_map need to be checked before * changing partly because the specified swap entry may be for another * swap device which has been swapoff. And in do_swap_page(), after * the page is read from the swap device, the PTE is verified not * changed with the page table locked to check whether the swap device * has been swapoff or swapoff+swapon. */ struct swap_info_struct *get_swap_device(swp_entry_t entry) { struct swap_info_struct *si; unsigned long offset; if (!entry.val) goto out; si = swp_swap_info(entry); if (!si) goto bad_nofile; if (!percpu_ref_tryget_live(&si->users)) goto out; /* * Guarantee the si->users are checked before accessing other * fields of swap_info_struct. * * Paired with the spin_unlock() after setup_swap_info() in * enable_swap_info(). */ smp_rmb(); offset = swp_offset(entry); if (offset >= si->max) goto put_out; return si; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; put_out: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); percpu_ref_put(&si->users); return NULL; } static unsigned char __swap_entry_free(struct swap_info_struct *p, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); unsigned char usage; ci = lock_cluster_or_swap_info(p, offset); usage = __swap_entry_free_locked(p, offset, 1); unlock_cluster_or_swap_info(p, ci); if (!usage) free_swap_slot(entry); return usage; } static void swap_entry_free(struct swap_info_struct *p, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); unsigned char count; ci = lock_cluster(p, offset); count = p->swap_map[offset]; VM_BUG_ON(count != SWAP_HAS_CACHE); p->swap_map[offset] = 0; dec_cluster_info_page(p, p->cluster_info, offset); unlock_cluster(ci); mem_cgroup_uncharge_swap(entry, 1); swap_range_free(p, offset, 1); } /* * Caller has made sure that the swap device corresponding to entry * is still around or has not been recycled. */ void swap_free(swp_entry_t entry) { struct swap_info_struct *p; p = _swap_info_get(entry); if (p) __swap_entry_free(p, entry); } /* * Called after dropping swapcache to decrease refcnt to swap entries. */ void put_swap_folio(struct folio *folio, swp_entry_t entry) { unsigned long offset = swp_offset(entry); unsigned long idx = offset / SWAPFILE_CLUSTER; struct swap_cluster_info *ci; struct swap_info_struct *si; unsigned char *map; unsigned int i, free_entries = 0; unsigned char val; int size = swap_entry_size(folio_nr_pages(folio)); si = _swap_info_get(entry); if (!si) return; ci = lock_cluster_or_swap_info(si, offset); if (size == SWAPFILE_CLUSTER) { VM_BUG_ON(!cluster_is_huge(ci)); map = si->swap_map + offset; for (i = 0; i < SWAPFILE_CLUSTER; i++) { val = map[i]; VM_BUG_ON(!(val & SWAP_HAS_CACHE)); if (val == SWAP_HAS_CACHE) free_entries++; } cluster_clear_huge(ci); if (free_entries == SWAPFILE_CLUSTER) { unlock_cluster_or_swap_info(si, ci); spin_lock(&si->lock); mem_cgroup_uncharge_swap(entry, SWAPFILE_CLUSTER); swap_free_cluster(si, idx); spin_unlock(&si->lock); return; } } for (i = 0; i < size; i++, entry.val++) { if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE)) { unlock_cluster_or_swap_info(si, ci); free_swap_slot(entry); if (i == size - 1) return; lock_cluster_or_swap_info(si, offset); } } unlock_cluster_or_swap_info(si, ci); } #ifdef CONFIG_THP_SWAP int split_swap_cluster(swp_entry_t entry) { struct swap_info_struct *si; struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); si = _swap_info_get(entry); if (!si) return -EBUSY; ci = lock_cluster(si, offset); cluster_clear_huge(ci); unlock_cluster(ci); return 0; } #endif static int swp_entry_cmp(const void *ent1, const void *ent2) { const swp_entry_t *e1 = ent1, *e2 = ent2; return (int)swp_type(*e1) - (int)swp_type(*e2); } void swapcache_free_entries(swp_entry_t *entries, int n) { struct swap_info_struct *p, *prev; int i; if (n <= 0) return; prev = NULL; p = NULL; /* * Sort swap entries by swap device, so each lock is only taken once. * nr_swapfiles isn't absolutely correct, but the overhead of sort() is * so low that it isn't necessary to optimize further. */ if (nr_swapfiles > 1) sort(entries, n, sizeof(entries[0]), swp_entry_cmp, NULL); for (i = 0; i < n; ++i) { p = swap_info_get_cont(entries[i], prev); if (p) swap_entry_free(p, entries[i]); prev = p; } if (p) spin_unlock(&p->lock); } int __swap_count(swp_entry_t entry) { struct swap_info_struct *si; pgoff_t offset = swp_offset(entry); int count = 0; si = get_swap_device(entry); if (si) { count = swap_count(si->swap_map[offset]); put_swap_device(si); } return count; } /* * How many references to @entry are currently swapped out? * This does not give an exact answer when swap count is continued, * but does include the high COUNT_CONTINUED flag to allow for that. */ static int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) { pgoff_t offset = swp_offset(entry); struct swap_cluster_info *ci; int count; ci = lock_cluster_or_swap_info(si, offset); count = swap_count(si->swap_map[offset]); unlock_cluster_or_swap_info(si, ci); return count; } /* * How many references to @entry are currently swapped out? * This does not give an exact answer when swap count is continued, * but does include the high COUNT_CONTINUED flag to allow for that. */ int __swp_swapcount(swp_entry_t entry) { int count = 0; struct swap_info_struct *si; si = get_swap_device(entry); if (si) { count = swap_swapcount(si, entry); put_swap_device(si); } return count; } /* * How many references to @entry are currently swapped out? * This considers COUNT_CONTINUED so it returns exact answer. */ int swp_swapcount(swp_entry_t entry) { int count, tmp_count, n; struct swap_info_struct *p; struct swap_cluster_info *ci; struct page *page; pgoff_t offset; unsigned char *map; p = _swap_info_get(entry); if (!p) return 0; offset = swp_offset(entry); ci = lock_cluster_or_swap_info(p, offset); count = swap_count(p->swap_map[offset]); if (!(count & COUNT_CONTINUED)) goto out; count &= ~COUNT_CONTINUED; n = SWAP_MAP_MAX + 1; page = vmalloc_to_page(p->swap_map + offset); offset &= ~PAGE_MASK; VM_BUG_ON(page_private(page) != SWP_CONTINUED); do { page = list_next_entry(page, lru); map = kmap_atomic(page); tmp_count = map[offset]; kunmap_atomic(map); count += (tmp_count & ~COUNT_CONTINUED) * n; n *= (SWAP_CONT_MAX + 1); } while (tmp_count & COUNT_CONTINUED); out: unlock_cluster_or_swap_info(p, ci); return count; } static bool swap_page_trans_huge_swapped(struct swap_info_struct *si, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned char *map = si->swap_map; unsigned long roffset = swp_offset(entry); unsigned long offset = round_down(roffset, SWAPFILE_CLUSTER); int i; bool ret = false; ci = lock_cluster_or_swap_info(si, offset); if (!ci || !cluster_is_huge(ci)) { if (swap_count(map[roffset])) ret = true; goto unlock_out; } for (i = 0; i < SWAPFILE_CLUSTER; i++) { if (swap_count(map[offset + i])) { ret = true; break; } } unlock_out: unlock_cluster_or_swap_info(si, ci); return ret; } static bool folio_swapped(struct folio *folio) { swp_entry_t entry = folio_swap_entry(folio); struct swap_info_struct *si = _swap_info_get(entry); if (!si) return false; if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!folio_test_large(folio))) return swap_swapcount(si, entry) != 0; return swap_page_trans_huge_swapped(si, entry); } /** * folio_free_swap() - Free the swap space used for this folio. * @folio: The folio to remove. * * If swap is getting full, or if there are no more mappings of this folio, * then call folio_free_swap to free its swap space. * * Return: true if we were able to release the swap space. */ bool folio_free_swap(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (!folio_test_swapcache(folio)) return false; if (folio_test_writeback(folio)) return false; if (folio_swapped(folio)) return false; /* * Once hibernation has begun to create its image of memory, * there's a danger that one of the calls to folio_free_swap() * - most probably a call from __try_to_reclaim_swap() while * hibernation is allocating its own swap pages for the image, * but conceivably even a call from memory reclaim - will free * the swap from a folio which has already been recorded in the * image as a clean swapcache folio, and then reuse its swap for * another page of the image. On waking from hibernation, the * original folio might be freed under memory pressure, then * later read back in from swap, now with the wrong data. * * Hibernation suspends storage while it is writing the image * to disk so check that here. */ if (pm_suspended_storage()) return false; delete_from_swap_cache(folio); folio_set_dirty(folio); return true; } /* * Free the swap entry like above, but also try to * free the page cache entry if it is the last user. */ int free_swap_and_cache(swp_entry_t entry) { struct swap_info_struct *p; unsigned char count; if (non_swap_entry(entry)) return 1; p = get_swap_device(entry); if (p) { if (WARN_ON(data_race(!p->swap_map[swp_offset(entry)]))) { put_swap_device(p); return 0; } count = __swap_entry_free(p, entry); if (count == SWAP_HAS_CACHE && !swap_page_trans_huge_swapped(p, entry)) __try_to_reclaim_swap(p, swp_offset(entry), TTRS_UNMAPPED | TTRS_FULL); put_swap_device(p); } return p != NULL; } #ifdef CONFIG_HIBERNATION swp_entry_t get_swap_page_of_type(int type) { struct swap_info_struct *si = swap_type_to_swap_info(type); swp_entry_t entry = {0}; if (!si) goto fail; /* This is called for allocating swap entry, not cache */ spin_lock(&si->lock); if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry)) atomic_long_dec(&nr_swap_pages); spin_unlock(&si->lock); fail: return entry; } /* * Find the swap type that corresponds to given device (if any). * * @offset - number of the PAGE_SIZE-sized block of the device, starting * from 0, in which the swap header is expected to be located. * * This is needed for the suspend to disk (aka swsusp). */ int swap_type_of(dev_t device, sector_t offset) { int type; if (!device) return -1; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; if (device == sis->bdev->bd_dev) { struct swap_extent *se = first_se(sis); if (se->start_block == offset) { spin_unlock(&swap_lock); return type; } } } spin_unlock(&swap_lock); return -ENODEV; } int find_first_swap(dev_t *device) { int type; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; *device = sis->bdev->bd_dev; spin_unlock(&swap_lock); return type; } spin_unlock(&swap_lock); return -ENODEV; } /* * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev * corresponding to given index in swap_info (swap type). */ sector_t swapdev_block(int type, pgoff_t offset) { struct swap_info_struct *si = swap_type_to_swap_info(type); struct swap_extent *se; if (!si || !(si->flags & SWP_WRITEOK)) return 0; se = offset_to_swap_extent(si, offset); return se->start_block + (offset - se->start_page); } /* * Return either the total number of swap pages of given type, or the number * of free pages of that type (depending on @free) * * This is needed for software suspend */ unsigned int count_swap_pages(int type, int free) { unsigned int n = 0; spin_lock(&swap_lock); if ((unsigned int)type < nr_swapfiles) { struct swap_info_struct *sis = swap_info[type]; spin_lock(&sis->lock); if (sis->flags & SWP_WRITEOK) { n = sis->pages; if (free) n -= sis->inuse_pages; } spin_unlock(&sis->lock); } spin_unlock(&swap_lock); return n; } #endif /* CONFIG_HIBERNATION */ static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) { return pte_same(pte_swp_clear_flags(pte), swp_pte); } /* * No need to decide whether this PTE shares the swap entry with others, * just let do_wp_page work it out if a write is requested later - to * force COW, vm_page_prot omits write permission from any private vma. */ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, swp_entry_t entry, struct folio *folio) { struct page *page = folio_file_page(folio, swp_offset(entry)); struct page *swapcache; spinlock_t *ptl; pte_t *pte, new_pte; int ret = 1; swapcache = page; page = ksm_might_need_to_copy(page, vma, addr); if (unlikely(!page)) return -ENOMEM; pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) { ret = 0; goto out; } if (unlikely(!PageUptodate(page))) { pte_t pteval; dec_mm_counter(vma->vm_mm, MM_SWAPENTS); pteval = swp_entry_to_pte(make_swapin_error_entry(page)); set_pte_at(vma->vm_mm, addr, pte, pteval); swap_free(entry); ret = 0; goto out; } /* * Some architectures may have to restore extra metadata to the page * when reading from swap. This metadata may be indexed by swap entry * so this must be called before swap_free(). */ arch_swap_restore(entry, page_folio(page)); /* See do_swap_page() */ BUG_ON(!PageAnon(page) && PageMappedToDisk(page)); BUG_ON(PageAnon(page) && PageAnonExclusive(page)); dec_mm_counter(vma->vm_mm, MM_SWAPENTS); inc_mm_counter(vma->vm_mm, MM_ANONPAGES); get_page(page); if (page == swapcache) { rmap_t rmap_flags = RMAP_NONE; /* * See do_swap_page(): PageWriteback() would be problematic. * However, we do a wait_on_page_writeback() just before this * call and have the page locked. */ VM_BUG_ON_PAGE(PageWriteback(page), page); if (pte_swp_exclusive(*pte)) rmap_flags |= RMAP_EXCLUSIVE; page_add_anon_rmap(page, vma, addr, rmap_flags); } else { /* ksm created a completely new copy */ page_add_new_anon_rmap(page, vma, addr); lru_cache_add_inactive_or_unevictable(page, vma); } new_pte = pte_mkold(mk_pte(page, vma->vm_page_prot)); if (pte_swp_soft_dirty(*pte)) new_pte = pte_mksoft_dirty(new_pte); if (pte_swp_uffd_wp(*pte)) new_pte = pte_mkuffd_wp(new_pte); set_pte_at(vma->vm_mm, addr, pte, new_pte); swap_free(entry); out: pte_unmap_unlock(pte, ptl); if (page != swapcache) { unlock_page(page); put_page(page); } return ret; } int unuse_swap_pte(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, swp_entry_t entry, struct folio *folio) { return unuse_pte(vma, pmd, addr, entry, folio); } EXPORT_SYMBOL_GPL(unuse_swap_pte); static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned int type) { swp_entry_t entry; pte_t *pte; struct swap_info_struct *si; int ret = 0; volatile unsigned char *swap_map; si = swap_info[type]; pte = pte_offset_map(pmd, addr); do { struct folio *folio; unsigned long offset; if (!is_swap_pte(*pte)) continue; entry = pte_to_swp_entry(*pte); if (swp_type(entry) != type) continue; offset = swp_offset(entry); pte_unmap(pte); swap_map = &si->swap_map[offset]; folio = swap_cache_get_folio(entry, vma, addr); if (!folio) { struct page *page; struct vm_fault vmf = { .vma = vma, .address = addr, .real_address = addr, .pmd = pmd, }; page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, &vmf); if (page) folio = page_folio(page); } if (!folio) { if (*swap_map == 0 || *swap_map == SWAP_MAP_BAD) goto try_next; return -ENOMEM; } folio_lock(folio); folio_wait_writeback(folio); ret = unuse_pte(vma, pmd, addr, entry, folio); if (ret < 0) { folio_unlock(folio); folio_put(folio); goto out; } folio_free_swap(folio); folio_unlock(folio); folio_put(folio); try_next: pte = pte_offset_map(pmd, addr); } while (pte++, addr += PAGE_SIZE, addr != end); pte_unmap(pte - 1); ret = 0; out: return ret; } static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, unsigned int type) { pmd_t *pmd; unsigned long next; int ret; pmd = pmd_offset(pud, addr); do { cond_resched(); next = pmd_addr_end(addr, end); if (pmd_none_or_trans_huge_or_clear_bad(pmd)) continue; ret = unuse_pte_range(vma, pmd, addr, next, type); if (ret) return ret; } while (pmd++, addr = next, addr != end); return 0; } static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned int type) { pud_t *pud; unsigned long next; int ret; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; ret = unuse_pmd_range(vma, pud, addr, next, type); if (ret) return ret; } while (pud++, addr = next, addr != end); return 0; } static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned int type) { p4d_t *p4d; unsigned long next; int ret; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; ret = unuse_pud_range(vma, p4d, addr, next, type); if (ret) return ret; } while (p4d++, addr = next, addr != end); return 0; } static int unuse_vma(struct vm_area_struct *vma, unsigned int type) { pgd_t *pgd; unsigned long addr, end, next; int ret; addr = vma->vm_start; end = vma->vm_end; pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; ret = unuse_p4d_range(vma, pgd, addr, next, type); if (ret) return ret; } while (pgd++, addr = next, addr != end); return 0; } static int unuse_mm(struct mm_struct *mm, unsigned int type) { struct vm_area_struct *vma; int ret = 0; VMA_ITERATOR(vmi, mm, 0); mmap_read_lock(mm); for_each_vma(vmi, vma) { if (vma->anon_vma && !is_vm_hugetlb_page(vma)) { ret = unuse_vma(vma, type); if (ret) break; } cond_resched(); } mmap_read_unlock(mm); return ret; } /* * Scan swap_map from current position to next entry still in use. * Return 0 if there are no inuse entries after prev till end of * the map. */ static unsigned int find_next_to_unuse(struct swap_info_struct *si, unsigned int prev) { unsigned int i; unsigned char count; /* * No need for swap_lock here: we're just looking * for whether an entry is in use, not modifying it; false * hits are okay, and sys_swapoff() has already prevented new * allocations from this area (while holding swap_lock). */ for (i = prev + 1; i < si->max; i++) { count = READ_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) break; if ((i % LATENCY_LIMIT) == 0) cond_resched(); } if (i == si->max) i = 0; return i; } static int try_to_unuse(unsigned int type) { struct mm_struct *prev_mm; struct mm_struct *mm; struct list_head *p; int retval = 0; struct swap_info_struct *si = swap_info[type]; struct folio *folio; swp_entry_t entry; unsigned int i; if (!READ_ONCE(si->inuse_pages)) return 0; retry: retval = shmem_unuse(type); if (retval) return retval; prev_mm = &init_mm; mmget(prev_mm); spin_lock(&mmlist_lock); p = &init_mm.mmlist; while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (p = p->next) != &init_mm.mmlist) { mm = list_entry(p, struct mm_struct, mmlist); if (!mmget_not_zero(mm)) continue; spin_unlock(&mmlist_lock); mmput(prev_mm); prev_mm = mm; retval = unuse_mm(mm, type); if (retval) { mmput(prev_mm); return retval; } /* * Make sure that we aren't completely killing * interactive performance. */ cond_resched(); spin_lock(&mmlist_lock); } spin_unlock(&mmlist_lock); mmput(prev_mm); i = 0; while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (i = find_next_to_unuse(si, i)) != 0) { entry = swp_entry(type, i); folio = filemap_get_folio(swap_address_space(entry), i); if (!folio) continue; /* * It is conceivable that a racing task removed this folio from * swap cache just before we acquired the page lock. The folio * might even be back in swap cache on another swap area. But * that is okay, folio_free_swap() only removes stale folios. */ folio_lock(folio); folio_wait_writeback(folio); folio_free_swap(folio); folio_unlock(folio); folio_put(folio); } /* * Lets check again to see if there are still swap entries in the map. * If yes, we would need to do retry the unuse logic again. * Under global memory pressure, swap entries can be reinserted back * into process space after the mmlist loop above passes over them. * * Limit the number of retries? No: when mmget_not_zero() * above fails, that mm is likely to be freeing swap from * exit_mmap(), which proceeds at its own independent pace; * and even shmem_writepage() could have been preempted after * folio_alloc_swap(), temporarily hiding that swap. It's easy * and robust (though cpu-intensive) just to keep retrying. */ if (READ_ONCE(si->inuse_pages)) { if (!signal_pending(current)) goto retry; return -EINTR; } return 0; } /* * After a successful try_to_unuse, if no swap is now in use, we know * we can empty the mmlist. swap_lock must be held on entry and exit. * Note that mmlist_lock nests inside swap_lock, and an mm must be * added to the mmlist just after page_duplicate - before would be racy. */ static void drain_mmlist(void) { struct list_head *p, *next; unsigned int type; for (type = 0; type < nr_swapfiles; type++) if (swap_info[type]->inuse_pages) return; spin_lock(&mmlist_lock); list_for_each_safe(p, next, &init_mm.mmlist) list_del_init(p); spin_unlock(&mmlist_lock); } /* * Free all of a swapdev's extent information */ static void destroy_swap_extents(struct swap_info_struct *sis) { while (!RB_EMPTY_ROOT(&sis->swap_extent_root)) { struct rb_node *rb = sis->swap_extent_root.rb_node; struct swap_extent *se = rb_entry(rb, struct swap_extent, rb_node); rb_erase(rb, &sis->swap_extent_root); kfree(se); } if (sis->flags & SWP_ACTIVATED) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; sis->flags &= ~SWP_ACTIVATED; if (mapping->a_ops->swap_deactivate) mapping->a_ops->swap_deactivate(swap_file); } } /* * Add a block range (and the corresponding page range) into this swapdev's * extent tree. * * This function rather assumes that it is called in ascending page order. */ int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { struct rb_node **link = &sis->swap_extent_root.rb_node, *parent = NULL; struct swap_extent *se; struct swap_extent *new_se; /* * place the new node at the right most since the * function is called in ascending page order. */ while (*link) { parent = *link; link = &parent->rb_right; } if (parent) { se = rb_entry(parent, struct swap_extent, rb_node); BUG_ON(se->start_page + se->nr_pages != start_page); if (se->start_block + se->nr_pages == start_block) { /* Merge it */ se->nr_pages += nr_pages; return 0; } } /* No merge, insert a new extent. */ new_se = kmalloc(sizeof(*se), GFP_KERNEL); if (new_se == NULL) return -ENOMEM; new_se->start_page = start_page; new_se->nr_pages = nr_pages; new_se->start_block = start_block; rb_link_node(&new_se->rb_node, parent, link); rb_insert_color(&new_se->rb_node, &sis->swap_extent_root); return 1; } EXPORT_SYMBOL_GPL(add_swap_extent); /* * A `swap extent' is a simple thing which maps a contiguous range of pages * onto a contiguous range of disk blocks. A rbtree of swap extents is * built at swapon time and is then used at swap_writepage/swap_readpage * time for locating where on disk a page belongs. * * If the swapfile is an S_ISBLK block device, a single extent is installed. * This is done so that the main operating code can treat S_ISBLK and S_ISREG * swap files identically. * * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap * extent rbtree operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK * swapfiles are handled *identically* after swapon time. * * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks * and will parse them into a rbtree, in PAGE_SIZE chunks. If some stray * blocks are found which do not fall within the PAGE_SIZE alignment * requirements, they are simply tossed out - we will never use those blocks * for swapping. * * For all swap devices we set S_SWAPFILE across the life of the swapon. This * prevents users from writing to the swap device, which will corrupt memory. * * The amount of disk space which a single swap extent represents varies. * Typically it is in the 1-4 megabyte range. So we can have hundreds of * extents in the rbtree. - akpm. */ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; struct inode *inode = mapping->host; int ret; if (S_ISBLK(inode->i_mode)) { ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; return ret; } if (mapping->a_ops->swap_activate) { ret = mapping->a_ops->swap_activate(sis, swap_file, span); if (ret < 0) return ret; sis->flags |= SWP_ACTIVATED; if ((sis->flags & SWP_FS_OPS) && sio_pool_init() != 0) { destroy_swap_extents(sis); return -ENOMEM; } return ret; } return generic_swapfile_activate(sis, swap_file, span); } static int swap_node(struct swap_info_struct *p) { struct block_device *bdev; if (p->bdev) bdev = p->bdev; else bdev = p->swap_file->f_inode->i_sb->s_bdev; return bdev ? bdev->bd_disk->node_id : NUMA_NO_NODE; } static void setup_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info) { int i; if (prio >= 0) p->prio = prio; else p->prio = --least_priority; /* * the plist prio is negated because plist ordering is * low-to-high, while swap ordering is high-to-low */ p->list.prio = -p->prio; for_each_node(i) { if (p->prio >= 0) p->avail_lists[i].prio = -p->prio; else { if (swap_node(p) == i) p->avail_lists[i].prio = 1; else p->avail_lists[i].prio = -p->prio; } } p->swap_map = swap_map; p->cluster_info = cluster_info; } static void _enable_swap_info(struct swap_info_struct *p) { p->flags |= SWP_WRITEOK; atomic_long_add(p->pages, &nr_swap_pages); total_swap_pages += p->pages; assert_spin_locked(&swap_lock); /* * both lists are plists, and thus priority ordered. * swap_active_head needs to be priority ordered for swapoff(), * which on removal of any swap_info_struct with an auto-assigned * (i.e. negative) priority increments the auto-assigned priority * of any lower-priority swap_info_structs. * swap_avail_head needs to be priority ordered for folio_alloc_swap(), * which allocates swap pages from the highest available priority * swap_info_struct. */ plist_add(&p->list, &swap_active_head); add_to_avail_list(p); } static void enable_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long *frontswap_map) { if (IS_ENABLED(CONFIG_FRONTSWAP)) frontswap_init(p->type, frontswap_map); spin_lock(&swap_lock); spin_lock(&p->lock); setup_swap_info(p, prio, swap_map, cluster_info); spin_unlock(&p->lock); spin_unlock(&swap_lock); /* * Finished initializing swap device, now it's safe to reference it. */ percpu_ref_resurrect(&p->users); spin_lock(&swap_lock); spin_lock(&p->lock); _enable_swap_info(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); } static void reinsert_swap_info(struct swap_info_struct *p) { spin_lock(&swap_lock); spin_lock(&p->lock); setup_swap_info(p, p->prio, p->swap_map, p->cluster_info); _enable_swap_info(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); } bool has_usable_swap(void) { bool ret = true; spin_lock(&swap_lock); if (plist_head_empty(&swap_active_head)) ret = false; spin_unlock(&swap_lock); return ret; } SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; unsigned char *swap_map; struct swap_cluster_info *cluster_info; unsigned long *frontswap_map; struct file *swap_file, *victim; struct address_space *mapping; struct inode *inode; struct filename *pathname; int err, found = 0; unsigned int old_block_size; bool hibernation_swap = false; if (!capable(CAP_SYS_ADMIN)) return -EPERM; BUG_ON(!current->mm); pathname = getname(specialfile); if (IS_ERR(pathname)) return PTR_ERR(pathname); victim = file_open_name(pathname, O_RDWR|O_LARGEFILE, 0); err = PTR_ERR(victim); if (IS_ERR(victim)) goto out; mapping = victim->f_mapping; spin_lock(&swap_lock); plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { if (p->swap_file->f_mapping == mapping) { found = 1; break; } } } if (!found) { err = -EINVAL; spin_unlock(&swap_lock); goto out_dput; } if (!security_vm_enough_memory_mm(current->mm, p->pages)) vm_unacct_memory(p->pages); else { err = -ENOMEM; spin_unlock(&swap_lock); goto out_dput; } spin_lock(&p->lock); del_from_avail_list(p); if (p->prio < 0) { struct swap_info_struct *si = p; int nid; plist_for_each_entry_continue(si, &swap_active_head, list) { si->prio++; si->list.prio--; for_each_node(nid) { if (si->avail_lists[nid].prio != 1) si->avail_lists[nid].prio--; } } least_priority++; } plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; p->flags &= ~SWP_WRITEOK; spin_unlock(&p->lock); spin_unlock(&swap_lock); disable_swap_slots_cache_lock(); set_current_oom_origin(); err = try_to_unuse(p->type); clear_current_oom_origin(); if (err) { /* re-insert swap space back into swap_list */ reinsert_swap_info(p); reenable_swap_slots_cache_unlock(); goto out_dput; } reenable_swap_slots_cache_unlock(); /* * Wait for swap operations protected by get/put_swap_device() * to complete. * * We need synchronize_rcu() here to protect the accessing to * the swap cache data structure. */ percpu_ref_kill(&p->users); synchronize_rcu(); wait_for_completion(&p->comp); flush_work(&p->discard_work); destroy_swap_extents(p); trace_android_vh_check_hibernation_swap(p->bdev, &hibernation_swap); if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); if (!p->bdev || hibernation_swap || !bdev_nonrot(p->bdev)) atomic_dec(&nr_rotate_swap); mutex_lock(&swapon_mutex); spin_lock(&swap_lock); spin_lock(&p->lock); drain_mmlist(); /* wait for anyone still in scan_swap_map_slots */ p->highest_bit = 0; /* cuts scans short */ while (p->flags >= SWP_SCANNING) { spin_unlock(&p->lock); spin_unlock(&swap_lock); schedule_timeout_uninterruptible(1); spin_lock(&swap_lock); spin_lock(&p->lock); } swap_file = p->swap_file; old_block_size = p->old_block_size; p->swap_file = NULL; p->max = 0; swap_map = p->swap_map; p->swap_map = NULL; cluster_info = p->cluster_info; p->cluster_info = NULL; frontswap_map = frontswap_map_get(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); arch_swap_invalidate_area(p->type); frontswap_invalidate_area(p->type); frontswap_map_set(p, NULL); mutex_unlock(&swapon_mutex); free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; free_percpu(p->cluster_next_cpu); p->cluster_next_cpu = NULL; vfree(swap_map); kvfree(cluster_info); kvfree(frontswap_map); /* Destroy swap account information */ swap_cgroup_swapoff(p->type); exit_swap_address_space(p->type); inode = mapping->host; if (S_ISBLK(inode->i_mode)) { struct block_device *bdev = I_BDEV(inode); set_blocksize(bdev, old_block_size); blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); } inode_lock(inode); inode->i_flags &= ~S_SWAPFILE; inode_unlock(inode); filp_close(swap_file, NULL); /* * Clear the SWP_USED flag after all resources are freed so that swapon * can reuse this swap_info in alloc_swap_info() safely. It is ok to * not hold p->lock after we cleared its SWP_WRITEOK. */ spin_lock(&swap_lock); p->flags = 0; spin_unlock(&swap_lock); err = 0; atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); out_dput: filp_close(victim, NULL); out: putname(pathname); return err; } #ifdef CONFIG_PROC_FS static __poll_t swaps_poll(struct file *file, poll_table *wait) { struct seq_file *seq = file->private_data; poll_wait(file, &proc_poll_wait, wait); if (seq->poll_event != atomic_read(&proc_poll_event)) { seq->poll_event = atomic_read(&proc_poll_event); return EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI; } return EPOLLIN | EPOLLRDNORM; } /* iterator */ static void *swap_start(struct seq_file *swap, loff_t *pos) { struct swap_info_struct *si; int type; loff_t l = *pos; mutex_lock(&swapon_mutex); if (!l) return SEQ_START_TOKEN; for (type = 0; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; if (!--l) return si; } return NULL; } static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) { struct swap_info_struct *si = v; int type; if (v == SEQ_START_TOKEN) type = 0; else type = si->type + 1; ++(*pos); for (; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; return si; } return NULL; } static void swap_stop(struct seq_file *swap, void *v) { mutex_unlock(&swapon_mutex); } static int swap_show(struct seq_file *swap, void *v) { struct swap_info_struct *si = v; struct file *file; int len; unsigned long bytes, inuse; if (si == SEQ_START_TOKEN) { seq_puts(swap, "Filename\t\t\t\tType\t\tSize\t\tUsed\t\tPriority\n"); return 0; } bytes = si->pages << (PAGE_SHIFT - 10); inuse = READ_ONCE(si->inuse_pages) << (PAGE_SHIFT - 10); file = si->swap_file; len = seq_file_path(swap, file, " \t\n\\"); seq_printf(swap, "%*s%s\t%lu\t%s%lu\t%s%d\n", len < 40 ? 40 - len : 1, " ", S_ISBLK(file_inode(file)->i_mode) ? "partition" : "file\t", bytes, bytes < 10000000 ? "\t" : "", inuse, inuse < 10000000 ? "\t" : "", si->prio); return 0; } static const struct seq_operations swaps_op = { .start = swap_start, .next = swap_next, .stop = swap_stop, .show = swap_show }; static int swaps_open(struct inode *inode, struct file *file) { struct seq_file *seq; int ret; ret = seq_open(file, &swaps_op); if (ret) return ret; seq = file->private_data; seq->poll_event = atomic_read(&proc_poll_event); return 0; } static const struct proc_ops swaps_proc_ops = { .proc_flags = PROC_ENTRY_PERMANENT, .proc_open = swaps_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = seq_release, .proc_poll = swaps_poll, }; static int __init procswaps_init(void) { proc_create("swaps", 0, NULL, &swaps_proc_ops); return 0; } __initcall(procswaps_init); #endif /* CONFIG_PROC_FS */ #ifdef MAX_SWAPFILES_CHECK static int __init max_swapfiles_check(void) { MAX_SWAPFILES_CHECK(); return 0; } late_initcall(max_swapfiles_check); #endif static struct swap_info_struct *alloc_swap_info(void) { struct swap_info_struct *p; struct swap_info_struct *defer = NULL; unsigned int type; int i; p = kvzalloc(struct_size(p, avail_lists, nr_node_ids), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); if (percpu_ref_init(&p->users, swap_users_ref_free, PERCPU_REF_INIT_DEAD, GFP_KERNEL)) { kvfree(p); return ERR_PTR(-ENOMEM); } spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { if (!(swap_info[type]->flags & SWP_USED)) break; } if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); percpu_ref_exit(&p->users); kvfree(p); return ERR_PTR(-EPERM); } if (type >= nr_swapfiles) { p->type = type; /* * Publish the swap_info_struct after initializing it. * Note that kvzalloc() above zeroes all its fields. */ smp_store_release(&swap_info[type], p); /* rcu_assign_pointer() */ nr_swapfiles++; } else { defer = p; p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() * would be relying on p->type to remain valid. */ } p->swap_extent_root = RB_ROOT; plist_node_init(&p->list, 0); for_each_node(i) plist_node_init(&p->avail_lists[i], 0); p->flags = SWP_USED; spin_unlock(&swap_lock); if (defer) { percpu_ref_exit(&defer->users); kvfree(defer); } spin_lock_init(&p->lock); spin_lock_init(&p->cont_lock); init_completion(&p->comp); return p; } static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) { int error; if (S_ISBLK(inode->i_mode)) { p->bdev = blkdev_get_by_dev(inode->i_rdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL, p); if (IS_ERR(p->bdev)) { error = PTR_ERR(p->bdev); p->bdev = NULL; return error; } p->old_block_size = block_size(p->bdev); error = set_blocksize(p->bdev, PAGE_SIZE); if (error < 0) return error; /* * Zoned block devices contain zones that have a sequential * write only restriction. Hence zoned block devices are not * suitable for swapping. Disallow them here. */ if (bdev_is_zoned(p->bdev)) return -EINVAL; p->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { p->bdev = inode->i_sb->s_bdev; } return 0; } /* * Find out how many pages are allowed for a single swap device. There * are two limiting factors: * 1) the number of bits for the swap offset in the swp_entry_t type, and * 2) the number of bits in the swap pte, as defined by the different * architectures. * * In order to find the largest possible bit mask, a swap entry with * swap type 0 and swap offset ~0UL is created, encoded to a swap pte, * decoded to a swp_entry_t again, and finally the swap offset is * extracted. * * This will mask all the bits from the initial ~0UL mask that can't * be encoded in either the swp_entry_t or the architecture definition * of a swap pte. */ unsigned long generic_max_swapfile_size(void) { return swp_offset(pte_to_swp_entry( swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; } /* Can be overridden by an architecture for additional checks. */ __weak unsigned long arch_max_swapfile_size(void) { return generic_max_swapfile_size(); } static unsigned long read_swap_header(struct swap_info_struct *p, union swap_header *swap_header, struct inode *inode) { int i; unsigned long maxpages; unsigned long swapfilepages; unsigned long last_page; if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) { pr_err("Unable to find swap-space signature\n"); return 0; } /* swap partition endianness hack... */ if (swab32(swap_header->info.version) == 1) { swab32s(&swap_header->info.version); swab32s(&swap_header->info.last_page); swab32s(&swap_header->info.nr_badpages); if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; for (i = 0; i < swap_header->info.nr_badpages; i++) swab32s(&swap_header->info.badpages[i]); } /* Check the swap header's sub-version */ if (swap_header->info.version != 1) { pr_warn("Unable to handle swap header version %d\n", swap_header->info.version); return 0; } p->lowest_bit = 1; p->cluster_next = 1; p->cluster_nr = 0; maxpages = swapfile_maximum_size; last_page = swap_header->info.last_page; if (!last_page) { pr_warn("Empty swap-file\n"); return 0; } if (last_page > maxpages) { pr_warn("Truncating oversized swap area, only using %luk out of %luk\n", maxpages << (PAGE_SHIFT - 10), last_page << (PAGE_SHIFT - 10)); } if (maxpages > last_page) { maxpages = last_page + 1; /* p->max is an unsigned int: don't overflow it */ if ((unsigned int)maxpages == 0) maxpages = UINT_MAX; } p->highest_bit = maxpages - 1; if (!maxpages) return 0; swapfilepages = i_size_read(inode) >> PAGE_SHIFT; if (swapfilepages && maxpages > swapfilepages) { pr_warn("Swap area shorter than signature indicates\n"); return 0; } if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) return 0; if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; return maxpages; } #define SWAP_CLUSTER_INFO_COLS \ DIV_ROUND_UP(L1_CACHE_BYTES, sizeof(struct swap_cluster_info)) #define SWAP_CLUSTER_SPACE_COLS \ DIV_ROUND_UP(SWAP_ADDRESS_SPACE_PAGES, SWAPFILE_CLUSTER) #define SWAP_CLUSTER_COLS \ max_t(unsigned int, SWAP_CLUSTER_INFO_COLS, SWAP_CLUSTER_SPACE_COLS) static int setup_swap_map_and_extents(struct swap_info_struct *p, union swap_header *swap_header, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long maxpages, sector_t *span) { unsigned int j, k; unsigned int nr_good_pages; int nr_extents; unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); unsigned long col = p->cluster_next / SWAPFILE_CLUSTER % SWAP_CLUSTER_COLS; unsigned long i, idx; nr_good_pages = maxpages - 1; /* omit header page */ cluster_list_init(&p->free_clusters); cluster_list_init(&p->discard_clusters); for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (page_nr == 0 || page_nr > swap_header->info.last_page) return -EINVAL; if (page_nr < maxpages) { swap_map[page_nr] = SWAP_MAP_BAD; nr_good_pages--; /* * Haven't marked the cluster free yet, no list * operation involved */ inc_cluster_info_page(p, cluster_info, page_nr); } } /* Haven't marked the cluster free yet, no list operation involved */ for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++) inc_cluster_info_page(p, cluster_info, i); if (nr_good_pages) { swap_map[0] = SWAP_MAP_BAD; /* * Not mark the cluster free yet, no list * operation involved */ inc_cluster_info_page(p, cluster_info, 0); p->max = maxpages; p->pages = nr_good_pages; nr_extents = setup_swap_extents(p, span); if (nr_extents < 0) return nr_extents; nr_good_pages = p->pages; } if (!nr_good_pages) { pr_warn("Empty swap-file\n"); return -EINVAL; } if (!cluster_info) return nr_extents; /* * Reduce false cache line sharing between cluster_info and * sharing same address space. */ for (k = 0; k < SWAP_CLUSTER_COLS; k++) { j = (k + col) % SWAP_CLUSTER_COLS; for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) { idx = i * SWAP_CLUSTER_COLS + j; if (idx >= nr_clusters) continue; if (cluster_count(&cluster_info[idx])) continue; cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE); cluster_list_add_tail(&p->free_clusters, cluster_info, idx); } } return nr_extents; } SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct *p; struct filename *name; struct file *swap_file = NULL; struct address_space *mapping; struct dentry *dentry; int prio; int error; union swap_header *swap_header; int nr_extents; sector_t span; unsigned long maxpages; unsigned char *swap_map = NULL; struct swap_cluster_info *cluster_info = NULL; unsigned long *frontswap_map = NULL; struct page *page = NULL; struct inode *inode = NULL; bool inced_nr_rotate_swap = false; bool hibernation_swap = false; if (swap_flags & ~SWAP_FLAGS_VALID) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!swap_avail_heads) return -ENOMEM; p = alloc_swap_info(); if (IS_ERR(p)) return PTR_ERR(p); INIT_WORK(&p->discard_work, swap_discard_work); name = getname(specialfile); if (IS_ERR(name)) { error = PTR_ERR(name); name = NULL; goto bad_swap; } swap_file = file_open_name(name, O_RDWR|O_LARGEFILE, 0); if (IS_ERR(swap_file)) { error = PTR_ERR(swap_file); swap_file = NULL; goto bad_swap; } p->swap_file = swap_file; mapping = swap_file->f_mapping; dentry = swap_file->f_path.dentry; inode = mapping->host; error = claim_swapfile(p, inode); if (unlikely(error)) goto bad_swap; inode_lock(inode); if (d_unlinked(dentry) || cant_mount(dentry)) { error = -ENOENT; goto bad_swap_unlock_inode; } if (IS_SWAPFILE(inode)) { error = -EBUSY; goto bad_swap_unlock_inode; } /* * Read the swap header. */ if (!mapping->a_ops->read_folio) { error = -EINVAL; goto bad_swap_unlock_inode; } page = read_mapping_page(mapping, 0, swap_file); if (IS_ERR(page)) { error = PTR_ERR(page); goto bad_swap_unlock_inode; } swap_header = kmap(page); maxpages = read_swap_header(p, swap_header, inode); if (unlikely(!maxpages)) { error = -EINVAL; goto bad_swap_unlock_inode; } /* OK, set up the swap map and apply the bad block list */ swap_map = vzalloc(maxpages); if (!swap_map) { error = -ENOMEM; goto bad_swap_unlock_inode; } trace_android_vh_check_hibernation_swap(p->bdev, &hibernation_swap); if (p->bdev && bdev_stable_writes(p->bdev)) p->flags |= SWP_STABLE_WRITES; if (p->bdev && p->bdev->bd_disk->fops->rw_page) p->flags |= SWP_SYNCHRONOUS_IO; if (p->bdev && !hibernation_swap && bdev_nonrot(p->bdev)) { int cpu; unsigned long ci, nr_cluster; p->flags |= SWP_SOLIDSTATE; p->cluster_next_cpu = alloc_percpu(unsigned int); if (!p->cluster_next_cpu) { error = -ENOMEM; goto bad_swap_unlock_inode; } /* * select a random position to start with to help wear leveling * SSD */ for_each_possible_cpu(cpu) { per_cpu(*p->cluster_next_cpu, cpu) = 1 + prandom_u32_max(p->highest_bit); } nr_cluster = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); cluster_info = kvcalloc(nr_cluster, sizeof(*cluster_info), GFP_KERNEL); if (!cluster_info) { error = -ENOMEM; goto bad_swap_unlock_inode; } for (ci = 0; ci < nr_cluster; ci++) spin_lock_init(&((cluster_info + ci)->lock)); p->percpu_cluster = alloc_percpu(struct percpu_cluster); if (!p->percpu_cluster) { error = -ENOMEM; goto bad_swap_unlock_inode; } for_each_possible_cpu(cpu) { struct percpu_cluster *cluster; cluster = per_cpu_ptr(p->percpu_cluster, cpu); cluster_set_null(&cluster->index); } } else { atomic_inc(&nr_rotate_swap); inced_nr_rotate_swap = true; } error = swap_cgroup_swapon(p->type, maxpages); if (error) goto bad_swap_unlock_inode; nr_extents = setup_swap_map_and_extents(p, swap_header, swap_map, cluster_info, maxpages, &span); if (unlikely(nr_extents < 0)) { error = nr_extents; goto bad_swap_unlock_inode; } /* frontswap enabled? set up bit-per-page map for frontswap */ if (IS_ENABLED(CONFIG_FRONTSWAP)) frontswap_map = kvcalloc(BITS_TO_LONGS(maxpages), sizeof(long), GFP_KERNEL); if ((swap_flags & SWAP_FLAG_DISCARD) && p->bdev && bdev_max_discard_sectors(p->bdev)) { /* * When discard is enabled for swap with no particular * policy flagged, we set all swap discard flags here in * order to sustain backward compatibility with older * swapon(8) releases. */ p->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | SWP_PAGE_DISCARD); /* * By flagging sys_swapon, a sysadmin can tell us to * either do single-time area discards only, or to just * perform discards for released swap page-clusters. * Now it's time to adjust the p->flags accordingly. */ if (swap_flags & SWAP_FLAG_DISCARD_ONCE) p->flags &= ~SWP_PAGE_DISCARD; else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) p->flags &= ~SWP_AREA_DISCARD; /* issue a swapon-time discard if it's still required */ if (p->flags & SWP_AREA_DISCARD) { int err = discard_swap(p); if (unlikely(err)) pr_err("swapon: discard_swap(%p): %d\n", p, err); } } error = init_swap_address_space(p->type, maxpages); if (error) goto bad_swap_unlock_inode; /* * Flush any pending IO and dirty mappings before we start using this * swap device. */ inode->i_flags |= S_SWAPFILE; error = inode_drain_writes(inode); if (error) { inode->i_flags &= ~S_SWAPFILE; goto free_swap_address_space; } mutex_lock(&swapon_mutex); prio = -1; if (swap_flags & SWAP_FLAG_PREFER) prio = (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; enable_swap_info(p, prio, swap_map, cluster_info, frontswap_map); pr_info("Adding %uk swap on %s. Priority:%d extents:%d across:%lluk %s%s%s%s%s\n", p->pages<<(PAGE_SHIFT-10), name->name, p->prio, nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10), (p->flags & SWP_SOLIDSTATE) ? "SS" : "", (p->flags & SWP_DISCARDABLE) ? "D" : "", (p->flags & SWP_AREA_DISCARD) ? "s" : "", (p->flags & SWP_PAGE_DISCARD) ? "c" : "", (frontswap_map) ? "FS" : ""); mutex_unlock(&swapon_mutex); atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); error = 0; goto out; free_swap_address_space: exit_swap_address_space(p->type); bad_swap_unlock_inode: inode_unlock(inode); bad_swap: free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; free_percpu(p->cluster_next_cpu); p->cluster_next_cpu = NULL; if (inode && S_ISBLK(inode->i_mode) && p->bdev) { set_blocksize(p->bdev, p->old_block_size); blkdev_put(p->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); } inode = NULL; destroy_swap_extents(p); swap_cgroup_swapoff(p->type); spin_lock(&swap_lock); p->swap_file = NULL; p->flags = 0; spin_unlock(&swap_lock); vfree(swap_map); kvfree(cluster_info); kvfree(frontswap_map); if (inced_nr_rotate_swap) atomic_dec(&nr_rotate_swap); if (swap_file) filp_close(swap_file, NULL); out: if (page && !IS_ERR(page)) { kunmap(page); put_page(page); } if (name) putname(name); if (inode) inode_unlock(inode); if (!error) enable_swap_slots_cache(); return error; } void si_swapinfo(struct sysinfo *val) { unsigned int type; unsigned long nr_to_be_unused = 0; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *si = swap_info[type]; if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK)) nr_to_be_unused += READ_ONCE(si->inuse_pages); } val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; spin_unlock(&swap_lock); } EXPORT_SYMBOL_NS_GPL(si_swapinfo, MINIDUMP); /* * Verify that a swap entry is valid and increment its swap map count. * * Returns error code in following case. * - success -> 0 * - swp_entry is invalid -> EINVAL * - swp_entry is migration entry -> EINVAL * - swap-cache reference is requested but there is already one. -> EEXIST * - swap-cache reference is requested but the entry is not used. -> ENOENT * - swap-mapped reference requested but needs continued swap count. -> ENOMEM */ static int __swap_duplicate(swp_entry_t entry, unsigned char usage) { struct swap_info_struct *p; struct swap_cluster_info *ci; unsigned long offset; unsigned char count; unsigned char has_cache; int err; p = get_swap_device(entry); if (!p) return -EINVAL; offset = swp_offset(entry); ci = lock_cluster_or_swap_info(p, offset); count = p->swap_map[offset]; /* * swapin_readahead() doesn't check if a swap entry is valid, so the * swap entry could be SWAP_MAP_BAD. Check here with lock held. */ if (unlikely(swap_count(count) == SWAP_MAP_BAD)) { err = -ENOENT; goto unlock_out; } has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; err = 0; if (usage == SWAP_HAS_CACHE) { /* set SWAP_HAS_CACHE if there is no cache and entry is used */ if (!has_cache && count) has_cache = SWAP_HAS_CACHE; else if (has_cache) /* someone else added cache */ err = -EEXIST; else /* no users remaining */ err = -ENOENT; } else if (count || has_cache) { if ((count & ~COUNT_CONTINUED) < SWAP_MAP_MAX) count += usage; else if ((count & ~COUNT_CONTINUED) > SWAP_MAP_MAX) err = -EINVAL; else if (swap_count_continued(p, offset, count)) count = COUNT_CONTINUED; else err = -ENOMEM; } else err = -ENOENT; /* unused swap entry */ WRITE_ONCE(p->swap_map[offset], count | has_cache); unlock_out: unlock_cluster_or_swap_info(p, ci); put_swap_device(p); return err; } /* * Help swapoff by noting that swap entry belongs to shmem/tmpfs * (in which case its reference count is never incremented). */ void swap_shmem_alloc(swp_entry_t entry) { __swap_duplicate(entry, SWAP_MAP_SHMEM); } /* * Increase reference count of swap entry by 1. * Returns 0 for success, or -ENOMEM if a swap_count_continuation is required * but could not be atomically allocated. Returns 0, just as if it succeeded, * if __swap_duplicate() fails for another reason (-EINVAL or -ENOENT), which * might occur if a page table entry has got corrupted. */ int swap_duplicate(swp_entry_t entry) { int err = 0; while (!err && __swap_duplicate(entry, 1) == -ENOMEM) err = add_swap_count_continuation(entry, GFP_ATOMIC); return err; } /* * @entry: swap entry for which we allocate swap cache. * * Called when allocating swap cache for existing swap entry, * This can return error codes. Returns 0 at success. * -EEXIST means there is a swap cache. * Note: return code is different from swap_duplicate(). */ int swapcache_prepare(swp_entry_t entry) { return __swap_duplicate(entry, SWAP_HAS_CACHE); } void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); unsigned char usage; ci = lock_cluster_or_swap_info(si, offset); usage = __swap_entry_free_locked(si, offset, SWAP_HAS_CACHE); unlock_cluster_or_swap_info(si, ci); if (!usage) free_swap_slot(entry); } struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return swap_type_to_swap_info(swp_type(entry)); } struct swap_info_struct *page_swap_info(struct page *page) { swp_entry_t entry = { .val = page_private(page) }; return swp_swap_info(entry); } EXPORT_SYMBOL_GPL(page_swap_info); /* * out-of-line methods to avoid include hell. */ struct address_space *swapcache_mapping(struct folio *folio) { return page_swap_info(&folio->page)->swap_file->f_mapping; } EXPORT_SYMBOL_GPL(swapcache_mapping); pgoff_t __page_file_index(struct page *page) { swp_entry_t swap = { .val = page_private(page) }; return swp_offset(swap); } EXPORT_SYMBOL_GPL(__page_file_index); /* * add_swap_count_continuation - called when a swap count is duplicated * beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's * page of the original vmalloc'ed swap_map, to hold the continuation count * (for that entry and for its neighbouring PAGE_SIZE swap entries). Called * again when count is duplicated beyond SWAP_MAP_MAX * SWAP_CONT_MAX, etc. * * These continuation pages are seldom referenced: the common paths all work * on the original swap_map, only referring to a continuation page when the * low "digit" of a count is incremented or decremented through SWAP_MAP_MAX. * * add_swap_count_continuation(, GFP_ATOMIC) can be called while holding * page table locks; if it fails, add_swap_count_continuation(, GFP_KERNEL) * can be called after dropping locks. */ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) { struct swap_info_struct *si; struct swap_cluster_info *ci; struct page *head; struct page *page; struct page *list_page; pgoff_t offset; unsigned char count; int ret = 0; /* * When debugging, it's easier to use __GFP_ZERO here; but it's better * for latency not to zero a page while GFP_ATOMIC and holding locks. */ page = alloc_page(gfp_mask | __GFP_HIGHMEM); si = get_swap_device(entry); if (!si) { /* * An acceptable race has occurred since the failing * __swap_duplicate(): the swap device may be swapoff */ goto outer; } spin_lock(&si->lock); offset = swp_offset(entry); ci = lock_cluster(si, offset); count = swap_count(si->swap_map[offset]); if ((count & ~COUNT_CONTINUED) != SWAP_MAP_MAX) { /* * The higher the swap count, the more likely it is that tasks * will race to add swap count continuation: we need to avoid * over-provisioning. */ goto out; } if (!page) { ret = -ENOMEM; goto out; } /* * We are fortunate that although vmalloc_to_page uses pte_offset_map, * no architecture is using highmem pages for kernel page tables: so it * will not corrupt the GFP_ATOMIC caller's atomic page table kmaps. */ head = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; spin_lock(&si->cont_lock); /* * Page allocation does not initialize the page's lru field, * but it does always reset its private field. */ if (!page_private(head)) { BUG_ON(count & COUNT_CONTINUED); INIT_LIST_HEAD(&head->lru); set_page_private(head, SWP_CONTINUED); si->flags |= SWP_CONTINUED; } list_for_each_entry(list_page, &head->lru, lru) { unsigned char *map; /* * If the previous map said no continuation, but we've found * a continuation page, free our allocation and use this one. */ if (!(count & COUNT_CONTINUED)) goto out_unlock_cont; map = kmap_atomic(list_page) + offset; count = *map; kunmap_atomic(map); /* * If this continuation count now has some space in it, * free our allocation and use this one. */ if ((count & ~COUNT_CONTINUED) != SWAP_CONT_MAX) goto out_unlock_cont; } list_add_tail(&page->lru, &head->lru); page = NULL; /* now it's attached, don't free it */ out_unlock_cont: spin_unlock(&si->cont_lock); out: unlock_cluster(ci); spin_unlock(&si->lock); put_swap_device(si); outer: if (page) __free_page(page); return ret; } /* * swap_count_continued - when the original swap_map count is incremented * from SWAP_MAP_MAX, check if there is already a continuation page to carry * into, carry if so, or else fail until a new continuation page is allocated; * when the original swap_map count is decremented from 0 with continuation, * borrow from the continuation and report whether it still holds more. * Called while __swap_duplicate() or swap_entry_free() holds swap or cluster * lock. */ static bool swap_count_continued(struct swap_info_struct *si, pgoff_t offset, unsigned char count) { struct page *head; struct page *page; unsigned char *map; bool ret; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head) != SWP_CONTINUED) { BUG_ON(count & COUNT_CONTINUED); return false; /* need to add count continuation */ } spin_lock(&si->cont_lock); offset &= ~PAGE_MASK; page = list_next_entry(head, lru); map = kmap_atomic(page) + offset; if (count == SWAP_MAP_MAX) /* initial increment from swap_map */ goto init_map; /* jump over SWAP_CONT_MAX checks */ if (count == (SWAP_MAP_MAX | COUNT_CONTINUED)) { /* incrementing */ /* * Think of how you add 1 to 999 */ while (*map == (SWAP_CONT_MAX | COUNT_CONTINUED)) { kunmap_atomic(map); page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_atomic(page) + offset; } if (*map == SWAP_CONT_MAX) { kunmap_atomic(map); page = list_next_entry(page, lru); if (page == head) { ret = false; /* add count continuation */ goto out; } map = kmap_atomic(page) + offset; init_map: *map = 0; /* we didn't zero the page */ } *map += 1; kunmap_atomic(map); while ((page = list_prev_entry(page, lru)) != head) { map = kmap_atomic(page) + offset; *map = COUNT_CONTINUED; kunmap_atomic(map); } ret = true; /* incremented */ } else { /* decrementing */ /* * Think of how you subtract 1 from 1000 */ BUG_ON(count != COUNT_CONTINUED); while (*map == COUNT_CONTINUED) { kunmap_atomic(map); page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_atomic(page) + offset; } BUG_ON(*map == 0); *map -= 1; if (*map == 0) count = 0; kunmap_atomic(map); while ((page = list_prev_entry(page, lru)) != head) { map = kmap_atomic(page) + offset; *map = SWAP_CONT_MAX | count; count = COUNT_CONTINUED; kunmap_atomic(map); } ret = count == COUNT_CONTINUED; } out: spin_unlock(&si->cont_lock); return ret; } /* * free_swap_count_continuations - swapoff free all the continuation pages * appended to the swap_map, after swap_map is quiesced, before vfree'ing it. */ static void free_swap_count_continuations(struct swap_info_struct *si) { pgoff_t offset; for (offset = 0; offset < si->max; offset += PAGE_SIZE) { struct page *head; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head)) { struct page *page, *next; list_for_each_entry_safe(page, next, &head->lru, lru) { list_del(&page->lru); __free_page(page); } } } } #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) { struct swap_info_struct *si, *next; int nid = page_to_nid(page); if (!(gfp_mask & __GFP_IO)) return; if (!blk_cgroup_congested()) return; /* * We've already scheduled a throttle, avoid taking the global swap * lock. */ if (current->throttle_queue) return; spin_lock(&swap_avail_lock); plist_for_each_entry_safe(si, next, &swap_avail_heads[nid], avail_lists[nid]) { if (si->bdev) { blkcg_schedule_throttle(si->bdev->bd_disk, true); break; } } spin_unlock(&swap_avail_lock); } #endif static int __init swapfile_init(void) { int nid; swap_avail_heads = kmalloc_array(nr_node_ids, sizeof(struct plist_head), GFP_KERNEL); if (!swap_avail_heads) { pr_emerg("Not enough memory for swap heads, swap is disabled\n"); return -ENOMEM; } for_each_node(nid) plist_head_init(&swap_avail_heads[nid]); swapfile_maximum_size = arch_max_swapfile_size(); #ifdef CONFIG_MIGRATION if (swapfile_maximum_size >= (1UL << SWP_MIG_TOTAL_BITS)) swap_migration_ad_supported = true; #endif /* CONFIG_MIGRATION */ return 0; } subsys_initcall(swapfile_init); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 | /* SPDX-License-Identifier: GPL-2.0 */ /* * fscrypt_private.h * * Copyright (C) 2015, Google, Inc. * * Originally written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar. * Heavily modified since then. */ #ifndef _FSCRYPT_PRIVATE_H #define _FSCRYPT_PRIVATE_H #include <linux/fscrypt.h> #include <linux/siphash.h> #include <crypto/hash.h> #include <linux/blk-crypto.h> #define CONST_STRLEN(str) (sizeof(str) - 1) #define FSCRYPT_FILE_NONCE_SIZE 16 /* * Minimum size of an fscrypt master key. Note: a longer key will be required * if ciphers with a 256-bit security strength are used. This is just the * absolute minimum, which applies when only 128-bit encryption is used. */ #define FSCRYPT_MIN_KEY_SIZE 16 /* Maximum size of a standard fscrypt master key */ #define FSCRYPT_MAX_STANDARD_KEY_SIZE 64 /* Maximum size of a hardware-wrapped fscrypt master key */ #define FSCRYPT_MAX_HW_WRAPPED_KEY_SIZE BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE /* * Maximum size of an fscrypt master key across both key types. * This should just use max(), but max() doesn't work in a struct definition. */ #define FSCRYPT_MAX_ANY_KEY_SIZE \ (FSCRYPT_MAX_HW_WRAPPED_KEY_SIZE > FSCRYPT_MAX_STANDARD_KEY_SIZE ? \ FSCRYPT_MAX_HW_WRAPPED_KEY_SIZE : FSCRYPT_MAX_STANDARD_KEY_SIZE) /* * FSCRYPT_MAX_KEY_SIZE is defined in the UAPI header, but the addition of * hardware-wrapped keys has made it misleading as it's only for standard keys. * Don't use it in kernel code; use one of the above constants instead. */ #undef FSCRYPT_MAX_KEY_SIZE #define FSCRYPT_CONTEXT_V1 1 #define FSCRYPT_CONTEXT_V2 2 /* Keep this in sync with include/uapi/linux/fscrypt.h */ #define FSCRYPT_MODE_MAX FSCRYPT_MODE_AES_256_HCTR2 struct fscrypt_context_v1 { u8 version; /* FSCRYPT_CONTEXT_V1 */ u8 contents_encryption_mode; u8 filenames_encryption_mode; u8 flags; u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE]; u8 nonce[FSCRYPT_FILE_NONCE_SIZE]; }; struct fscrypt_context_v2 { u8 version; /* FSCRYPT_CONTEXT_V2 */ u8 contents_encryption_mode; u8 filenames_encryption_mode; u8 flags; u8 log2_data_unit_size; u8 __reserved[3]; u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]; u8 nonce[FSCRYPT_FILE_NONCE_SIZE]; }; /* * fscrypt_context - the encryption context of an inode * * This is the on-disk equivalent of an fscrypt_policy, stored alongside each * encrypted file usually in a hidden extended attribute. It contains the * fields from the fscrypt_policy, in order to identify the encryption algorithm * and key with which the file is encrypted. It also contains a nonce that was * randomly generated by fscrypt itself; this is used as KDF input or as a tweak * to cause different files to be encrypted differently. */ union fscrypt_context { u8 version; struct fscrypt_context_v1 v1; struct fscrypt_context_v2 v2; }; /* * Return the size expected for the given fscrypt_context based on its version * number, or 0 if the context version is unrecognized. */ static inline int fscrypt_context_size(const union fscrypt_context *ctx) { switch (ctx->version) { case FSCRYPT_CONTEXT_V1: BUILD_BUG_ON(sizeof(ctx->v1) != 28); return sizeof(ctx->v1); case FSCRYPT_CONTEXT_V2: BUILD_BUG_ON(sizeof(ctx->v2) != 40); return sizeof(ctx->v2); } return 0; } /* Check whether an fscrypt_context has a recognized version number and size */ static inline bool fscrypt_context_is_valid(const union fscrypt_context *ctx, int ctx_size) { return ctx_size >= 1 && ctx_size == fscrypt_context_size(ctx); } /* Retrieve the context's nonce, assuming the context was already validated */ static inline const u8 *fscrypt_context_nonce(const union fscrypt_context *ctx) { switch (ctx->version) { case FSCRYPT_CONTEXT_V1: return ctx->v1.nonce; case FSCRYPT_CONTEXT_V2: return ctx->v2.nonce; } WARN_ON_ONCE(1); return NULL; } union fscrypt_policy { u8 version; struct fscrypt_policy_v1 v1; struct fscrypt_policy_v2 v2; }; /* * Return the size expected for the given fscrypt_policy based on its version * number, or 0 if the policy version is unrecognized. */ static inline int fscrypt_policy_size(const union fscrypt_policy *policy) { switch (policy->version) { case FSCRYPT_POLICY_V1: return sizeof(policy->v1); case FSCRYPT_POLICY_V2: return sizeof(policy->v2); } return 0; } /* Return the contents encryption mode of a valid encryption policy */ static inline u8 fscrypt_policy_contents_mode(const union fscrypt_policy *policy) { switch (policy->version) { case FSCRYPT_POLICY_V1: return policy->v1.contents_encryption_mode; case FSCRYPT_POLICY_V2: return policy->v2.contents_encryption_mode; } BUG(); } /* Return the filenames encryption mode of a valid encryption policy */ static inline u8 fscrypt_policy_fnames_mode(const union fscrypt_policy *policy) { switch (policy->version) { case FSCRYPT_POLICY_V1: return policy->v1.filenames_encryption_mode; case FSCRYPT_POLICY_V2: return policy->v2.filenames_encryption_mode; } BUG(); } /* Return the flags (FSCRYPT_POLICY_FLAG*) of a valid encryption policy */ static inline u8 fscrypt_policy_flags(const union fscrypt_policy *policy) { switch (policy->version) { case FSCRYPT_POLICY_V1: return policy->v1.flags; case FSCRYPT_POLICY_V2: return policy->v2.flags; } BUG(); } static inline int fscrypt_policy_v2_du_bits(const struct fscrypt_policy_v2 *policy, const struct inode *inode) { return policy->log2_data_unit_size ?: inode->i_blkbits; } static inline int fscrypt_policy_du_bits(const union fscrypt_policy *policy, const struct inode *inode) { switch (policy->version) { case FSCRYPT_POLICY_V1: return inode->i_blkbits; case FSCRYPT_POLICY_V2: return fscrypt_policy_v2_du_bits(&policy->v2, inode); } BUG(); } /* * For encrypted symlinks, the ciphertext length is stored at the beginning * of the string in little-endian format. */ struct fscrypt_symlink_data { __le16 len; char encrypted_path[1]; } __packed; /** * struct fscrypt_prepared_key - a key prepared for actual encryption/decryption * @tfm: crypto API transform object * @blk_key: key for blk-crypto * * Normally only one of the fields will be non-NULL. */ struct fscrypt_prepared_key { struct crypto_skcipher *tfm; #ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT struct blk_crypto_key *blk_key; #endif }; /* * fscrypt_info - the "encryption key" for an inode * * When an encrypted file's key is made available, an instance of this struct is * allocated and stored in ->i_crypt_info. Once created, it remains until the * inode is evicted. */ struct fscrypt_info { /* The key in a form prepared for actual encryption/decryption */ struct fscrypt_prepared_key ci_enc_key; /* True if ci_enc_key should be freed when this fscrypt_info is freed */ bool ci_owns_key; #ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT /* * True if this inode will use inline encryption (blk-crypto) instead of * the traditional filesystem-layer encryption. */ bool ci_inlinecrypt; #endif /* * log2 of the data unit size (granularity of contents encryption) of * this file. This is computable from ci_policy and ci_inode but is * cached here for efficiency. Only used for regular files. */ u8 ci_data_unit_bits; /* Cached value: log2 of number of data units per FS block */ u8 ci_data_units_per_block_bits; /* * Encryption mode used for this inode. It corresponds to either the * contents or filenames encryption mode, depending on the inode type. */ struct fscrypt_mode *ci_mode; /* Back-pointer to the inode */ struct inode *ci_inode; /* * The master key with which this inode was unlocked (decrypted). This * will be NULL if the master key was found in a process-subscribed * keyring rather than in the filesystem-level keyring. */ struct fscrypt_master_key *ci_master_key; /* * Link in list of inodes that were unlocked with the master key. * Only used when ->ci_master_key is set. */ struct list_head ci_master_key_link; /* * If non-NULL, then encryption is done using the master key directly * and ci_enc_key will equal ci_direct_key->dk_key. */ struct fscrypt_direct_key *ci_direct_key; /* * This inode's hash key for filenames. This is a 128-bit SipHash-2-4 * key. This is only set for directories that use a keyed dirhash over * the plaintext filenames -- currently just casefolded directories. */ siphash_key_t ci_dirhash_key; bool ci_dirhash_key_initialized; /* The encryption policy used by this inode */ union fscrypt_policy ci_policy; /* This inode's nonce, copied from the fscrypt_context */ u8 ci_nonce[FSCRYPT_FILE_NONCE_SIZE]; /* Hashed inode number. Only set for IV_INO_LBLK_32 */ u32 ci_hashed_ino; }; typedef enum { FS_DECRYPT = 0, FS_ENCRYPT, } fscrypt_direction_t; /* crypto.c */ extern struct kmem_cache *fscrypt_info_cachep; int fscrypt_initialize(struct super_block *sb); int fscrypt_crypt_data_unit(const struct fscrypt_info *ci, fscrypt_direction_t rw, u64 index, struct page *src_page, struct page *dest_page, unsigned int len, unsigned int offs, gfp_t gfp_flags); struct page *fscrypt_alloc_bounce_page(gfp_t gfp_flags); void __printf(3, 4) __cold fscrypt_msg(const struct inode *inode, const char *level, const char *fmt, ...); #define fscrypt_warn(inode, fmt, ...) \ fscrypt_msg((inode), KERN_WARNING, fmt, ##__VA_ARGS__) #define fscrypt_err(inode, fmt, ...) \ fscrypt_msg((inode), KERN_ERR, fmt, ##__VA_ARGS__) #define FSCRYPT_MAX_IV_SIZE 32 union fscrypt_iv { struct { /* zero-based index of data unit within the file */ __le64 index; /* per-file nonce; only set in DIRECT_KEY mode */ u8 nonce[FSCRYPT_FILE_NONCE_SIZE]; }; u8 raw[FSCRYPT_MAX_IV_SIZE]; __le64 dun[FSCRYPT_MAX_IV_SIZE / sizeof(__le64)]; }; void fscrypt_generate_iv(union fscrypt_iv *iv, u64 index, const struct fscrypt_info *ci); /* * Return the number of bits used by the maximum file data unit index that is * possible on the given filesystem, using the given log2 data unit size. */ static inline int fscrypt_max_file_dun_bits(const struct super_block *sb, int du_bits) { return fls64(sb->s_maxbytes - 1) - du_bits; } /* fname.c */ bool __fscrypt_fname_encrypted_size(const union fscrypt_policy *policy, u32 orig_len, u32 max_len, u32 *encrypted_len_ret); /* hkdf.c */ struct fscrypt_hkdf { struct crypto_shash *hmac_tfm; }; int fscrypt_init_hkdf(struct fscrypt_hkdf *hkdf, const u8 *master_key, unsigned int master_key_size); /* * The list of contexts in which fscrypt uses HKDF. These values are used as * the first byte of the HKDF application-specific info string to guarantee that * info strings are never repeated between contexts. This ensures that all HKDF * outputs are unique and cryptographically isolated, i.e. knowledge of one * output doesn't reveal another. */ #define HKDF_CONTEXT_KEY_IDENTIFIER 1 /* info=<empty> */ #define HKDF_CONTEXT_PER_FILE_ENC_KEY 2 /* info=file_nonce */ #define HKDF_CONTEXT_DIRECT_KEY 3 /* info=mode_num */ #define HKDF_CONTEXT_IV_INO_LBLK_64_KEY 4 /* info=mode_num||fs_uuid */ #define HKDF_CONTEXT_DIRHASH_KEY 5 /* info=file_nonce */ #define HKDF_CONTEXT_IV_INO_LBLK_32_KEY 6 /* info=mode_num||fs_uuid */ #define HKDF_CONTEXT_INODE_HASH_KEY 7 /* info=<empty> */ int fscrypt_hkdf_expand(const struct fscrypt_hkdf *hkdf, u8 context, const u8 *info, unsigned int infolen, u8 *okm, unsigned int okmlen); void fscrypt_destroy_hkdf(struct fscrypt_hkdf *hkdf); /* inline_crypt.c */ #ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT int fscrypt_select_encryption_impl(struct fscrypt_info *ci, bool is_hw_wrapped_key); static inline bool fscrypt_using_inline_encryption(const struct fscrypt_info *ci) { return ci->ci_inlinecrypt; } int fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key, const u8 *raw_key, size_t raw_key_size, bool is_hw_wrapped, const struct fscrypt_info *ci); void fscrypt_destroy_inline_crypt_key(struct super_block *sb, struct fscrypt_prepared_key *prep_key); int fscrypt_derive_sw_secret(struct super_block *sb, const u8 *wrapped_key, size_t wrapped_key_size, u8 sw_secret[BLK_CRYPTO_SW_SECRET_SIZE]); /* * Check whether the crypto transform or blk-crypto key has been allocated in * @prep_key, depending on which encryption implementation the file will use. */ static inline bool fscrypt_is_key_prepared(struct fscrypt_prepared_key *prep_key, const struct fscrypt_info *ci) { /* * The two smp_load_acquire()'s here pair with the smp_store_release()'s * in fscrypt_prepare_inline_crypt_key() and fscrypt_prepare_key(). * I.e., in some cases (namely, if this prep_key is a per-mode * encryption key) another task can publish blk_key or tfm concurrently, * executing a RELEASE barrier. We need to use smp_load_acquire() here * to safely ACQUIRE the memory the other task published. */ if (fscrypt_using_inline_encryption(ci)) return smp_load_acquire(&prep_key->blk_key) != NULL; return smp_load_acquire(&prep_key->tfm) != NULL; } #else /* CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ static inline int fscrypt_select_encryption_impl(struct fscrypt_info *ci, bool is_hw_wrapped_key) { return 0; } static inline bool fscrypt_using_inline_encryption(const struct fscrypt_info *ci) { return false; } static inline int fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key, const u8 *raw_key, size_t raw_key_size, bool is_hw_wrapped, const struct fscrypt_info *ci) { WARN_ON_ONCE(1); return -EOPNOTSUPP; } static inline void fscrypt_destroy_inline_crypt_key(struct super_block *sb, struct fscrypt_prepared_key *prep_key) { } static inline int fscrypt_derive_sw_secret(struct super_block *sb, const u8 *wrapped_key, size_t wrapped_key_size, u8 sw_secret[BLK_CRYPTO_SW_SECRET_SIZE]) { fscrypt_warn(NULL, "kernel doesn't support hardware-wrapped keys"); return -EOPNOTSUPP; } static inline bool fscrypt_is_key_prepared(struct fscrypt_prepared_key *prep_key, const struct fscrypt_info *ci) { return smp_load_acquire(&prep_key->tfm) != NULL; } #endif /* !CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ /* keyring.c */ /* * fscrypt_master_key_secret - secret key material of an in-use master key */ struct fscrypt_master_key_secret { /* * The KDF with which subkeys of this key can be derived. * * For v1 policy keys, this isn't applicable and won't be set. * Otherwise, this KDF will be keyed by this master key if * ->is_hw_wrapped=false, or by the "software secret" that hardware * derived from this master key if ->is_hw_wrapped=true. */ struct fscrypt_hkdf hkdf; /* * True if this key is a hardware-wrapped key; false if this key is a * standard key (i.e. a "software key"). For v1 policy keys this will * always be false, as v1 policy support is a legacy feature which * doesn't support newer functionality such as hardware-wrapped keys. */ bool is_hw_wrapped; /* * Size of the raw key in bytes. This remains set even if ->raw was * zeroized due to no longer being needed. I.e. we still remember the * size of the key even if we don't need to remember the key itself. */ u32 size; /* * The raw key which userspace provided, when still needed. This can be * either a standard key or a hardware-wrapped key, as indicated by * ->is_hw_wrapped. In the case of a standard, v2 policy key, there is * no need to remember the raw key separately from ->hkdf so this field * will be zeroized as soon as ->hkdf is initialized. */ u8 raw[FSCRYPT_MAX_ANY_KEY_SIZE]; } __randomize_layout; /* * fscrypt_master_key - an in-use master key * * This represents a master encryption key which has been added to the * filesystem and can be used to "unlock" the encrypted files which were * encrypted with it. */ struct fscrypt_master_key { /* * Link in ->s_master_keys->key_hashtable. * Only valid if ->mk_active_refs > 0. */ struct hlist_node mk_node; /* Semaphore that protects ->mk_secret and ->mk_users */ struct rw_semaphore mk_sem; /* * Active and structural reference counts. An active ref guarantees * that the struct continues to exist, continues to be in the keyring * ->s_master_keys, and that any embedded subkeys (e.g. * ->mk_direct_keys) that have been prepared continue to exist. * A structural ref only guarantees that the struct continues to exist. * * There is one active ref associated with ->mk_secret being present, * and one active ref for each inode in ->mk_decrypted_inodes. * * There is one structural ref associated with the active refcount being * nonzero. Finding a key in the keyring also takes a structural ref, * which is then held temporarily while the key is operated on. */ refcount_t mk_active_refs; refcount_t mk_struct_refs; struct rcu_head mk_rcu_head; /* * The secret key material. After FS_IOC_REMOVE_ENCRYPTION_KEY is * executed, this is wiped and no new inodes can be unlocked with this * key; however, there may still be inodes in ->mk_decrypted_inodes * which could not be evicted. As long as some inodes still remain, * FS_IOC_REMOVE_ENCRYPTION_KEY can be retried, or * FS_IOC_ADD_ENCRYPTION_KEY can add the secret again. * * While ->mk_secret is present, one ref in ->mk_active_refs is held. * * Locking: protected by ->mk_sem. The manipulation of ->mk_active_refs * associated with this field is protected by ->mk_sem as well. */ struct fscrypt_master_key_secret mk_secret; /* * For v1 policy keys: an arbitrary key descriptor which was assigned by * userspace (->descriptor). * * For v2 policy keys: a cryptographic hash of this key (->identifier). */ struct fscrypt_key_specifier mk_spec; /* * Keyring which contains a key of type 'key_type_fscrypt_user' for each * user who has added this key. Normally each key will be added by just * one user, but it's possible that multiple users share a key, and in * that case we need to keep track of those users so that one user can't * remove the key before the others want it removed too. * * This is NULL for v1 policy keys; those can only be added by root. * * Locking: protected by ->mk_sem. (We don't just rely on the keyrings * subsystem semaphore ->mk_users->sem, as we need support for atomic * search+insert along with proper synchronization with ->mk_secret.) */ struct key *mk_users; /* * List of inodes that were unlocked using this key. This allows the * inodes to be evicted efficiently if the key is removed. */ struct list_head mk_decrypted_inodes; spinlock_t mk_decrypted_inodes_lock; /* * Per-mode encryption keys for the various types of encryption policies * that use them. Allocated and derived on-demand. */ struct fscrypt_prepared_key mk_direct_keys[FSCRYPT_MODE_MAX + 1]; struct fscrypt_prepared_key mk_iv_ino_lblk_64_keys[FSCRYPT_MODE_MAX + 1]; struct fscrypt_prepared_key mk_iv_ino_lblk_32_keys[FSCRYPT_MODE_MAX + 1]; /* Hash key for inode numbers. Initialized only when needed. */ siphash_key_t mk_ino_hash_key; bool mk_ino_hash_key_initialized; } __randomize_layout; static inline bool is_master_key_secret_present(const struct fscrypt_master_key_secret *secret) { /* * The READ_ONCE() is only necessary for fscrypt_drop_inode(). * fscrypt_drop_inode() runs in atomic context, so it can't take the key * semaphore and thus 'secret' can change concurrently which would be a * data race. But fscrypt_drop_inode() only need to know whether the * secret *was* present at the time of check, so READ_ONCE() suffices. */ return READ_ONCE(secret->size) != 0; } static inline const char *master_key_spec_type( const struct fscrypt_key_specifier *spec) { switch (spec->type) { case FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR: return "descriptor"; case FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER: return "identifier"; } return "[unknown]"; } static inline int master_key_spec_len(const struct fscrypt_key_specifier *spec) { switch (spec->type) { case FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR: return FSCRYPT_KEY_DESCRIPTOR_SIZE; case FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER: return FSCRYPT_KEY_IDENTIFIER_SIZE; } return 0; } void fscrypt_put_master_key(struct fscrypt_master_key *mk); void fscrypt_put_master_key_activeref(struct super_block *sb, struct fscrypt_master_key *mk); struct fscrypt_master_key * fscrypt_find_master_key(struct super_block *sb, const struct fscrypt_key_specifier *mk_spec); int fscrypt_get_test_dummy_key_identifier( u8 key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]); int fscrypt_add_test_dummy_key(struct super_block *sb, struct fscrypt_key_specifier *key_spec); int fscrypt_verify_key_added(struct super_block *sb, const u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]); int __init fscrypt_init_keyring(void); /* keysetup.c */ struct fscrypt_mode { const char *friendly_name; const char *cipher_str; int keysize; /* key size in bytes */ int security_strength; /* security strength in bytes */ int ivsize; /* IV size in bytes */ int logged_cryptoapi_impl; int logged_blk_crypto_native; int logged_blk_crypto_fallback; enum blk_crypto_mode_num blk_crypto_mode; }; extern struct fscrypt_mode fscrypt_modes[]; int fscrypt_prepare_key(struct fscrypt_prepared_key *prep_key, const u8 *raw_key, const struct fscrypt_info *ci); void fscrypt_destroy_prepared_key(struct super_block *sb, struct fscrypt_prepared_key *prep_key); int fscrypt_set_per_file_enc_key(struct fscrypt_info *ci, const u8 *raw_key); int fscrypt_derive_dirhash_key(struct fscrypt_info *ci, const struct fscrypt_master_key *mk); void fscrypt_hash_inode_number(struct fscrypt_info *ci, const struct fscrypt_master_key *mk); int fscrypt_get_encryption_info(struct inode *inode, bool allow_unsupported); /** * fscrypt_require_key() - require an inode's encryption key * @inode: the inode we need the key for * * If the inode is encrypted, set up its encryption key if not already done. * Then require that the key be present and return -ENOKEY otherwise. * * No locks are needed, and the key will live as long as the struct inode --- so * it won't go away from under you. * * Return: 0 on success, -ENOKEY if the key is missing, or another -errno code * if a problem occurred while setting up the encryption key. */ static inline int fscrypt_require_key(struct inode *inode) { if (IS_ENCRYPTED(inode)) { int err = fscrypt_get_encryption_info(inode, false); if (err) return err; if (!fscrypt_has_encryption_key(inode)) return -ENOKEY; } return 0; } /* keysetup_v1.c */ void fscrypt_put_direct_key(struct fscrypt_direct_key *dk); int fscrypt_setup_v1_file_key(struct fscrypt_info *ci, const u8 *raw_master_key); int fscrypt_setup_v1_file_key_via_subscribed_keyrings(struct fscrypt_info *ci); /* policy.c */ bool fscrypt_policies_equal(const union fscrypt_policy *policy1, const union fscrypt_policy *policy2); int fscrypt_policy_to_key_spec(const union fscrypt_policy *policy, struct fscrypt_key_specifier *key_spec); const union fscrypt_policy *fscrypt_get_dummy_policy(struct super_block *sb); bool fscrypt_supported_policy(const union fscrypt_policy *policy_u, const struct inode *inode); int fscrypt_policy_from_context(union fscrypt_policy *policy_u, const union fscrypt_context *ctx_u, int ctx_size); const union fscrypt_policy *fscrypt_policy_to_inherit(struct inode *dir); #endif /* _FSCRYPT_PRIVATE_H */ |
| 999 999 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_police.c Input police filter * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * J Hadi Salim (action changes) */ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/slab.h> #include <net/act_api.h> #include <net/netlink.h> #include <net/pkt_cls.h> #include <net/tc_act/tc_police.h> /* Each policer is serialized by its individual spinlock */ static struct tc_action_ops act_police_ops; static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { [TCA_POLICE_RATE] = { .len = TC_RTAB_SIZE }, [TCA_POLICE_PEAKRATE] = { .len = TC_RTAB_SIZE }, [TCA_POLICE_AVRATE] = { .type = NLA_U32 }, [TCA_POLICE_RESULT] = { .type = NLA_U32 }, [TCA_POLICE_RATE64] = { .type = NLA_U64 }, [TCA_POLICE_PEAKRATE64] = { .type = NLA_U64 }, [TCA_POLICE_PKTRATE64] = { .type = NLA_U64, .min = 1 }, [TCA_POLICE_PKTBURST64] = { .type = NLA_U64, .min = 1 }, }; static int tcf_police_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { int ret = 0, tcfp_result = TC_ACT_OK, err, size; bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_POLICE_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tc_police *parm; struct tcf_police *police; struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL; struct tc_action_net *tn = net_generic(net, act_police_ops.net_id); struct tcf_police_params *new; bool exists = false; u32 index; u64 rate64, prate64; u64 pps, ppsburst; if (nla == NULL) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_POLICE_MAX, nla, police_policy, NULL); if (err < 0) return err; if (tb[TCA_POLICE_TBF] == NULL) return -EINVAL; size = nla_len(tb[TCA_POLICE_TBF]); if (size != sizeof(*parm) && size != sizeof(struct tc_police_compat)) return -EINVAL; parm = nla_data(tb[TCA_POLICE_TBF]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; if (exists && bind) return 0; if (!exists) { ret = tcf_idr_create(tn, index, NULL, a, &act_police_ops, bind, true, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; spin_lock_init(&(to_police(*a)->tcfp_lock)); } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; police = to_police(*a); if (parm->rate.rate) { err = -ENOMEM; R_tab = qdisc_get_rtab(&parm->rate, tb[TCA_POLICE_RATE], NULL); if (R_tab == NULL) goto failure; if (parm->peakrate.rate) { P_tab = qdisc_get_rtab(&parm->peakrate, tb[TCA_POLICE_PEAKRATE], NULL); if (P_tab == NULL) goto failure; } } if (est) { err = gen_replace_estimator(&police->tcf_bstats, police->common.cpu_bstats, &police->tcf_rate_est, &police->tcf_lock, false, est); if (err) goto failure; } else if (tb[TCA_POLICE_AVRATE] && (ret == ACT_P_CREATED || !gen_estimator_active(&police->tcf_rate_est))) { err = -EINVAL; goto failure; } if (tb[TCA_POLICE_RESULT]) { tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]); if (TC_ACT_EXT_CMP(tcfp_result, TC_ACT_GOTO_CHAIN)) { NL_SET_ERR_MSG(extack, "goto chain not allowed on fallback"); err = -EINVAL; goto failure; } } if ((tb[TCA_POLICE_PKTRATE64] && !tb[TCA_POLICE_PKTBURST64]) || (!tb[TCA_POLICE_PKTRATE64] && tb[TCA_POLICE_PKTBURST64])) { NL_SET_ERR_MSG(extack, "Both or neither packet-per-second burst and rate must be provided"); err = -EINVAL; goto failure; } if (tb[TCA_POLICE_PKTRATE64] && R_tab) { NL_SET_ERR_MSG(extack, "packet-per-second and byte-per-second rate limits not allowed in same action"); err = -EINVAL; goto failure; } new = kzalloc(sizeof(*new), GFP_KERNEL); if (unlikely(!new)) { err = -ENOMEM; goto failure; } /* No failure allowed after this point */ new->tcfp_result = tcfp_result; new->tcfp_mtu = parm->mtu; if (!new->tcfp_mtu) { new->tcfp_mtu = ~0; if (R_tab) new->tcfp_mtu = 255 << R_tab->rate.cell_log; } if (R_tab) { new->rate_present = true; rate64 = tb[TCA_POLICE_RATE64] ? nla_get_u64(tb[TCA_POLICE_RATE64]) : 0; psched_ratecfg_precompute(&new->rate, &R_tab->rate, rate64); qdisc_put_rtab(R_tab); } else { new->rate_present = false; } if (P_tab) { new->peak_present = true; prate64 = tb[TCA_POLICE_PEAKRATE64] ? nla_get_u64(tb[TCA_POLICE_PEAKRATE64]) : 0; psched_ratecfg_precompute(&new->peak, &P_tab->rate, prate64); qdisc_put_rtab(P_tab); } else { new->peak_present = false; } new->tcfp_burst = PSCHED_TICKS2NS(parm->burst); if (new->peak_present) new->tcfp_mtu_ptoks = (s64)psched_l2t_ns(&new->peak, new->tcfp_mtu); if (tb[TCA_POLICE_AVRATE]) new->tcfp_ewma_rate = nla_get_u32(tb[TCA_POLICE_AVRATE]); if (tb[TCA_POLICE_PKTRATE64]) { pps = nla_get_u64(tb[TCA_POLICE_PKTRATE64]); ppsburst = nla_get_u64(tb[TCA_POLICE_PKTBURST64]); new->pps_present = true; new->tcfp_pkt_burst = PSCHED_TICKS2NS(ppsburst); psched_ppscfg_precompute(&new->ppsrate, pps); } spin_lock_bh(&police->tcf_lock); spin_lock_bh(&police->tcfp_lock); police->tcfp_t_c = ktime_get_ns(); police->tcfp_toks = new->tcfp_burst; if (new->peak_present) police->tcfp_ptoks = new->tcfp_mtu_ptoks; spin_unlock_bh(&police->tcfp_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); new = rcu_replace_pointer(police->params, new, lockdep_is_held(&police->tcf_lock)); spin_unlock_bh(&police->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (new) kfree_rcu(new, rcu); return ret; failure: qdisc_put_rtab(P_tab); qdisc_put_rtab(R_tab); if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*a, bind); return err; } static bool tcf_police_mtu_check(struct sk_buff *skb, u32 limit) { u32 len; if (skb_is_gso(skb)) return skb_gso_validate_mac_len(skb, limit); len = qdisc_pkt_len(skb); if (skb_at_tc_ingress(skb)) len += skb->mac_len; return len <= limit; } static int tcf_police_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_police *police = to_police(a); s64 now, toks, ppstoks = 0, ptoks = 0; struct tcf_police_params *p; int ret; tcf_lastuse_update(&police->tcf_tm); bstats_update(this_cpu_ptr(police->common.cpu_bstats), skb); ret = READ_ONCE(police->tcf_action); p = rcu_dereference_bh(police->params); if (p->tcfp_ewma_rate) { struct gnet_stats_rate_est64 sample; if (!gen_estimator_read(&police->tcf_rate_est, &sample) || sample.bps >= p->tcfp_ewma_rate) goto inc_overlimits; } if (tcf_police_mtu_check(skb, p->tcfp_mtu)) { if (!p->rate_present && !p->pps_present) { ret = p->tcfp_result; goto end; } now = ktime_get_ns(); spin_lock_bh(&police->tcfp_lock); toks = min_t(s64, now - police->tcfp_t_c, p->tcfp_burst); if (p->peak_present) { ptoks = toks + police->tcfp_ptoks; if (ptoks > p->tcfp_mtu_ptoks) ptoks = p->tcfp_mtu_ptoks; ptoks -= (s64)psched_l2t_ns(&p->peak, qdisc_pkt_len(skb)); } if (p->rate_present) { toks += police->tcfp_toks; if (toks > p->tcfp_burst) toks = p->tcfp_burst; toks -= (s64)psched_l2t_ns(&p->rate, qdisc_pkt_len(skb)); } else if (p->pps_present) { ppstoks = min_t(s64, now - police->tcfp_t_c, p->tcfp_pkt_burst); ppstoks += police->tcfp_pkttoks; if (ppstoks > p->tcfp_pkt_burst) ppstoks = p->tcfp_pkt_burst; ppstoks -= (s64)psched_pkt2t_ns(&p->ppsrate, 1); } if ((toks | ptoks | ppstoks) >= 0) { police->tcfp_t_c = now; police->tcfp_toks = toks; police->tcfp_ptoks = ptoks; police->tcfp_pkttoks = ppstoks; spin_unlock_bh(&police->tcfp_lock); ret = p->tcfp_result; goto inc_drops; } spin_unlock_bh(&police->tcfp_lock); } inc_overlimits: qstats_overlimit_inc(this_cpu_ptr(police->common.cpu_qstats)); inc_drops: if (ret == TC_ACT_SHOT) qstats_drop_inc(this_cpu_ptr(police->common.cpu_qstats)); end: return ret; } static void tcf_police_cleanup(struct tc_action *a) { struct tcf_police *police = to_police(a); struct tcf_police_params *p; p = rcu_dereference_protected(police->params, 1); if (p) kfree_rcu(p, rcu); } static void tcf_police_stats_update(struct tc_action *a, u64 bytes, u64 packets, u64 drops, u64 lastuse, bool hw) { struct tcf_police *police = to_police(a); struct tcf_t *tm = &police->tcf_tm; tcf_action_update_stats(a, bytes, packets, drops, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_police *police = to_police(a); struct tcf_police_params *p; struct tc_police opt = { .index = police->tcf_index, .refcnt = refcount_read(&police->tcf_refcnt) - ref, .bindcnt = atomic_read(&police->tcf_bindcnt) - bind, }; struct tcf_t t; spin_lock_bh(&police->tcf_lock); opt.action = police->tcf_action; p = rcu_dereference_protected(police->params, lockdep_is_held(&police->tcf_lock)); opt.mtu = p->tcfp_mtu; opt.burst = PSCHED_NS2TICKS(p->tcfp_burst); if (p->rate_present) { psched_ratecfg_getrate(&opt.rate, &p->rate); if ((p->rate.rate_bytes_ps >= (1ULL << 32)) && nla_put_u64_64bit(skb, TCA_POLICE_RATE64, p->rate.rate_bytes_ps, TCA_POLICE_PAD)) goto nla_put_failure; } if (p->peak_present) { psched_ratecfg_getrate(&opt.peakrate, &p->peak); if ((p->peak.rate_bytes_ps >= (1ULL << 32)) && nla_put_u64_64bit(skb, TCA_POLICE_PEAKRATE64, p->peak.rate_bytes_ps, TCA_POLICE_PAD)) goto nla_put_failure; } if (p->pps_present) { if (nla_put_u64_64bit(skb, TCA_POLICE_PKTRATE64, p->ppsrate.rate_pkts_ps, TCA_POLICE_PAD)) goto nla_put_failure; if (nla_put_u64_64bit(skb, TCA_POLICE_PKTBURST64, PSCHED_NS2TICKS(p->tcfp_pkt_burst), TCA_POLICE_PAD)) goto nla_put_failure; } if (nla_put(skb, TCA_POLICE_TBF, sizeof(opt), &opt)) goto nla_put_failure; if (p->tcfp_result && nla_put_u32(skb, TCA_POLICE_RESULT, p->tcfp_result)) goto nla_put_failure; if (p->tcfp_ewma_rate && nla_put_u32(skb, TCA_POLICE_AVRATE, p->tcfp_ewma_rate)) goto nla_put_failure; tcf_tm_dump(&t, &police->tcf_tm); if (nla_put_64bit(skb, TCA_POLICE_TM, sizeof(t), &t, TCA_POLICE_PAD)) goto nla_put_failure; spin_unlock_bh(&police->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&police->tcf_lock); nlmsg_trim(skb, b); return -1; } static int tcf_police_act_to_flow_act(int tc_act, u32 *extval, struct netlink_ext_ack *extack) { int act_id = -EOPNOTSUPP; if (!TC_ACT_EXT_OPCODE(tc_act)) { if (tc_act == TC_ACT_OK) act_id = FLOW_ACTION_ACCEPT; else if (tc_act == TC_ACT_SHOT) act_id = FLOW_ACTION_DROP; else if (tc_act == TC_ACT_PIPE) act_id = FLOW_ACTION_PIPE; else if (tc_act == TC_ACT_RECLASSIFY) NL_SET_ERR_MSG_MOD(extack, "Offload not supported when conform/exceed action is \"reclassify\""); else NL_SET_ERR_MSG_MOD(extack, "Unsupported conform/exceed action offload"); } else if (TC_ACT_EXT_CMP(tc_act, TC_ACT_GOTO_CHAIN)) { act_id = FLOW_ACTION_GOTO; *extval = tc_act & TC_ACT_EXT_VAL_MASK; } else if (TC_ACT_EXT_CMP(tc_act, TC_ACT_JUMP)) { act_id = FLOW_ACTION_JUMP; *extval = tc_act & TC_ACT_EXT_VAL_MASK; } else if (tc_act == TC_ACT_UNSPEC) { act_id = FLOW_ACTION_CONTINUE; } else { NL_SET_ERR_MSG_MOD(extack, "Unsupported conform/exceed action offload"); } return act_id; } static int tcf_police_offload_act_setup(struct tc_action *act, void *entry_data, u32 *index_inc, bool bind, struct netlink_ext_ack *extack) { if (bind) { struct flow_action_entry *entry = entry_data; struct tcf_police *police = to_police(act); struct tcf_police_params *p; int act_id; p = rcu_dereference_protected(police->params, lockdep_is_held(&police->tcf_lock)); entry->id = FLOW_ACTION_POLICE; entry->police.burst = tcf_police_burst(act); entry->police.rate_bytes_ps = tcf_police_rate_bytes_ps(act); entry->police.peakrate_bytes_ps = tcf_police_peakrate_bytes_ps(act); entry->police.avrate = tcf_police_tcfp_ewma_rate(act); entry->police.overhead = tcf_police_rate_overhead(act); entry->police.burst_pkt = tcf_police_burst_pkt(act); entry->police.rate_pkt_ps = tcf_police_rate_pkt_ps(act); entry->police.mtu = tcf_police_tcfp_mtu(act); act_id = tcf_police_act_to_flow_act(police->tcf_action, &entry->police.exceed.extval, extack); if (act_id < 0) return act_id; entry->police.exceed.act_id = act_id; act_id = tcf_police_act_to_flow_act(p->tcfp_result, &entry->police.notexceed.extval, extack); if (act_id < 0) return act_id; entry->police.notexceed.act_id = act_id; *index_inc = 1; } else { struct flow_offload_action *fl_action = entry_data; fl_action->id = FLOW_ACTION_POLICE; } return 0; } MODULE_AUTHOR("Alexey Kuznetsov"); MODULE_DESCRIPTION("Policing actions"); MODULE_LICENSE("GPL"); static struct tc_action_ops act_police_ops = { .kind = "police", .id = TCA_ID_POLICE, .owner = THIS_MODULE, .stats_update = tcf_police_stats_update, .act = tcf_police_act, .dump = tcf_police_dump, .init = tcf_police_init, .cleanup = tcf_police_cleanup, .offload_act_setup = tcf_police_offload_act_setup, .size = sizeof(struct tcf_police), }; static __net_init int police_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_police_ops.net_id); return tc_action_net_init(net, tn, &act_police_ops); } static void __net_exit police_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_police_ops.net_id); } static struct pernet_operations police_net_ops = { .init = police_init_net, .exit_batch = police_exit_net, .id = &act_police_ops.net_id, .size = sizeof(struct tc_action_net), }; static int __init police_init_module(void) { return tcf_register_action(&act_police_ops, &police_net_ops); } static void __exit police_cleanup_module(void) { tcf_unregister_action(&act_police_ops, &police_net_ops); } module_init(police_init_module); module_exit(police_cleanup_module); |
| 73 73 73 73 73 67 67 67 9 4 5 5 5 5 5 5 1 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include "queueing.h" #include "socket.h" #include "timers.h" #include "device.h" #include "ratelimiter.h" #include "peer.h" #include "messages.h" #include <linux/module.h> #include <linux/rtnetlink.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/if_arp.h> #include <linux/icmp.h> #include <linux/suspend.h> #include <net/dst_metadata.h> #include <net/icmp.h> #include <net/rtnetlink.h> #include <net/ip_tunnels.h> #include <net/addrconf.h> static LIST_HEAD(device_list); static int wg_open(struct net_device *dev) { struct in_device *dev_v4 = __in_dev_get_rtnl(dev); struct inet6_dev *dev_v6 = __in6_dev_get(dev); struct wg_device *wg = netdev_priv(dev); struct wg_peer *peer; int ret; if (dev_v4) { /* At some point we might put this check near the ip_rt_send_ * redirect call of ip_forward in net/ipv4/ip_forward.c, similar * to the current secpath check. */ IN_DEV_CONF_SET(dev_v4, SEND_REDIRECTS, false); IPV4_DEVCONF_ALL(dev_net(dev), SEND_REDIRECTS) = false; } if (dev_v6) dev_v6->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_NONE; mutex_lock(&wg->device_update_lock); ret = wg_socket_init(wg, wg->incoming_port); if (ret < 0) goto out; list_for_each_entry(peer, &wg->peer_list, peer_list) { wg_packet_send_staged_packets(peer); if (peer->persistent_keepalive_interval) wg_packet_send_keepalive(peer); } out: mutex_unlock(&wg->device_update_lock); return ret; } static int wg_pm_notification(struct notifier_block *nb, unsigned long action, void *data) { struct wg_device *wg; struct wg_peer *peer; /* If the machine is constantly suspending and resuming, as part of * its normal operation rather than as a somewhat rare event, then we * don't actually want to clear keys. */ if (IS_ENABLED(CONFIG_PM_AUTOSLEEP) || IS_ENABLED(CONFIG_PM_USERSPACE_AUTOSLEEP)) return 0; if (action != PM_HIBERNATION_PREPARE && action != PM_SUSPEND_PREPARE) return 0; rtnl_lock(); list_for_each_entry(wg, &device_list, device_list) { mutex_lock(&wg->device_update_lock); list_for_each_entry(peer, &wg->peer_list, peer_list) { del_timer(&peer->timer_zero_key_material); wg_noise_handshake_clear(&peer->handshake); wg_noise_keypairs_clear(&peer->keypairs); } mutex_unlock(&wg->device_update_lock); } rtnl_unlock(); rcu_barrier(); return 0; } static struct notifier_block pm_notifier = { .notifier_call = wg_pm_notification }; static int wg_vm_notification(struct notifier_block *nb, unsigned long action, void *data) { struct wg_device *wg; struct wg_peer *peer; rtnl_lock(); list_for_each_entry(wg, &device_list, device_list) { mutex_lock(&wg->device_update_lock); list_for_each_entry(peer, &wg->peer_list, peer_list) wg_noise_expire_current_peer_keypairs(peer); mutex_unlock(&wg->device_update_lock); } rtnl_unlock(); return 0; } static struct notifier_block vm_notifier = { .notifier_call = wg_vm_notification }; static int wg_stop(struct net_device *dev) { struct wg_device *wg = netdev_priv(dev); struct wg_peer *peer; struct sk_buff *skb; mutex_lock(&wg->device_update_lock); list_for_each_entry(peer, &wg->peer_list, peer_list) { wg_packet_purge_staged_packets(peer); wg_timers_stop(peer); wg_noise_handshake_clear(&peer->handshake); wg_noise_keypairs_clear(&peer->keypairs); wg_noise_reset_last_sent_handshake(&peer->last_sent_handshake); } mutex_unlock(&wg->device_update_lock); while ((skb = ptr_ring_consume(&wg->handshake_queue.ring)) != NULL) kfree_skb(skb); atomic_set(&wg->handshake_queue_len, 0); wg_socket_reinit(wg, NULL, NULL); return 0; } static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev) { struct wg_device *wg = netdev_priv(dev); struct sk_buff_head packets; struct wg_peer *peer; struct sk_buff *next; sa_family_t family; u32 mtu; int ret; if (unlikely(!wg_check_packet_protocol(skb))) { ret = -EPROTONOSUPPORT; net_dbg_ratelimited("%s: Invalid IP packet\n", dev->name); goto err; } peer = wg_allowedips_lookup_dst(&wg->peer_allowedips, skb); if (unlikely(!peer)) { ret = -ENOKEY; if (skb->protocol == htons(ETH_P_IP)) net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI4\n", dev->name, &ip_hdr(skb)->daddr); else if (skb->protocol == htons(ETH_P_IPV6)) net_dbg_ratelimited("%s: No peer has allowed IPs matching %pI6\n", dev->name, &ipv6_hdr(skb)->daddr); goto err_icmp; } family = READ_ONCE(peer->endpoint.addr.sa_family); if (unlikely(family != AF_INET && family != AF_INET6)) { ret = -EDESTADDRREQ; net_dbg_ratelimited("%s: No valid endpoint has been configured or discovered for peer %llu\n", dev->name, peer->internal_id); goto err_peer; } mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; __skb_queue_head_init(&packets); if (!skb_is_gso(skb)) { skb_mark_not_on_list(skb); } else { struct sk_buff *segs = skb_gso_segment(skb, 0); if (IS_ERR(segs)) { ret = PTR_ERR(segs); goto err_peer; } dev_kfree_skb(skb); skb = segs; } skb_list_walk_safe(skb, skb, next) { skb_mark_not_on_list(skb); skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) continue; /* We only need to keep the original dst around for icmp, * so at this point we're in a position to drop it. */ skb_dst_drop(skb); PACKET_CB(skb)->mtu = mtu; __skb_queue_tail(&packets, skb); } spin_lock_bh(&peer->staged_packet_queue.lock); /* If the queue is getting too big, we start removing the oldest packets * until it's small again. We do this before adding the new packet, so * we don't remove GSO segments that are in excess. */ while (skb_queue_len(&peer->staged_packet_queue) > MAX_STAGED_PACKETS) { dev_kfree_skb(__skb_dequeue(&peer->staged_packet_queue)); DEV_STATS_INC(dev, tx_dropped); } skb_queue_splice_tail(&packets, &peer->staged_packet_queue); spin_unlock_bh(&peer->staged_packet_queue.lock); wg_packet_send_staged_packets(peer); wg_peer_put(peer); return NETDEV_TX_OK; err_peer: wg_peer_put(peer); err_icmp: if (skb->protocol == htons(ETH_P_IP)) icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); else if (skb->protocol == htons(ETH_P_IPV6)) icmpv6_ndo_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); err: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return ret; } static const struct net_device_ops netdev_ops = { .ndo_open = wg_open, .ndo_stop = wg_stop, .ndo_start_xmit = wg_xmit, .ndo_get_stats64 = dev_get_tstats64 }; static void wg_destruct(struct net_device *dev) { struct wg_device *wg = netdev_priv(dev); rtnl_lock(); list_del(&wg->device_list); rtnl_unlock(); mutex_lock(&wg->device_update_lock); rcu_assign_pointer(wg->creating_net, NULL); wg->incoming_port = 0; wg_socket_reinit(wg, NULL, NULL); /* The final references are cleared in the below calls to destroy_workqueue. */ wg_peer_remove_all(wg); destroy_workqueue(wg->handshake_receive_wq); destroy_workqueue(wg->handshake_send_wq); destroy_workqueue(wg->packet_crypt_wq); wg_packet_queue_free(&wg->handshake_queue, true); wg_packet_queue_free(&wg->decrypt_queue, false); wg_packet_queue_free(&wg->encrypt_queue, false); rcu_barrier(); /* Wait for all the peers to be actually freed. */ wg_ratelimiter_uninit(); memzero_explicit(&wg->static_identity, sizeof(wg->static_identity)); free_percpu(dev->tstats); kvfree(wg->index_hashtable); kvfree(wg->peer_hashtable); mutex_unlock(&wg->device_update_lock); pr_debug("%s: Interface destroyed\n", dev->name); free_netdev(dev); } static const struct device_type device_type = { .name = KBUILD_MODNAME }; static void wg_setup(struct net_device *dev) { struct wg_device *wg = netdev_priv(dev); enum { WG_NETDEV_FEATURES = NETIF_F_HW_CSUM | NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO | NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA }; const int overhead = MESSAGE_MINIMUM_LENGTH + sizeof(struct udphdr) + max(sizeof(struct ipv6hdr), sizeof(struct iphdr)); dev->netdev_ops = &netdev_ops; dev->header_ops = &ip_tunnel_header_ops; dev->hard_header_len = 0; dev->addr_len = 0; dev->needed_headroom = DATA_PACKET_HEAD_ROOM; dev->needed_tailroom = noise_encrypted_len(MESSAGE_PADDING_MULTIPLE); dev->type = ARPHRD_NONE; dev->flags = IFF_POINTOPOINT | IFF_NOARP; dev->priv_flags |= IFF_NO_QUEUE; dev->features |= NETIF_F_LLTX; dev->features |= WG_NETDEV_FEATURES; dev->hw_features |= WG_NETDEV_FEATURES; dev->hw_enc_features |= WG_NETDEV_FEATURES; dev->mtu = ETH_DATA_LEN - overhead; dev->max_mtu = round_down(INT_MAX, MESSAGE_PADDING_MULTIPLE) - overhead; SET_NETDEV_DEVTYPE(dev, &device_type); /* We need to keep the dst around in case of icmp replies. */ netif_keep_dst(dev); memset(wg, 0, sizeof(*wg)); wg->dev = dev; } static int wg_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct wg_device *wg = netdev_priv(dev); int ret = -ENOMEM; rcu_assign_pointer(wg->creating_net, src_net); init_rwsem(&wg->static_identity.lock); mutex_init(&wg->socket_update_lock); mutex_init(&wg->device_update_lock); wg_allowedips_init(&wg->peer_allowedips); wg_cookie_checker_init(&wg->cookie_checker, wg); INIT_LIST_HEAD(&wg->peer_list); wg->device_update_gen = 1; wg->peer_hashtable = wg_pubkey_hashtable_alloc(); if (!wg->peer_hashtable) return ret; wg->index_hashtable = wg_index_hashtable_alloc(); if (!wg->index_hashtable) goto err_free_peer_hashtable; dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) goto err_free_index_hashtable; wg->handshake_receive_wq = alloc_workqueue("wg-kex-%s", WQ_CPU_INTENSIVE | WQ_FREEZABLE, 0, dev->name); if (!wg->handshake_receive_wq) goto err_free_tstats; wg->handshake_send_wq = alloc_workqueue("wg-kex-%s", WQ_UNBOUND | WQ_FREEZABLE, 0, dev->name); if (!wg->handshake_send_wq) goto err_destroy_handshake_receive; wg->packet_crypt_wq = alloc_workqueue("wg-crypt-%s", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 0, dev->name); if (!wg->packet_crypt_wq) goto err_destroy_handshake_send; ret = wg_packet_queue_init(&wg->encrypt_queue, wg_packet_encrypt_worker, MAX_QUEUED_PACKETS); if (ret < 0) goto err_destroy_packet_crypt; ret = wg_packet_queue_init(&wg->decrypt_queue, wg_packet_decrypt_worker, MAX_QUEUED_PACKETS); if (ret < 0) goto err_free_encrypt_queue; ret = wg_packet_queue_init(&wg->handshake_queue, wg_packet_handshake_receive_worker, MAX_QUEUED_INCOMING_HANDSHAKES); if (ret < 0) goto err_free_decrypt_queue; ret = wg_ratelimiter_init(); if (ret < 0) goto err_free_handshake_queue; ret = register_netdevice(dev); if (ret < 0) goto err_uninit_ratelimiter; list_add(&wg->device_list, &device_list); /* We wait until the end to assign priv_destructor, so that * register_netdevice doesn't call it for us if it fails. */ dev->priv_destructor = wg_destruct; pr_debug("%s: Interface created\n", dev->name); return ret; err_uninit_ratelimiter: wg_ratelimiter_uninit(); err_free_handshake_queue: wg_packet_queue_free(&wg->handshake_queue, false); err_free_decrypt_queue: wg_packet_queue_free(&wg->decrypt_queue, false); err_free_encrypt_queue: wg_packet_queue_free(&wg->encrypt_queue, false); err_destroy_packet_crypt: destroy_workqueue(wg->packet_crypt_wq); err_destroy_handshake_send: destroy_workqueue(wg->handshake_send_wq); err_destroy_handshake_receive: destroy_workqueue(wg->handshake_receive_wq); err_free_tstats: free_percpu(dev->tstats); err_free_index_hashtable: kvfree(wg->index_hashtable); err_free_peer_hashtable: kvfree(wg->peer_hashtable); return ret; } static struct rtnl_link_ops link_ops __read_mostly = { .kind = KBUILD_MODNAME, .priv_size = sizeof(struct wg_device), .setup = wg_setup, .newlink = wg_newlink, }; static void wg_netns_pre_exit(struct net *net) { struct wg_device *wg; struct wg_peer *peer; rtnl_lock(); list_for_each_entry(wg, &device_list, device_list) { if (rcu_access_pointer(wg->creating_net) == net) { pr_debug("%s: Creating namespace exiting\n", wg->dev->name); netif_carrier_off(wg->dev); mutex_lock(&wg->device_update_lock); rcu_assign_pointer(wg->creating_net, NULL); wg_socket_reinit(wg, NULL, NULL); list_for_each_entry(peer, &wg->peer_list, peer_list) wg_socket_clear_peer_endpoint_src(peer); mutex_unlock(&wg->device_update_lock); } } rtnl_unlock(); } static struct pernet_operations pernet_ops = { .pre_exit = wg_netns_pre_exit }; int __init wg_device_init(void) { int ret; ret = register_pm_notifier(&pm_notifier); if (ret) return ret; ret = register_random_vmfork_notifier(&vm_notifier); if (ret) goto error_pm; ret = register_pernet_device(&pernet_ops); if (ret) goto error_vm; ret = rtnl_link_register(&link_ops); if (ret) goto error_pernet; return 0; error_pernet: unregister_pernet_device(&pernet_ops); error_vm: unregister_random_vmfork_notifier(&vm_notifier); error_pm: unregister_pm_notifier(&pm_notifier); return ret; } void wg_device_uninit(void) { rtnl_link_unregister(&link_ops); unregister_pernet_device(&pernet_ops); unregister_random_vmfork_notifier(&vm_notifier); unregister_pm_notifier(&pm_notifier); rcu_barrier(); } |
| 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/profile.c * Simple profiling. Manages a direct-mapped profile hit count buffer, * with configurable resolution, support for restricting the cpus on * which profiling is done, and switching between cpu time and * schedule() calls via kernel command line parameters passed at boot. * * Scheduler profiling support, Arjan van de Ven and Ingo Molnar, * Red Hat, July 2004 * Consolidation of architecture support code for profiling, * Nadia Yvette Chambers, Oracle, July 2004 * Amortized hit count accounting via per-cpu open-addressed hashtables * to resolve timer interrupt livelocks, Nadia Yvette Chambers, * Oracle, 2004 */ #include <linux/export.h> #include <linux/profile.h> #include <linux/memblock.h> #include <linux/notifier.h> #include <linux/mm.h> #include <linux/cpumask.h> #include <linux/cpu.h> #include <linux/highmem.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/sched/stat.h> #include <asm/sections.h> #include <asm/irq_regs.h> #include <asm/ptrace.h> struct profile_hit { u32 pc, hits; }; #define PROFILE_GRPSHIFT 3 #define PROFILE_GRPSZ (1 << PROFILE_GRPSHIFT) #define NR_PROFILE_HIT (PAGE_SIZE/sizeof(struct profile_hit)) #define NR_PROFILE_GRP (NR_PROFILE_HIT/PROFILE_GRPSZ) static atomic_t *prof_buffer; static unsigned long prof_len; static unsigned short int prof_shift; int prof_on __read_mostly; EXPORT_SYMBOL_GPL(prof_on); static cpumask_var_t prof_cpu_mask; #if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS) static DEFINE_PER_CPU(struct profile_hit *[2], cpu_profile_hits); static DEFINE_PER_CPU(int, cpu_profile_flip); static DEFINE_MUTEX(profile_flip_mutex); #endif /* CONFIG_SMP */ int profile_setup(char *str) { static const char schedstr[] = "schedule"; static const char kvmstr[] = "kvm"; const char *select = NULL; int par; if (!strncmp(str, schedstr, strlen(schedstr))) { prof_on = SCHED_PROFILING; select = schedstr; } else if (!strncmp(str, kvmstr, strlen(kvmstr))) { prof_on = KVM_PROFILING; select = kvmstr; } else if (get_option(&str, &par)) { prof_shift = clamp(par, 0, BITS_PER_LONG - 1); prof_on = CPU_PROFILING; pr_info("kernel profiling enabled (shift: %u)\n", prof_shift); } if (select) { if (str[strlen(select)] == ',') str += strlen(select) + 1; if (get_option(&str, &par)) prof_shift = clamp(par, 0, BITS_PER_LONG - 1); pr_info("kernel %s profiling enabled (shift: %u)\n", select, prof_shift); } return 1; } __setup("profile=", profile_setup); int __ref profile_init(void) { int buffer_bytes; if (!prof_on) return 0; /* only text is profiled */ prof_len = (_etext - _stext) >> prof_shift; if (!prof_len) { pr_warn("profiling shift: %u too large\n", prof_shift); prof_on = 0; return -EINVAL; } buffer_bytes = prof_len*sizeof(atomic_t); if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL)) return -ENOMEM; cpumask_copy(prof_cpu_mask, cpu_possible_mask); prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL|__GFP_NOWARN); if (prof_buffer) return 0; prof_buffer = alloc_pages_exact(buffer_bytes, GFP_KERNEL|__GFP_ZERO|__GFP_NOWARN); if (prof_buffer) return 0; prof_buffer = vzalloc(buffer_bytes); if (prof_buffer) return 0; free_cpumask_var(prof_cpu_mask); return -ENOMEM; } /* Profile event notifications */ static BLOCKING_NOTIFIER_HEAD(task_exit_notifier); static BLOCKING_NOTIFIER_HEAD(munmap_notifier); void profile_task_exit(struct task_struct *task) { blocking_notifier_call_chain(&task_exit_notifier, 0, task); } void profile_munmap(unsigned long addr) { blocking_notifier_call_chain(&munmap_notifier, 0, (void *)addr); } int profile_event_register(enum profile_type type, struct notifier_block *n) { int err = -EINVAL; switch (type) { case PROFILE_TASK_EXIT: err = blocking_notifier_chain_register( &task_exit_notifier, n); break; case PROFILE_MUNMAP: err = blocking_notifier_chain_register( &munmap_notifier, n); break; } return err; } EXPORT_SYMBOL_GPL(profile_event_register); int profile_event_unregister(enum profile_type type, struct notifier_block *n) { int err = -EINVAL; switch (type) { case PROFILE_TASK_EXIT: err = blocking_notifier_chain_unregister( &task_exit_notifier, n); break; case PROFILE_MUNMAP: err = blocking_notifier_chain_unregister( &munmap_notifier, n); break; } return err; } EXPORT_SYMBOL_GPL(profile_event_unregister); #if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS) /* * Each cpu has a pair of open-addressed hashtables for pending * profile hits. read_profile() IPI's all cpus to request them * to flip buffers and flushes their contents to prof_buffer itself. * Flip requests are serialized by the profile_flip_mutex. The sole * use of having a second hashtable is for avoiding cacheline * contention that would otherwise happen during flushes of pending * profile hits required for the accuracy of reported profile hits * and so resurrect the interrupt livelock issue. * * The open-addressed hashtables are indexed by profile buffer slot * and hold the number of pending hits to that profile buffer slot on * a cpu in an entry. When the hashtable overflows, all pending hits * are accounted to their corresponding profile buffer slots with * atomic_add() and the hashtable emptied. As numerous pending hits * may be accounted to a profile buffer slot in a hashtable entry, * this amortizes a number of atomic profile buffer increments likely * to be far larger than the number of entries in the hashtable, * particularly given that the number of distinct profile buffer * positions to which hits are accounted during short intervals (e.g. * several seconds) is usually very small. Exclusion from buffer * flipping is provided by interrupt disablement (note that for * SCHED_PROFILING or SLEEP_PROFILING profile_hit() may be called from * process context). * The hash function is meant to be lightweight as opposed to strong, * and was vaguely inspired by ppc64 firmware-supported inverted * pagetable hash functions, but uses a full hashtable full of finite * collision chains, not just pairs of them. * * -- nyc */ static void __profile_flip_buffers(void *unused) { int cpu = smp_processor_id(); per_cpu(cpu_profile_flip, cpu) = !per_cpu(cpu_profile_flip, cpu); } static void profile_flip_buffers(void) { int i, j, cpu; mutex_lock(&profile_flip_mutex); j = per_cpu(cpu_profile_flip, get_cpu()); put_cpu(); on_each_cpu(__profile_flip_buffers, NULL, 1); for_each_online_cpu(cpu) { struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[j]; for (i = 0; i < NR_PROFILE_HIT; ++i) { if (!hits[i].hits) { if (hits[i].pc) hits[i].pc = 0; continue; } atomic_add(hits[i].hits, &prof_buffer[hits[i].pc]); hits[i].hits = hits[i].pc = 0; } } mutex_unlock(&profile_flip_mutex); } static void profile_discard_flip_buffers(void) { int i, cpu; mutex_lock(&profile_flip_mutex); i = per_cpu(cpu_profile_flip, get_cpu()); put_cpu(); on_each_cpu(__profile_flip_buffers, NULL, 1); for_each_online_cpu(cpu) { struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[i]; memset(hits, 0, NR_PROFILE_HIT*sizeof(struct profile_hit)); } mutex_unlock(&profile_flip_mutex); } static void do_profile_hits(int type, void *__pc, unsigned int nr_hits) { unsigned long primary, secondary, flags, pc = (unsigned long)__pc; int i, j, cpu; struct profile_hit *hits; pc = min((pc - (unsigned long)_stext) >> prof_shift, prof_len - 1); i = primary = (pc & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT; secondary = (~(pc << 1) & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT; cpu = get_cpu(); hits = per_cpu(cpu_profile_hits, cpu)[per_cpu(cpu_profile_flip, cpu)]; if (!hits) { put_cpu(); return; } /* * We buffer the global profiler buffer into a per-CPU * queue and thus reduce the number of global (and possibly * NUMA-alien) accesses. The write-queue is self-coalescing: */ local_irq_save(flags); do { for (j = 0; j < PROFILE_GRPSZ; ++j) { if (hits[i + j].pc == pc) { hits[i + j].hits += nr_hits; goto out; } else if (!hits[i + j].hits) { hits[i + j].pc = pc; hits[i + j].hits = nr_hits; goto out; } } i = (i + secondary) & (NR_PROFILE_HIT - 1); } while (i != primary); /* * Add the current hit(s) and flush the write-queue out * to the global buffer: */ atomic_add(nr_hits, &prof_buffer[pc]); for (i = 0; i < NR_PROFILE_HIT; ++i) { atomic_add(hits[i].hits, &prof_buffer[hits[i].pc]); hits[i].pc = hits[i].hits = 0; } out: local_irq_restore(flags); put_cpu(); } static int profile_dead_cpu(unsigned int cpu) { struct page *page; int i; if (cpumask_available(prof_cpu_mask)) cpumask_clear_cpu(cpu, prof_cpu_mask); for (i = 0; i < 2; i++) { if (per_cpu(cpu_profile_hits, cpu)[i]) { page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[i]); per_cpu(cpu_profile_hits, cpu)[i] = NULL; __free_page(page); } } return 0; } static int profile_prepare_cpu(unsigned int cpu) { int i, node = cpu_to_mem(cpu); struct page *page; per_cpu(cpu_profile_flip, cpu) = 0; for (i = 0; i < 2; i++) { if (per_cpu(cpu_profile_hits, cpu)[i]) continue; page = __alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0); if (!page) { profile_dead_cpu(cpu); return -ENOMEM; } per_cpu(cpu_profile_hits, cpu)[i] = page_address(page); } return 0; } static int profile_online_cpu(unsigned int cpu) { if (cpumask_available(prof_cpu_mask)) cpumask_set_cpu(cpu, prof_cpu_mask); return 0; } #else /* !CONFIG_SMP */ #define profile_flip_buffers() do { } while (0) #define profile_discard_flip_buffers() do { } while (0) static void do_profile_hits(int type, void *__pc, unsigned int nr_hits) { unsigned long pc; pc = ((unsigned long)__pc - (unsigned long)_stext) >> prof_shift; atomic_add(nr_hits, &prof_buffer[min(pc, prof_len - 1)]); } #endif /* !CONFIG_SMP */ void profile_hits(int type, void *__pc, unsigned int nr_hits) { if (prof_on != type || !prof_buffer) return; do_profile_hits(type, __pc, nr_hits); } EXPORT_SYMBOL_GPL(profile_hits); void profile_tick(int type) { struct pt_regs *regs = get_irq_regs(); if (!user_mode(regs) && cpumask_available(prof_cpu_mask) && cpumask_test_cpu(smp_processor_id(), prof_cpu_mask)) profile_hit(type, (void *)profile_pc(regs)); } #ifdef CONFIG_PROC_FS #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/uaccess.h> static int prof_cpu_mask_proc_show(struct seq_file *m, void *v) { seq_printf(m, "%*pb\n", cpumask_pr_args(prof_cpu_mask)); return 0; } static int prof_cpu_mask_proc_open(struct inode *inode, struct file *file) { return single_open(file, prof_cpu_mask_proc_show, NULL); } static ssize_t prof_cpu_mask_proc_write(struct file *file, const char __user *buffer, size_t count, loff_t *pos) { cpumask_var_t new_value; int err; if (!zalloc_cpumask_var(&new_value, GFP_KERNEL)) return -ENOMEM; err = cpumask_parse_user(buffer, count, new_value); if (!err) { cpumask_copy(prof_cpu_mask, new_value); err = count; } free_cpumask_var(new_value); return err; } static const struct proc_ops prof_cpu_mask_proc_ops = { .proc_open = prof_cpu_mask_proc_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = single_release, .proc_write = prof_cpu_mask_proc_write, }; void create_prof_cpu_mask(void) { /* create /proc/irq/prof_cpu_mask */ proc_create("irq/prof_cpu_mask", 0600, NULL, &prof_cpu_mask_proc_ops); } /* * This function accesses profiling information. The returned data is * binary: the sampling step and the actual contents of the profile * buffer. Use of the program readprofile is recommended in order to * get meaningful info out of these data. */ static ssize_t read_profile(struct file *file, char __user *buf, size_t count, loff_t *ppos) { unsigned long p = *ppos; ssize_t read; char *pnt; unsigned long sample_step = 1UL << prof_shift; profile_flip_buffers(); if (p >= (prof_len+1)*sizeof(unsigned int)) return 0; if (count > (prof_len+1)*sizeof(unsigned int) - p) count = (prof_len+1)*sizeof(unsigned int) - p; read = 0; while (p < sizeof(unsigned int) && count > 0) { if (put_user(*((char *)(&sample_step)+p), buf)) return -EFAULT; buf++; p++; count--; read++; } pnt = (char *)prof_buffer + p - sizeof(atomic_t); if (copy_to_user(buf, (void *)pnt, count)) return -EFAULT; read += count; *ppos += read; return read; } /* default is to not implement this call */ int __weak setup_profiling_timer(unsigned mult) { return -EINVAL; } /* * Writing to /proc/profile resets the counters * * Writing a 'profiling multiplier' value into it also re-sets the profiling * interrupt frequency, on architectures that support this. */ static ssize_t write_profile(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { #ifdef CONFIG_SMP if (count == sizeof(int)) { unsigned int multiplier; if (copy_from_user(&multiplier, buf, sizeof(int))) return -EFAULT; if (setup_profiling_timer(multiplier)) return -EINVAL; } #endif profile_discard_flip_buffers(); memset(prof_buffer, 0, prof_len * sizeof(atomic_t)); return count; } static const struct proc_ops profile_proc_ops = { .proc_read = read_profile, .proc_write = write_profile, .proc_lseek = default_llseek, }; int __ref create_proc_profile(void) { struct proc_dir_entry *entry; #ifdef CONFIG_SMP enum cpuhp_state online_state; #endif int err = 0; if (!prof_on) return 0; #ifdef CONFIG_SMP err = cpuhp_setup_state(CPUHP_PROFILE_PREPARE, "PROFILE_PREPARE", profile_prepare_cpu, profile_dead_cpu); if (err) return err; err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "AP_PROFILE_ONLINE", profile_online_cpu, NULL); if (err < 0) goto err_state_prep; online_state = err; err = 0; #endif entry = proc_create("profile", S_IWUSR | S_IRUGO, NULL, &profile_proc_ops); if (!entry) goto err_state_onl; proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t)); return err; err_state_onl: #ifdef CONFIG_SMP cpuhp_remove_state(online_state); err_state_prep: cpuhp_remove_state(CPUHP_PROFILE_PREPARE); #endif return err; } subsys_initcall(create_proc_profile); #endif /* CONFIG_PROC_FS */ |
| 77 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * This file is part of the Linux kernel. * * Copyright (c) 2011-2014, Intel Corporation * Authors: Fenghua Yu <fenghua.yu@intel.com>, * H. Peter Anvin <hpa@linux.intel.com> */ #ifndef ASM_X86_ARCHRANDOM_H #define ASM_X86_ARCHRANDOM_H #include <asm/processor.h> #include <asm/cpufeature.h> #define RDRAND_RETRY_LOOPS 10 /* Unconditional execution of RDRAND and RDSEED */ static inline bool __must_check rdrand_long(unsigned long *v) { bool ok; unsigned int retry = RDRAND_RETRY_LOOPS; do { asm volatile("rdrand %[out]" CC_SET(c) : CC_OUT(c) (ok), [out] "=r" (*v)); if (ok) return true; } while (--retry); return false; } static inline bool __must_check rdseed_long(unsigned long *v) { bool ok; asm volatile("rdseed %[out]" CC_SET(c) : CC_OUT(c) (ok), [out] "=r" (*v)); return ok; } /* * These are the generic interfaces; they must not be declared if the * stubs in <linux/random.h> are to be invoked. */ static inline size_t __must_check arch_get_random_longs(unsigned long *v, size_t max_longs) { return max_longs && static_cpu_has(X86_FEATURE_RDRAND) && rdrand_long(v) ? 1 : 0; } static inline size_t __must_check arch_get_random_seed_longs(unsigned long *v, size_t max_longs) { return max_longs && static_cpu_has(X86_FEATURE_RDSEED) && rdseed_long(v) ? 1 : 0; } #ifndef CONFIG_UML void x86_init_rdrand(struct cpuinfo_x86 *c); #endif #endif /* ASM_X86_ARCHRANDOM_H */ |
| 11 11 7 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 | // SPDX-License-Identifier: GPL-2.0 /* * Interface for controlling IO bandwidth on a request queue * * Copyright (C) 2010 Vivek Goyal <vgoyal@redhat.com> */ #include <linux/module.h> #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/bio.h> #include <linux/blktrace_api.h> #include "blk.h" #include "blk-cgroup-rwstat.h" #include "blk-stat.h" #include "blk-throttle.h" /* Max dispatch from a group in 1 round */ #define THROTL_GRP_QUANTUM 8 /* Total max dispatch from all groups in one round */ #define THROTL_QUANTUM 32 /* Throttling is performed over a slice and after that slice is renewed */ #define DFL_THROTL_SLICE_HD (HZ / 10) #define DFL_THROTL_SLICE_SSD (HZ / 50) #define MAX_THROTL_SLICE (HZ) #define MAX_IDLE_TIME (5L * 1000 * 1000) /* 5 s */ #define MIN_THROTL_BPS (320 * 1024) #define MIN_THROTL_IOPS (10) #define DFL_LATENCY_TARGET (-1L) #define DFL_IDLE_THRESHOLD (0) #define DFL_HD_BASELINE_LATENCY (4000L) /* 4ms */ #define LATENCY_FILTERED_SSD (0) /* * For HD, very small latency comes from sequential IO. Such IO is helpless to * help determine if its IO is impacted by others, hence we ignore the IO */ #define LATENCY_FILTERED_HD (1000L) /* 1ms */ /* A workqueue to queue throttle related work */ static struct workqueue_struct *kthrotld_workqueue; #define rb_entry_tg(node) rb_entry((node), struct throtl_grp, rb_node) /* We measure latency for request size from <= 4k to >= 1M */ #define LATENCY_BUCKET_SIZE 9 struct latency_bucket { unsigned long total_latency; /* ns / 1024 */ int samples; }; struct avg_latency_bucket { unsigned long latency; /* ns / 1024 */ bool valid; }; struct throtl_data { /* service tree for active throtl groups */ struct throtl_service_queue service_queue; struct request_queue *queue; /* Total Number of queued bios on READ and WRITE lists */ unsigned int nr_queued[2]; unsigned int throtl_slice; /* Work for dispatching throttled bios */ struct work_struct dispatch_work; unsigned int limit_index; bool limit_valid[LIMIT_CNT]; unsigned long low_upgrade_time; unsigned long low_downgrade_time; unsigned int scale; struct latency_bucket tmp_buckets[2][LATENCY_BUCKET_SIZE]; struct avg_latency_bucket avg_buckets[2][LATENCY_BUCKET_SIZE]; struct latency_bucket __percpu *latency_buckets[2]; unsigned long last_calculate_time; unsigned long filtered_latency; bool track_bio_latency; }; static void throtl_pending_timer_fn(struct timer_list *t); static inline struct blkcg_gq *tg_to_blkg(struct throtl_grp *tg) { return pd_to_blkg(&tg->pd); } /** * sq_to_tg - return the throl_grp the specified service queue belongs to * @sq: the throtl_service_queue of interest * * Return the throtl_grp @sq belongs to. If @sq is the top-level one * embedded in throtl_data, %NULL is returned. */ static struct throtl_grp *sq_to_tg(struct throtl_service_queue *sq) { if (sq && sq->parent_sq) return container_of(sq, struct throtl_grp, service_queue); else return NULL; } /** * sq_to_td - return throtl_data the specified service queue belongs to * @sq: the throtl_service_queue of interest * * A service_queue can be embedded in either a throtl_grp or throtl_data. * Determine the associated throtl_data accordingly and return it. */ static struct throtl_data *sq_to_td(struct throtl_service_queue *sq) { struct throtl_grp *tg = sq_to_tg(sq); if (tg) return tg->td; else return container_of(sq, struct throtl_data, service_queue); } /* * cgroup's limit in LIMIT_MAX is scaled if low limit is set. This scale is to * make the IO dispatch more smooth. * Scale up: linearly scale up according to lapsed time since upgrade. For * every throtl_slice, the limit scales up 1/2 .low limit till the * limit hits .max limit * Scale down: exponentially scale down if a cgroup doesn't hit its .low limit */ static uint64_t throtl_adjusted_limit(uint64_t low, struct throtl_data *td) { /* arbitrary value to avoid too big scale */ if (td->scale < 4096 && time_after_eq(jiffies, td->low_upgrade_time + td->scale * td->throtl_slice)) td->scale = (jiffies - td->low_upgrade_time) / td->throtl_slice; return low + (low >> 1) * td->scale; } static uint64_t tg_bps_limit(struct throtl_grp *tg, int rw) { struct blkcg_gq *blkg = tg_to_blkg(tg); struct throtl_data *td; uint64_t ret; if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent) return U64_MAX; td = tg->td; ret = tg->bps[rw][td->limit_index]; if (ret == 0 && td->limit_index == LIMIT_LOW) { /* intermediate node or iops isn't 0 */ if (!list_empty(&blkg->blkcg->css.children) || tg->iops[rw][td->limit_index]) return U64_MAX; else return MIN_THROTL_BPS; } if (td->limit_index == LIMIT_MAX && tg->bps[rw][LIMIT_LOW] && tg->bps[rw][LIMIT_LOW] != tg->bps[rw][LIMIT_MAX]) { uint64_t adjusted; adjusted = throtl_adjusted_limit(tg->bps[rw][LIMIT_LOW], td); ret = min(tg->bps[rw][LIMIT_MAX], adjusted); } return ret; } static unsigned int tg_iops_limit(struct throtl_grp *tg, int rw) { struct blkcg_gq *blkg = tg_to_blkg(tg); struct throtl_data *td; unsigned int ret; if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent) return UINT_MAX; td = tg->td; ret = tg->iops[rw][td->limit_index]; if (ret == 0 && tg->td->limit_index == LIMIT_LOW) { /* intermediate node or bps isn't 0 */ if (!list_empty(&blkg->blkcg->css.children) || tg->bps[rw][td->limit_index]) return UINT_MAX; else return MIN_THROTL_IOPS; } if (td->limit_index == LIMIT_MAX && tg->iops[rw][LIMIT_LOW] && tg->iops[rw][LIMIT_LOW] != tg->iops[rw][LIMIT_MAX]) { uint64_t adjusted; adjusted = throtl_adjusted_limit(tg->iops[rw][LIMIT_LOW], td); if (adjusted > UINT_MAX) adjusted = UINT_MAX; ret = min_t(unsigned int, tg->iops[rw][LIMIT_MAX], adjusted); } return ret; } #define request_bucket_index(sectors) \ clamp_t(int, order_base_2(sectors) - 3, 0, LATENCY_BUCKET_SIZE - 1) /** * throtl_log - log debug message via blktrace * @sq: the service_queue being reported * @fmt: printf format string * @args: printf args * * The messages are prefixed with "throtl BLKG_NAME" if @sq belongs to a * throtl_grp; otherwise, just "throtl". */ #define throtl_log(sq, fmt, args...) do { \ struct throtl_grp *__tg = sq_to_tg((sq)); \ struct throtl_data *__td = sq_to_td((sq)); \ \ (void)__td; \ if (likely(!blk_trace_note_message_enabled(__td->queue))) \ break; \ if ((__tg)) { \ blk_add_cgroup_trace_msg(__td->queue, \ &tg_to_blkg(__tg)->blkcg->css, "throtl " fmt, ##args);\ } else { \ blk_add_trace_msg(__td->queue, "throtl " fmt, ##args); \ } \ } while (0) static inline unsigned int throtl_bio_data_size(struct bio *bio) { /* assume it's one sector */ if (unlikely(bio_op(bio) == REQ_OP_DISCARD)) return 512; return bio->bi_iter.bi_size; } static void throtl_qnode_init(struct throtl_qnode *qn, struct throtl_grp *tg) { INIT_LIST_HEAD(&qn->node); bio_list_init(&qn->bios); qn->tg = tg; } /** * throtl_qnode_add_bio - add a bio to a throtl_qnode and activate it * @bio: bio being added * @qn: qnode to add bio to * @queued: the service_queue->queued[] list @qn belongs to * * Add @bio to @qn and put @qn on @queued if it's not already on. * @qn->tg's reference count is bumped when @qn is activated. See the * comment on top of throtl_qnode definition for details. */ static void throtl_qnode_add_bio(struct bio *bio, struct throtl_qnode *qn, struct list_head *queued) { bio_list_add(&qn->bios, bio); if (list_empty(&qn->node)) { list_add_tail(&qn->node, queued); blkg_get(tg_to_blkg(qn->tg)); } } /** * throtl_peek_queued - peek the first bio on a qnode list * @queued: the qnode list to peek */ static struct bio *throtl_peek_queued(struct list_head *queued) { struct throtl_qnode *qn; struct bio *bio; if (list_empty(queued)) return NULL; qn = list_first_entry(queued, struct throtl_qnode, node); bio = bio_list_peek(&qn->bios); WARN_ON_ONCE(!bio); return bio; } /** * throtl_pop_queued - pop the first bio form a qnode list * @queued: the qnode list to pop a bio from * @tg_to_put: optional out argument for throtl_grp to put * * Pop the first bio from the qnode list @queued. After popping, the first * qnode is removed from @queued if empty or moved to the end of @queued so * that the popping order is round-robin. * * When the first qnode is removed, its associated throtl_grp should be put * too. If @tg_to_put is NULL, this function automatically puts it; * otherwise, *@tg_to_put is set to the throtl_grp to put and the caller is * responsible for putting it. */ static struct bio *throtl_pop_queued(struct list_head *queued, struct throtl_grp **tg_to_put) { struct throtl_qnode *qn; struct bio *bio; if (list_empty(queued)) return NULL; qn = list_first_entry(queued, struct throtl_qnode, node); bio = bio_list_pop(&qn->bios); WARN_ON_ONCE(!bio); if (bio_list_empty(&qn->bios)) { list_del_init(&qn->node); if (tg_to_put) *tg_to_put = qn->tg; else blkg_put(tg_to_blkg(qn->tg)); } else { list_move_tail(&qn->node, queued); } return bio; } /* init a service_queue, assumes the caller zeroed it */ static void throtl_service_queue_init(struct throtl_service_queue *sq) { INIT_LIST_HEAD(&sq->queued[READ]); INIT_LIST_HEAD(&sq->queued[WRITE]); sq->pending_tree = RB_ROOT_CACHED; timer_setup(&sq->pending_timer, throtl_pending_timer_fn, 0); } static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp, struct request_queue *q, struct blkcg *blkcg) { struct throtl_grp *tg; int rw; tg = kzalloc_node(sizeof(*tg), gfp, q->node); if (!tg) return NULL; if (blkg_rwstat_init(&tg->stat_bytes, gfp)) goto err_free_tg; if (blkg_rwstat_init(&tg->stat_ios, gfp)) goto err_exit_stat_bytes; throtl_service_queue_init(&tg->service_queue); for (rw = READ; rw <= WRITE; rw++) { throtl_qnode_init(&tg->qnode_on_self[rw], tg); throtl_qnode_init(&tg->qnode_on_parent[rw], tg); } RB_CLEAR_NODE(&tg->rb_node); tg->bps[READ][LIMIT_MAX] = U64_MAX; tg->bps[WRITE][LIMIT_MAX] = U64_MAX; tg->iops[READ][LIMIT_MAX] = UINT_MAX; tg->iops[WRITE][LIMIT_MAX] = UINT_MAX; tg->bps_conf[READ][LIMIT_MAX] = U64_MAX; tg->bps_conf[WRITE][LIMIT_MAX] = U64_MAX; tg->iops_conf[READ][LIMIT_MAX] = UINT_MAX; tg->iops_conf[WRITE][LIMIT_MAX] = UINT_MAX; /* LIMIT_LOW will have default value 0 */ tg->latency_target = DFL_LATENCY_TARGET; tg->latency_target_conf = DFL_LATENCY_TARGET; tg->idletime_threshold = DFL_IDLE_THRESHOLD; tg->idletime_threshold_conf = DFL_IDLE_THRESHOLD; return &tg->pd; err_exit_stat_bytes: blkg_rwstat_exit(&tg->stat_bytes); err_free_tg: kfree(tg); return NULL; } static void throtl_pd_init(struct blkg_policy_data *pd) { struct throtl_grp *tg = pd_to_tg(pd); struct blkcg_gq *blkg = tg_to_blkg(tg); struct throtl_data *td = blkg->q->td; struct throtl_service_queue *sq = &tg->service_queue; /* * If on the default hierarchy, we switch to properly hierarchical * behavior where limits on a given throtl_grp are applied to the * whole subtree rather than just the group itself. e.g. If 16M * read_bps limit is set on the root group, the whole system can't * exceed 16M for the device. * * If not on the default hierarchy, the broken flat hierarchy * behavior is retained where all throtl_grps are treated as if * they're all separate root groups right below throtl_data. * Limits of a group don't interact with limits of other groups * regardless of the position of the group in the hierarchy. */ sq->parent_sq = &td->service_queue; if (cgroup_subsys_on_dfl(io_cgrp_subsys) && blkg->parent) sq->parent_sq = &blkg_to_tg(blkg->parent)->service_queue; tg->td = td; } /* * Set has_rules[] if @tg or any of its parents have limits configured. * This doesn't require walking up to the top of the hierarchy as the * parent's has_rules[] is guaranteed to be correct. */ static void tg_update_has_rules(struct throtl_grp *tg) { struct throtl_grp *parent_tg = sq_to_tg(tg->service_queue.parent_sq); struct throtl_data *td = tg->td; int rw; for (rw = READ; rw <= WRITE; rw++) { tg->has_rules_iops[rw] = (parent_tg && parent_tg->has_rules_iops[rw]) || (td->limit_valid[td->limit_index] && tg_iops_limit(tg, rw) != UINT_MAX); tg->has_rules_bps[rw] = (parent_tg && parent_tg->has_rules_bps[rw]) || (td->limit_valid[td->limit_index] && (tg_bps_limit(tg, rw) != U64_MAX)); } } static void throtl_pd_online(struct blkg_policy_data *pd) { struct throtl_grp *tg = pd_to_tg(pd); /* * We don't want new groups to escape the limits of its ancestors. * Update has_rules[] after a new group is brought online. */ tg_update_has_rules(tg); } #ifdef CONFIG_BLK_DEV_THROTTLING_LOW static void blk_throtl_update_limit_valid(struct throtl_data *td) { struct cgroup_subsys_state *pos_css; struct blkcg_gq *blkg; bool low_valid = false; rcu_read_lock(); blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) { struct throtl_grp *tg = blkg_to_tg(blkg); if (tg->bps[READ][LIMIT_LOW] || tg->bps[WRITE][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW]) { low_valid = true; break; } } rcu_read_unlock(); td->limit_valid[LIMIT_LOW] = low_valid; } #else static inline void blk_throtl_update_limit_valid(struct throtl_data *td) { } #endif static void throtl_upgrade_state(struct throtl_data *td); static void throtl_pd_offline(struct blkg_policy_data *pd) { struct throtl_grp *tg = pd_to_tg(pd); tg->bps[READ][LIMIT_LOW] = 0; tg->bps[WRITE][LIMIT_LOW] = 0; tg->iops[READ][LIMIT_LOW] = 0; tg->iops[WRITE][LIMIT_LOW] = 0; blk_throtl_update_limit_valid(tg->td); if (!tg->td->limit_valid[tg->td->limit_index]) throtl_upgrade_state(tg->td); } static void throtl_pd_free(struct blkg_policy_data *pd) { struct throtl_grp *tg = pd_to_tg(pd); del_timer_sync(&tg->service_queue.pending_timer); blkg_rwstat_exit(&tg->stat_bytes); blkg_rwstat_exit(&tg->stat_ios); kfree(tg); } static struct throtl_grp * throtl_rb_first(struct throtl_service_queue *parent_sq) { struct rb_node *n; n = rb_first_cached(&parent_sq->pending_tree); WARN_ON_ONCE(!n); if (!n) return NULL; return rb_entry_tg(n); } static void throtl_rb_erase(struct rb_node *n, struct throtl_service_queue *parent_sq) { rb_erase_cached(n, &parent_sq->pending_tree); RB_CLEAR_NODE(n); } static void update_min_dispatch_time(struct throtl_service_queue *parent_sq) { struct throtl_grp *tg; tg = throtl_rb_first(parent_sq); if (!tg) return; parent_sq->first_pending_disptime = tg->disptime; } static void tg_service_queue_add(struct throtl_grp *tg) { struct throtl_service_queue *parent_sq = tg->service_queue.parent_sq; struct rb_node **node = &parent_sq->pending_tree.rb_root.rb_node; struct rb_node *parent = NULL; struct throtl_grp *__tg; unsigned long key = tg->disptime; bool leftmost = true; while (*node != NULL) { parent = *node; __tg = rb_entry_tg(parent); if (time_before(key, __tg->disptime)) node = &parent->rb_left; else { node = &parent->rb_right; leftmost = false; } } rb_link_node(&tg->rb_node, parent, node); rb_insert_color_cached(&tg->rb_node, &parent_sq->pending_tree, leftmost); } static void throtl_enqueue_tg(struct throtl_grp *tg) { if (!(tg->flags & THROTL_TG_PENDING)) { tg_service_queue_add(tg); tg->flags |= THROTL_TG_PENDING; tg->service_queue.parent_sq->nr_pending++; } } static void throtl_dequeue_tg(struct throtl_grp *tg) { if (tg->flags & THROTL_TG_PENDING) { struct throtl_service_queue *parent_sq = tg->service_queue.parent_sq; throtl_rb_erase(&tg->rb_node, parent_sq); --parent_sq->nr_pending; tg->flags &= ~THROTL_TG_PENDING; } } /* Call with queue lock held */ static void throtl_schedule_pending_timer(struct throtl_service_queue *sq, unsigned long expires) { unsigned long max_expire = jiffies + 8 * sq_to_td(sq)->throtl_slice; /* * Since we are adjusting the throttle limit dynamically, the sleep * time calculated according to previous limit might be invalid. It's * possible the cgroup sleep time is very long and no other cgroups * have IO running so notify the limit changes. Make sure the cgroup * doesn't sleep too long to avoid the missed notification. */ if (time_after(expires, max_expire)) expires = max_expire; mod_timer(&sq->pending_timer, expires); throtl_log(sq, "schedule timer. delay=%lu jiffies=%lu", expires - jiffies, jiffies); } /** * throtl_schedule_next_dispatch - schedule the next dispatch cycle * @sq: the service_queue to schedule dispatch for * @force: force scheduling * * Arm @sq->pending_timer so that the next dispatch cycle starts on the * dispatch time of the first pending child. Returns %true if either timer * is armed or there's no pending child left. %false if the current * dispatch window is still open and the caller should continue * dispatching. * * If @force is %true, the dispatch timer is always scheduled and this * function is guaranteed to return %true. This is to be used when the * caller can't dispatch itself and needs to invoke pending_timer * unconditionally. Note that forced scheduling is likely to induce short * delay before dispatch starts even if @sq->first_pending_disptime is not * in the future and thus shouldn't be used in hot paths. */ static bool throtl_schedule_next_dispatch(struct throtl_service_queue *sq, bool force) { /* any pending children left? */ if (!sq->nr_pending) return true; update_min_dispatch_time(sq); /* is the next dispatch time in the future? */ if (force || time_after(sq->first_pending_disptime, jiffies)) { throtl_schedule_pending_timer(sq, sq->first_pending_disptime); return true; } /* tell the caller to continue dispatching */ return false; } static inline void throtl_start_new_slice_with_credit(struct throtl_grp *tg, bool rw, unsigned long start) { tg->bytes_disp[rw] = 0; tg->io_disp[rw] = 0; tg->carryover_bytes[rw] = 0; tg->carryover_ios[rw] = 0; /* * Previous slice has expired. We must have trimmed it after last * bio dispatch. That means since start of last slice, we never used * that bandwidth. Do try to make use of that bandwidth while giving * credit. */ if (time_after_eq(start, tg->slice_start[rw])) tg->slice_start[rw] = start; tg->slice_end[rw] = jiffies + tg->td->throtl_slice; throtl_log(&tg->service_queue, "[%c] new slice with credit start=%lu end=%lu jiffies=%lu", rw == READ ? 'R' : 'W', tg->slice_start[rw], tg->slice_end[rw], jiffies); } static inline void throtl_start_new_slice(struct throtl_grp *tg, bool rw, bool clear_carryover) { tg->bytes_disp[rw] = 0; tg->io_disp[rw] = 0; tg->slice_start[rw] = jiffies; tg->slice_end[rw] = jiffies + tg->td->throtl_slice; if (clear_carryover) { tg->carryover_bytes[rw] = 0; tg->carryover_ios[rw] = 0; } throtl_log(&tg->service_queue, "[%c] new slice start=%lu end=%lu jiffies=%lu", rw == READ ? 'R' : 'W', tg->slice_start[rw], tg->slice_end[rw], jiffies); } static inline void throtl_set_slice_end(struct throtl_grp *tg, bool rw, unsigned long jiffy_end) { tg->slice_end[rw] = roundup(jiffy_end, tg->td->throtl_slice); } static inline void throtl_extend_slice(struct throtl_grp *tg, bool rw, unsigned long jiffy_end) { throtl_set_slice_end(tg, rw, jiffy_end); throtl_log(&tg->service_queue, "[%c] extend slice start=%lu end=%lu jiffies=%lu", rw == READ ? 'R' : 'W', tg->slice_start[rw], tg->slice_end[rw], jiffies); } /* Determine if previously allocated or extended slice is complete or not */ static bool throtl_slice_used(struct throtl_grp *tg, bool rw) { if (time_in_range(jiffies, tg->slice_start[rw], tg->slice_end[rw])) return false; return true; } static unsigned int calculate_io_allowed(u32 iops_limit, unsigned long jiffy_elapsed) { unsigned int io_allowed; u64 tmp; /* * jiffy_elapsed should not be a big value as minimum iops can be * 1 then at max jiffy elapsed should be equivalent of 1 second as we * will allow dispatch after 1 second and after that slice should * have been trimmed. */ tmp = (u64)iops_limit * jiffy_elapsed; do_div(tmp, HZ); if (tmp > UINT_MAX) io_allowed = UINT_MAX; else io_allowed = tmp; return io_allowed; } static u64 calculate_bytes_allowed(u64 bps_limit, unsigned long jiffy_elapsed) { /* * Can result be wider than 64 bits? * We check against 62, not 64, due to ilog2 truncation. */ if (ilog2(bps_limit) + ilog2(jiffy_elapsed) - ilog2(HZ) > 62) return U64_MAX; return mul_u64_u64_div_u64(bps_limit, (u64)jiffy_elapsed, (u64)HZ); } /* Trim the used slices and adjust slice start accordingly */ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw) { unsigned long time_elapsed; long long bytes_trim; int io_trim; BUG_ON(time_before(tg->slice_end[rw], tg->slice_start[rw])); /* * If bps are unlimited (-1), then time slice don't get * renewed. Don't try to trim the slice if slice is used. A new * slice will start when appropriate. */ if (throtl_slice_used(tg, rw)) return; /* * A bio has been dispatched. Also adjust slice_end. It might happen * that initially cgroup limit was very low resulting in high * slice_end, but later limit was bumped up and bio was dispatched * sooner, then we need to reduce slice_end. A high bogus slice_end * is bad because it does not allow new slice to start. */ throtl_set_slice_end(tg, rw, jiffies + tg->td->throtl_slice); time_elapsed = rounddown(jiffies - tg->slice_start[rw], tg->td->throtl_slice); if (!time_elapsed) return; bytes_trim = calculate_bytes_allowed(tg_bps_limit(tg, rw), time_elapsed) + tg->carryover_bytes[rw]; io_trim = calculate_io_allowed(tg_iops_limit(tg, rw), time_elapsed) + tg->carryover_ios[rw]; if (bytes_trim <= 0 && io_trim <= 0) return; tg->carryover_bytes[rw] = 0; if ((long long)tg->bytes_disp[rw] >= bytes_trim) tg->bytes_disp[rw] -= bytes_trim; else tg->bytes_disp[rw] = 0; tg->carryover_ios[rw] = 0; if ((int)tg->io_disp[rw] >= io_trim) tg->io_disp[rw] -= io_trim; else tg->io_disp[rw] = 0; tg->slice_start[rw] += time_elapsed; throtl_log(&tg->service_queue, "[%c] trim slice nr=%lu bytes=%lld io=%d start=%lu end=%lu jiffies=%lu", rw == READ ? 'R' : 'W', time_elapsed / tg->td->throtl_slice, bytes_trim, io_trim, tg->slice_start[rw], tg->slice_end[rw], jiffies); } static void __tg_update_carryover(struct throtl_grp *tg, bool rw) { unsigned long jiffy_elapsed = jiffies - tg->slice_start[rw]; u64 bps_limit = tg_bps_limit(tg, rw); u32 iops_limit = tg_iops_limit(tg, rw); /* * If config is updated while bios are still throttled, calculate and * accumulate how many bytes/ios are waited across changes. And * carryover_bytes/ios will be used to calculate new wait time under new * configuration. */ if (bps_limit != U64_MAX) tg->carryover_bytes[rw] += calculate_bytes_allowed(bps_limit, jiffy_elapsed) - tg->bytes_disp[rw]; if (iops_limit != UINT_MAX) tg->carryover_ios[rw] += calculate_io_allowed(iops_limit, jiffy_elapsed) - tg->io_disp[rw]; } static void tg_update_carryover(struct throtl_grp *tg) { if (tg->service_queue.nr_queued[READ]) __tg_update_carryover(tg, READ); if (tg->service_queue.nr_queued[WRITE]) __tg_update_carryover(tg, WRITE); /* see comments in struct throtl_grp for meaning of these fields. */ throtl_log(&tg->service_queue, "%s: %llu %llu %u %u\n", __func__, tg->carryover_bytes[READ], tg->carryover_bytes[WRITE], tg->carryover_ios[READ], tg->carryover_ios[WRITE]); } static bool tg_within_iops_limit(struct throtl_grp *tg, struct bio *bio, u32 iops_limit, unsigned long *wait) { bool rw = bio_data_dir(bio); unsigned int io_allowed; unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd; if (iops_limit == UINT_MAX) { if (wait) *wait = 0; return true; } jiffy_elapsed = jiffies - tg->slice_start[rw]; /* Round up to the next throttle slice, wait time must be nonzero */ jiffy_elapsed_rnd = roundup(jiffy_elapsed + 1, tg->td->throtl_slice); io_allowed = calculate_io_allowed(iops_limit, jiffy_elapsed_rnd) + tg->carryover_ios[rw]; if (tg->io_disp[rw] + 1 <= io_allowed) { if (wait) *wait = 0; return true; } /* Calc approx time to dispatch */ jiffy_wait = jiffy_elapsed_rnd - jiffy_elapsed; if (wait) *wait = jiffy_wait; return false; } static bool tg_within_bps_limit(struct throtl_grp *tg, struct bio *bio, u64 bps_limit, unsigned long *wait) { bool rw = bio_data_dir(bio); u64 bytes_allowed, extra_bytes; unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd; unsigned int bio_size = throtl_bio_data_size(bio); /* no need to throttle if this bio's bytes have been accounted */ if (bps_limit == U64_MAX || bio_flagged(bio, BIO_BPS_THROTTLED)) { if (wait) *wait = 0; return true; } jiffy_elapsed = jiffy_elapsed_rnd = jiffies - tg->slice_start[rw]; /* Slice has just started. Consider one slice interval */ if (!jiffy_elapsed) jiffy_elapsed_rnd = tg->td->throtl_slice; jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice); bytes_allowed = calculate_bytes_allowed(bps_limit, jiffy_elapsed_rnd) + tg->carryover_bytes[rw]; if (tg->bytes_disp[rw] + bio_size <= bytes_allowed) { if (wait) *wait = 0; return true; } /* Calc approx time to dispatch */ extra_bytes = tg->bytes_disp[rw] + bio_size - bytes_allowed; jiffy_wait = div64_u64(extra_bytes * HZ, bps_limit); if (!jiffy_wait) jiffy_wait = 1; /* * This wait time is without taking into consideration the rounding * up we did. Add that time also. */ jiffy_wait = jiffy_wait + (jiffy_elapsed_rnd - jiffy_elapsed); if (wait) *wait = jiffy_wait; return false; } /* * Returns whether one can dispatch a bio or not. Also returns approx number * of jiffies to wait before this bio is with-in IO rate and can be dispatched */ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio, unsigned long *wait) { bool rw = bio_data_dir(bio); unsigned long bps_wait = 0, iops_wait = 0, max_wait = 0; u64 bps_limit = tg_bps_limit(tg, rw); u32 iops_limit = tg_iops_limit(tg, rw); /* * Currently whole state machine of group depends on first bio * queued in the group bio list. So one should not be calling * this function with a different bio if there are other bios * queued. */ BUG_ON(tg->service_queue.nr_queued[rw] && bio != throtl_peek_queued(&tg->service_queue.queued[rw])); /* If tg->bps = -1, then BW is unlimited */ if ((bps_limit == U64_MAX && iops_limit == UINT_MAX) || tg->flags & THROTL_TG_CANCELING) { if (wait) *wait = 0; return true; } /* * If previous slice expired, start a new one otherwise renew/extend * existing slice to make sure it is at least throtl_slice interval * long since now. New slice is started only for empty throttle group. * If there is queued bio, that means there should be an active * slice and it should be extended instead. */ if (throtl_slice_used(tg, rw) && !(tg->service_queue.nr_queued[rw])) throtl_start_new_slice(tg, rw, true); else { if (time_before(tg->slice_end[rw], jiffies + tg->td->throtl_slice)) throtl_extend_slice(tg, rw, jiffies + tg->td->throtl_slice); } if (tg_within_bps_limit(tg, bio, bps_limit, &bps_wait) && tg_within_iops_limit(tg, bio, iops_limit, &iops_wait)) { if (wait) *wait = 0; return true; } max_wait = max(bps_wait, iops_wait); if (wait) *wait = max_wait; if (time_before(tg->slice_end[rw], jiffies + max_wait)) throtl_extend_slice(tg, rw, jiffies + max_wait); return false; } static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio) { bool rw = bio_data_dir(bio); unsigned int bio_size = throtl_bio_data_size(bio); /* Charge the bio to the group */ if (!bio_flagged(bio, BIO_BPS_THROTTLED)) { tg->bytes_disp[rw] += bio_size; tg->last_bytes_disp[rw] += bio_size; } tg->io_disp[rw]++; tg->last_io_disp[rw]++; } /** * throtl_add_bio_tg - add a bio to the specified throtl_grp * @bio: bio to add * @qn: qnode to use * @tg: the target throtl_grp * * Add @bio to @tg's service_queue using @qn. If @qn is not specified, * tg->qnode_on_self[] is used. */ static void throtl_add_bio_tg(struct bio *bio, struct throtl_qnode *qn, struct throtl_grp *tg) { struct throtl_service_queue *sq = &tg->service_queue; bool rw = bio_data_dir(bio); if (!qn) qn = &tg->qnode_on_self[rw]; /* * If @tg doesn't currently have any bios queued in the same * direction, queueing @bio can change when @tg should be * dispatched. Mark that @tg was empty. This is automatically * cleared on the next tg_update_disptime(). */ if (!sq->nr_queued[rw]) tg->flags |= THROTL_TG_WAS_EMPTY; throtl_qnode_add_bio(bio, qn, &sq->queued[rw]); sq->nr_queued[rw]++; throtl_enqueue_tg(tg); } static void tg_update_disptime(struct throtl_grp *tg) { struct throtl_service_queue *sq = &tg->service_queue; unsigned long read_wait = -1, write_wait = -1, min_wait = -1, disptime; struct bio *bio; bio = throtl_peek_queued(&sq->queued[READ]); if (bio) tg_may_dispatch(tg, bio, &read_wait); bio = throtl_peek_queued(&sq->queued[WRITE]); if (bio) tg_may_dispatch(tg, bio, &write_wait); min_wait = min(read_wait, write_wait); disptime = jiffies + min_wait; /* Update dispatch time */ throtl_rb_erase(&tg->rb_node, tg->service_queue.parent_sq); tg->disptime = disptime; tg_service_queue_add(tg); /* see throtl_add_bio_tg() */ tg->flags &= ~THROTL_TG_WAS_EMPTY; } static void start_parent_slice_with_credit(struct throtl_grp *child_tg, struct throtl_grp *parent_tg, bool rw) { if (throtl_slice_used(parent_tg, rw)) { throtl_start_new_slice_with_credit(parent_tg, rw, child_tg->slice_start[rw]); } } static void tg_dispatch_one_bio(struct throtl_grp *tg, bool rw) { struct throtl_service_queue *sq = &tg->service_queue; struct throtl_service_queue *parent_sq = sq->parent_sq; struct throtl_grp *parent_tg = sq_to_tg(parent_sq); struct throtl_grp *tg_to_put = NULL; struct bio *bio; /* * @bio is being transferred from @tg to @parent_sq. Popping a bio * from @tg may put its reference and @parent_sq might end up * getting released prematurely. Remember the tg to put and put it * after @bio is transferred to @parent_sq. */ bio = throtl_pop_queued(&sq->queued[rw], &tg_to_put); sq->nr_queued[rw]--; throtl_charge_bio(tg, bio); /* * If our parent is another tg, we just need to transfer @bio to * the parent using throtl_add_bio_tg(). If our parent is * @td->service_queue, @bio is ready to be issued. Put it on its * bio_lists[] and decrease total number queued. The caller is * responsible for issuing these bios. */ if (parent_tg) { throtl_add_bio_tg(bio, &tg->qnode_on_parent[rw], parent_tg); start_parent_slice_with_credit(tg, parent_tg, rw); } else { bio_set_flag(bio, BIO_BPS_THROTTLED); throtl_qnode_add_bio(bio, &tg->qnode_on_parent[rw], &parent_sq->queued[rw]); BUG_ON(tg->td->nr_queued[rw] <= 0); tg->td->nr_queued[rw]--; } throtl_trim_slice(tg, rw); if (tg_to_put) blkg_put(tg_to_blkg(tg_to_put)); } static int throtl_dispatch_tg(struct throtl_grp *tg) { struct throtl_service_queue *sq = &tg->service_queue; unsigned int nr_reads = 0, nr_writes = 0; unsigned int max_nr_reads = THROTL_GRP_QUANTUM * 3 / 4; unsigned int max_nr_writes = THROTL_GRP_QUANTUM - max_nr_reads; struct bio *bio; /* Try to dispatch 75% READS and 25% WRITES */ while ((bio = throtl_peek_queued(&sq->queued[READ])) && tg_may_dispatch(tg, bio, NULL)) { tg_dispatch_one_bio(tg, bio_data_dir(bio)); nr_reads++; if (nr_reads >= max_nr_reads) break; } while ((bio = throtl_peek_queued(&sq->queued[WRITE])) && tg_may_dispatch(tg, bio, NULL)) { tg_dispatch_one_bio(tg, bio_data_dir(bio)); nr_writes++; if (nr_writes >= max_nr_writes) break; } return nr_reads + nr_writes; } static int throtl_select_dispatch(struct throtl_service_queue *parent_sq) { unsigned int nr_disp = 0; while (1) { struct throtl_grp *tg; struct throtl_service_queue *sq; if (!parent_sq->nr_pending) break; tg = throtl_rb_first(parent_sq); if (!tg) break; if (time_before(jiffies, tg->disptime)) break; nr_disp += throtl_dispatch_tg(tg); sq = &tg->service_queue; if (sq->nr_queued[READ] || sq->nr_queued[WRITE]) tg_update_disptime(tg); else throtl_dequeue_tg(tg); if (nr_disp >= THROTL_QUANTUM) break; } return nr_disp; } static bool throtl_can_upgrade(struct throtl_data *td, struct throtl_grp *this_tg); /** * throtl_pending_timer_fn - timer function for service_queue->pending_timer * @t: the pending_timer member of the throtl_service_queue being serviced * * This timer is armed when a child throtl_grp with active bio's become * pending and queued on the service_queue's pending_tree and expires when * the first child throtl_grp should be dispatched. This function * dispatches bio's from the children throtl_grps to the parent * service_queue. * * If the parent's parent is another throtl_grp, dispatching is propagated * by either arming its pending_timer or repeating dispatch directly. If * the top-level service_tree is reached, throtl_data->dispatch_work is * kicked so that the ready bio's are issued. */ static void throtl_pending_timer_fn(struct timer_list *t) { struct throtl_service_queue *sq = from_timer(sq, t, pending_timer); struct throtl_grp *tg = sq_to_tg(sq); struct throtl_data *td = sq_to_td(sq); struct throtl_service_queue *parent_sq; struct request_queue *q; bool dispatched; int ret; /* throtl_data may be gone, so figure out request queue by blkg */ if (tg) q = tg->pd.blkg->q; else q = td->queue; spin_lock_irq(&q->queue_lock); if (!q->root_blkg) goto out_unlock; if (throtl_can_upgrade(td, NULL)) throtl_upgrade_state(td); again: parent_sq = sq->parent_sq; dispatched = false; while (true) { throtl_log(sq, "dispatch nr_queued=%u read=%u write=%u", sq->nr_queued[READ] + sq->nr_queued[WRITE], sq->nr_queued[READ], sq->nr_queued[WRITE]); ret = throtl_select_dispatch(sq); if (ret) { throtl_log(sq, "bios disp=%u", ret); dispatched = true; } if (throtl_schedule_next_dispatch(sq, false)) break; /* this dispatch windows is still open, relax and repeat */ spin_unlock_irq(&q->queue_lock); cpu_relax(); spin_lock_irq(&q->queue_lock); } if (!dispatched) goto out_unlock; if (parent_sq) { /* @parent_sq is another throl_grp, propagate dispatch */ if (tg->flags & THROTL_TG_WAS_EMPTY) { tg_update_disptime(tg); if (!throtl_schedule_next_dispatch(parent_sq, false)) { /* window is already open, repeat dispatching */ sq = parent_sq; tg = sq_to_tg(sq); goto again; } } } else { /* reached the top-level, queue issuing */ queue_work(kthrotld_workqueue, &td->dispatch_work); } out_unlock: spin_unlock_irq(&q->queue_lock); } /** * blk_throtl_dispatch_work_fn - work function for throtl_data->dispatch_work * @work: work item being executed * * This function is queued for execution when bios reach the bio_lists[] * of throtl_data->service_queue. Those bios are ready and issued by this * function. */ static void blk_throtl_dispatch_work_fn(struct work_struct *work) { struct throtl_data *td = container_of(work, struct throtl_data, dispatch_work); struct throtl_service_queue *td_sq = &td->service_queue; struct request_queue *q = td->queue; struct bio_list bio_list_on_stack; struct bio *bio; struct blk_plug plug; int rw; bio_list_init(&bio_list_on_stack); spin_lock_irq(&q->queue_lock); for (rw = READ; rw <= WRITE; rw++) while ((bio = throtl_pop_queued(&td_sq->queued[rw], NULL))) bio_list_add(&bio_list_on_stack, bio); spin_unlock_irq(&q->queue_lock); if (!bio_list_empty(&bio_list_on_stack)) { blk_start_plug(&plug); while ((bio = bio_list_pop(&bio_list_on_stack))) submit_bio_noacct_nocheck(bio); blk_finish_plug(&plug); } } static u64 tg_prfill_conf_u64(struct seq_file *sf, struct blkg_policy_data *pd, int off) { struct throtl_grp *tg = pd_to_tg(pd); u64 v = *(u64 *)((void *)tg + off); if (v == U64_MAX) return 0; return __blkg_prfill_u64(sf, pd, v); } static u64 tg_prfill_conf_uint(struct seq_file *sf, struct blkg_policy_data *pd, int off) { struct throtl_grp *tg = pd_to_tg(pd); unsigned int v = *(unsigned int *)((void *)tg + off); if (v == UINT_MAX) return 0; return __blkg_prfill_u64(sf, pd, v); } static int tg_print_conf_u64(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_conf_u64, &blkcg_policy_throtl, seq_cft(sf)->private, false); return 0; } static int tg_print_conf_uint(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_conf_uint, &blkcg_policy_throtl, seq_cft(sf)->private, false); return 0; } static void tg_conf_updated(struct throtl_grp *tg, bool global) { struct throtl_service_queue *sq = &tg->service_queue; struct cgroup_subsys_state *pos_css; struct blkcg_gq *blkg; throtl_log(&tg->service_queue, "limit change rbps=%llu wbps=%llu riops=%u wiops=%u", tg_bps_limit(tg, READ), tg_bps_limit(tg, WRITE), tg_iops_limit(tg, READ), tg_iops_limit(tg, WRITE)); rcu_read_lock(); /* * Update has_rules[] flags for the updated tg's subtree. A tg is * considered to have rules if either the tg itself or any of its * ancestors has rules. This identifies groups without any * restrictions in the whole hierarchy and allows them to bypass * blk-throttle. */ blkg_for_each_descendant_pre(blkg, pos_css, global ? tg->td->queue->root_blkg : tg_to_blkg(tg)) { struct throtl_grp *this_tg = blkg_to_tg(blkg); struct throtl_grp *parent_tg; tg_update_has_rules(this_tg); /* ignore root/second level */ if (!cgroup_subsys_on_dfl(io_cgrp_subsys) || !blkg->parent || !blkg->parent->parent) continue; parent_tg = blkg_to_tg(blkg->parent); /* * make sure all children has lower idle time threshold and * higher latency target */ this_tg->idletime_threshold = min(this_tg->idletime_threshold, parent_tg->idletime_threshold); this_tg->latency_target = max(this_tg->latency_target, parent_tg->latency_target); } rcu_read_unlock(); /* * We're already holding queue_lock and know @tg is valid. Let's * apply the new config directly. * * Restart the slices for both READ and WRITES. It might happen * that a group's limit are dropped suddenly and we don't want to * account recently dispatched IO with new low rate. */ throtl_start_new_slice(tg, READ, false); throtl_start_new_slice(tg, WRITE, false); if (tg->flags & THROTL_TG_PENDING) { tg_update_disptime(tg); throtl_schedule_next_dispatch(sq->parent_sq, true); } } static ssize_t tg_set_conf(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off, bool is_u64) { struct blkcg *blkcg = css_to_blkcg(of_css(of)); struct blkg_conf_ctx ctx; struct throtl_grp *tg; int ret; u64 v; ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, buf, &ctx); if (ret) return ret; ret = -EINVAL; if (sscanf(ctx.body, "%llu", &v) != 1) goto out_finish; if (!v) v = U64_MAX; tg = blkg_to_tg(ctx.blkg); tg_update_carryover(tg); if (is_u64) *(u64 *)((void *)tg + of_cft(of)->private) = v; else *(unsigned int *)((void *)tg + of_cft(of)->private) = v; tg_conf_updated(tg, false); ret = 0; out_finish: blkg_conf_finish(&ctx); return ret ?: nbytes; } static ssize_t tg_set_conf_u64(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return tg_set_conf(of, buf, nbytes, off, true); } static ssize_t tg_set_conf_uint(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return tg_set_conf(of, buf, nbytes, off, false); } static int tg_print_rwstat(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat, &blkcg_policy_throtl, seq_cft(sf)->private, true); return 0; } static u64 tg_prfill_rwstat_recursive(struct seq_file *sf, struct blkg_policy_data *pd, int off) { struct blkg_rwstat_sample sum; blkg_rwstat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_throtl, off, &sum); return __blkg_prfill_rwstat(sf, pd, &sum); } static int tg_print_rwstat_recursive(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_rwstat_recursive, &blkcg_policy_throtl, seq_cft(sf)->private, true); return 0; } static struct cftype throtl_legacy_files[] = { { .name = "throttle.read_bps_device", .private = offsetof(struct throtl_grp, bps[READ][LIMIT_MAX]), .seq_show = tg_print_conf_u64, .write = tg_set_conf_u64, }, { .name = "throttle.write_bps_device", .private = offsetof(struct throtl_grp, bps[WRITE][LIMIT_MAX]), .seq_show = tg_print_conf_u64, .write = tg_set_conf_u64, }, { .name = "throttle.read_iops_device", .private = offsetof(struct throtl_grp, iops[READ][LIMIT_MAX]), .seq_show = tg_print_conf_uint, .write = tg_set_conf_uint, }, { .name = "throttle.write_iops_device", .private = offsetof(struct throtl_grp, iops[WRITE][LIMIT_MAX]), .seq_show = tg_print_conf_uint, .write = tg_set_conf_uint, }, { .name = "throttle.io_service_bytes", .private = offsetof(struct throtl_grp, stat_bytes), .seq_show = tg_print_rwstat, }, { .name = "throttle.io_service_bytes_recursive", .private = offsetof(struct throtl_grp, stat_bytes), .seq_show = tg_print_rwstat_recursive, }, { .name = "throttle.io_serviced", .private = offsetof(struct throtl_grp, stat_ios), .seq_show = tg_print_rwstat, }, { .name = "throttle.io_serviced_recursive", .private = offsetof(struct throtl_grp, stat_ios), .seq_show = tg_print_rwstat_recursive, }, { } /* terminate */ }; static u64 tg_prfill_limit(struct seq_file *sf, struct blkg_policy_data *pd, int off) { struct throtl_grp *tg = pd_to_tg(pd); const char *dname = blkg_dev_name(pd->blkg); char bufs[4][21] = { "max", "max", "max", "max" }; u64 bps_dft; unsigned int iops_dft; char idle_time[26] = ""; char latency_time[26] = ""; if (!dname) return 0; if (off == LIMIT_LOW) { bps_dft = 0; iops_dft = 0; } else { bps_dft = U64_MAX; iops_dft = UINT_MAX; } if (tg->bps_conf[READ][off] == bps_dft && tg->bps_conf[WRITE][off] == bps_dft && tg->iops_conf[READ][off] == iops_dft && tg->iops_conf[WRITE][off] == iops_dft && (off != LIMIT_LOW || (tg->idletime_threshold_conf == DFL_IDLE_THRESHOLD && tg->latency_target_conf == DFL_LATENCY_TARGET))) return 0; if (tg->bps_conf[READ][off] != U64_MAX) snprintf(bufs[0], sizeof(bufs[0]), "%llu", tg->bps_conf[READ][off]); if (tg->bps_conf[WRITE][off] != U64_MAX) snprintf(bufs[1], sizeof(bufs[1]), "%llu", tg->bps_conf[WRITE][off]); if (tg->iops_conf[READ][off] != UINT_MAX) snprintf(bufs[2], sizeof(bufs[2]), "%u", tg->iops_conf[READ][off]); if (tg->iops_conf[WRITE][off] != UINT_MAX) snprintf(bufs[3], sizeof(bufs[3]), "%u", tg->iops_conf[WRITE][off]); if (off == LIMIT_LOW) { if (tg->idletime_threshold_conf == ULONG_MAX) strcpy(idle_time, " idle=max"); else snprintf(idle_time, sizeof(idle_time), " idle=%lu", tg->idletime_threshold_conf); if (tg->latency_target_conf == ULONG_MAX) strcpy(latency_time, " latency=max"); else snprintf(latency_time, sizeof(latency_time), " latency=%lu", tg->latency_target_conf); } seq_printf(sf, "%s rbps=%s wbps=%s riops=%s wiops=%s%s%s\n", dname, bufs[0], bufs[1], bufs[2], bufs[3], idle_time, latency_time); return 0; } static int tg_print_limit(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_limit, &blkcg_policy_throtl, seq_cft(sf)->private, false); return 0; } static ssize_t tg_set_limit(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct blkcg *blkcg = css_to_blkcg(of_css(of)); struct blkg_conf_ctx ctx; struct throtl_grp *tg; u64 v[4]; unsigned long idle_time; unsigned long latency_time; int ret; int index = of_cft(of)->private; ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, buf, &ctx); if (ret) return ret; tg = blkg_to_tg(ctx.blkg); tg_update_carryover(tg); v[0] = tg->bps_conf[READ][index]; v[1] = tg->bps_conf[WRITE][index]; v[2] = tg->iops_conf[READ][index]; v[3] = tg->iops_conf[WRITE][index]; idle_time = tg->idletime_threshold_conf; latency_time = tg->latency_target_conf; while (true) { char tok[27]; /* wiops=18446744073709551616 */ char *p; u64 val = U64_MAX; int len; if (sscanf(ctx.body, "%26s%n", tok, &len) != 1) break; if (tok[0] == '\0') break; ctx.body += len; ret = -EINVAL; p = tok; strsep(&p, "="); if (!p || (sscanf(p, "%llu", &val) != 1 && strcmp(p, "max"))) goto out_finish; ret = -ERANGE; if (!val) goto out_finish; ret = -EINVAL; if (!strcmp(tok, "rbps") && val > 1) v[0] = val; else if (!strcmp(tok, "wbps") && val > 1) v[1] = val; else if (!strcmp(tok, "riops") && val > 1) v[2] = min_t(u64, val, UINT_MAX); else if (!strcmp(tok, "wiops") && val > 1) v[3] = min_t(u64, val, UINT_MAX); else if (off == LIMIT_LOW && !strcmp(tok, "idle")) idle_time = val; else if (off == LIMIT_LOW && !strcmp(tok, "latency")) latency_time = val; else goto out_finish; } tg->bps_conf[READ][index] = v[0]; tg->bps_conf[WRITE][index] = v[1]; tg->iops_conf[READ][index] = v[2]; tg->iops_conf[WRITE][index] = v[3]; if (index == LIMIT_MAX) { tg->bps[READ][index] = v[0]; tg->bps[WRITE][index] = v[1]; tg->iops[READ][index] = v[2]; tg->iops[WRITE][index] = v[3]; } tg->bps[READ][LIMIT_LOW] = min(tg->bps_conf[READ][LIMIT_LOW], tg->bps_conf[READ][LIMIT_MAX]); tg->bps[WRITE][LIMIT_LOW] = min(tg->bps_conf[WRITE][LIMIT_LOW], tg->bps_conf[WRITE][LIMIT_MAX]); tg->iops[READ][LIMIT_LOW] = min(tg->iops_conf[READ][LIMIT_LOW], tg->iops_conf[READ][LIMIT_MAX]); tg->iops[WRITE][LIMIT_LOW] = min(tg->iops_conf[WRITE][LIMIT_LOW], tg->iops_conf[WRITE][LIMIT_MAX]); tg->idletime_threshold_conf = idle_time; tg->latency_target_conf = latency_time; /* force user to configure all settings for low limit */ if (!(tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW] || tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW]) || tg->idletime_threshold_conf == DFL_IDLE_THRESHOLD || tg->latency_target_conf == DFL_LATENCY_TARGET) { tg->bps[READ][LIMIT_LOW] = 0; tg->bps[WRITE][LIMIT_LOW] = 0; tg->iops[READ][LIMIT_LOW] = 0; tg->iops[WRITE][LIMIT_LOW] = 0; tg->idletime_threshold = DFL_IDLE_THRESHOLD; tg->latency_target = DFL_LATENCY_TARGET; } else if (index == LIMIT_LOW) { tg->idletime_threshold = tg->idletime_threshold_conf; tg->latency_target = tg->latency_target_conf; } blk_throtl_update_limit_valid(tg->td); if (tg->td->limit_valid[LIMIT_LOW]) { if (index == LIMIT_LOW) tg->td->limit_index = LIMIT_LOW; } else tg->td->limit_index = LIMIT_MAX; tg_conf_updated(tg, index == LIMIT_LOW && tg->td->limit_valid[LIMIT_LOW]); ret = 0; out_finish: blkg_conf_finish(&ctx); return ret ?: nbytes; } static struct cftype throtl_files[] = { #ifdef CONFIG_BLK_DEV_THROTTLING_LOW { .name = "low", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = tg_print_limit, .write = tg_set_limit, .private = LIMIT_LOW, }, #endif { .name = "max", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = tg_print_limit, .write = tg_set_limit, .private = LIMIT_MAX, }, { } /* terminate */ }; static void throtl_shutdown_wq(struct request_queue *q) { struct throtl_data *td = q->td; cancel_work_sync(&td->dispatch_work); } struct blkcg_policy blkcg_policy_throtl = { .dfl_cftypes = throtl_files, .legacy_cftypes = throtl_legacy_files, .pd_alloc_fn = throtl_pd_alloc, .pd_init_fn = throtl_pd_init, .pd_online_fn = throtl_pd_online, .pd_offline_fn = throtl_pd_offline, .pd_free_fn = throtl_pd_free, }; void blk_throtl_cancel_bios(struct gendisk *disk) { struct request_queue *q = disk->queue; struct cgroup_subsys_state *pos_css; struct blkcg_gq *blkg; spin_lock_irq(&q->queue_lock); /* * queue_lock is held, rcu lock is not needed here technically. * However, rcu lock is still held to emphasize that following * path need RCU protection and to prevent warning from lockdep. */ rcu_read_lock(); blkg_for_each_descendant_post(blkg, pos_css, q->root_blkg) { struct throtl_grp *tg = blkg_to_tg(blkg); struct throtl_service_queue *sq = &tg->service_queue; /* * Set the flag to make sure throtl_pending_timer_fn() won't * stop until all throttled bios are dispatched. */ blkg_to_tg(blkg)->flags |= THROTL_TG_CANCELING; /* * Update disptime after setting the above flag to make sure * throtl_select_dispatch() won't exit without dispatching. */ tg_update_disptime(tg); throtl_schedule_pending_timer(sq, jiffies + 1); } rcu_read_unlock(); spin_unlock_irq(&q->queue_lock); } #ifdef CONFIG_BLK_DEV_THROTTLING_LOW static unsigned long __tg_last_low_overflow_time(struct throtl_grp *tg) { unsigned long rtime = jiffies, wtime = jiffies; if (tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW]) rtime = tg->last_low_overflow_time[READ]; if (tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW]) wtime = tg->last_low_overflow_time[WRITE]; return min(rtime, wtime); } /* tg should not be an intermediate node */ static unsigned long tg_last_low_overflow_time(struct throtl_grp *tg) { struct throtl_service_queue *parent_sq; struct throtl_grp *parent = tg; unsigned long ret = __tg_last_low_overflow_time(tg); while (true) { parent_sq = parent->service_queue.parent_sq; parent = sq_to_tg(parent_sq); if (!parent) break; /* * The parent doesn't have low limit, it always reaches low * limit. Its overflow time is useless for children */ if (!parent->bps[READ][LIMIT_LOW] && !parent->iops[READ][LIMIT_LOW] && !parent->bps[WRITE][LIMIT_LOW] && !parent->iops[WRITE][LIMIT_LOW]) continue; if (time_after(__tg_last_low_overflow_time(parent), ret)) ret = __tg_last_low_overflow_time(parent); } return ret; } static bool throtl_tg_is_idle(struct throtl_grp *tg) { /* * cgroup is idle if: * - single idle is too long, longer than a fixed value (in case user * configure a too big threshold) or 4 times of idletime threshold * - average think time is more than threshold * - IO latency is largely below threshold */ unsigned long time; bool ret; time = min_t(unsigned long, MAX_IDLE_TIME, 4 * tg->idletime_threshold); ret = tg->latency_target == DFL_LATENCY_TARGET || tg->idletime_threshold == DFL_IDLE_THRESHOLD || (ktime_get_ns() >> 10) - tg->last_finish_time > time || tg->avg_idletime > tg->idletime_threshold || (tg->latency_target && tg->bio_cnt && tg->bad_bio_cnt * 5 < tg->bio_cnt); throtl_log(&tg->service_queue, "avg_idle=%ld, idle_threshold=%ld, bad_bio=%d, total_bio=%d, is_idle=%d, scale=%d", tg->avg_idletime, tg->idletime_threshold, tg->bad_bio_cnt, tg->bio_cnt, ret, tg->td->scale); return ret; } static bool throtl_tg_can_upgrade(struct throtl_grp *tg) { struct throtl_service_queue *sq = &tg->service_queue; bool read_limit, write_limit; /* * if cgroup reaches low limit (if low limit is 0, the cgroup always * reaches), it's ok to upgrade to next limit */ read_limit = tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW]; write_limit = tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW]; if (!read_limit && !write_limit) return true; if (read_limit && sq->nr_queued[READ] && (!write_limit || sq->nr_queued[WRITE])) return true; if (write_limit && sq->nr_queued[WRITE] && (!read_limit || sq->nr_queued[READ])) return true; if (time_after_eq(jiffies, tg_last_low_overflow_time(tg) + tg->td->throtl_slice) && throtl_tg_is_idle(tg)) return true; return false; } static bool throtl_hierarchy_can_upgrade(struct throtl_grp *tg) { while (true) { if (throtl_tg_can_upgrade(tg)) return true; tg = sq_to_tg(tg->service_queue.parent_sq); if (!tg || !tg_to_blkg(tg)->parent) return false; } return false; } static bool throtl_can_upgrade(struct throtl_data *td, struct throtl_grp *this_tg) { struct cgroup_subsys_state *pos_css; struct blkcg_gq *blkg; if (td->limit_index != LIMIT_LOW) return false; if (time_before(jiffies, td->low_downgrade_time + td->throtl_slice)) return false; rcu_read_lock(); blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) { struct throtl_grp *tg = blkg_to_tg(blkg); if (tg == this_tg) continue; if (!list_empty(&tg_to_blkg(tg)->blkcg->css.children)) continue; if (!throtl_hierarchy_can_upgrade(tg)) { rcu_read_unlock(); return false; } } rcu_read_unlock(); return true; } static void throtl_upgrade_check(struct throtl_grp *tg) { unsigned long now = jiffies; if (tg->td->limit_index != LIMIT_LOW) return; if (time_after(tg->last_check_time + tg->td->throtl_slice, now)) return; tg->last_check_time = now; if (!time_after_eq(now, __tg_last_low_overflow_time(tg) + tg->td->throtl_slice)) return; if (throtl_can_upgrade(tg->td, NULL)) throtl_upgrade_state(tg->td); } static void throtl_upgrade_state(struct throtl_data *td) { struct cgroup_subsys_state *pos_css; struct blkcg_gq *blkg; throtl_log(&td->service_queue, "upgrade to max"); td->limit_index = LIMIT_MAX; td->low_upgrade_time = jiffies; td->scale = 0; rcu_read_lock(); blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) { struct throtl_grp *tg = blkg_to_tg(blkg); struct throtl_service_queue *sq = &tg->service_queue; tg->disptime = jiffies - 1; throtl_select_dispatch(sq); throtl_schedule_next_dispatch(sq, true); } rcu_read_unlock(); throtl_select_dispatch(&td->service_queue); throtl_schedule_next_dispatch(&td->service_queue, true); queue_work(kthrotld_workqueue, &td->dispatch_work); } static void throtl_downgrade_state(struct throtl_data *td) { td->scale /= 2; throtl_log(&td->service_queue, "downgrade, scale %d", td->scale); if (td->scale) { td->low_upgrade_time = jiffies - td->scale * td->throtl_slice; return; } td->limit_index = LIMIT_LOW; td->low_downgrade_time = jiffies; } static bool throtl_tg_can_downgrade(struct throtl_grp *tg) { struct throtl_data *td = tg->td; unsigned long now = jiffies; /* * If cgroup is below low limit, consider downgrade and throttle other * cgroups */ if (time_after_eq(now, td->low_upgrade_time + td->throtl_slice) && time_after_eq(now, tg_last_low_overflow_time(tg) + td->throtl_slice) && (!throtl_tg_is_idle(tg) || !list_empty(&tg_to_blkg(tg)->blkcg->css.children))) return true; return false; } static bool throtl_hierarchy_can_downgrade(struct throtl_grp *tg) { while (true) { if (!throtl_tg_can_downgrade(tg)) return false; tg = sq_to_tg(tg->service_queue.parent_sq); if (!tg || !tg_to_blkg(tg)->parent) break; } return true; } static void throtl_downgrade_check(struct throtl_grp *tg) { uint64_t bps; unsigned int iops; unsigned long elapsed_time; unsigned long now = jiffies; if (tg->td->limit_index != LIMIT_MAX || !tg->td->limit_valid[LIMIT_LOW]) return; if (!list_empty(&tg_to_blkg(tg)->blkcg->css.children)) return; if (time_after(tg->last_check_time + tg->td->throtl_slice, now)) return; elapsed_time = now - tg->last_check_time; tg->last_check_time = now; if (time_before(now, tg_last_low_overflow_time(tg) + tg->td->throtl_slice)) return; if (tg->bps[READ][LIMIT_LOW]) { bps = tg->last_bytes_disp[READ] * HZ; do_div(bps, elapsed_time); if (bps >= tg->bps[READ][LIMIT_LOW]) tg->last_low_overflow_time[READ] = now; } if (tg->bps[WRITE][LIMIT_LOW]) { bps = tg->last_bytes_disp[WRITE] * HZ; do_div(bps, elapsed_time); if (bps >= tg->bps[WRITE][LIMIT_LOW]) tg->last_low_overflow_time[WRITE] = now; } if (tg->iops[READ][LIMIT_LOW]) { iops = tg->last_io_disp[READ] * HZ / elapsed_time; if (iops >= tg->iops[READ][LIMIT_LOW]) tg->last_low_overflow_time[READ] = now; } if (tg->iops[WRITE][LIMIT_LOW]) { iops = tg->last_io_disp[WRITE] * HZ / elapsed_time; if (iops >= tg->iops[WRITE][LIMIT_LOW]) tg->last_low_overflow_time[WRITE] = now; } /* * If cgroup is below low limit, consider downgrade and throttle other * cgroups */ if (throtl_hierarchy_can_downgrade(tg)) throtl_downgrade_state(tg->td); tg->last_bytes_disp[READ] = 0; tg->last_bytes_disp[WRITE] = 0; tg->last_io_disp[READ] = 0; tg->last_io_disp[WRITE] = 0; } static void blk_throtl_update_idletime(struct throtl_grp *tg) { unsigned long now; unsigned long last_finish_time = tg->last_finish_time; if (last_finish_time == 0) return; now = ktime_get_ns() >> 10; if (now <= last_finish_time || last_finish_time == tg->checked_last_finish_time) return; tg->avg_idletime = (tg->avg_idletime * 7 + now - last_finish_time) >> 3; tg->checked_last_finish_time = last_finish_time; } static void throtl_update_latency_buckets(struct throtl_data *td) { struct avg_latency_bucket avg_latency[2][LATENCY_BUCKET_SIZE]; int i, cpu, rw; unsigned long last_latency[2] = { 0 }; unsigned long latency[2]; if (!blk_queue_nonrot(td->queue) || !td->limit_valid[LIMIT_LOW]) return; if (time_before(jiffies, td->last_calculate_time + HZ)) return; td->last_calculate_time = jiffies; memset(avg_latency, 0, sizeof(avg_latency)); for (rw = READ; rw <= WRITE; rw++) { for (i = 0; i < LATENCY_BUCKET_SIZE; i++) { struct latency_bucket *tmp = &td->tmp_buckets[rw][i]; for_each_possible_cpu(cpu) { struct latency_bucket *bucket; /* this isn't race free, but ok in practice */ bucket = per_cpu_ptr(td->latency_buckets[rw], cpu); tmp->total_latency += bucket[i].total_latency; tmp->samples += bucket[i].samples; bucket[i].total_latency = 0; bucket[i].samples = 0; } if (tmp->samples >= 32) { int samples = tmp->samples; latency[rw] = tmp->total_latency; tmp->total_latency = 0; tmp->samples = 0; latency[rw] /= samples; if (latency[rw] == 0) continue; avg_latency[rw][i].latency = latency[rw]; } } } for (rw = READ; rw <= WRITE; rw++) { for (i = 0; i < LATENCY_BUCKET_SIZE; i++) { if (!avg_latency[rw][i].latency) { if (td->avg_buckets[rw][i].latency < last_latency[rw]) td->avg_buckets[rw][i].latency = last_latency[rw]; continue; } if (!td->avg_buckets[rw][i].valid) latency[rw] = avg_latency[rw][i].latency; else latency[rw] = (td->avg_buckets[rw][i].latency * 7 + avg_latency[rw][i].latency) >> 3; td->avg_buckets[rw][i].latency = max(latency[rw], last_latency[rw]); td->avg_buckets[rw][i].valid = true; last_latency[rw] = td->avg_buckets[rw][i].latency; } } for (i = 0; i < LATENCY_BUCKET_SIZE; i++) throtl_log(&td->service_queue, "Latency bucket %d: read latency=%ld, read valid=%d, " "write latency=%ld, write valid=%d", i, td->avg_buckets[READ][i].latency, td->avg_buckets[READ][i].valid, td->avg_buckets[WRITE][i].latency, td->avg_buckets[WRITE][i].valid); } #else static inline void throtl_update_latency_buckets(struct throtl_data *td) { } static void blk_throtl_update_idletime(struct throtl_grp *tg) { } static void throtl_downgrade_check(struct throtl_grp *tg) { } static void throtl_upgrade_check(struct throtl_grp *tg) { } static bool throtl_can_upgrade(struct throtl_data *td, struct throtl_grp *this_tg) { return false; } static void throtl_upgrade_state(struct throtl_data *td) { } #endif bool __blk_throtl_bio(struct bio *bio) { struct request_queue *q = bdev_get_queue(bio->bi_bdev); struct blkcg_gq *blkg = bio->bi_blkg; struct throtl_qnode *qn = NULL; struct throtl_grp *tg = blkg_to_tg(blkg); struct throtl_service_queue *sq; bool rw = bio_data_dir(bio); bool throttled = false; struct throtl_data *td = tg->td; rcu_read_lock(); if (!cgroup_subsys_on_dfl(io_cgrp_subsys)) { blkg_rwstat_add(&tg->stat_bytes, bio->bi_opf, bio->bi_iter.bi_size); blkg_rwstat_add(&tg->stat_ios, bio->bi_opf, 1); } spin_lock_irq(&q->queue_lock); throtl_update_latency_buckets(td); blk_throtl_update_idletime(tg); sq = &tg->service_queue; again: while (true) { if (tg->last_low_overflow_time[rw] == 0) tg->last_low_overflow_time[rw] = jiffies; throtl_downgrade_check(tg); throtl_upgrade_check(tg); /* throtl is FIFO - if bios are already queued, should queue */ if (sq->nr_queued[rw]) break; /* if above limits, break to queue */ if (!tg_may_dispatch(tg, bio, NULL)) { tg->last_low_overflow_time[rw] = jiffies; if (throtl_can_upgrade(td, tg)) { throtl_upgrade_state(td); goto again; } break; } /* within limits, let's charge and dispatch directly */ throtl_charge_bio(tg, bio); /* * We need to trim slice even when bios are not being queued * otherwise it might happen that a bio is not queued for * a long time and slice keeps on extending and trim is not * called for a long time. Now if limits are reduced suddenly * we take into account all the IO dispatched so far at new * low rate and * newly queued IO gets a really long dispatch * time. * * So keep on trimming slice even if bio is not queued. */ throtl_trim_slice(tg, rw); /* * @bio passed through this layer without being throttled. * Climb up the ladder. If we're already at the top, it * can be executed directly. */ qn = &tg->qnode_on_parent[rw]; sq = sq->parent_sq; tg = sq_to_tg(sq); if (!tg) { bio_set_flag(bio, BIO_BPS_THROTTLED); goto out_unlock; } } /* out-of-limit, queue to @tg */ throtl_log(sq, "[%c] bio. bdisp=%llu sz=%u bps=%llu iodisp=%u iops=%u queued=%d/%d", rw == READ ? 'R' : 'W', tg->bytes_disp[rw], bio->bi_iter.bi_size, tg_bps_limit(tg, rw), tg->io_disp[rw], tg_iops_limit(tg, rw), sq->nr_queued[READ], sq->nr_queued[WRITE]); tg->last_low_overflow_time[rw] = jiffies; td->nr_queued[rw]++; throtl_add_bio_tg(bio, qn, tg); throttled = true; /* * Update @tg's dispatch time and force schedule dispatch if @tg * was empty before @bio. The forced scheduling isn't likely to * cause undue delay as @bio is likely to be dispatched directly if * its @tg's disptime is not in the future. */ if (tg->flags & THROTL_TG_WAS_EMPTY) { tg_update_disptime(tg); throtl_schedule_next_dispatch(tg->service_queue.parent_sq, true); } out_unlock: #ifdef CONFIG_BLK_DEV_THROTTLING_LOW if (throttled || !td->track_bio_latency) bio->bi_issue.value |= BIO_ISSUE_THROTL_SKIP_LATENCY; #endif spin_unlock_irq(&q->queue_lock); rcu_read_unlock(); return throttled; } #ifdef CONFIG_BLK_DEV_THROTTLING_LOW static void throtl_track_latency(struct throtl_data *td, sector_t size, enum req_op op, unsigned long time) { const bool rw = op_is_write(op); struct latency_bucket *latency; int index; if (!td || td->limit_index != LIMIT_LOW || !(op == REQ_OP_READ || op == REQ_OP_WRITE) || !blk_queue_nonrot(td->queue)) return; index = request_bucket_index(size); latency = get_cpu_ptr(td->latency_buckets[rw]); latency[index].total_latency += time; latency[index].samples++; put_cpu_ptr(td->latency_buckets[rw]); } void blk_throtl_stat_add(struct request *rq, u64 time_ns) { struct request_queue *q = rq->q; struct throtl_data *td = q->td; throtl_track_latency(td, blk_rq_stats_sectors(rq), req_op(rq), time_ns >> 10); } void blk_throtl_bio_endio(struct bio *bio) { struct blkcg_gq *blkg; struct throtl_grp *tg; u64 finish_time_ns; unsigned long finish_time; unsigned long start_time; unsigned long lat; int rw = bio_data_dir(bio); blkg = bio->bi_blkg; if (!blkg) return; tg = blkg_to_tg(blkg); if (!tg->td->limit_valid[LIMIT_LOW]) return; finish_time_ns = ktime_get_ns(); tg->last_finish_time = finish_time_ns >> 10; start_time = bio_issue_time(&bio->bi_issue) >> 10; finish_time = __bio_issue_time(finish_time_ns) >> 10; if (!start_time || finish_time <= start_time) return; lat = finish_time - start_time; /* this is only for bio based driver */ if (!(bio->bi_issue.value & BIO_ISSUE_THROTL_SKIP_LATENCY)) throtl_track_latency(tg->td, bio_issue_size(&bio->bi_issue), bio_op(bio), lat); if (tg->latency_target && lat >= tg->td->filtered_latency) { int bucket; unsigned int threshold; bucket = request_bucket_index(bio_issue_size(&bio->bi_issue)); threshold = tg->td->avg_buckets[rw][bucket].latency + tg->latency_target; if (lat > threshold) tg->bad_bio_cnt++; /* * Not race free, could get wrong count, which means cgroups * will be throttled */ tg->bio_cnt++; } if (time_after(jiffies, tg->bio_cnt_reset_time) || tg->bio_cnt > 1024) { tg->bio_cnt_reset_time = tg->td->throtl_slice + jiffies; tg->bio_cnt /= 2; tg->bad_bio_cnt /= 2; } } #endif int blk_throtl_init(struct gendisk *disk) { struct request_queue *q = disk->queue; struct throtl_data *td; int ret; td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node); if (!td) return -ENOMEM; td->latency_buckets[READ] = __alloc_percpu(sizeof(struct latency_bucket) * LATENCY_BUCKET_SIZE, __alignof__(u64)); if (!td->latency_buckets[READ]) { kfree(td); return -ENOMEM; } td->latency_buckets[WRITE] = __alloc_percpu(sizeof(struct latency_bucket) * LATENCY_BUCKET_SIZE, __alignof__(u64)); if (!td->latency_buckets[WRITE]) { free_percpu(td->latency_buckets[READ]); kfree(td); return -ENOMEM; } INIT_WORK(&td->dispatch_work, blk_throtl_dispatch_work_fn); throtl_service_queue_init(&td->service_queue); q->td = td; td->queue = q; td->limit_valid[LIMIT_MAX] = true; td->limit_index = LIMIT_MAX; td->low_upgrade_time = jiffies; td->low_downgrade_time = jiffies; /* activate policy */ ret = blkcg_activate_policy(q, &blkcg_policy_throtl); if (ret) { free_percpu(td->latency_buckets[READ]); free_percpu(td->latency_buckets[WRITE]); kfree(td); } return ret; } void blk_throtl_exit(struct gendisk *disk) { struct request_queue *q = disk->queue; BUG_ON(!q->td); del_timer_sync(&q->td->service_queue.pending_timer); throtl_shutdown_wq(q); blkcg_deactivate_policy(q, &blkcg_policy_throtl); free_percpu(q->td->latency_buckets[READ]); free_percpu(q->td->latency_buckets[WRITE]); kfree(q->td); } void blk_throtl_register(struct gendisk *disk) { struct request_queue *q = disk->queue; struct throtl_data *td; int i; td = q->td; BUG_ON(!td); if (blk_queue_nonrot(q)) { td->throtl_slice = DFL_THROTL_SLICE_SSD; td->filtered_latency = LATENCY_FILTERED_SSD; } else { td->throtl_slice = DFL_THROTL_SLICE_HD; td->filtered_latency = LATENCY_FILTERED_HD; for (i = 0; i < LATENCY_BUCKET_SIZE; i++) { td->avg_buckets[READ][i].latency = DFL_HD_BASELINE_LATENCY; td->avg_buckets[WRITE][i].latency = DFL_HD_BASELINE_LATENCY; } } #ifndef CONFIG_BLK_DEV_THROTTLING_LOW /* if no low limit, use previous default */ td->throtl_slice = DFL_THROTL_SLICE_HD; #endif td->track_bio_latency = !queue_is_mq(q); if (!td->track_bio_latency) blk_stat_enable_accounting(q); } #ifdef CONFIG_BLK_DEV_THROTTLING_LOW ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page) { if (!q->td) return -EINVAL; return sprintf(page, "%u\n", jiffies_to_msecs(q->td->throtl_slice)); } ssize_t blk_throtl_sample_time_store(struct request_queue *q, const char *page, size_t count) { unsigned long v; unsigned long t; if (!q->td) return -EINVAL; if (kstrtoul(page, 10, &v)) return -EINVAL; t = msecs_to_jiffies(v); if (t == 0 || t > MAX_THROTL_SLICE) return -EINVAL; q->td->throtl_slice = t; return count; } #endif static int __init throtl_init(void) { kthrotld_workqueue = alloc_workqueue("kthrotld", WQ_MEM_RECLAIM, 0); if (!kthrotld_workqueue) panic("Failed to create kthrotld\n"); return blkcg_policy_register(&blkcg_policy_throtl); } module_init(throtl_init); |
| 69 13 959 62 1585 651 162 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM sched #define TRACE_INCLUDE_PATH trace/hooks #if !defined(_TRACE_HOOK_SCHED_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_HOOK_SCHED_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 task_struct; DECLARE_RESTRICTED_HOOK(android_rvh_select_task_rq_fair, TP_PROTO(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags, int *new_cpu), TP_ARGS(p, prev_cpu, sd_flag, wake_flags, new_cpu), 1); DECLARE_RESTRICTED_HOOK(android_rvh_select_task_rq_rt, TP_PROTO(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags, int *new_cpu), TP_ARGS(p, prev_cpu, sd_flag, wake_flags, new_cpu), 1); DECLARE_RESTRICTED_HOOK(android_rvh_select_fallback_rq, TP_PROTO(int cpu, struct task_struct *p, int *new_cpu), TP_ARGS(cpu, p, new_cpu), 1); struct rq; DECLARE_HOOK(android_vh_scheduler_tick, TP_PROTO(struct rq *rq), TP_ARGS(rq)); DECLARE_RESTRICTED_HOOK(android_rvh_enqueue_task, TP_PROTO(struct rq *rq, struct task_struct *p, int flags), TP_ARGS(rq, p, flags), 1); DECLARE_RESTRICTED_HOOK(android_rvh_dequeue_task, TP_PROTO(struct rq *rq, struct task_struct *p, int flags), TP_ARGS(rq, p, flags), 1); DECLARE_RESTRICTED_HOOK(android_rvh_can_migrate_task, TP_PROTO(struct task_struct *p, int dst_cpu, int *can_migrate), TP_ARGS(p, dst_cpu, can_migrate), 1); DECLARE_RESTRICTED_HOOK(android_rvh_find_lowest_rq, TP_PROTO(struct task_struct *p, struct cpumask *local_cpu_mask, int ret, int *lowest_cpu), TP_ARGS(p, local_cpu_mask, ret, lowest_cpu), 1); DECLARE_RESTRICTED_HOOK(android_rvh_prepare_prio_fork, TP_PROTO(struct task_struct *p), TP_ARGS(p), 1); DECLARE_RESTRICTED_HOOK(android_rvh_finish_prio_fork, TP_PROTO(struct task_struct *p), TP_ARGS(p), 1); DECLARE_RESTRICTED_HOOK(android_rvh_rtmutex_force_update, TP_PROTO(struct task_struct *p, struct task_struct *pi_task, int *update), TP_ARGS(p, pi_task, update), 1); DECLARE_RESTRICTED_HOOK(android_rvh_rtmutex_prepare_setprio, TP_PROTO(struct task_struct *p, struct task_struct *pi_task), TP_ARGS(p, pi_task), 1); DECLARE_RESTRICTED_HOOK(android_rvh_rto_next_cpu, TP_PROTO(int rto_cpu, struct cpumask *rto_mask, int *cpu), TP_ARGS(rto_cpu, rto_mask, cpu), 1); DECLARE_RESTRICTED_HOOK(android_rvh_is_cpu_allowed, TP_PROTO(struct task_struct *p, int cpu, bool *allowed), TP_ARGS(p, cpu, allowed), 1); DECLARE_RESTRICTED_HOOK(android_rvh_get_nohz_timer_target, TP_PROTO(int *cpu, bool *done), TP_ARGS(cpu, done), 1); DECLARE_RESTRICTED_HOOK(android_rvh_set_user_nice, TP_PROTO(struct task_struct *p, long *nice, bool *allowed), TP_ARGS(p, nice, allowed), 1); DECLARE_RESTRICTED_HOOK(android_rvh_set_user_nice_locked, TP_PROTO(struct task_struct *p, long *nice), TP_ARGS(p, nice), 1); DECLARE_RESTRICTED_HOOK(android_rvh_setscheduler, TP_PROTO(struct task_struct *p), TP_ARGS(p), 1); DECLARE_RESTRICTED_HOOK(android_rvh_setscheduler_prio, TP_PROTO(struct task_struct *p), TP_ARGS(p), 1); struct sched_group; DECLARE_RESTRICTED_HOOK(android_rvh_find_busiest_group, TP_PROTO(struct sched_group *busiest, struct rq *dst_rq, int *out_balance), TP_ARGS(busiest, dst_rq, out_balance), 1); DECLARE_HOOK(android_vh_dump_throttled_rt_tasks, TP_PROTO(int cpu, u64 clock, ktime_t rt_period, u64 rt_runtime, s64 rt_period_timer_expires), TP_ARGS(cpu, clock, rt_period, rt_runtime, rt_period_timer_expires)); DECLARE_HOOK(android_vh_jiffies_update, TP_PROTO(void *unused), TP_ARGS(unused)); struct rq_flags; DECLARE_RESTRICTED_HOOK(android_rvh_sched_newidle_balance, TP_PROTO(struct rq *this_rq, struct rq_flags *rf, int *pulled_task, int *done), TP_ARGS(this_rq, rf, pulled_task, done), 1); DECLARE_RESTRICTED_HOOK(android_rvh_sched_nohz_balancer_kick, TP_PROTO(struct rq *rq, unsigned int *flags, int *done), TP_ARGS(rq, flags, done), 1); DECLARE_RESTRICTED_HOOK(android_rvh_sched_rebalance_domains, TP_PROTO(struct rq *rq, int *continue_balancing), TP_ARGS(rq, continue_balancing), 1); DECLARE_RESTRICTED_HOOK(android_rvh_find_busiest_queue, TP_PROTO(int dst_cpu, struct sched_group *group, struct cpumask *env_cpus, struct rq **busiest, int *done), TP_ARGS(dst_cpu, group, env_cpus, busiest, done), 1); DECLARE_RESTRICTED_HOOK(android_rvh_migrate_queued_task, TP_PROTO(struct rq *rq, struct rq_flags *rf, struct task_struct *p, int new_cpu, int *detached), TP_ARGS(rq, rf, p, new_cpu, detached), 1); DECLARE_RESTRICTED_HOOK(android_rvh_cpu_overutilized, TP_PROTO(int cpu, int *overutilized), TP_ARGS(cpu, overutilized), 1); DECLARE_RESTRICTED_HOOK(android_rvh_sched_setaffinity, TP_PROTO(struct task_struct *p, const struct cpumask *in_mask, int *retval), TP_ARGS(p, in_mask, retval), 1); DECLARE_RESTRICTED_HOOK(android_rvh_sched_getaffinity, TP_PROTO(struct task_struct *p, struct cpumask *in_mask), TP_ARGS(p, in_mask), 1); DECLARE_RESTRICTED_HOOK(android_rvh_set_task_cpu, TP_PROTO(struct task_struct *p, unsigned int new_cpu), TP_ARGS(p, new_cpu), 1); DECLARE_RESTRICTED_HOOK(android_rvh_try_to_wake_up, TP_PROTO(struct task_struct *p), TP_ARGS(p), 1); DECLARE_RESTRICTED_HOOK(android_rvh_try_to_wake_up_success, TP_PROTO(struct task_struct *p), TP_ARGS(p), 1); DECLARE_RESTRICTED_HOOK(android_rvh_sched_fork, TP_PROTO(struct task_struct *p), TP_ARGS(p), 1); DECLARE_RESTRICTED_HOOK(android_rvh_wake_up_new_task, TP_PROTO(struct task_struct *p), TP_ARGS(p), 1); DECLARE_RESTRICTED_HOOK(android_rvh_new_task_stats, TP_PROTO(struct task_struct *p), TP_ARGS(p), 1); DECLARE_RESTRICTED_HOOK(android_rvh_flush_task, TP_PROTO(struct task_struct *prev), TP_ARGS(prev), 1); DECLARE_RESTRICTED_HOOK(android_rvh_tick_entry, TP_PROTO(struct rq *rq), TP_ARGS(rq), 1); DECLARE_RESTRICTED_HOOK(android_rvh_schedule, TP_PROTO(unsigned int sched_mode, struct task_struct *prev, struct task_struct *next, struct rq *rq), TP_ARGS(sched_mode, prev, next, rq), 1); DECLARE_RESTRICTED_HOOK(android_rvh_sched_cpu_starting, TP_PROTO(int cpu), TP_ARGS(cpu), 1); DECLARE_RESTRICTED_HOOK(android_rvh_sched_cpu_dying, TP_PROTO(int cpu), TP_ARGS(cpu), 1); DECLARE_RESTRICTED_HOOK(android_rvh_account_irq, TP_PROTO(struct task_struct *curr, int cpu, s64 delta, bool start), TP_ARGS(curr, cpu, delta, start), 1); struct sched_entity; DECLARE_RESTRICTED_HOOK(android_rvh_place_entity, TP_PROTO(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial, u64 *vruntime), TP_ARGS(cfs_rq, se, initial, vruntime), 1); DECLARE_RESTRICTED_HOOK(android_rvh_build_perf_domains, TP_PROTO(bool *eas_check), TP_ARGS(eas_check), 1); DECLARE_RESTRICTED_HOOK(android_rvh_update_cpu_capacity, TP_PROTO(int cpu, unsigned long *capacity), TP_ARGS(cpu, capacity), 1); DECLARE_RESTRICTED_HOOK(android_rvh_update_misfit_status, TP_PROTO(struct task_struct *p, struct rq *rq, bool *need_update), TP_ARGS(p, rq, need_update), 1); DECLARE_RESTRICTED_HOOK(android_rvh_util_fits_cpu, TP_PROTO(unsigned long util, unsigned long uclamp_min, unsigned long uclamp_max, int cpu, bool *fits, bool *done), TP_ARGS(util, uclamp_min, uclamp_max, cpu, fits, done), 1); DECLARE_RESTRICTED_HOOK(android_rvh_update_cpus_allowed, TP_PROTO(struct task_struct *p, cpumask_var_t cpus_requested, const struct cpumask *new_mask, int *ret), TP_ARGS(p, cpus_requested, new_mask, ret), 1); DECLARE_RESTRICTED_HOOK(android_rvh_sched_fork_init, TP_PROTO(struct task_struct *p), TP_ARGS(p), 1); DECLARE_RESTRICTED_HOOK(android_rvh_ttwu_cond, TP_PROTO(int cpu, bool *cond), TP_ARGS(cpu, cond), 1); DECLARE_RESTRICTED_HOOK(android_rvh_schedule_bug, TP_PROTO(void *unused), TP_ARGS(unused), 1); DECLARE_RESTRICTED_HOOK(android_rvh_sched_exec, TP_PROTO(bool *cond), TP_ARGS(cond), 1); DECLARE_HOOK(android_vh_build_sched_domains, TP_PROTO(bool has_asym), TP_ARGS(has_asym)); DECLARE_RESTRICTED_HOOK(android_rvh_check_preempt_tick, TP_PROTO(struct task_struct *p, unsigned long *ideal_runtime, bool *skip_preempt, unsigned long delta_exec, struct cfs_rq *cfs_rq, struct sched_entity *curr, unsigned int granularity), TP_ARGS(p, ideal_runtime, skip_preempt, delta_exec, cfs_rq, curr, granularity), 1); DECLARE_RESTRICTED_HOOK(android_rvh_check_preempt_wakeup_ignore, TP_PROTO(struct task_struct *p, bool *ignore), TP_ARGS(p, ignore), 1); DECLARE_RESTRICTED_HOOK(android_rvh_replace_next_task_fair, TP_PROTO(struct rq *rq, struct task_struct **p, struct sched_entity **se, bool *repick, bool simple, struct task_struct *prev), TP_ARGS(rq, p, se, repick, simple, prev), 1); DECLARE_RESTRICTED_HOOK(android_rvh_sched_balance_rt, TP_PROTO(struct rq *rq, struct task_struct *p, int *done), TP_ARGS(rq, p, done), 1); struct cfs_rq; DECLARE_RESTRICTED_HOOK(android_rvh_pick_next_entity, TP_PROTO(struct cfs_rq *cfs_rq, struct sched_entity *curr, struct sched_entity **se), TP_ARGS(cfs_rq, curr, se), 1); DECLARE_RESTRICTED_HOOK(android_rvh_check_preempt_wakeup, TP_PROTO(struct rq *rq, struct task_struct *p, bool *preempt, bool *nopreempt, int wake_flags, struct sched_entity *se, struct sched_entity *pse, int next_buddy_marked, unsigned int granularity), TP_ARGS(rq, p, preempt, nopreempt, wake_flags, se, pse, next_buddy_marked, granularity), 1); DECLARE_RESTRICTED_HOOK(android_rvh_set_cpus_allowed_by_task, TP_PROTO(const struct cpumask *cpu_valid_mask, const struct cpumask *new_mask, struct task_struct *p, unsigned int *dest_cpu), TP_ARGS(cpu_valid_mask, new_mask, p, dest_cpu), 1); DECLARE_RESTRICTED_HOOK(android_rvh_do_sched_yield, TP_PROTO(struct rq *rq), TP_ARGS(rq), 1); DECLARE_RESTRICTED_HOOK(android_rvh_before_do_sched_yield, TP_PROTO(long *unused), TP_ARGS(unused), 1); DECLARE_HOOK(android_vh_free_task, TP_PROTO(struct task_struct *p), TP_ARGS(p)); DECLARE_HOOK(android_vh_copy_process, TP_PROTO(struct task_struct *p, int nr_threads, int current_signal_nr_threads), TP_ARGS(p, nr_threads, current_signal_nr_threads)); DECLARE_HOOK(android_vh_irqtime_account_process_tick, TP_PROTO(struct task_struct *p, struct rq *rq, int user_tick, int ticks), TP_ARGS(p, rq, user_tick, ticks)); enum uclamp_id; struct uclamp_se; DECLARE_RESTRICTED_HOOK(android_rvh_uclamp_eff_get, TP_PROTO(struct task_struct *p, enum uclamp_id clamp_id, struct uclamp_se *uclamp_max, struct uclamp_se *uclamp_eff, int *ret), TP_ARGS(p, clamp_id, uclamp_max, uclamp_eff, ret), 1); DECLARE_RESTRICTED_HOOK(android_rvh_after_enqueue_task, TP_PROTO(struct rq *rq, struct task_struct *p, int flags), TP_ARGS(rq, p, flags), 1); DECLARE_RESTRICTED_HOOK(android_rvh_after_dequeue_task, TP_PROTO(struct rq *rq, struct task_struct *p, int flags), TP_ARGS(rq, p, flags), 1); struct cfs_rq; struct sched_entity; struct rq_flags; DECLARE_RESTRICTED_HOOK(android_rvh_enqueue_entity, TP_PROTO(struct cfs_rq *cfs, struct sched_entity *se), TP_ARGS(cfs, se), 1); DECLARE_RESTRICTED_HOOK(android_rvh_dequeue_entity, TP_PROTO(struct cfs_rq *cfs, struct sched_entity *se), TP_ARGS(cfs, se), 1); DECLARE_RESTRICTED_HOOK(android_rvh_entity_tick, TP_PROTO(struct cfs_rq *cfs_rq, struct sched_entity *se), TP_ARGS(cfs_rq, se), 1); DECLARE_RESTRICTED_HOOK(android_rvh_enqueue_task_fair, TP_PROTO(struct rq *rq, struct task_struct *p, int flags), TP_ARGS(rq, p, flags), 1); DECLARE_RESTRICTED_HOOK(android_rvh_dequeue_task_fair, TP_PROTO(struct rq *rq, struct task_struct *p, int flags), TP_ARGS(rq, p, flags), 1); DECLARE_HOOK(android_vh_sched_stat_runtime_rt, TP_PROTO(struct task_struct *tsk, u64 delta), TP_ARGS(tsk, delta)); DECLARE_RESTRICTED_HOOK(android_rvh_util_est_update, TP_PROTO(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep, int *ret), TP_ARGS(cfs_rq, p, task_sleep, ret), 1); DECLARE_HOOK(android_vh_setscheduler_uclamp, TP_PROTO(struct task_struct *tsk, int clamp_id, unsigned int value), TP_ARGS(tsk, clamp_id, value)); DECLARE_HOOK(android_vh_uclamp_validate, TP_PROTO(struct task_struct *p, const struct sched_attr *attr, bool user, int *ret, bool *done), TP_ARGS(p, attr, user, ret, done)); DECLARE_HOOK(android_vh_update_topology_flags_workfn, TP_PROTO(void *unused), TP_ARGS(unused)); DECLARE_RESTRICTED_HOOK(android_rvh_update_thermal_stats, TP_PROTO(int cpu), TP_ARGS(cpu), 1); DECLARE_HOOK(android_vh_do_wake_up_sync, TP_PROTO(struct wait_queue_head *wq_head, int *done, struct sock *sk), TP_ARGS(wq_head, done, sk)); DECLARE_HOOK(android_vh_set_wake_flags, TP_PROTO(int *wake_flags, unsigned int *mode), TP_ARGS(wake_flags, mode)); DECLARE_RESTRICTED_HOOK(android_rvh_find_new_ilb, TP_PROTO(struct cpumask *nohz_idle_cpus_mask, int *ilb), TP_ARGS(nohz_idle_cpus_mask, ilb), 1); DECLARE_RESTRICTED_HOOK(android_rvh_find_energy_efficient_cpu, TP_PROTO(struct task_struct *p, int prev_cpu, int sync, int *new_cpu), TP_ARGS(p, prev_cpu, sync, new_cpu), 1); DECLARE_HOOK(android_vh_sched_pelt_multiplier, TP_PROTO(unsigned int old, unsigned int cur, int *ret), TP_ARGS(old, cur, ret)); struct cpufreq_policy; DECLARE_HOOK(android_vh_map_util_freq, TP_PROTO(unsigned long util, unsigned long freq, unsigned long cap, unsigned long *next_freq, struct cpufreq_policy *policy, bool *need_freq_update), TP_ARGS(util, freq, cap, next_freq, policy, need_freq_update)); DECLARE_RESTRICTED_HOOK(android_rvh_set_cpus_allowed_comm, TP_PROTO(struct task_struct *p, const struct cpumask *new_mask), TP_ARGS(p, new_mask), 1); DECLARE_HOOK(android_vh_sched_setaffinity_early, TP_PROTO(struct task_struct *p, const struct cpumask *new_mask, bool *retval), TP_ARGS(p, new_mask, retval)); DECLARE_HOOK(android_vh_account_process_tick_gran, TP_PROTO(int user_tick, int *ticks), TP_ARGS(user_tick, ticks)); DECLARE_HOOK(android_vh_account_task_time, TP_PROTO(struct task_struct *p, struct rq *rq, int user_tick, int ticks), TP_ARGS(p, rq, user_tick, ticks)); DECLARE_HOOK(android_vh_dup_task_struct, TP_PROTO(struct task_struct *tsk, struct task_struct *orig), TP_ARGS(tsk, orig)); DECLARE_RESTRICTED_HOOK(android_rvh_post_init_entity_util_avg, TP_PROTO(struct sched_entity *se), TP_ARGS(se), 1); DECLARE_RESTRICTED_HOOK(android_rvh_effective_cpu_util, TP_PROTO(int cpu, unsigned long util_cfs, unsigned long max, int type, struct task_struct *p, unsigned long *new_util), TP_ARGS(cpu, util_cfs, max, type, p, new_util), 1); DECLARE_HOOK(android_vh_mmput, TP_PROTO(struct mm_struct *mm), TP_ARGS(mm)); struct sched_attr; DECLARE_HOOK(android_vh_set_sugov_sched_attr, TP_PROTO(struct sched_attr *attr), TP_ARGS(attr)); DECLARE_RESTRICTED_HOOK(android_rvh_set_iowait, TP_PROTO(struct task_struct *p, struct rq *rq, int *should_iowait_boost), TP_ARGS(p, rq, should_iowait_boost), 1); DECLARE_RESTRICTED_HOOK(android_rvh_attach_entity_load_avg, TP_PROTO(struct cfs_rq *cfs_rq, struct sched_entity *se), TP_ARGS(cfs_rq, se), 1); DECLARE_RESTRICTED_HOOK(android_rvh_detach_entity_load_avg, TP_PROTO(struct cfs_rq *cfs_rq, struct sched_entity *se), TP_ARGS(cfs_rq, se), 1); DECLARE_RESTRICTED_HOOK(android_rvh_update_load_avg, TP_PROTO(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se), TP_ARGS(now, cfs_rq, se), 1); DECLARE_RESTRICTED_HOOK(android_rvh_update_load_sum, TP_PROTO(struct sched_avg *sa, u64 *delta, unsigned int *sched_pelt_lshift), TP_ARGS(sa, delta, sched_pelt_lshift), 1); DECLARE_RESTRICTED_HOOK(android_rvh_remove_entity_load_avg, TP_PROTO(struct cfs_rq *cfs_rq, struct sched_entity *se), TP_ARGS(cfs_rq, se), 1); DECLARE_RESTRICTED_HOOK(android_rvh_update_blocked_fair, TP_PROTO(struct rq *rq), TP_ARGS(rq), 1); DECLARE_RESTRICTED_HOOK(android_rvh_update_rt_rq_load_avg, TP_PROTO(u64 now, struct rq *rq, struct task_struct *tsk, int running), TP_ARGS(now, rq, tsk, running), 1); DECLARE_HOOK(android_vh_prio_inheritance, TP_PROTO(struct task_struct *p, int *saved_prio, bool *prio_inherited), TP_ARGS(p, saved_prio, prio_inherited)); DECLARE_HOOK(android_vh_prio_restore, TP_PROTO(int saved_prio), TP_ARGS(saved_prio)); DECLARE_HOOK(android_vh_set_task_comm, TP_PROTO(struct task_struct *p), TP_ARGS(p)); #endif /* _TRACE_HOOK_SCHED_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 2107 583 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 | // SPDX-License-Identifier: GPL-2.0 /* * class.c - basic device class management * * Copyright (c) 2002-3 Patrick Mochel * Copyright (c) 2002-3 Open Source Development Labs * Copyright (c) 2003-2004 Greg Kroah-Hartman * Copyright (c) 2003-2004 IBM Corp. */ #include <linux/device/class.h> #include <linux/device.h> #include <linux/module.h> #include <linux/init.h> #include <linux/string.h> #include <linux/kdev_t.h> #include <linux/err.h> #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/mutex.h> #include "base.h" #define to_class_attr(_attr) container_of(_attr, struct class_attribute, attr) static ssize_t class_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct class_attribute *class_attr = to_class_attr(attr); struct subsys_private *cp = to_subsys_private(kobj); ssize_t ret = -EIO; if (class_attr->show) ret = class_attr->show(cp->class, class_attr, buf); return ret; } static ssize_t class_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { struct class_attribute *class_attr = to_class_attr(attr); struct subsys_private *cp = to_subsys_private(kobj); ssize_t ret = -EIO; if (class_attr->store) ret = class_attr->store(cp->class, class_attr, buf, count); return ret; } static void class_release(struct kobject *kobj) { struct subsys_private *cp = to_subsys_private(kobj); struct class *class = cp->class; pr_debug("class '%s': release.\n", class->name); if (class->class_release) class->class_release(class); else pr_debug("class '%s' does not have a release() function, " "be careful\n", class->name); kfree(cp); } static const struct kobj_ns_type_operations *class_child_ns_type(struct kobject *kobj) { struct subsys_private *cp = to_subsys_private(kobj); struct class *class = cp->class; return class->ns_type; } static const struct sysfs_ops class_sysfs_ops = { .show = class_attr_show, .store = class_attr_store, }; static struct kobj_type class_ktype = { .sysfs_ops = &class_sysfs_ops, .release = class_release, .child_ns_type = class_child_ns_type, }; /* Hotplug events for classes go to the class subsys */ static struct kset *class_kset; int class_create_file_ns(struct class *cls, const struct class_attribute *attr, const void *ns) { int error; if (cls) error = sysfs_create_file_ns(&cls->p->subsys.kobj, &attr->attr, ns); else error = -EINVAL; return error; } void class_remove_file_ns(struct class *cls, const struct class_attribute *attr, const void *ns) { if (cls) sysfs_remove_file_ns(&cls->p->subsys.kobj, &attr->attr, ns); } static struct class *class_get(struct class *cls) { if (cls) kset_get(&cls->p->subsys); return cls; } static void class_put(struct class *cls) { if (cls) kset_put(&cls->p->subsys); } static struct device *klist_class_to_dev(struct klist_node *n) { struct device_private *p = to_device_private_class(n); return p->device; } static void klist_class_dev_get(struct klist_node *n) { struct device *dev = klist_class_to_dev(n); get_device(dev); } static void klist_class_dev_put(struct klist_node *n) { struct device *dev = klist_class_to_dev(n); put_device(dev); } static int class_add_groups(struct class *cls, const struct attribute_group **groups) { return sysfs_create_groups(&cls->p->subsys.kobj, groups); } static void class_remove_groups(struct class *cls, const struct attribute_group **groups) { return sysfs_remove_groups(&cls->p->subsys.kobj, groups); } int __class_register(struct class *cls, struct lock_class_key *key) { struct subsys_private *cp; int error; pr_debug("device class '%s': registering\n", cls->name); cp = kzalloc(sizeof(*cp), GFP_KERNEL); if (!cp) return -ENOMEM; klist_init(&cp->klist_devices, klist_class_dev_get, klist_class_dev_put); INIT_LIST_HEAD(&cp->interfaces); kset_init(&cp->glue_dirs); __mutex_init(&cp->mutex, "subsys mutex", key); error = kobject_set_name(&cp->subsys.kobj, "%s", cls->name); if (error) { kfree(cp); return error; } /* set the default /sys/dev directory for devices of this class */ if (!cls->dev_kobj) cls->dev_kobj = sysfs_dev_char_kobj; #if defined(CONFIG_BLOCK) /* let the block class directory show up in the root of sysfs */ if (!sysfs_deprecated || cls != &block_class) cp->subsys.kobj.kset = class_kset; #else cp->subsys.kobj.kset = class_kset; #endif cp->subsys.kobj.ktype = &class_ktype; cp->class = cls; cls->p = cp; error = kset_register(&cp->subsys); if (error) { kfree(cp); return error; } error = class_add_groups(class_get(cls), cls->class_groups); class_put(cls); if (error) { kobject_del(&cp->subsys.kobj); kfree_const(cp->subsys.kobj.name); kfree(cp); } return error; } EXPORT_SYMBOL_GPL(__class_register); void class_unregister(struct class *cls) { pr_debug("device class '%s': unregistering\n", cls->name); class_remove_groups(cls, cls->class_groups); kset_unregister(&cls->p->subsys); } static void class_create_release(struct class *cls) { pr_debug("%s called for %s\n", __func__, cls->name); kfree(cls); } /** * __class_create - create a struct class structure * @owner: pointer to the module that is to "own" this struct class * @name: pointer to a string for the name of this class. * @key: the lock_class_key for this class; used by mutex lock debugging * * This is used to create a struct class pointer that can then be used * in calls to device_create(). * * Returns &struct class pointer on success, or ERR_PTR() on error. * * Note, the pointer created here is to be destroyed when finished by * making a call to class_destroy(). */ struct class *__class_create(struct module *owner, const char *name, struct lock_class_key *key) { struct class *cls; int retval; cls = kzalloc(sizeof(*cls), GFP_KERNEL); if (!cls) { retval = -ENOMEM; goto error; } cls->name = name; cls->owner = owner; cls->class_release = class_create_release; retval = __class_register(cls, key); if (retval) goto error; return cls; error: kfree(cls); return ERR_PTR(retval); } EXPORT_SYMBOL_GPL(__class_create); /** * class_destroy - destroys a struct class structure * @cls: pointer to the struct class that is to be destroyed * * Note, the pointer to be destroyed must have been created with a call * to class_create(). */ void class_destroy(struct class *cls) { if (IS_ERR_OR_NULL(cls)) return; class_unregister(cls); } /** * class_dev_iter_init - initialize class device iterator * @iter: class iterator to initialize * @class: the class we wanna iterate over * @start: the device to start iterating from, if any * @type: device_type of the devices to iterate over, NULL for all * * Initialize class iterator @iter such that it iterates over devices * of @class. If @start is set, the list iteration will start there, * otherwise if it is NULL, the iteration starts at the beginning of * the list. */ void class_dev_iter_init(struct class_dev_iter *iter, struct class *class, struct device *start, const struct device_type *type) { struct klist_node *start_knode = NULL; if (start) start_knode = &start->p->knode_class; klist_iter_init_node(&class->p->klist_devices, &iter->ki, start_knode); iter->type = type; } EXPORT_SYMBOL_GPL(class_dev_iter_init); /** * class_dev_iter_next - iterate to the next device * @iter: class iterator to proceed * * Proceed @iter to the next device and return it. Returns NULL if * iteration is complete. * * The returned device is referenced and won't be released till * iterator is proceed to the next device or exited. The caller is * free to do whatever it wants to do with the device including * calling back into class code. */ struct device *class_dev_iter_next(struct class_dev_iter *iter) { struct klist_node *knode; struct device *dev; while (1) { knode = klist_next(&iter->ki); if (!knode) return NULL; dev = klist_class_to_dev(knode); if (!iter->type || iter->type == dev->type) return dev; } } EXPORT_SYMBOL_GPL(class_dev_iter_next); /** * class_dev_iter_exit - finish iteration * @iter: class iterator to finish * * Finish an iteration. Always call this function after iteration is * complete whether the iteration ran till the end or not. */ void class_dev_iter_exit(struct class_dev_iter *iter) { klist_iter_exit(&iter->ki); } EXPORT_SYMBOL_GPL(class_dev_iter_exit); /** * class_for_each_device - device iterator * @class: the class we're iterating * @start: the device to start with in the list, if any. * @data: data for the callback * @fn: function to be called for each device * * Iterate over @class's list of devices, and call @fn for each, * passing it @data. If @start is set, the list iteration will start * there, otherwise if it is NULL, the iteration starts at the * beginning of the list. * * We check the return of @fn each time. If it returns anything * other than 0, we break out and return that value. * * @fn is allowed to do anything including calling back into class * code. There's no locking restriction. */ int class_for_each_device(struct class *class, struct device *start, void *data, int (*fn)(struct device *, void *)) { struct class_dev_iter iter; struct device *dev; int error = 0; if (!class) return -EINVAL; if (!class->p) { WARN(1, "%s called for class '%s' before it was initialized", __func__, class->name); return -EINVAL; } class_dev_iter_init(&iter, class, start, NULL); while ((dev = class_dev_iter_next(&iter))) { error = fn(dev, data); if (error) break; } class_dev_iter_exit(&iter); return error; } EXPORT_SYMBOL_GPL(class_for_each_device); /** * class_find_device - device iterator for locating a particular device * @class: the class we're iterating * @start: Device to begin with * @data: data for the match function * @match: function to check device * * This is similar to the class_for_each_dev() function above, but it * returns a reference to a device that is 'found' for later use, as * determined by the @match callback. * * The callback should return 0 if the device doesn't match and non-zero * if it does. If the callback returns non-zero, this function will * return to the caller and not iterate over any more devices. * * Note, you will need to drop the reference with put_device() after use. * * @match is allowed to do anything including calling back into class * code. There's no locking restriction. */ struct device *class_find_device(struct class *class, struct device *start, const void *data, int (*match)(struct device *, const void *)) { struct class_dev_iter iter; struct device *dev; if (!class) return NULL; if (!class->p) { WARN(1, "%s called for class '%s' before it was initialized", __func__, class->name); return NULL; } class_dev_iter_init(&iter, class, start, NULL); while ((dev = class_dev_iter_next(&iter))) { if (match(dev, data)) { get_device(dev); break; } } class_dev_iter_exit(&iter); return dev; } EXPORT_SYMBOL_GPL(class_find_device); int class_interface_register(struct class_interface *class_intf) { struct class *parent; struct class_dev_iter iter; struct device *dev; if (!class_intf || !class_intf->class) return -ENODEV; parent = class_get(class_intf->class); if (!parent) return -EINVAL; mutex_lock(&parent->p->mutex); list_add_tail(&class_intf->node, &parent->p->interfaces); if (class_intf->add_dev) { class_dev_iter_init(&iter, parent, NULL, NULL); while ((dev = class_dev_iter_next(&iter))) class_intf->add_dev(dev, class_intf); class_dev_iter_exit(&iter); } mutex_unlock(&parent->p->mutex); return 0; } void class_interface_unregister(struct class_interface *class_intf) { struct class *parent = class_intf->class; struct class_dev_iter iter; struct device *dev; if (!parent) return; mutex_lock(&parent->p->mutex); list_del_init(&class_intf->node); if (class_intf->remove_dev) { class_dev_iter_init(&iter, parent, NULL, NULL); while ((dev = class_dev_iter_next(&iter))) class_intf->remove_dev(dev, class_intf); class_dev_iter_exit(&iter); } mutex_unlock(&parent->p->mutex); class_put(parent); } ssize_t show_class_attr_string(struct class *class, struct class_attribute *attr, char *buf) { struct class_attribute_string *cs; cs = container_of(attr, struct class_attribute_string, attr); return sysfs_emit(buf, "%s\n", cs->str); } EXPORT_SYMBOL_GPL(show_class_attr_string); struct class_compat { struct kobject *kobj; }; /** * class_compat_register - register a compatibility class * @name: the name of the class * * Compatibility class are meant as a temporary user-space compatibility * workaround when converting a family of class devices to a bus devices. */ struct class_compat *class_compat_register(const char *name) { struct class_compat *cls; cls = kmalloc(sizeof(struct class_compat), GFP_KERNEL); if (!cls) return NULL; cls->kobj = kobject_create_and_add(name, &class_kset->kobj); if (!cls->kobj) { kfree(cls); return NULL; } return cls; } EXPORT_SYMBOL_GPL(class_compat_register); /** * class_compat_unregister - unregister a compatibility class * @cls: the class to unregister */ void class_compat_unregister(struct class_compat *cls) { kobject_put(cls->kobj); kfree(cls); } EXPORT_SYMBOL_GPL(class_compat_unregister); /** * class_compat_create_link - create a compatibility class device link to * a bus device * @cls: the compatibility class * @dev: the target bus device * @device_link: an optional device to which a "device" link should be created */ int class_compat_create_link(struct class_compat *cls, struct device *dev, struct device *device_link) { int error; error = sysfs_create_link(cls->kobj, &dev->kobj, dev_name(dev)); if (error) return error; /* * Optionally add a "device" link (typically to the parent), as a * class device would have one and we want to provide as much * backwards compatibility as possible. */ if (device_link) { error = sysfs_create_link(&dev->kobj, &device_link->kobj, "device"); if (error) sysfs_remove_link(cls->kobj, dev_name(dev)); } return error; } EXPORT_SYMBOL_GPL(class_compat_create_link); /** * class_compat_remove_link - remove a compatibility class device link to * a bus device * @cls: the compatibility class * @dev: the target bus device * @device_link: an optional device to which a "device" link was previously * created */ void class_compat_remove_link(struct class_compat *cls, struct device *dev, struct device *device_link) { if (device_link) sysfs_remove_link(&dev->kobj, "device"); sysfs_remove_link(cls->kobj, dev_name(dev)); } EXPORT_SYMBOL_GPL(class_compat_remove_link); int __init classes_init(void) { class_kset = kset_create_and_add("class", NULL, NULL); if (!class_kset) return -ENOMEM; return 0; } EXPORT_SYMBOL_GPL(class_create_file_ns); EXPORT_SYMBOL_GPL(class_remove_file_ns); EXPORT_SYMBOL_GPL(class_unregister); EXPORT_SYMBOL_GPL(class_destroy); EXPORT_SYMBOL_GPL(class_interface_register); EXPORT_SYMBOL_GPL(class_interface_unregister); |
| 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 | #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 |
| 3 1 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 | // SPDX-License-Identifier: GPL-2.0-only /* * ppp_deflate.c - interface the zlib procedures for Deflate compression * and decompression (as used by gzip) to the PPP code. * * Copyright 1994-1998 Paul Mackerras. */ #include <linux/module.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/init.h> #include <linux/string.h> #include <linux/ppp_defs.h> #include <linux/ppp-comp.h> #include <linux/zlib.h> #include <asm/unaligned.h> /* * State for a Deflate (de)compressor. */ struct ppp_deflate_state { int seqno; int w_size; int unit; int mru; int debug; z_stream strm; struct compstat stats; }; #define DEFLATE_OVHD 2 /* Deflate overhead/packet */ static void *z_comp_alloc(unsigned char *options, int opt_len); static void *z_decomp_alloc(unsigned char *options, int opt_len); static void z_comp_free(void *state); static void z_decomp_free(void *state); static int z_comp_init(void *state, unsigned char *options, int opt_len, int unit, int hdrlen, int debug); static int z_decomp_init(void *state, unsigned char *options, int opt_len, int unit, int hdrlen, int mru, int debug); static int z_compress(void *state, unsigned char *rptr, unsigned char *obuf, int isize, int osize); static void z_incomp(void *state, unsigned char *ibuf, int icnt); static int z_decompress(void *state, unsigned char *ibuf, int isize, unsigned char *obuf, int osize); static void z_comp_reset(void *state); static void z_decomp_reset(void *state); static void z_comp_stats(void *state, struct compstat *stats); /** * z_comp_free - free the memory used by a compressor * @arg: pointer to the private state for the compressor. */ static void z_comp_free(void *arg) { struct ppp_deflate_state *state = (struct ppp_deflate_state *) arg; if (state) { zlib_deflateEnd(&state->strm); vfree(state->strm.workspace); kfree(state); } } /** * z_comp_alloc - allocate space for a compressor. * @options: pointer to CCP option data * @opt_len: length of the CCP option at @options. * * The @options pointer points to the a buffer containing the * CCP option data for the compression being negotiated. It is * formatted according to RFC1979, and describes the window * size that the peer is requesting that we use in compressing * data to be sent to it. * * Returns the pointer to the private state for the compressor, * or NULL if we could not allocate enough memory. */ static void *z_comp_alloc(unsigned char *options, int opt_len) { struct ppp_deflate_state *state; int w_size; if (opt_len != CILEN_DEFLATE || (options[0] != CI_DEFLATE && options[0] != CI_DEFLATE_DRAFT) || options[1] != CILEN_DEFLATE || DEFLATE_METHOD(options[2]) != DEFLATE_METHOD_VAL || options[3] != DEFLATE_CHK_SEQUENCE) return NULL; w_size = DEFLATE_SIZE(options[2]); if (w_size < DEFLATE_MIN_SIZE || w_size > DEFLATE_MAX_SIZE) return NULL; state = kzalloc(sizeof(*state), GFP_KERNEL); if (state == NULL) return NULL; state->strm.next_in = NULL; state->w_size = w_size; state->strm.workspace = vmalloc(zlib_deflate_workspacesize(-w_size, 8)); if (state->strm.workspace == NULL) goto out_free; if (zlib_deflateInit2(&state->strm, Z_DEFAULT_COMPRESSION, DEFLATE_METHOD_VAL, -w_size, 8, Z_DEFAULT_STRATEGY) != Z_OK) goto out_free; return (void *) state; out_free: z_comp_free(state); return NULL; } /** * z_comp_init - initialize a previously-allocated compressor. * @arg: pointer to the private state for the compressor * @options: pointer to the CCP option data describing the * compression that was negotiated with the peer * @opt_len: length of the CCP option data at @options * @unit: PPP unit number for diagnostic messages * @hdrlen: ignored (present for backwards compatibility) * @debug: debug flag; if non-zero, debug messages are printed. * * The CCP options described by @options must match the options * specified when the compressor was allocated. The compressor * history is reset. Returns 0 for failure (CCP options don't * match) or 1 for success. */ static int z_comp_init(void *arg, unsigned char *options, int opt_len, int unit, int hdrlen, int debug) { struct ppp_deflate_state *state = (struct ppp_deflate_state *) arg; if (opt_len < CILEN_DEFLATE || (options[0] != CI_DEFLATE && options[0] != CI_DEFLATE_DRAFT) || options[1] != CILEN_DEFLATE || DEFLATE_METHOD(options[2]) != DEFLATE_METHOD_VAL || DEFLATE_SIZE(options[2]) != state->w_size || options[3] != DEFLATE_CHK_SEQUENCE) return 0; state->seqno = 0; state->unit = unit; state->debug = debug; zlib_deflateReset(&state->strm); return 1; } /** * z_comp_reset - reset a previously-allocated compressor. * @arg: pointer to private state for the compressor. * * This clears the history for the compressor and makes it * ready to start emitting a new compressed stream. */ static void z_comp_reset(void *arg) { struct ppp_deflate_state *state = (struct ppp_deflate_state *) arg; state->seqno = 0; zlib_deflateReset(&state->strm); } /** * z_compress - compress a PPP packet with Deflate compression. * @arg: pointer to private state for the compressor * @rptr: uncompressed packet (input) * @obuf: compressed packet (output) * @isize: size of uncompressed packet * @osize: space available at @obuf * * Returns the length of the compressed packet, or 0 if the * packet is incompressible. */ static int z_compress(void *arg, unsigned char *rptr, unsigned char *obuf, int isize, int osize) { struct ppp_deflate_state *state = (struct ppp_deflate_state *) arg; int r, proto, off, olen, oavail; unsigned char *wptr; /* * Check that the protocol is in the range we handle. */ proto = PPP_PROTOCOL(rptr); if (proto > 0x3fff || proto == 0xfd || proto == 0xfb) return 0; /* Don't generate compressed packets which are larger than the uncompressed packet. */ if (osize > isize) osize = isize; wptr = obuf; /* * Copy over the PPP header and store the 2-byte sequence number. */ wptr[0] = PPP_ADDRESS(rptr); wptr[1] = PPP_CONTROL(rptr); put_unaligned_be16(PPP_COMP, wptr + 2); wptr += PPP_HDRLEN; put_unaligned_be16(state->seqno, wptr); wptr += DEFLATE_OVHD; olen = PPP_HDRLEN + DEFLATE_OVHD; state->strm.next_out = wptr; state->strm.avail_out = oavail = osize - olen; ++state->seqno; off = (proto > 0xff) ? 2 : 3; /* skip 1st proto byte if 0 */ rptr += off; state->strm.next_in = rptr; state->strm.avail_in = (isize - off); for (;;) { r = zlib_deflate(&state->strm, Z_PACKET_FLUSH); if (r != Z_OK) { if (state->debug) printk(KERN_ERR "z_compress: deflate returned %d\n", r); break; } if (state->strm.avail_out == 0) { olen += oavail; state->strm.next_out = NULL; state->strm.avail_out = oavail = 1000000; } else { break; /* all done */ } } olen += oavail - state->strm.avail_out; /* * See if we managed to reduce the size of the packet. */ if (olen < isize && olen <= osize) { state->stats.comp_bytes += olen; state->stats.comp_packets++; } else { state->stats.inc_bytes += isize; state->stats.inc_packets++; olen = 0; } state->stats.unc_bytes += isize; state->stats.unc_packets++; return olen; } /** * z_comp_stats - return compression statistics for a compressor * or decompressor. * @arg: pointer to private space for the (de)compressor * @stats: pointer to a struct compstat to receive the result. */ static void z_comp_stats(void *arg, struct compstat *stats) { struct ppp_deflate_state *state = (struct ppp_deflate_state *) arg; *stats = state->stats; } /** * z_decomp_free - Free the memory used by a decompressor. * @arg: pointer to private space for the decompressor. */ static void z_decomp_free(void *arg) { struct ppp_deflate_state *state = (struct ppp_deflate_state *) arg; if (state) { vfree(state->strm.workspace); kfree(state); } } /** * z_decomp_alloc - allocate space for a decompressor. * @options: pointer to CCP option data * @opt_len: length of the CCP option at @options. * * The @options pointer points to the a buffer containing the * CCP option data for the compression being negotiated. It is * formatted according to RFC1979, and describes the window * size that we are requesting the peer to use in compressing * data to be sent to us. * * Returns the pointer to the private state for the decompressor, * or NULL if we could not allocate enough memory. */ static void *z_decomp_alloc(unsigned char *options, int opt_len) { struct ppp_deflate_state *state; int w_size; if (opt_len != CILEN_DEFLATE || (options[0] != CI_DEFLATE && options[0] != CI_DEFLATE_DRAFT) || options[1] != CILEN_DEFLATE || DEFLATE_METHOD(options[2]) != DEFLATE_METHOD_VAL || options[3] != DEFLATE_CHK_SEQUENCE) return NULL; w_size = DEFLATE_SIZE(options[2]); if (w_size < DEFLATE_MIN_SIZE || w_size > DEFLATE_MAX_SIZE) return NULL; state = kzalloc(sizeof(*state), GFP_KERNEL); if (state == NULL) return NULL; state->w_size = w_size; state->strm.next_out = NULL; state->strm.workspace = vmalloc(zlib_inflate_workspacesize()); if (state->strm.workspace == NULL) goto out_free; if (zlib_inflateInit2(&state->strm, -w_size) != Z_OK) goto out_free; return (void *) state; out_free: z_decomp_free(state); return NULL; } /** * z_decomp_init - initialize a previously-allocated decompressor. * @arg: pointer to the private state for the decompressor * @options: pointer to the CCP option data describing the * compression that was negotiated with the peer * @opt_len: length of the CCP option data at @options * @unit: PPP unit number for diagnostic messages * @hdrlen: ignored (present for backwards compatibility) * @mru: maximum length of decompressed packets * @debug: debug flag; if non-zero, debug messages are printed. * * The CCP options described by @options must match the options * specified when the decompressor was allocated. The decompressor * history is reset. Returns 0 for failure (CCP options don't * match) or 1 for success. */ static int z_decomp_init(void *arg, unsigned char *options, int opt_len, int unit, int hdrlen, int mru, int debug) { struct ppp_deflate_state *state = (struct ppp_deflate_state *) arg; if (opt_len < CILEN_DEFLATE || (options[0] != CI_DEFLATE && options[0] != CI_DEFLATE_DRAFT) || options[1] != CILEN_DEFLATE || DEFLATE_METHOD(options[2]) != DEFLATE_METHOD_VAL || DEFLATE_SIZE(options[2]) != state->w_size || options[3] != DEFLATE_CHK_SEQUENCE) return 0; state->seqno = 0; state->unit = unit; state->debug = debug; state->mru = mru; zlib_inflateReset(&state->strm); return 1; } /** * z_decomp_reset - reset a previously-allocated decompressor. * @arg: pointer to private state for the decompressor. * * This clears the history for the decompressor and makes it * ready to receive a new compressed stream. */ static void z_decomp_reset(void *arg) { struct ppp_deflate_state *state = (struct ppp_deflate_state *) arg; state->seqno = 0; zlib_inflateReset(&state->strm); } /** * z_decompress - decompress a Deflate-compressed packet. * @arg: pointer to private state for the decompressor * @ibuf: pointer to input (compressed) packet data * @isize: length of input packet * @obuf: pointer to space for output (decompressed) packet * @osize: amount of space available at @obuf * * Because of patent problems, we return DECOMP_ERROR for errors * found by inspecting the input data and for system problems, but * DECOMP_FATALERROR for any errors which could possibly be said to * be being detected "after" decompression. For DECOMP_ERROR, * we can issue a CCP reset-request; for DECOMP_FATALERROR, we may be * infringing a patent of Motorola's if we do, so we take CCP down * instead. * * Given that the frame has the correct sequence number and a good FCS, * errors such as invalid codes in the input most likely indicate a * bug, so we return DECOMP_FATALERROR for them in order to turn off * compression, even though they are detected by inspecting the input. */ static int z_decompress(void *arg, unsigned char *ibuf, int isize, unsigned char *obuf, int osize) { struct ppp_deflate_state *state = (struct ppp_deflate_state *) arg; int olen, seq, r; int decode_proto, overflow; unsigned char overflow_buf[1]; if (isize <= PPP_HDRLEN + DEFLATE_OVHD) { if (state->debug) printk(KERN_DEBUG "z_decompress%d: short pkt (%d)\n", state->unit, isize); return DECOMP_ERROR; } /* Check the sequence number. */ seq = get_unaligned_be16(ibuf + PPP_HDRLEN); if (seq != (state->seqno & 0xffff)) { if (state->debug) printk(KERN_DEBUG "z_decompress%d: bad seq # %d, expected %d\n", state->unit, seq, state->seqno & 0xffff); return DECOMP_ERROR; } ++state->seqno; /* * Fill in the first part of the PPP header. The protocol field * comes from the decompressed data. */ obuf[0] = PPP_ADDRESS(ibuf); obuf[1] = PPP_CONTROL(ibuf); obuf[2] = 0; /* * Set up to call inflate. We set avail_out to 1 initially so we can * look at the first byte of the output and decide whether we have * a 1-byte or 2-byte protocol field. */ state->strm.next_in = ibuf + PPP_HDRLEN + DEFLATE_OVHD; state->strm.avail_in = isize - (PPP_HDRLEN + DEFLATE_OVHD); state->strm.next_out = obuf + 3; state->strm.avail_out = 1; decode_proto = 1; overflow = 0; /* * Call inflate, supplying more input or output as needed. */ for (;;) { r = zlib_inflate(&state->strm, Z_PACKET_FLUSH); if (r != Z_OK) { if (state->debug) printk(KERN_DEBUG "z_decompress%d: inflate returned %d (%s)\n", state->unit, r, (state->strm.msg? state->strm.msg: "")); return DECOMP_FATALERROR; } if (state->strm.avail_out != 0) break; /* all done */ if (decode_proto) { state->strm.avail_out = osize - PPP_HDRLEN; if ((obuf[3] & 1) == 0) { /* 2-byte protocol field */ obuf[2] = obuf[3]; --state->strm.next_out; ++state->strm.avail_out; } decode_proto = 0; } else if (!overflow) { /* * We've filled up the output buffer; the only way to * find out whether inflate has any more characters * left is to give it another byte of output space. */ state->strm.next_out = overflow_buf; state->strm.avail_out = 1; overflow = 1; } else { if (state->debug) printk(KERN_DEBUG "z_decompress%d: ran out of mru\n", state->unit); return DECOMP_FATALERROR; } } if (decode_proto) { if (state->debug) printk(KERN_DEBUG "z_decompress%d: didn't get proto\n", state->unit); return DECOMP_ERROR; } olen = osize + overflow - state->strm.avail_out; state->stats.unc_bytes += olen; state->stats.unc_packets++; state->stats.comp_bytes += isize; state->stats.comp_packets++; return olen; } /** * z_incomp - add incompressible input data to the history. * @arg: pointer to private state for the decompressor * @ibuf: pointer to input packet data * @icnt: length of input data. */ static void z_incomp(void *arg, unsigned char *ibuf, int icnt) { struct ppp_deflate_state *state = (struct ppp_deflate_state *) arg; int proto, r; /* * Check that the protocol is one we handle. */ proto = PPP_PROTOCOL(ibuf); if (proto > 0x3fff || proto == 0xfd || proto == 0xfb) return; ++state->seqno; /* * We start at the either the 1st or 2nd byte of the protocol field, * depending on whether the protocol value is compressible. */ state->strm.next_in = ibuf + 3; state->strm.avail_in = icnt - 3; if (proto > 0xff) { --state->strm.next_in; ++state->strm.avail_in; } r = zlib_inflateIncomp(&state->strm); if (r != Z_OK) { /* gak! */ if (state->debug) { printk(KERN_DEBUG "z_incomp%d: inflateIncomp returned %d (%s)\n", state->unit, r, (state->strm.msg? state->strm.msg: "")); } return; } /* * Update stats. */ state->stats.inc_bytes += icnt; state->stats.inc_packets++; state->stats.unc_bytes += icnt; state->stats.unc_packets++; } /************************************************************* * Module interface table *************************************************************/ /* These are in ppp_generic.c */ extern int ppp_register_compressor (struct compressor *cp); extern void ppp_unregister_compressor (struct compressor *cp); /* * Procedures exported to if_ppp.c. */ static struct compressor ppp_deflate = { .compress_proto = CI_DEFLATE, .comp_alloc = z_comp_alloc, .comp_free = z_comp_free, .comp_init = z_comp_init, .comp_reset = z_comp_reset, .compress = z_compress, .comp_stat = z_comp_stats, .decomp_alloc = z_decomp_alloc, .decomp_free = z_decomp_free, .decomp_init = z_decomp_init, .decomp_reset = z_decomp_reset, .decompress = z_decompress, .incomp = z_incomp, .decomp_stat = z_comp_stats, .owner = THIS_MODULE }; static struct compressor ppp_deflate_draft = { .compress_proto = CI_DEFLATE_DRAFT, .comp_alloc = z_comp_alloc, .comp_free = z_comp_free, .comp_init = z_comp_init, .comp_reset = z_comp_reset, .compress = z_compress, .comp_stat = z_comp_stats, .decomp_alloc = z_decomp_alloc, .decomp_free = z_decomp_free, .decomp_init = z_decomp_init, .decomp_reset = z_decomp_reset, .decompress = z_decompress, .incomp = z_incomp, .decomp_stat = z_comp_stats, .owner = THIS_MODULE }; static int __init deflate_init(void) { int rc; rc = ppp_register_compressor(&ppp_deflate); if (rc) return rc; rc = ppp_register_compressor(&ppp_deflate_draft); if (rc) { ppp_unregister_compressor(&ppp_deflate); return rc; } pr_info("PPP Deflate Compression module registered\n"); return 0; } static void __exit deflate_cleanup(void) { ppp_unregister_compressor(&ppp_deflate); ppp_unregister_compressor(&ppp_deflate_draft); } module_init(deflate_init); module_exit(deflate_cleanup); MODULE_LICENSE("Dual BSD/GPL"); MODULE_ALIAS("ppp-compress-" __stringify(CI_DEFLATE)); MODULE_ALIAS("ppp-compress-" __stringify(CI_DEFLATE_DRAFT)); |
| 400 400 999 999 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 | // SPDX-License-Identifier: GPL-2.0 #include <linux/rtnetlink.h> #include <linux/notifier.h> #include <linux/socket.h> #include <linux/kernel.h> #include <linux/export.h> #include <net/net_namespace.h> #include <net/fib_notifier.h> #include <net/ip_fib.h> int call_fib4_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info) { info->family = AF_INET; return call_fib_notifier(nb, event_type, info); } int call_fib4_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info) { ASSERT_RTNL(); info->family = AF_INET; net->ipv4.fib_seq++; return call_fib_notifiers(net, event_type, info); } static unsigned int fib4_seq_read(struct net *net) { ASSERT_RTNL(); return net->ipv4.fib_seq + fib4_rules_seq_read(net); } static int fib4_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { int err; err = fib4_rules_dump(net, nb, extack); if (err) return err; return fib_notify(net, nb, extack); } static const struct fib_notifier_ops fib4_notifier_ops_template = { .family = AF_INET, .fib_seq_read = fib4_seq_read, .fib_dump = fib4_dump, .owner = THIS_MODULE, }; int __net_init fib4_notifier_init(struct net *net) { struct fib_notifier_ops *ops; net->ipv4.fib_seq = 0; ops = fib_notifier_ops_register(&fib4_notifier_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); net->ipv4.notifier_ops = ops; return 0; } void __net_exit fib4_notifier_exit(struct net *net) { fib_notifier_ops_unregister(net->ipv4.notifier_ops); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Type definitions for the multi-level security (MLS) policy. * * Author : Stephen Smalley, <sds@tycho.nsa.gov> */ /* * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com> * * Support for enhanced MLS infrastructure. * * Copyright (C) 2004-2005 Trusted Computer Solutions, Inc. */ #ifndef _SS_MLS_TYPES_H_ #define _SS_MLS_TYPES_H_ #include "security.h" #include "ebitmap.h" struct mls_level { u32 sens; /* sensitivity */ struct ebitmap cat; /* category set */ }; struct mls_range { struct mls_level level[2]; /* low == level[0], high == level[1] */ }; static inline int mls_level_eq(const struct mls_level *l1, const struct mls_level *l2) { return ((l1->sens == l2->sens) && ebitmap_cmp(&l1->cat, &l2->cat)); } static inline int mls_level_dom(const struct mls_level *l1, const struct mls_level *l2) { return ((l1->sens >= l2->sens) && ebitmap_contains(&l1->cat, &l2->cat, 0)); } #define mls_level_incomp(l1, l2) \ (!mls_level_dom((l1), (l2)) && !mls_level_dom((l2), (l1))) #define mls_level_between(l1, l2, l3) \ (mls_level_dom((l1), (l2)) && mls_level_dom((l3), (l1))) #define mls_range_contains(r1, r2) \ (mls_level_dom(&(r2).level[0], &(r1).level[0]) && \ mls_level_dom(&(r1).level[1], &(r2).level[1])) #endif /* _SS_MLS_TYPES_H_ */ |
| 1 1713 9017 175 175 175 319 319 319 175 1762 1764 1759 1761 1572 1577 1574 414 23 48 49 45 3 816 1705 1575 1575 1576 415 423 26 49 48 49 2289 69 2288 1 1 1266 1491 41 1491 604 602 604 1 603 175 175 175 175 175 175 175 175 319 319 319 319 319 319 319 319 319 319 319 319 319 319 319 319 319 319 319 319 319 175 175 175 175 175 3810 3810 175 175 175 174 3774 924 3810 8463 8463 319 319 318 319 175 175 175 175 175 175 175 175 175 175 175 175 175 175 175 175 175 175 175 175 319 319 319 319 319 319 319 319 319 319 175 175 175 319 319 319 1262 979 319 319 319 319 319 319 319 319 319 319 319 319 756 756 4 4 4 155 155 155 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/namespace.c * * (C) Copyright Al Viro 2000, 2001 * * Based on code from fs/super.c, copyright Linus Torvalds and others. * Heavily rewritten. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/capability.h> #include <linux/mnt_namespace.h> #include <linux/user_namespace.h> #include <linux/namei.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/idr.h> #include <linux/init.h> /* init_rootfs */ #include <linux/fs_struct.h> /* get_fs_root et.al. */ #include <linux/fsnotify.h> /* fsnotify_vfsmount_delete */ #include <linux/file.h> #include <linux/uaccess.h> #include <linux/proc_ns.h> #include <linux/magic.h> #include <linux/memblock.h> #include <linux/proc_fs.h> #include <linux/task_work.h> #include <linux/sched/task.h> #include <uapi/linux/mount.h> #include <linux/fs_context.h> #include <linux/shmem_fs.h> #include <linux/mnt_idmapping.h> #include "pnode.h" #include "internal.h" /* Maximum number of mounts in a mount namespace */ static unsigned int sysctl_mount_max __read_mostly = 100000; static unsigned int m_hash_mask __read_mostly; static unsigned int m_hash_shift __read_mostly; static unsigned int mp_hash_mask __read_mostly; static unsigned int mp_hash_shift __read_mostly; static __initdata unsigned long mhash_entries; static int __init set_mhash_entries(char *str) { if (!str) return 0; mhash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("mhash_entries=", set_mhash_entries); static __initdata unsigned long mphash_entries; static int __init set_mphash_entries(char *str) { if (!str) return 0; mphash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("mphash_entries=", set_mphash_entries); static u64 event; static DEFINE_IDA(mnt_id_ida); static DEFINE_IDA(mnt_group_ida); static struct hlist_head *mount_hashtable __read_mostly; static struct hlist_head *mountpoint_hashtable __read_mostly; static struct kmem_cache *mnt_cache __read_mostly; static DECLARE_RWSEM(namespace_sem); static HLIST_HEAD(unmounted); /* protected by namespace_sem */ static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */ struct mount_kattr { unsigned int attr_set; unsigned int attr_clr; unsigned int propagation; unsigned int lookup_flags; bool recurse; struct user_namespace *mnt_userns; }; /* /sys/fs */ struct kobject *fs_kobj; EXPORT_SYMBOL_GPL(fs_kobj); /* * vfsmount lock may be taken for read to prevent changes to the * vfsmount hash, ie. during mountpoint lookups or walking back * up the tree. * * It should be taken for write in all cases where the vfsmount * tree or hash is modified or when a vfsmount structure is modified. */ __cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock); static inline void lock_mount_hash(void) { write_seqlock(&mount_lock); } static inline void unlock_mount_hash(void) { write_sequnlock(&mount_lock); } static inline struct hlist_head *m_hash(struct vfsmount *mnt, struct dentry *dentry) { unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES); tmp += ((unsigned long)dentry / L1_CACHE_BYTES); tmp = tmp + (tmp >> m_hash_shift); return &mount_hashtable[tmp & m_hash_mask]; } static inline struct hlist_head *mp_hash(struct dentry *dentry) { unsigned long tmp = ((unsigned long)dentry / L1_CACHE_BYTES); tmp = tmp + (tmp >> mp_hash_shift); return &mountpoint_hashtable[tmp & mp_hash_mask]; } static int mnt_alloc_id(struct mount *mnt) { int res = ida_alloc(&mnt_id_ida, GFP_KERNEL); if (res < 0) return res; mnt->mnt_id = res; return 0; } static void mnt_free_id(struct mount *mnt) { ida_free(&mnt_id_ida, mnt->mnt_id); } /* * Allocate a new peer group ID */ static int mnt_alloc_group_id(struct mount *mnt) { int res = ida_alloc_min(&mnt_group_ida, 1, GFP_KERNEL); if (res < 0) return res; mnt->mnt_group_id = res; return 0; } /* * Release a peer group ID */ void mnt_release_group_id(struct mount *mnt) { ida_free(&mnt_group_ida, mnt->mnt_group_id); mnt->mnt_group_id = 0; } /* * vfsmount lock must be held for read */ static inline void mnt_add_count(struct mount *mnt, int n) { #ifdef CONFIG_SMP this_cpu_add(mnt->mnt_pcp->mnt_count, n); #else preempt_disable(); mnt->mnt_count += n; preempt_enable(); #endif } /* * vfsmount lock must be held for write */ int mnt_get_count(struct mount *mnt) { #ifdef CONFIG_SMP int count = 0; int cpu; for_each_possible_cpu(cpu) { count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_count; } return count; #else return mnt->mnt_count; #endif } static struct mount *alloc_vfsmnt(const char *name) { struct mount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL); if (mnt) { int err; err = mnt_alloc_id(mnt); if (err) goto out_free_cache; if (name) { mnt->mnt_devname = kstrdup_const(name, GFP_KERNEL_ACCOUNT); if (!mnt->mnt_devname) goto out_free_id; } #ifdef CONFIG_SMP mnt->mnt_pcp = alloc_percpu(struct mnt_pcp); if (!mnt->mnt_pcp) goto out_free_devname; this_cpu_add(mnt->mnt_pcp->mnt_count, 1); #else mnt->mnt_count = 1; mnt->mnt_writers = 0; #endif INIT_HLIST_NODE(&mnt->mnt_hash); INIT_LIST_HEAD(&mnt->mnt_child); INIT_LIST_HEAD(&mnt->mnt_mounts); INIT_LIST_HEAD(&mnt->mnt_list); INIT_LIST_HEAD(&mnt->mnt_expire); INIT_LIST_HEAD(&mnt->mnt_share); INIT_LIST_HEAD(&mnt->mnt_slave_list); INIT_LIST_HEAD(&mnt->mnt_slave); INIT_HLIST_NODE(&mnt->mnt_mp_list); INIT_LIST_HEAD(&mnt->mnt_umounting); INIT_HLIST_HEAD(&mnt->mnt_stuck_children); mnt->mnt.mnt_userns = &init_user_ns; } return mnt; #ifdef CONFIG_SMP out_free_devname: kfree_const(mnt->mnt_devname); #endif out_free_id: mnt_free_id(mnt); out_free_cache: kmem_cache_free(mnt_cache, mnt); return NULL; } /* * Most r/o checks on a fs are for operations that take * discrete amounts of time, like a write() or unlink(). * We must keep track of when those operations start * (for permission checks) and when they end, so that * we can determine when writes are able to occur to * a filesystem. */ /* * __mnt_is_readonly: check whether a mount is read-only * @mnt: the mount to check for its write status * * This shouldn't be used directly ouside of the VFS. * It does not guarantee that the filesystem will stay * r/w, just that it is right *now*. This can not and * should not be used in place of IS_RDONLY(inode). * mnt_want/drop_write() will _keep_ the filesystem * r/w. */ bool __mnt_is_readonly(struct vfsmount *mnt) { return (mnt->mnt_flags & MNT_READONLY) || sb_rdonly(mnt->mnt_sb); } EXPORT_SYMBOL_GPL(__mnt_is_readonly); static inline void mnt_inc_writers(struct mount *mnt) { #ifdef CONFIG_SMP this_cpu_inc(mnt->mnt_pcp->mnt_writers); #else mnt->mnt_writers++; #endif } static inline void mnt_dec_writers(struct mount *mnt) { #ifdef CONFIG_SMP this_cpu_dec(mnt->mnt_pcp->mnt_writers); #else mnt->mnt_writers--; #endif } static unsigned int mnt_get_writers(struct mount *mnt) { #ifdef CONFIG_SMP unsigned int count = 0; int cpu; for_each_possible_cpu(cpu) { count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_writers; } return count; #else return mnt->mnt_writers; #endif } static int mnt_is_readonly(struct vfsmount *mnt) { if (mnt->mnt_sb->s_readonly_remount) return 1; /* Order wrt setting s_flags/s_readonly_remount in do_remount() */ smp_rmb(); return __mnt_is_readonly(mnt); } /* * Most r/o & frozen checks on a fs are for operations that take discrete * amounts of time, like a write() or unlink(). We must keep track of when * those operations start (for permission checks) and when they end, so that we * can determine when writes are able to occur to a filesystem. */ /** * __mnt_want_write - get write access to a mount without freeze protection * @m: the mount on which to take a write * * This tells the low-level filesystem that a write is about to be performed to * it, and makes sure that writes are allowed (mnt it read-write) before * returning success. This operation does not protect against filesystem being * frozen. When the write operation is finished, __mnt_drop_write() must be * called. This is effectively a refcount. */ int __mnt_want_write(struct vfsmount *m) { struct mount *mnt = real_mount(m); int ret = 0; preempt_disable(); mnt_inc_writers(mnt); /* * The store to mnt_inc_writers must be visible before we pass * MNT_WRITE_HOLD loop below, so that the slowpath can see our * incremented count after it has set MNT_WRITE_HOLD. */ smp_mb(); might_lock(&mount_lock.lock); while (READ_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) { if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { cpu_relax(); } else { /* * This prevents priority inversion, if the task * setting MNT_WRITE_HOLD got preempted on a remote * CPU, and it prevents life lock if the task setting * MNT_WRITE_HOLD has a lower priority and is bound to * the same CPU as the task that is spinning here. */ preempt_enable(); lock_mount_hash(); unlock_mount_hash(); preempt_disable(); } } /* * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will * be set to match its requirements. So we must not load that until * MNT_WRITE_HOLD is cleared. */ smp_rmb(); if (mnt_is_readonly(m)) { mnt_dec_writers(mnt); ret = -EROFS; } preempt_enable(); return ret; } /** * mnt_want_write - get write access to a mount * @m: the mount on which to take a write * * This tells the low-level filesystem that a write is about to be performed to * it, and makes sure that writes are allowed (mount is read-write, filesystem * is not frozen) before returning success. When the write operation is * finished, mnt_drop_write() must be called. This is effectively a refcount. */ int mnt_want_write(struct vfsmount *m) { int ret; sb_start_write(m->mnt_sb); ret = __mnt_want_write(m); if (ret) sb_end_write(m->mnt_sb); return ret; } EXPORT_SYMBOL_GPL(mnt_want_write); /** * __mnt_want_write_file - get write access to a file's mount * @file: the file who's mount on which to take a write * * This is like __mnt_want_write, but if the file is already open for writing it * skips incrementing mnt_writers (since the open file already has a reference) * and instead only does the check for emergency r/o remounts. This must be * paired with __mnt_drop_write_file. */ int __mnt_want_write_file(struct file *file) { if (file->f_mode & FMODE_WRITER) { /* * Superblock may have become readonly while there are still * writable fd's, e.g. due to a fs error with errors=remount-ro */ if (__mnt_is_readonly(file->f_path.mnt)) return -EROFS; return 0; } return __mnt_want_write(file->f_path.mnt); } /** * mnt_want_write_file - get write access to a file's mount * @file: the file who's mount on which to take a write * * This is like mnt_want_write, but if the file is already open for writing it * skips incrementing mnt_writers (since the open file already has a reference) * and instead only does the freeze protection and the check for emergency r/o * remounts. This must be paired with mnt_drop_write_file. */ int mnt_want_write_file(struct file *file) { int ret; sb_start_write(file_inode(file)->i_sb); ret = __mnt_want_write_file(file); if (ret) sb_end_write(file_inode(file)->i_sb); return ret; } EXPORT_SYMBOL_GPL(mnt_want_write_file); /** * __mnt_drop_write - give up write access to a mount * @mnt: the mount on which to give up write access * * Tells the low-level filesystem that we are done * performing writes to it. Must be matched with * __mnt_want_write() call above. */ void __mnt_drop_write(struct vfsmount *mnt) { preempt_disable(); mnt_dec_writers(real_mount(mnt)); preempt_enable(); } /** * mnt_drop_write - give up write access to a mount * @mnt: the mount on which to give up write access * * Tells the low-level filesystem that we are done performing writes to it and * also allows filesystem to be frozen again. Must be matched with * mnt_want_write() call above. */ void mnt_drop_write(struct vfsmount *mnt) { __mnt_drop_write(mnt); sb_end_write(mnt->mnt_sb); } EXPORT_SYMBOL_GPL(mnt_drop_write); void __mnt_drop_write_file(struct file *file) { if (!(file->f_mode & FMODE_WRITER)) __mnt_drop_write(file->f_path.mnt); } void mnt_drop_write_file(struct file *file) { __mnt_drop_write_file(file); sb_end_write(file_inode(file)->i_sb); } EXPORT_SYMBOL(mnt_drop_write_file); /** * mnt_hold_writers - prevent write access to the given mount * @mnt: mnt to prevent write access to * * Prevents write access to @mnt if there are no active writers for @mnt. * This function needs to be called and return successfully before changing * properties of @mnt that need to remain stable for callers with write access * to @mnt. * * After this functions has been called successfully callers must pair it with * a call to mnt_unhold_writers() in order to stop preventing write access to * @mnt. * * Context: This function expects lock_mount_hash() to be held serializing * setting MNT_WRITE_HOLD. * Return: On success 0 is returned. * On error, -EBUSY is returned. */ static inline int mnt_hold_writers(struct mount *mnt) { mnt->mnt.mnt_flags |= MNT_WRITE_HOLD; /* * After storing MNT_WRITE_HOLD, we'll read the counters. This store * should be visible before we do. */ smp_mb(); /* * With writers on hold, if this value is zero, then there are * definitely no active writers (although held writers may subsequently * increment the count, they'll have to wait, and decrement it after * seeing MNT_READONLY). * * It is OK to have counter incremented on one CPU and decremented on * another: the sum will add up correctly. The danger would be when we * sum up each counter, if we read a counter before it is incremented, * but then read another CPU's count which it has been subsequently * decremented from -- we would see more decrements than we should. * MNT_WRITE_HOLD protects against this scenario, because * mnt_want_write first increments count, then smp_mb, then spins on * MNT_WRITE_HOLD, so it can't be decremented by another CPU while * we're counting up here. */ if (mnt_get_writers(mnt) > 0) return -EBUSY; return 0; } /** * mnt_unhold_writers - stop preventing write access to the given mount * @mnt: mnt to stop preventing write access to * * Stop preventing write access to @mnt allowing callers to gain write access * to @mnt again. * * This function can only be called after a successful call to * mnt_hold_writers(). * * Context: This function expects lock_mount_hash() to be held. */ static inline void mnt_unhold_writers(struct mount *mnt) { /* * MNT_READONLY must become visible before ~MNT_WRITE_HOLD, so writers * that become unheld will see MNT_READONLY. */ smp_wmb(); mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD; } static int mnt_make_readonly(struct mount *mnt) { int ret; ret = mnt_hold_writers(mnt); if (!ret) mnt->mnt.mnt_flags |= MNT_READONLY; mnt_unhold_writers(mnt); return ret; } int sb_prepare_remount_readonly(struct super_block *sb) { struct mount *mnt; int err = 0; /* Racy optimization. Recheck the counter under MNT_WRITE_HOLD */ if (atomic_long_read(&sb->s_remove_count)) return -EBUSY; lock_mount_hash(); list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) { if (!(mnt->mnt.mnt_flags & MNT_READONLY)) { err = mnt_hold_writers(mnt); if (err) break; } } if (!err && atomic_long_read(&sb->s_remove_count)) err = -EBUSY; if (!err) { sb->s_readonly_remount = 1; smp_wmb(); } list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) { if (mnt->mnt.mnt_flags & MNT_WRITE_HOLD) mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD; } unlock_mount_hash(); return err; } static void free_vfsmnt(struct mount *mnt) { struct user_namespace *mnt_userns; mnt_userns = mnt_user_ns(&mnt->mnt); if (!initial_idmapping(mnt_userns)) put_user_ns(mnt_userns); kfree_const(mnt->mnt_devname); #ifdef CONFIG_SMP free_percpu(mnt->mnt_pcp); #endif kmem_cache_free(mnt_cache, mnt); } static void delayed_free_vfsmnt(struct rcu_head *head) { free_vfsmnt(container_of(head, struct mount, mnt_rcu)); } /* call under rcu_read_lock */ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq) { struct mount *mnt; if (read_seqretry(&mount_lock, seq)) return 1; if (bastard == NULL) return 0; mnt = real_mount(bastard); mnt_add_count(mnt, 1); smp_mb(); // see mntput_no_expire() if (likely(!read_seqretry(&mount_lock, seq))) return 0; if (bastard->mnt_flags & MNT_SYNC_UMOUNT) { mnt_add_count(mnt, -1); return 1; } lock_mount_hash(); if (unlikely(bastard->mnt_flags & MNT_DOOMED)) { mnt_add_count(mnt, -1); unlock_mount_hash(); return 1; } unlock_mount_hash(); /* caller will mntput() */ return -1; } /* call under rcu_read_lock */ static bool legitimize_mnt(struct vfsmount *bastard, unsigned seq) { int res = __legitimize_mnt(bastard, seq); if (likely(!res)) return true; if (unlikely(res < 0)) { rcu_read_unlock(); mntput(bastard); rcu_read_lock(); } return false; } /* * find the first mount at @dentry on vfsmount @mnt. * call under rcu_read_lock() */ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) { struct hlist_head *head = m_hash(mnt, dentry); struct mount *p; hlist_for_each_entry_rcu(p, head, mnt_hash) if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry) return p; return NULL; } /* * lookup_mnt - Return the first child mount mounted at path * * "First" means first mounted chronologically. If you create the * following mounts: * * mount /dev/sda1 /mnt * mount /dev/sda2 /mnt * mount /dev/sda3 /mnt * * Then lookup_mnt() on the base /mnt dentry in the root mount will * return successively the root dentry and vfsmount of /dev/sda1, then * /dev/sda2, then /dev/sda3, then NULL. * * lookup_mnt takes a reference to the found vfsmount. */ struct vfsmount *lookup_mnt(const struct path *path) { struct mount *child_mnt; struct vfsmount *m; unsigned seq; rcu_read_lock(); do { seq = read_seqbegin(&mount_lock); child_mnt = __lookup_mnt(path->mnt, path->dentry); m = child_mnt ? &child_mnt->mnt : NULL; } while (!legitimize_mnt(m, seq)); rcu_read_unlock(); return m; } static inline void lock_ns_list(struct mnt_namespace *ns) { spin_lock(&ns->ns_lock); } static inline void unlock_ns_list(struct mnt_namespace *ns) { spin_unlock(&ns->ns_lock); } static inline bool mnt_is_cursor(struct mount *mnt) { return mnt->mnt.mnt_flags & MNT_CURSOR; } /* * __is_local_mountpoint - Test to see if dentry is a mountpoint in the * current mount namespace. * * The common case is dentries are not mountpoints at all and that * test is handled inline. For the slow case when we are actually * dealing with a mountpoint of some kind, walk through all of the * mounts in the current mount namespace and test to see if the dentry * is a mountpoint. * * The mount_hashtable is not usable in the context because we * need to identify all mounts that may be in the current mount * namespace not just a mount that happens to have some specified * parent mount. */ bool __is_local_mountpoint(struct dentry *dentry) { struct mnt_namespace *ns = current->nsproxy->mnt_ns; struct mount *mnt; bool is_covered = false; down_read(&namespace_sem); lock_ns_list(ns); list_for_each_entry(mnt, &ns->list, mnt_list) { if (mnt_is_cursor(mnt)) continue; is_covered = (mnt->mnt_mountpoint == dentry); if (is_covered) break; } unlock_ns_list(ns); up_read(&namespace_sem); return is_covered; } static struct mountpoint *lookup_mountpoint(struct dentry *dentry) { struct hlist_head *chain = mp_hash(dentry); struct mountpoint *mp; hlist_for_each_entry(mp, chain, m_hash) { if (mp->m_dentry == dentry) { mp->m_count++; return mp; } } return NULL; } static struct mountpoint *get_mountpoint(struct dentry *dentry) { struct mountpoint *mp, *new = NULL; int ret; if (d_mountpoint(dentry)) { /* might be worth a WARN_ON() */ if (d_unlinked(dentry)) return ERR_PTR(-ENOENT); mountpoint: read_seqlock_excl(&mount_lock); mp = lookup_mountpoint(dentry); read_sequnlock_excl(&mount_lock); if (mp) goto done; } if (!new) new = kmalloc(sizeof(struct mountpoint), GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); /* Exactly one processes may set d_mounted */ ret = d_set_mounted(dentry); /* Someone else set d_mounted? */ if (ret == -EBUSY) goto mountpoint; /* The dentry is not available as a mountpoint? */ mp = ERR_PTR(ret); if (ret) goto done; /* Add the new mountpoint to the hash table */ read_seqlock_excl(&mount_lock); new->m_dentry = dget(dentry); new->m_count = 1; hlist_add_head(&new->m_hash, mp_hash(dentry)); INIT_HLIST_HEAD(&new->m_list); read_sequnlock_excl(&mount_lock); mp = new; new = NULL; done: kfree(new); return mp; } /* * vfsmount lock must be held. Additionally, the caller is responsible * for serializing calls for given disposal list. */ static void __put_mountpoint(struct mountpoint *mp, struct list_head *list) { if (!--mp->m_count) { struct dentry *dentry = mp->m_dentry; BUG_ON(!hlist_empty(&mp->m_list)); spin_lock(&dentry->d_lock); dentry->d_flags &= ~DCACHE_MOUNTED; spin_unlock(&dentry->d_lock); dput_to_list(dentry, list); hlist_del(&mp->m_hash); kfree(mp); } } /* called with namespace_lock and vfsmount lock */ static void put_mountpoint(struct mountpoint *mp) { __put_mountpoint(mp, &ex_mountpoints); } static inline int check_mnt(struct mount *mnt) { return mnt->mnt_ns == current->nsproxy->mnt_ns; } /* * vfsmount lock must be held for write */ static void touch_mnt_namespace(struct mnt_namespace *ns) { if (ns) { ns->event = ++event; wake_up_interruptible(&ns->poll); } } /* * vfsmount lock must be held for write */ static void __touch_mnt_namespace(struct mnt_namespace *ns) { if (ns && ns->event != event) { ns->event = event; wake_up_interruptible(&ns->poll); } } /* * vfsmount lock must be held for write */ static struct mountpoint *unhash_mnt(struct mount *mnt) { struct mountpoint *mp; mnt->mnt_parent = mnt; mnt->mnt_mountpoint = mnt->mnt.mnt_root; list_del_init(&mnt->mnt_child); hlist_del_init_rcu(&mnt->mnt_hash); hlist_del_init(&mnt->mnt_mp_list); mp = mnt->mnt_mp; mnt->mnt_mp = NULL; return mp; } /* * vfsmount lock must be held for write */ static void umount_mnt(struct mount *mnt) { put_mountpoint(unhash_mnt(mnt)); } /* * vfsmount lock must be held for write */ void mnt_set_mountpoint(struct mount *mnt, struct mountpoint *mp, struct mount *child_mnt) { mp->m_count++; mnt_add_count(mnt, 1); /* essentially, that's mntget */ child_mnt->mnt_mountpoint = mp->m_dentry; child_mnt->mnt_parent = mnt; child_mnt->mnt_mp = mp; hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list); } static void __attach_mnt(struct mount *mnt, struct mount *parent) { hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mnt->mnt_mountpoint)); list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); } /* * vfsmount lock must be held for write */ static void attach_mnt(struct mount *mnt, struct mount *parent, struct mountpoint *mp) { mnt_set_mountpoint(parent, mp, mnt); __attach_mnt(mnt, parent); } void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt) { struct mountpoint *old_mp = mnt->mnt_mp; struct mount *old_parent = mnt->mnt_parent; list_del_init(&mnt->mnt_child); hlist_del_init(&mnt->mnt_mp_list); hlist_del_init_rcu(&mnt->mnt_hash); attach_mnt(mnt, parent, mp); put_mountpoint(old_mp); mnt_add_count(old_parent, -1); } /* * vfsmount lock must be held for write */ static void commit_tree(struct mount *mnt) { struct mount *parent = mnt->mnt_parent; struct mount *m; LIST_HEAD(head); struct mnt_namespace *n = parent->mnt_ns; BUG_ON(parent == mnt); list_add_tail(&head, &mnt->mnt_list); list_for_each_entry(m, &head, mnt_list) m->mnt_ns = n; list_splice(&head, n->list.prev); n->mounts += n->pending_mounts; n->pending_mounts = 0; __attach_mnt(mnt, parent); touch_mnt_namespace(n); } static struct mount *next_mnt(struct mount *p, struct mount *root) { struct list_head *next = p->mnt_mounts.next; if (next == &p->mnt_mounts) { while (1) { if (p == root) return NULL; next = p->mnt_child.next; if (next != &p->mnt_parent->mnt_mounts) break; p = p->mnt_parent; } } return list_entry(next, struct mount, mnt_child); } static struct mount *skip_mnt_tree(struct mount *p) { struct list_head *prev = p->mnt_mounts.prev; while (prev != &p->mnt_mounts) { p = list_entry(prev, struct mount, mnt_child); prev = p->mnt_mounts.prev; } return p; } /** * vfs_create_mount - Create a mount for a configured superblock * @fc: The configuration context with the superblock attached * * Create a mount to an already configured superblock. If necessary, the * caller should invoke vfs_get_tree() before calling this. * * Note that this does not attach the mount to anything. */ struct vfsmount *vfs_create_mount(struct fs_context *fc) { struct mount *mnt; struct user_namespace *fs_userns; if (!fc->root) return ERR_PTR(-EINVAL); mnt = alloc_vfsmnt(fc->source ?: "none"); if (!mnt) return ERR_PTR(-ENOMEM); if (fc->sb_flags & SB_KERNMOUNT) mnt->mnt.mnt_flags = MNT_INTERNAL; atomic_inc(&fc->root->d_sb->s_active); mnt->mnt.mnt_sb = fc->root->d_sb; mnt->mnt.mnt_root = dget(fc->root); mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; fs_userns = mnt->mnt.mnt_sb->s_user_ns; if (!initial_idmapping(fs_userns)) mnt->mnt.mnt_userns = get_user_ns(fs_userns); lock_mount_hash(); list_add_tail(&mnt->mnt_instance, &mnt->mnt.mnt_sb->s_mounts); unlock_mount_hash(); return &mnt->mnt; } EXPORT_SYMBOL(vfs_create_mount); struct vfsmount *fc_mount(struct fs_context *fc) { int err = vfs_get_tree(fc); if (!err) { up_write(&fc->root->d_sb->s_umount); return vfs_create_mount(fc); } return ERR_PTR(err); } EXPORT_SYMBOL(fc_mount); struct vfsmount *vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data) { struct fs_context *fc; struct vfsmount *mnt; int ret = 0; if (!type) return ERR_PTR(-EINVAL); fc = fs_context_for_mount(type, flags); if (IS_ERR(fc)) return ERR_CAST(fc); if (name) ret = vfs_parse_fs_string(fc, "source", name, strlen(name)); if (!ret) ret = parse_monolithic_mount_data(fc, data); if (!ret) mnt = fc_mount(fc); else mnt = ERR_PTR(ret); put_fs_context(fc); return mnt; } EXPORT_SYMBOL_GPL(vfs_kern_mount); struct vfsmount * vfs_submount(const struct dentry *mountpoint, struct file_system_type *type, const char *name, void *data) { /* Until it is worked out how to pass the user namespace * through from the parent mount to the submount don't support * unprivileged mounts with submounts. */ if (mountpoint->d_sb->s_user_ns != &init_user_ns) return ERR_PTR(-EPERM); return vfs_kern_mount(type, SB_SUBMOUNT, name, data); } EXPORT_SYMBOL_GPL(vfs_submount); static struct mount *clone_mnt(struct mount *old, struct dentry *root, int flag) { struct super_block *sb = old->mnt.mnt_sb; struct mount *mnt; int err; mnt = alloc_vfsmnt(old->mnt_devname); if (!mnt) return ERR_PTR(-ENOMEM); if (flag & (CL_SLAVE | CL_PRIVATE | CL_SHARED_TO_SLAVE)) mnt->mnt_group_id = 0; /* not a peer of original */ else mnt->mnt_group_id = old->mnt_group_id; if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) { err = mnt_alloc_group_id(mnt); if (err) goto out_free; } mnt->mnt.mnt_flags = old->mnt.mnt_flags; mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL); atomic_inc(&sb->s_active); mnt->mnt.mnt_userns = mnt_user_ns(&old->mnt); if (!initial_idmapping(mnt->mnt.mnt_userns)) mnt->mnt.mnt_userns = get_user_ns(mnt->mnt.mnt_userns); mnt->mnt.mnt_sb = sb; mnt->mnt.mnt_root = dget(root); mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; lock_mount_hash(); list_add_tail(&mnt->mnt_instance, &sb->s_mounts); unlock_mount_hash(); if ((flag & CL_SLAVE) || ((flag & CL_SHARED_TO_SLAVE) && IS_MNT_SHARED(old))) { list_add(&mnt->mnt_slave, &old->mnt_slave_list); mnt->mnt_master = old; CLEAR_MNT_SHARED(mnt); } else if (!(flag & CL_PRIVATE)) { if ((flag & CL_MAKE_SHARED) || IS_MNT_SHARED(old)) list_add(&mnt->mnt_share, &old->mnt_share); if (IS_MNT_SLAVE(old)) list_add(&mnt->mnt_slave, &old->mnt_slave); mnt->mnt_master = old->mnt_master; } else { CLEAR_MNT_SHARED(mnt); } if (flag & CL_MAKE_SHARED) set_mnt_shared(mnt); /* stick the duplicate mount on the same expiry list * as the original if that was on one */ if (flag & CL_EXPIRE) { if (!list_empty(&old->mnt_expire)) list_add(&mnt->mnt_expire, &old->mnt_expire); } return mnt; out_free: mnt_free_id(mnt); free_vfsmnt(mnt); return ERR_PTR(err); } static void cleanup_mnt(struct mount *mnt) { struct hlist_node *p; struct mount *m; /* * The warning here probably indicates that somebody messed * up a mnt_want/drop_write() pair. If this happens, the * filesystem was probably unable to make r/w->r/o transitions. * The locking used to deal with mnt_count decrement provides barriers, * so mnt_get_writers() below is safe. */ WARN_ON(mnt_get_writers(mnt)); if (unlikely(mnt->mnt_pins.first)) mnt_pin_kill(mnt); hlist_for_each_entry_safe(m, p, &mnt->mnt_stuck_children, mnt_umount) { hlist_del(&m->mnt_umount); mntput(&m->mnt); } fsnotify_vfsmount_delete(&mnt->mnt); dput(mnt->mnt.mnt_root); deactivate_super(mnt->mnt.mnt_sb); mnt_free_id(mnt); call_rcu(&mnt->mnt_rcu, delayed_free_vfsmnt); } static void __cleanup_mnt(struct rcu_head *head) { cleanup_mnt(container_of(head, struct mount, mnt_rcu)); } static LLIST_HEAD(delayed_mntput_list); static void delayed_mntput(struct work_struct *unused) { struct llist_node *node = llist_del_all(&delayed_mntput_list); struct mount *m, *t; llist_for_each_entry_safe(m, t, node, mnt_llist) cleanup_mnt(m); } static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput); static void mntput_no_expire(struct mount *mnt) { LIST_HEAD(list); int count; rcu_read_lock(); if (likely(READ_ONCE(mnt->mnt_ns))) { /* * Since we don't do lock_mount_hash() here, * ->mnt_ns can change under us. However, if it's * non-NULL, then there's a reference that won't * be dropped until after an RCU delay done after * turning ->mnt_ns NULL. So if we observe it * non-NULL under rcu_read_lock(), the reference * we are dropping is not the final one. */ mnt_add_count(mnt, -1); rcu_read_unlock(); return; } lock_mount_hash(); /* * make sure that if __legitimize_mnt() has not seen us grab * mount_lock, we'll see their refcount increment here. */ smp_mb(); mnt_add_count(mnt, -1); count = mnt_get_count(mnt); if (count != 0) { WARN_ON(count < 0); rcu_read_unlock(); unlock_mount_hash(); return; } if (unlikely(mnt->mnt.mnt_flags & MNT_DOOMED)) { rcu_read_unlock(); unlock_mount_hash(); return; } mnt->mnt.mnt_flags |= MNT_DOOMED; rcu_read_unlock(); list_del(&mnt->mnt_instance); if (unlikely(!list_empty(&mnt->mnt_mounts))) { struct mount *p, *tmp; list_for_each_entry_safe(p, tmp, &mnt->mnt_mounts, mnt_child) { __put_mountpoint(unhash_mnt(p), &list); hlist_add_head(&p->mnt_umount, &mnt->mnt_stuck_children); } } unlock_mount_hash(); shrink_dentry_list(&list); if (likely(!(mnt->mnt.mnt_flags & MNT_INTERNAL))) { struct task_struct *task = current; if (likely(!(task->flags & PF_KTHREAD))) { init_task_work(&mnt->mnt_rcu, __cleanup_mnt); if (!task_work_add(task, &mnt->mnt_rcu, TWA_RESUME)) return; } if (llist_add(&mnt->mnt_llist, &delayed_mntput_list)) schedule_delayed_work(&delayed_mntput_work, 1); return; } cleanup_mnt(mnt); } void mntput(struct vfsmount *mnt) { if (mnt) { struct mount *m = real_mount(mnt); /* avoid cacheline pingpong, hope gcc doesn't get "smart" */ if (unlikely(m->mnt_expiry_mark)) m->mnt_expiry_mark = 0; mntput_no_expire(m); } } EXPORT_SYMBOL(mntput); struct vfsmount *mntget(struct vfsmount *mnt) { if (mnt) mnt_add_count(real_mount(mnt), 1); return mnt; } EXPORT_SYMBOL(mntget); /** * path_is_mountpoint() - Check if path is a mount in the current namespace. * @path: path to check * * d_mountpoint() can only be used reliably to establish if a dentry is * not mounted in any namespace and that common case is handled inline. * d_mountpoint() isn't aware of the possibility there may be multiple * mounts using a given dentry in a different namespace. This function * checks if the passed in path is a mountpoint rather than the dentry * alone. */ bool path_is_mountpoint(const struct path *path) { unsigned seq; bool res; if (!d_mountpoint(path->dentry)) return false; rcu_read_lock(); do { seq = read_seqbegin(&mount_lock); res = __path_is_mountpoint(path); } while (read_seqretry(&mount_lock, seq)); rcu_read_unlock(); return res; } EXPORT_SYMBOL(path_is_mountpoint); struct vfsmount *mnt_clone_internal(const struct path *path) { struct mount *p; p = clone_mnt(real_mount(path->mnt), path->dentry, CL_PRIVATE); if (IS_ERR(p)) return ERR_CAST(p); p->mnt.mnt_flags |= MNT_INTERNAL; return &p->mnt; } #ifdef CONFIG_PROC_FS static struct mount *mnt_list_next(struct mnt_namespace *ns, struct list_head *p) { struct mount *mnt, *ret = NULL; lock_ns_list(ns); list_for_each_continue(p, &ns->list) { mnt = list_entry(p, typeof(*mnt), mnt_list); if (!mnt_is_cursor(mnt)) { ret = mnt; break; } } unlock_ns_list(ns); return ret; } /* iterator; we want it to have access to namespace_sem, thus here... */ static void *m_start(struct seq_file *m, loff_t *pos) { struct proc_mounts *p = m->private; struct list_head *prev; down_read(&namespace_sem); if (!*pos) { prev = &p->ns->list; } else { prev = &p->cursor.mnt_list; /* Read after we'd reached the end? */ if (list_empty(prev)) return NULL; } return mnt_list_next(p->ns, prev); } static void *m_next(struct seq_file *m, void *v, loff_t *pos) { struct proc_mounts *p = m->private; struct mount *mnt = v; ++*pos; return mnt_list_next(p->ns, &mnt->mnt_list); } static void m_stop(struct seq_file *m, void *v) { struct proc_mounts *p = m->private; struct mount *mnt = v; lock_ns_list(p->ns); if (mnt) list_move_tail(&p->cursor.mnt_list, &mnt->mnt_list); else list_del_init(&p->cursor.mnt_list); unlock_ns_list(p->ns); up_read(&namespace_sem); } static int m_show(struct seq_file *m, void *v) { struct proc_mounts *p = m->private; struct mount *r = v; return p->show(m, &r->mnt); } const struct seq_operations mounts_op = { .start = m_start, .next = m_next, .stop = m_stop, .show = m_show, }; void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor) { down_read(&namespace_sem); lock_ns_list(ns); list_del(&cursor->mnt_list); unlock_ns_list(ns); up_read(&namespace_sem); } #endif /* CONFIG_PROC_FS */ /** * may_umount_tree - check if a mount tree is busy * @m: root of mount tree * * This is called to check if a tree of mounts has any * open files, pwds, chroots or sub mounts that are * busy. */ int may_umount_tree(struct vfsmount *m) { struct mount *mnt = real_mount(m); int actual_refs = 0; int minimum_refs = 0; struct mount *p; BUG_ON(!m); /* write lock needed for mnt_get_count */ lock_mount_hash(); for (p = mnt; p; p = next_mnt(p, mnt)) { actual_refs += mnt_get_count(p); minimum_refs += 2; } unlock_mount_hash(); if (actual_refs > minimum_refs) return 0; return 1; } EXPORT_SYMBOL(may_umount_tree); /** * may_umount - check if a mount point is busy * @mnt: root of mount * * This is called to check if a mount point has any * open files, pwds, chroots or sub mounts. If the * mount has sub mounts this will return busy * regardless of whether the sub mounts are busy. * * Doesn't take quota and stuff into account. IOW, in some cases it will * give false negatives. The main reason why it's here is that we need * a non-destructive way to look for easily umountable filesystems. */ int may_umount(struct vfsmount *mnt) { int ret = 1; down_read(&namespace_sem); lock_mount_hash(); if (propagate_mount_busy(real_mount(mnt), 2)) ret = 0; unlock_mount_hash(); up_read(&namespace_sem); return ret; } EXPORT_SYMBOL(may_umount); static void namespace_unlock(void) { struct hlist_head head; struct hlist_node *p; struct mount *m; LIST_HEAD(list); hlist_move_list(&unmounted, &head); list_splice_init(&ex_mountpoints, &list); up_write(&namespace_sem); shrink_dentry_list(&list); if (likely(hlist_empty(&head))) return; synchronize_rcu_expedited(); hlist_for_each_entry_safe(m, p, &head, mnt_umount) { hlist_del(&m->mnt_umount); mntput(&m->mnt); } } static inline void namespace_lock(void) { down_write(&namespace_sem); } enum umount_tree_flags { UMOUNT_SYNC = 1, UMOUNT_PROPAGATE = 2, UMOUNT_CONNECTED = 4, }; static bool disconnect_mount(struct mount *mnt, enum umount_tree_flags how) { /* Leaving mounts connected is only valid for lazy umounts */ if (how & UMOUNT_SYNC) return true; /* A mount without a parent has nothing to be connected to */ if (!mnt_has_parent(mnt)) return true; /* Because the reference counting rules change when mounts are * unmounted and connected, umounted mounts may not be * connected to mounted mounts. */ if (!(mnt->mnt_parent->mnt.mnt_flags & MNT_UMOUNT)) return true; /* Has it been requested that the mount remain connected? */ if (how & UMOUNT_CONNECTED) return false; /* Is the mount locked such that it needs to remain connected? */ if (IS_MNT_LOCKED(mnt)) return false; /* By default disconnect the mount */ return true; } /* * mount_lock must be held * namespace_sem must be held for write */ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) { LIST_HEAD(tmp_list); struct mount *p; if (how & UMOUNT_PROPAGATE) propagate_mount_unlock(mnt); /* Gather the mounts to umount */ for (p = mnt; p; p = next_mnt(p, mnt)) { p->mnt.mnt_flags |= MNT_UMOUNT; list_move(&p->mnt_list, &tmp_list); } /* Hide the mounts from mnt_mounts */ list_for_each_entry(p, &tmp_list, mnt_list) { list_del_init(&p->mnt_child); } /* Add propogated mounts to the tmp_list */ if (how & UMOUNT_PROPAGATE) propagate_umount(&tmp_list); while (!list_empty(&tmp_list)) { struct mnt_namespace *ns; bool disconnect; p = list_first_entry(&tmp_list, struct mount, mnt_list); list_del_init(&p->mnt_expire); list_del_init(&p->mnt_list); ns = p->mnt_ns; if (ns) { ns->mounts--; __touch_mnt_namespace(ns); } p->mnt_ns = NULL; if (how & UMOUNT_SYNC) p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; disconnect = disconnect_mount(p, how); if (mnt_has_parent(p)) { mnt_add_count(p->mnt_parent, -1); if (!disconnect) { /* Don't forget about p */ list_add_tail(&p->mnt_child, &p->mnt_parent->mnt_mounts); } else { umount_mnt(p); } } change_mnt_propagation(p, MS_PRIVATE); if (disconnect) hlist_add_head(&p->mnt_umount, &unmounted); } } static void shrink_submounts(struct mount *mnt); static int do_umount_root(struct super_block *sb) { int ret = 0; down_write(&sb->s_umount); if (!sb_rdonly(sb)) { struct fs_context *fc; fc = fs_context_for_reconfigure(sb->s_root, SB_RDONLY, SB_RDONLY); if (IS_ERR(fc)) { ret = PTR_ERR(fc); } else { ret = parse_monolithic_mount_data(fc, NULL); if (!ret) ret = reconfigure_super(fc); put_fs_context(fc); } } up_write(&sb->s_umount); return ret; } static int do_umount(struct mount *mnt, int flags) { struct super_block *sb = mnt->mnt.mnt_sb; int retval; retval = security_sb_umount(&mnt->mnt, flags); if (retval) return retval; /* * Allow userspace to request a mountpoint be expired rather than * unmounting unconditionally. Unmount only happens if: * (1) the mark is already set (the mark is cleared by mntput()) * (2) the usage count == 1 [parent vfsmount] + 1 [sys_umount] */ if (flags & MNT_EXPIRE) { if (&mnt->mnt == current->fs->root.mnt || flags & (MNT_FORCE | MNT_DETACH)) return -EINVAL; /* * probably don't strictly need the lock here if we examined * all race cases, but it's a slowpath. */ lock_mount_hash(); if (mnt_get_count(mnt) != 2) { unlock_mount_hash(); return -EBUSY; } unlock_mount_hash(); if (!xchg(&mnt->mnt_expiry_mark, 1)) return -EAGAIN; } /* * If we may have to abort operations to get out of this * mount, and they will themselves hold resources we must * allow the fs to do things. In the Unix tradition of * 'Gee thats tricky lets do it in userspace' the umount_begin * might fail to complete on the first run through as other tasks * must return, and the like. Thats for the mount program to worry * about for the moment. */ if (flags & MNT_FORCE && sb->s_op->umount_begin) { sb->s_op->umount_begin(sb); } /* * No sense to grab the lock for this test, but test itself looks * somewhat bogus. Suggestions for better replacement? * Ho-hum... In principle, we might treat that as umount + switch * to rootfs. GC would eventually take care of the old vfsmount. * Actually it makes sense, especially if rootfs would contain a * /reboot - static binary that would close all descriptors and * call reboot(9). Then init(8) could umount root and exec /reboot. */ if (&mnt->mnt == current->fs->root.mnt && !(flags & MNT_DETACH)) { /* * Special case for "unmounting" root ... * we just try to remount it readonly. */ if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; return do_umount_root(sb); } namespace_lock(); lock_mount_hash(); /* Recheck MNT_LOCKED with the locks held */ retval = -EINVAL; if (mnt->mnt.mnt_flags & MNT_LOCKED) goto out; event++; if (flags & MNT_DETACH) { if (!list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE); retval = 0; } else { shrink_submounts(mnt); retval = -EBUSY; if (!propagate_mount_busy(mnt, 2)) { if (!list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); retval = 0; } } out: unlock_mount_hash(); namespace_unlock(); return retval; } /* * __detach_mounts - lazily unmount all mounts on the specified dentry * * During unlink, rmdir, and d_drop it is possible to loose the path * to an existing mountpoint, and wind up leaking the mount. * detach_mounts allows lazily unmounting those mounts instead of * leaking them. * * The caller may hold dentry->d_inode->i_mutex. */ void __detach_mounts(struct dentry *dentry) { struct mountpoint *mp; struct mount *mnt; namespace_lock(); lock_mount_hash(); mp = lookup_mountpoint(dentry); if (!mp) goto out_unlock; event++; while (!hlist_empty(&mp->m_list)) { mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list); if (mnt->mnt.mnt_flags & MNT_UMOUNT) { umount_mnt(mnt); hlist_add_head(&mnt->mnt_umount, &unmounted); } else umount_tree(mnt, UMOUNT_CONNECTED); } put_mountpoint(mp); out_unlock: unlock_mount_hash(); namespace_unlock(); } /* * Is the caller allowed to modify his namespace? */ bool may_mount(void) { return ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN); } static void warn_mandlock(void) { pr_warn_once("=======================================================\n" "WARNING: The mand mount option has been deprecated and\n" " and is ignored by this kernel. Remove the mand\n" " option from the mount to silence this warning.\n" "=======================================================\n"); } static int can_umount(const struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); struct super_block *sb = path->dentry->d_sb; if (!may_mount()) return -EPERM; if (path->dentry != path->mnt->mnt_root) return -EINVAL; if (!check_mnt(mnt)) return -EINVAL; if (mnt->mnt.mnt_flags & MNT_LOCKED) /* Check optimistically */ return -EINVAL; if (flags & MNT_FORCE && !ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } // caller is responsible for flags being sane int path_umount(struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); int ret; ret = can_umount(path, flags); if (!ret) ret = do_umount(mnt, flags); /* we mustn't call path_put() as that would clear mnt_expiry_mark */ dput(path->dentry); mntput_no_expire(mnt); return ret; } static int ksys_umount(char __user *name, int flags) { int lookup_flags = LOOKUP_MOUNTPOINT; struct path path; int ret; // basic validity checks done first if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW)) return -EINVAL; if (!(flags & UMOUNT_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; ret = user_path_at(AT_FDCWD, name, lookup_flags, &path); if (ret) return ret; return path_umount(&path, flags); } SYSCALL_DEFINE2(umount, char __user *, name, int, flags) { return ksys_umount(name, flags); } #ifdef __ARCH_WANT_SYS_OLDUMOUNT /* * The 2.0 compatible umount. No flags. */ SYSCALL_DEFINE1(oldumount, char __user *, name) { return ksys_umount(name, 0); } #endif static bool is_mnt_ns_file(struct dentry *dentry) { /* Is this a proxy for a mount namespace? */ return dentry->d_op == &ns_dentry_operations && dentry->d_fsdata == &mntns_operations; } static struct mnt_namespace *to_mnt_ns(struct ns_common *ns) { return container_of(ns, struct mnt_namespace, ns); } struct ns_common *from_mnt_ns(struct mnt_namespace *mnt) { return &mnt->ns; } static bool mnt_ns_loop(struct dentry *dentry) { /* Could bind mounting the mount namespace inode cause a * mount namespace loop? */ struct mnt_namespace *mnt_ns; if (!is_mnt_ns_file(dentry)) return false; mnt_ns = to_mnt_ns(get_proc_ns(dentry->d_inode)); return current->nsproxy->mnt_ns->seq >= mnt_ns->seq; } struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, int flag) { struct mount *res, *p, *q, *r, *parent; if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(mnt)) return ERR_PTR(-EINVAL); if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(dentry)) return ERR_PTR(-EINVAL); res = q = clone_mnt(mnt, dentry, flag); if (IS_ERR(q)) return q; q->mnt_mountpoint = mnt->mnt_mountpoint; p = mnt; list_for_each_entry(r, &mnt->mnt_mounts, mnt_child) { struct mount *s; if (!is_subdir(r->mnt_mountpoint, dentry)) continue; for (s = r; s; s = next_mnt(s, r)) { if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(s)) { if (s->mnt.mnt_flags & MNT_LOCKED) { /* Both unbindable and locked. */ q = ERR_PTR(-EPERM); goto out; } else { s = skip_mnt_tree(s); continue; } } if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(s->mnt.mnt_root)) { s = skip_mnt_tree(s); continue; } while (p != s->mnt_parent) { p = p->mnt_parent; q = q->mnt_parent; } p = s; parent = q; q = clone_mnt(p, p->mnt.mnt_root, flag); if (IS_ERR(q)) goto out; lock_mount_hash(); list_add_tail(&q->mnt_list, &res->mnt_list); attach_mnt(q, parent, p->mnt_mp); unlock_mount_hash(); } } return res; out: if (res) { lock_mount_hash(); umount_tree(res, UMOUNT_SYNC); unlock_mount_hash(); } return q; } /* Caller should check returned pointer for errors */ struct vfsmount *collect_mounts(const struct path *path) { struct mount *tree; namespace_lock(); if (!check_mnt(real_mount(path->mnt))) tree = ERR_PTR(-EINVAL); else tree = copy_tree(real_mount(path->mnt), path->dentry, CL_COPY_ALL | CL_PRIVATE); namespace_unlock(); if (IS_ERR(tree)) return ERR_CAST(tree); return &tree->mnt; } static void free_mnt_ns(struct mnt_namespace *); static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *, bool); void dissolve_on_fput(struct vfsmount *mnt) { struct mnt_namespace *ns; namespace_lock(); lock_mount_hash(); ns = real_mount(mnt)->mnt_ns; if (ns) { if (is_anon_ns(ns)) umount_tree(real_mount(mnt), UMOUNT_CONNECTED); else ns = NULL; } unlock_mount_hash(); namespace_unlock(); if (ns) free_mnt_ns(ns); } void drop_collected_mounts(struct vfsmount *mnt) { namespace_lock(); lock_mount_hash(); umount_tree(real_mount(mnt), 0); unlock_mount_hash(); namespace_unlock(); } static bool has_locked_children(struct mount *mnt, struct dentry *dentry) { struct mount *child; list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { if (!is_subdir(child->mnt_mountpoint, dentry)) continue; if (child->mnt.mnt_flags & MNT_LOCKED) return true; } return false; } /** * clone_private_mount - create a private clone of a path * @path: path to clone * * This creates a new vfsmount, which will be the clone of @path. The new mount * will not be attached anywhere in the namespace and will be private (i.e. * changes to the originating mount won't be propagated into this). * * Release with mntput(). */ struct vfsmount *clone_private_mount(const struct path *path) { struct mount *old_mnt = real_mount(path->mnt); struct mount *new_mnt; down_read(&namespace_sem); if (IS_MNT_UNBINDABLE(old_mnt)) goto invalid; if (!check_mnt(old_mnt)) goto invalid; if (has_locked_children(old_mnt, path->dentry)) goto invalid; new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE); up_read(&namespace_sem); if (IS_ERR(new_mnt)) return ERR_CAST(new_mnt); /* Longterm mount to be removed by kern_unmount*() */ new_mnt->mnt_ns = MNT_NS_INTERNAL; return &new_mnt->mnt; invalid: up_read(&namespace_sem); return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(clone_private_mount); int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg, struct vfsmount *root) { struct mount *mnt; int res = f(root, arg); if (res) return res; list_for_each_entry(mnt, &real_mount(root)->mnt_list, mnt_list) { res = f(&mnt->mnt, arg); if (res) return res; } return 0; } static void lock_mnt_tree(struct mount *mnt) { struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) { int flags = p->mnt.mnt_flags; /* Don't allow unprivileged users to change mount flags */ flags |= MNT_LOCK_ATIME; if (flags & MNT_READONLY) flags |= MNT_LOCK_READONLY; if (flags & MNT_NODEV) flags |= MNT_LOCK_NODEV; if (flags & MNT_NOSUID) flags |= MNT_LOCK_NOSUID; if (flags & MNT_NOEXEC) flags |= MNT_LOCK_NOEXEC; /* Don't allow unprivileged users to reveal what is under a mount */ if (list_empty(&p->mnt_expire)) flags |= MNT_LOCKED; p->mnt.mnt_flags = flags; } } static void cleanup_group_ids(struct mount *mnt, struct mount *end) { struct mount *p; for (p = mnt; p != end; p = next_mnt(p, mnt)) { if (p->mnt_group_id && !IS_MNT_SHARED(p)) mnt_release_group_id(p); } } static int invent_group_ids(struct mount *mnt, bool recurse) { struct mount *p; for (p = mnt; p; p = recurse ? next_mnt(p, mnt) : NULL) { if (!p->mnt_group_id && !IS_MNT_SHARED(p)) { int err = mnt_alloc_group_id(p); if (err) { cleanup_group_ids(mnt, p); return err; } } } return 0; } int count_mounts(struct mnt_namespace *ns, struct mount *mnt) { unsigned int max = READ_ONCE(sysctl_mount_max); unsigned int mounts = 0; struct mount *p; if (ns->mounts >= max) return -ENOSPC; max -= ns->mounts; if (ns->pending_mounts >= max) return -ENOSPC; max -= ns->pending_mounts; for (p = mnt; p; p = next_mnt(p, mnt)) mounts++; if (mounts > max) return -ENOSPC; ns->pending_mounts += mounts; return 0; } /* * @source_mnt : mount tree to be attached * @nd : place the mount tree @source_mnt is attached * @parent_nd : if non-null, detach the source_mnt from its parent and * store the parent mount and mountpoint dentry. * (done when source_mnt is moved) * * NOTE: in the table below explains the semantics when a source mount * of a given type is attached to a destination mount of a given type. * --------------------------------------------------------------------------- * | BIND MOUNT OPERATION | * |************************************************************************** * | source-->| shared | private | slave | unbindable | * | dest | | | | | * | | | | | | | * | v | | | | | * |************************************************************************** * | shared | shared (++) | shared (+) | shared(+++)| invalid | * | | | | | | * |non-shared| shared (+) | private | slave (*) | invalid | * *************************************************************************** * A bind operation clones the source mount and mounts the clone on the * destination mount. * * (++) the cloned mount is propagated to all the mounts in the propagation * tree of the destination mount and the cloned mount is added to * the peer group of the source mount. * (+) the cloned mount is created under the destination mount and is marked * as shared. The cloned mount is added to the peer group of the source * mount. * (+++) the mount is propagated to all the mounts in the propagation tree * of the destination mount and the cloned mount is made slave * of the same master as that of the source mount. The cloned mount * is marked as 'shared and slave'. * (*) the cloned mount is made a slave of the same master as that of the * source mount. * * --------------------------------------------------------------------------- * | MOVE MOUNT OPERATION | * |************************************************************************** * | source-->| shared | private | slave | unbindable | * | dest | | | | | * | | | | | | | * | v | | | | | * |************************************************************************** * | shared | shared (+) | shared (+) | shared(+++) | invalid | * | | | | | | * |non-shared| shared (+*) | private | slave (*) | unbindable | * *************************************************************************** * * (+) the mount is moved to the destination. And is then propagated to * all the mounts in the propagation tree of the destination mount. * (+*) the mount is moved to the destination. * (+++) the mount is moved to the destination and is then propagated to * all the mounts belonging to the destination mount's propagation tree. * the mount is marked as 'shared and slave'. * (*) the mount continues to be a slave at the new location. * * if the source mount is a tree, the operations explained above is * applied to each mount in the tree. * Must be called without spinlocks held, since this function can sleep * in allocations. */ static int attach_recursive_mnt(struct mount *source_mnt, struct mount *dest_mnt, struct mountpoint *dest_mp, bool moving) { struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; HLIST_HEAD(tree_list); struct mnt_namespace *ns = dest_mnt->mnt_ns; struct mountpoint *smp; struct mount *child, *p; struct hlist_node *n; int err; /* Preallocate a mountpoint in case the new mounts need * to be tucked under other mounts. */ smp = get_mountpoint(source_mnt->mnt.mnt_root); if (IS_ERR(smp)) return PTR_ERR(smp); /* Is there space to add these mounts to the mount namespace? */ if (!moving) { err = count_mounts(ns, source_mnt); if (err) goto out; } if (IS_MNT_SHARED(dest_mnt)) { err = invent_group_ids(source_mnt, true); if (err) goto out; err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list); lock_mount_hash(); if (err) goto out_cleanup_ids; for (p = source_mnt; p; p = next_mnt(p, source_mnt)) set_mnt_shared(p); } else { lock_mount_hash(); } if (moving) { unhash_mnt(source_mnt); attach_mnt(source_mnt, dest_mnt, dest_mp); touch_mnt_namespace(source_mnt->mnt_ns); } else { if (source_mnt->mnt_ns) { /* move from anon - the caller will destroy */ list_del_init(&source_mnt->mnt_ns->list); } mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt); commit_tree(source_mnt); } hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) { struct mount *q; hlist_del_init(&child->mnt_hash); q = __lookup_mnt(&child->mnt_parent->mnt, child->mnt_mountpoint); if (q) mnt_change_mountpoint(child, smp, q); /* Notice when we are propagating across user namespaces */ if (child->mnt_parent->mnt_ns->user_ns != user_ns) lock_mnt_tree(child); child->mnt.mnt_flags &= ~MNT_LOCKED; commit_tree(child); } put_mountpoint(smp); unlock_mount_hash(); return 0; out_cleanup_ids: while (!hlist_empty(&tree_list)) { child = hlist_entry(tree_list.first, struct mount, mnt_hash); child->mnt_parent->mnt_ns->pending_mounts = 0; umount_tree(child, UMOUNT_SYNC); } unlock_mount_hash(); cleanup_group_ids(source_mnt, NULL); out: ns->pending_mounts = 0; read_seqlock_excl(&mount_lock); put_mountpoint(smp); read_sequnlock_excl(&mount_lock); return err; } static struct mountpoint *lock_mount(struct path *path) { struct vfsmount *mnt; struct dentry *dentry = path->dentry; retry: inode_lock(dentry->d_inode); if (unlikely(cant_mount(dentry))) { inode_unlock(dentry->d_inode); return ERR_PTR(-ENOENT); } namespace_lock(); mnt = lookup_mnt(path); if (likely(!mnt)) { struct mountpoint *mp = get_mountpoint(dentry); if (IS_ERR(mp)) { namespace_unlock(); inode_unlock(dentry->d_inode); return mp; } return mp; } namespace_unlock(); inode_unlock(path->dentry->d_inode); path_put(path); path->mnt = mnt; dentry = path->dentry = dget(mnt->mnt_root); goto retry; } static void unlock_mount(struct mountpoint *where) { struct dentry *dentry = where->m_dentry; read_seqlock_excl(&mount_lock); put_mountpoint(where); read_sequnlock_excl(&mount_lock); namespace_unlock(); inode_unlock(dentry->d_inode); } static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp) { if (mnt->mnt.mnt_sb->s_flags & SB_NOUSER) return -EINVAL; if (d_is_dir(mp->m_dentry) != d_is_dir(mnt->mnt.mnt_root)) return -ENOTDIR; return attach_recursive_mnt(mnt, p, mp, false); } /* * Sanity check the flags to change_mnt_propagation. */ static int flags_to_propagation_type(int ms_flags) { int type = ms_flags & ~(MS_REC | MS_SILENT); /* Fail if any non-propagation flags are set */ if (type & ~(MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) return 0; /* Only one propagation flag should be set */ if (!is_power_of_2(type)) return 0; return type; } /* * recursively change the type of the mountpoint. */ static int do_change_type(struct path *path, int ms_flags) { struct mount *m; struct mount *mnt = real_mount(path->mnt); int recurse = ms_flags & MS_REC; int type; int err = 0; if (path->dentry != path->mnt->mnt_root) return -EINVAL; type = flags_to_propagation_type(ms_flags); if (!type) return -EINVAL; namespace_lock(); if (type == MS_SHARED) { err = invent_group_ids(mnt, recurse); if (err) goto out_unlock; } lock_mount_hash(); for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL)) change_mnt_propagation(m, type); unlock_mount_hash(); out_unlock: namespace_unlock(); return err; } static struct mount *__do_loopback(struct path *old_path, int recurse) { struct mount *mnt = ERR_PTR(-EINVAL), *old = real_mount(old_path->mnt); if (IS_MNT_UNBINDABLE(old)) return mnt; if (!check_mnt(old) && old_path->dentry->d_op != &ns_dentry_operations) return mnt; if (!recurse && has_locked_children(old, old_path->dentry)) return mnt; if (recurse) mnt = copy_tree(old, old_path->dentry, CL_COPY_MNT_NS_FILE); else mnt = clone_mnt(old, old_path->dentry, 0); if (!IS_ERR(mnt)) mnt->mnt.mnt_flags &= ~MNT_LOCKED; return mnt; } /* * do loopback mount. */ static int do_loopback(struct path *path, const char *old_name, int recurse) { struct path old_path; struct mount *mnt = NULL, *parent; struct mountpoint *mp; int err; if (!old_name || !*old_name) return -EINVAL; err = kern_path(old_name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &old_path); if (err) return err; err = -EINVAL; if (mnt_ns_loop(old_path.dentry)) goto out; mp = lock_mount(path); if (IS_ERR(mp)) { err = PTR_ERR(mp); goto out; } parent = real_mount(path->mnt); if (!check_mnt(parent)) goto out2; mnt = __do_loopback(&old_path, recurse); if (IS_ERR(mnt)) { err = PTR_ERR(mnt); goto out2; } err = graft_tree(mnt, parent, mp); if (err) { lock_mount_hash(); umount_tree(mnt, UMOUNT_SYNC); unlock_mount_hash(); } out2: unlock_mount(mp); out: path_put(&old_path); return err; } static struct file *open_detached_copy(struct path *path, bool recursive) { struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; struct mnt_namespace *ns = alloc_mnt_ns(user_ns, true); struct mount *mnt, *p; struct file *file; if (IS_ERR(ns)) return ERR_CAST(ns); namespace_lock(); mnt = __do_loopback(path, recursive); if (IS_ERR(mnt)) { namespace_unlock(); free_mnt_ns(ns); return ERR_CAST(mnt); } lock_mount_hash(); for (p = mnt; p; p = next_mnt(p, mnt)) { p->mnt_ns = ns; ns->mounts++; } ns->root = mnt; list_add_tail(&ns->list, &mnt->mnt_list); mntget(&mnt->mnt); unlock_mount_hash(); namespace_unlock(); mntput(path->mnt); path->mnt = &mnt->mnt; file = dentry_open(path, O_PATH, current_cred()); if (IS_ERR(file)) dissolve_on_fput(path->mnt); else file->f_mode |= FMODE_NEED_UNMOUNT; return file; } SYSCALL_DEFINE3(open_tree, int, dfd, const char __user *, filename, unsigned, flags) { struct file *file; struct path path; int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW; bool detached = flags & OPEN_TREE_CLONE; int error; int fd; BUILD_BUG_ON(OPEN_TREE_CLOEXEC != O_CLOEXEC); if (flags & ~(AT_EMPTY_PATH | AT_NO_AUTOMOUNT | AT_RECURSIVE | AT_SYMLINK_NOFOLLOW | OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC)) return -EINVAL; if ((flags & (AT_RECURSIVE | OPEN_TREE_CLONE)) == AT_RECURSIVE) return -EINVAL; if (flags & AT_NO_AUTOMOUNT) lookup_flags &= ~LOOKUP_AUTOMOUNT; if (flags & AT_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; if (detached && !may_mount()) return -EPERM; fd = get_unused_fd_flags(flags & O_CLOEXEC); if (fd < 0) return fd; error = user_path_at(dfd, filename, lookup_flags, &path); if (unlikely(error)) { file = ERR_PTR(error); } else { if (detached) file = open_detached_copy(&path, flags & AT_RECURSIVE); else file = dentry_open(&path, O_PATH, current_cred()); path_put(&path); } if (IS_ERR(file)) { put_unused_fd(fd); return PTR_ERR(file); } fd_install(fd, file); return fd; } /* * Don't allow locked mount flags to be cleared. * * No locks need to be held here while testing the various MNT_LOCK * flags because those flags can never be cleared once they are set. */ static bool can_change_locked_flags(struct mount *mnt, unsigned int mnt_flags) { unsigned int fl = mnt->mnt.mnt_flags; if ((fl & MNT_LOCK_READONLY) && !(mnt_flags & MNT_READONLY)) return false; if ((fl & MNT_LOCK_NODEV) && !(mnt_flags & MNT_NODEV)) return false; if ((fl & MNT_LOCK_NOSUID) && !(mnt_flags & MNT_NOSUID)) return false; if ((fl & MNT_LOCK_NOEXEC) && !(mnt_flags & MNT_NOEXEC)) return false; if ((fl & MNT_LOCK_ATIME) && ((fl & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK))) return false; return true; } static int change_mount_ro_state(struct mount *mnt, unsigned int mnt_flags) { bool readonly_request = (mnt_flags & MNT_READONLY); if (readonly_request == __mnt_is_readonly(&mnt->mnt)) return 0; if (readonly_request) return mnt_make_readonly(mnt); mnt->mnt.mnt_flags &= ~MNT_READONLY; return 0; } static void set_mount_attributes(struct mount *mnt, unsigned int mnt_flags) { mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK; mnt->mnt.mnt_flags = mnt_flags; touch_mnt_namespace(mnt->mnt_ns); } static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount *mnt) { struct super_block *sb = mnt->mnt_sb; if (!__mnt_is_readonly(mnt) && (!(sb->s_iflags & SB_I_TS_EXPIRY_WARNED)) && (ktime_get_real_seconds() + TIME_UPTIME_SEC_MAX > sb->s_time_max)) { char *buf, *mntpath; buf = (char *)__get_free_page(GFP_KERNEL); if (buf) mntpath = d_path(mountpoint, buf, PAGE_SIZE); else mntpath = ERR_PTR(-ENOMEM); if (IS_ERR(mntpath)) mntpath = "(unknown)"; pr_warn("%s filesystem being %s at %s supports timestamps until %ptTd (0x%llx)\n", sb->s_type->name, is_mounted(mnt) ? "remounted" : "mounted", mntpath, &sb->s_time_max, (unsigned long long)sb->s_time_max); sb->s_iflags |= SB_I_TS_EXPIRY_WARNED; if (buf) free_page((unsigned long)buf); } } /* * Handle reconfiguration of the mountpoint only without alteration of the * superblock it refers to. This is triggered by specifying MS_REMOUNT|MS_BIND * to mount(2). */ static int do_reconfigure_mnt(struct path *path, unsigned int mnt_flags) { struct super_block *sb = path->mnt->mnt_sb; struct mount *mnt = real_mount(path->mnt); int ret; if (!check_mnt(mnt)) return -EINVAL; if (path->dentry != mnt->mnt.mnt_root) return -EINVAL; if (!can_change_locked_flags(mnt, mnt_flags)) return -EPERM; /* * We're only checking whether the superblock is read-only not * changing it, so only take down_read(&sb->s_umount). */ down_read(&sb->s_umount); lock_mount_hash(); ret = change_mount_ro_state(mnt, mnt_flags); if (ret == 0) set_mount_attributes(mnt, mnt_flags); unlock_mount_hash(); up_read(&sb->s_umount); mnt_warn_timestamp_expiry(path, &mnt->mnt); return ret; } /* * change filesystem flags. dir should be a physical root of filesystem. * If you've mounted a non-root directory somewhere and want to do remount * on it - tough luck. */ static int do_remount(struct path *path, int ms_flags, int sb_flags, int mnt_flags, void *data) { int err; struct super_block *sb = path->mnt->mnt_sb; struct mount *mnt = real_mount(path->mnt); struct fs_context *fc; if (!check_mnt(mnt)) return -EINVAL; if (path->dentry != path->mnt->mnt_root) return -EINVAL; if (!can_change_locked_flags(mnt, mnt_flags)) return -EPERM; fc = fs_context_for_reconfigure(path->dentry, sb_flags, MS_RMT_MASK); if (IS_ERR(fc)) return PTR_ERR(fc); /* * Indicate to the filesystem that the remount request is coming * from the legacy mount system call. */ fc->oldapi = true; err = parse_monolithic_mount_data(fc, data); if (!err) { down_write(&sb->s_umount); err = -EPERM; if (ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) { err = reconfigure_super(fc); if (!err) { lock_mount_hash(); set_mount_attributes(mnt, mnt_flags); unlock_mount_hash(); } } up_write(&sb->s_umount); } mnt_warn_timestamp_expiry(path, &mnt->mnt); put_fs_context(fc); return err; } static inline int tree_contains_unbindable(struct mount *mnt) { struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) { if (IS_MNT_UNBINDABLE(p)) return 1; } return 0; } /* * Check that there aren't references to earlier/same mount namespaces in the * specified subtree. Such references can act as pins for mount namespaces * that aren't checked by the mount-cycle checking code, thereby allowing * cycles to be made. */ static bool check_for_nsfs_mounts(struct mount *subtree) { struct mount *p; bool ret = false; lock_mount_hash(); for (p = subtree; p; p = next_mnt(p, subtree)) if (mnt_ns_loop(p->mnt.mnt_root)) goto out; ret = true; out: unlock_mount_hash(); return ret; } static int do_set_group(struct path *from_path, struct path *to_path) { struct mount *from, *to; int err; from = real_mount(from_path->mnt); to = real_mount(to_path->mnt); namespace_lock(); err = -EINVAL; /* To and From must be mounted */ if (!is_mounted(&from->mnt)) goto out; if (!is_mounted(&to->mnt)) goto out; err = -EPERM; /* We should be allowed to modify mount namespaces of both mounts */ if (!ns_capable(from->mnt_ns->user_ns, CAP_SYS_ADMIN)) goto out; if (!ns_capable(to->mnt_ns->user_ns, CAP_SYS_ADMIN)) goto out; err = -EINVAL; /* To and From paths should be mount roots */ if (from_path->dentry != from_path->mnt->mnt_root) goto out; if (to_path->dentry != to_path->mnt->mnt_root) goto out; /* Setting sharing groups is only allowed across same superblock */ if (from->mnt.mnt_sb != to->mnt.mnt_sb) goto out; /* From mount root should be wider than To mount root */ if (!is_subdir(to->mnt.mnt_root, from->mnt.mnt_root)) goto out; /* From mount should not have locked children in place of To's root */ if (has_locked_children(from, to->mnt.mnt_root)) goto out; /* Setting sharing groups is only allowed on private mounts */ if (IS_MNT_SHARED(to) || IS_MNT_SLAVE(to)) goto out; /* From should not be private */ if (!IS_MNT_SHARED(from) && !IS_MNT_SLAVE(from)) goto out; if (IS_MNT_SLAVE(from)) { struct mount *m = from->mnt_master; list_add(&to->mnt_slave, &m->mnt_slave_list); to->mnt_master = m; } if (IS_MNT_SHARED(from)) { to->mnt_group_id = from->mnt_group_id; list_add(&to->mnt_share, &from->mnt_share); lock_mount_hash(); set_mnt_shared(to); unlock_mount_hash(); } err = 0; out: namespace_unlock(); return err; } static int do_move_mount(struct path *old_path, struct path *new_path) { struct mnt_namespace *ns; struct mount *p; struct mount *old; struct mount *parent; struct mountpoint *mp, *old_mp; int err; bool attached; mp = lock_mount(new_path); if (IS_ERR(mp)) return PTR_ERR(mp); old = real_mount(old_path->mnt); p = real_mount(new_path->mnt); parent = old->mnt_parent; attached = mnt_has_parent(old); old_mp = old->mnt_mp; ns = old->mnt_ns; err = -EINVAL; /* The mountpoint must be in our namespace. */ if (!check_mnt(p)) goto out; /* The thing moved must be mounted... */ if (!is_mounted(&old->mnt)) goto out; /* ... and either ours or the root of anon namespace */ if (!(attached ? check_mnt(old) : is_anon_ns(ns))) goto out; if (old->mnt.mnt_flags & MNT_LOCKED) goto out; if (old_path->dentry != old_path->mnt->mnt_root) goto out; if (d_is_dir(new_path->dentry) != d_is_dir(old_path->dentry)) goto out; /* * Don't move a mount residing in a shared parent. */ if (attached && IS_MNT_SHARED(parent)) goto out; /* * Don't move a mount tree containing unbindable mounts to a destination * mount which is shared. */ if (IS_MNT_SHARED(p) && tree_contains_unbindable(old)) goto out; err = -ELOOP; if (!check_for_nsfs_mounts(old)) goto out; for (; mnt_has_parent(p); p = p->mnt_parent) if (p == old) goto out; err = attach_recursive_mnt(old, real_mount(new_path->mnt), mp, attached); if (err) goto out; /* if the mount is moved, it should no longer be expire * automatically */ list_del_init(&old->mnt_expire); if (attached) put_mountpoint(old_mp); out: unlock_mount(mp); if (!err) { if (attached) mntput_no_expire(parent); else free_mnt_ns(ns); } return err; } static int do_move_mount_old(struct path *path, const char *old_name) { struct path old_path; int err; if (!old_name || !*old_name) return -EINVAL; err = kern_path(old_name, LOOKUP_FOLLOW, &old_path); if (err) return err; err = do_move_mount(&old_path, path); path_put(&old_path); return err; } /* * add a mount into a namespace's mount tree */ static int do_add_mount(struct mount *newmnt, struct mountpoint *mp, const struct path *path, int mnt_flags) { struct mount *parent = real_mount(path->mnt); mnt_flags &= ~MNT_INTERNAL_FLAGS; if (unlikely(!check_mnt(parent))) { /* that's acceptable only for automounts done in private ns */ if (!(mnt_flags & MNT_SHRINKABLE)) return -EINVAL; /* ... and for those we'd better have mountpoint still alive */ if (!parent->mnt_ns) return -EINVAL; } /* Refuse the same filesystem on the same mount point */ if (path->mnt->mnt_sb == newmnt->mnt.mnt_sb && path->mnt->mnt_root == path->dentry) return -EBUSY; if (d_is_symlink(newmnt->mnt.mnt_root)) return -EINVAL; newmnt->mnt.mnt_flags = mnt_flags; return graft_tree(newmnt, parent, mp); } static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags); /* * Create a new mount using a superblock configuration and request it * be added to the namespace tree. */ static int do_new_mount_fc(struct fs_context *fc, struct path *mountpoint, unsigned int mnt_flags) { struct vfsmount *mnt; struct mountpoint *mp; struct super_block *sb = fc->root->d_sb; int error; error = security_sb_kern_mount(sb); if (!error && mount_too_revealing(sb, &mnt_flags)) error = -EPERM; if (unlikely(error)) { fc_drop_locked(fc); return error; } up_write(&sb->s_umount); mnt = vfs_create_mount(fc); if (IS_ERR(mnt)) return PTR_ERR(mnt); mnt_warn_timestamp_expiry(mountpoint, mnt); mp = lock_mount(mountpoint); if (IS_ERR(mp)) { mntput(mnt); return PTR_ERR(mp); } error = do_add_mount(real_mount(mnt), mp, mountpoint, mnt_flags); unlock_mount(mp); if (error < 0) mntput(mnt); return error; } /* * create a new mount for userspace and request it to be added into the * namespace's tree */ static int do_new_mount(struct path *path, const char *fstype, int sb_flags, int mnt_flags, const char *name, void *data) { struct file_system_type *type; struct fs_context *fc; const char *subtype = NULL; int err = 0; if (!fstype) return -EINVAL; type = get_fs_type(fstype); if (!type) return -ENODEV; if (type->fs_flags & FS_HAS_SUBTYPE) { subtype = strchr(fstype, '.'); if (subtype) { subtype++; if (!*subtype) { put_filesystem(type); return -EINVAL; } } } fc = fs_context_for_mount(type, sb_flags); put_filesystem(type); if (IS_ERR(fc)) return PTR_ERR(fc); /* * Indicate to the filesystem that the mount request is coming * from the legacy mount system call. */ fc->oldapi = true; if (subtype) err = vfs_parse_fs_string(fc, "subtype", subtype, strlen(subtype)); if (!err && name) err = vfs_parse_fs_string(fc, "source", name, strlen(name)); if (!err) err = parse_monolithic_mount_data(fc, data); if (!err && !mount_capable(fc)) err = -EPERM; if (!err) err = vfs_get_tree(fc); if (!err) err = do_new_mount_fc(fc, path, mnt_flags); put_fs_context(fc); return err; } int finish_automount(struct vfsmount *m, const struct path *path) { struct dentry *dentry = path->dentry; struct mountpoint *mp; struct mount *mnt; int err; if (!m) return 0; if (IS_ERR(m)) return PTR_ERR(m); mnt = real_mount(m); /* The new mount record should have at least 2 refs to prevent it being * expired before we get a chance to add it */ BUG_ON(mnt_get_count(mnt) < 2); if (m->mnt_sb == path->mnt->mnt_sb && m->mnt_root == dentry) { err = -ELOOP; goto discard; } /* * we don't want to use lock_mount() - in this case finding something * that overmounts our mountpoint to be means "quitely drop what we've * got", not "try to mount it on top". */ inode_lock(dentry->d_inode); namespace_lock(); if (unlikely(cant_mount(dentry))) { err = -ENOENT; goto discard_locked; } rcu_read_lock(); if (unlikely(__lookup_mnt(path->mnt, dentry))) { rcu_read_unlock(); err = 0; goto discard_locked; } rcu_read_unlock(); mp = get_mountpoint(dentry); if (IS_ERR(mp)) { err = PTR_ERR(mp); goto discard_locked; } err = do_add_mount(mnt, mp, path, path->mnt->mnt_flags | MNT_SHRINKABLE); unlock_mount(mp); if (unlikely(err)) goto discard; mntput(m); return 0; discard_locked: namespace_unlock(); inode_unlock(dentry->d_inode); discard: /* remove m from any expiration list it may be on */ if (!list_empty(&mnt->mnt_expire)) { namespace_lock(); list_del_init(&mnt->mnt_expire); namespace_unlock(); } mntput(m); mntput(m); return err; } /** * mnt_set_expiry - Put a mount on an expiration list * @mnt: The mount to list. * @expiry_list: The list to add the mount to. */ void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list) { namespace_lock(); list_add_tail(&real_mount(mnt)->mnt_expire, expiry_list); namespace_unlock(); } EXPORT_SYMBOL(mnt_set_expiry); /* * process a list of expirable mountpoints with the intent of discarding any * mountpoints that aren't in use and haven't been touched since last we came * here */ void mark_mounts_for_expiry(struct list_head *mounts) { struct mount *mnt, *next; LIST_HEAD(graveyard); if (list_empty(mounts)) return; namespace_lock(); lock_mount_hash(); /* extract from the expiration list every vfsmount that matches the * following criteria: * - only referenced by its parent vfsmount * - still marked for expiry (marked on the last call here; marks are * cleared by mntput()) */ list_for_each_entry_safe(mnt, next, mounts, mnt_expire) { if (!xchg(&mnt->mnt_expiry_mark, 1) || propagate_mount_busy(mnt, 1)) continue; list_move(&mnt->mnt_expire, &graveyard); } while (!list_empty(&graveyard)) { mnt = list_first_entry(&graveyard, struct mount, mnt_expire); touch_mnt_namespace(mnt->mnt_ns); umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); } unlock_mount_hash(); namespace_unlock(); } EXPORT_SYMBOL_GPL(mark_mounts_for_expiry); /* * Ripoff of 'select_parent()' * * search the list of submounts for a given mountpoint, and move any * shrinkable submounts to the 'graveyard' list. */ static int select_submounts(struct mount *parent, struct list_head *graveyard) { struct mount *this_parent = parent; struct list_head *next; int found = 0; repeat: next = this_parent->mnt_mounts.next; resume: while (next != &this_parent->mnt_mounts) { struct list_head *tmp = next; struct mount *mnt = list_entry(tmp, struct mount, mnt_child); next = tmp->next; if (!(mnt->mnt.mnt_flags & MNT_SHRINKABLE)) continue; /* * Descend a level if the d_mounts list is non-empty. */ if (!list_empty(&mnt->mnt_mounts)) { this_parent = mnt; goto repeat; } if (!propagate_mount_busy(mnt, 1)) { list_move_tail(&mnt->mnt_expire, graveyard); found++; } } /* * All done at this level ... ascend and resume the search */ if (this_parent != parent) { next = this_parent->mnt_child.next; this_parent = this_parent->mnt_parent; goto resume; } return found; } /* * process a list of expirable mountpoints with the intent of discarding any * submounts of a specific parent mountpoint * * mount_lock must be held for write */ static void shrink_submounts(struct mount *mnt) { LIST_HEAD(graveyard); struct mount *m; /* extract submounts of 'mountpoint' from the expiration list */ while (select_submounts(mnt, &graveyard)) { while (!list_empty(&graveyard)) { m = list_first_entry(&graveyard, struct mount, mnt_expire); touch_mnt_namespace(m->mnt_ns); umount_tree(m, UMOUNT_PROPAGATE|UMOUNT_SYNC); } } } static void *copy_mount_options(const void __user * data) { char *copy; unsigned left, offset; if (!data) return NULL; copy = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!copy) return ERR_PTR(-ENOMEM); left = copy_from_user(copy, data, PAGE_SIZE); /* * Not all architectures have an exact copy_from_user(). Resort to * byte at a time. */ offset = PAGE_SIZE - left; while (left) { char c; if (get_user(c, (const char __user *)data + offset)) break; copy[offset] = c; left--; offset++; } if (left == PAGE_SIZE) { kfree(copy); return ERR_PTR(-EFAULT); } return copy; } static char *copy_mount_string(const void __user *data) { return data ? strndup_user(data, PATH_MAX) : NULL; } /* * Flags is a 32-bit value that allows up to 31 non-fs dependent flags to * be given to the mount() call (ie: read-only, no-dev, no-suid etc). * * data is a (void *) that can point to any structure up to * PAGE_SIZE-1 bytes, which can contain arbitrary fs-dependent * information (or be NULL). * * Pre-0.97 versions of mount() didn't have a flags word. * When the flags word was introduced its top half was required * to have the magic value 0xC0ED, and this remained so until 2.4.0-test9. * Therefore, if this magic number is present, it carries no information * and must be discarded. */ int path_mount(const char *dev_name, struct path *path, const char *type_page, unsigned long flags, void *data_page) { unsigned int mnt_flags = 0, sb_flags; int ret; /* Discard magic */ if ((flags & MS_MGC_MSK) == MS_MGC_VAL) flags &= ~MS_MGC_MSK; /* Basic sanity checks */ if (data_page) ((char *)data_page)[PAGE_SIZE - 1] = 0; if (flags & MS_NOUSER) return -EINVAL; ret = security_sb_mount(dev_name, path, type_page, flags, data_page); if (ret) return ret; if (!may_mount()) return -EPERM; if (flags & SB_MANDLOCK) warn_mandlock(); /* Default to relatime unless overriden */ if (!(flags & MS_NOATIME)) mnt_flags |= MNT_RELATIME; /* Separate the per-mountpoint flags */ if (flags & MS_NOSUID) mnt_flags |= MNT_NOSUID; if (flags & MS_NODEV) mnt_flags |= MNT_NODEV; if (flags & MS_NOEXEC) mnt_flags |= MNT_NOEXEC; if (flags & MS_NOATIME) mnt_flags |= MNT_NOATIME; if (flags & MS_NODIRATIME) mnt_flags |= MNT_NODIRATIME; if (flags & MS_STRICTATIME) mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME); if (flags & MS_RDONLY) mnt_flags |= MNT_READONLY; if (flags & MS_NOSYMFOLLOW) mnt_flags |= MNT_NOSYMFOLLOW; /* The default atime for remount is preservation */ if ((flags & MS_REMOUNT) && ((flags & (MS_NOATIME | MS_NODIRATIME | MS_RELATIME | MS_STRICTATIME)) == 0)) { mnt_flags &= ~MNT_ATIME_MASK; mnt_flags |= path->mnt->mnt_flags & MNT_ATIME_MASK; } sb_flags = flags & (SB_RDONLY | SB_SYNCHRONOUS | SB_MANDLOCK | SB_DIRSYNC | SB_SILENT | SB_POSIXACL | SB_LAZYTIME | SB_I_VERSION); if ((flags & (MS_REMOUNT | MS_BIND)) == (MS_REMOUNT | MS_BIND)) return do_reconfigure_mnt(path, mnt_flags); if (flags & MS_REMOUNT) return do_remount(path, flags, sb_flags, mnt_flags, data_page); if (flags & MS_BIND) return do_loopback(path, dev_name, flags & MS_REC); if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) return do_change_type(path, flags); if (flags & MS_MOVE) return do_move_mount_old(path, dev_name); return do_new_mount(path, type_page, sb_flags, mnt_flags, dev_name, data_page); } long do_mount(const char *dev_name, const char __user *dir_name, const char *type_page, unsigned long flags, void *data_page) { struct path path; int ret; ret = user_path_at(AT_FDCWD, dir_name, LOOKUP_FOLLOW, &path); if (ret) return ret; ret = path_mount(dev_name, &path, type_page, flags, data_page); path_put(&path); return ret; } static struct ucounts *inc_mnt_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_MNT_NAMESPACES); } static void dec_mnt_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_MNT_NAMESPACES); } static void free_mnt_ns(struct mnt_namespace *ns) { if (!is_anon_ns(ns)) ns_free_inum(&ns->ns); dec_mnt_namespaces(ns->ucounts); put_user_ns(ns->user_ns); kfree(ns); } /* * Assign a sequence number so we can detect when we attempt to bind * mount a reference to an older mount namespace into the current * mount namespace, preventing reference counting loops. A 64bit * number incrementing at 10Ghz will take 12,427 years to wrap which * is effectively never, so we can ignore the possibility. */ static atomic64_t mnt_ns_seq = ATOMIC64_INIT(1); static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool anon) { struct mnt_namespace *new_ns; struct ucounts *ucounts; int ret; ucounts = inc_mnt_namespaces(user_ns); if (!ucounts) return ERR_PTR(-ENOSPC); new_ns = kzalloc(sizeof(struct mnt_namespace), GFP_KERNEL_ACCOUNT); if (!new_ns) { dec_mnt_namespaces(ucounts); return ERR_PTR(-ENOMEM); } if (!anon) { ret = ns_alloc_inum(&new_ns->ns); if (ret) { kfree(new_ns); dec_mnt_namespaces(ucounts); return ERR_PTR(ret); } } new_ns->ns.ops = &mntns_operations; if (!anon) new_ns->seq = atomic64_add_return(1, &mnt_ns_seq); refcount_set(&new_ns->ns.count, 1); INIT_LIST_HEAD(&new_ns->list); init_waitqueue_head(&new_ns->poll); spin_lock_init(&new_ns->ns_lock); new_ns->user_ns = get_user_ns(user_ns); new_ns->ucounts = ucounts; return new_ns; } __latent_entropy struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns, struct user_namespace *user_ns, struct fs_struct *new_fs) { struct mnt_namespace *new_ns; struct vfsmount *rootmnt = NULL, *pwdmnt = NULL; struct mount *p, *q; struct mount *old; struct mount *new; int copy_flags; BUG_ON(!ns); if (likely(!(flags & CLONE_NEWNS))) { get_mnt_ns(ns); return ns; } old = ns->root; new_ns = alloc_mnt_ns(user_ns, false); if (IS_ERR(new_ns)) return new_ns; namespace_lock(); /* First pass: copy the tree topology */ copy_flags = CL_COPY_UNBINDABLE | CL_EXPIRE; if (user_ns != ns->user_ns) copy_flags |= CL_SHARED_TO_SLAVE; new = copy_tree(old, old->mnt.mnt_root, copy_flags); if (IS_ERR(new)) { namespace_unlock(); free_mnt_ns(new_ns); return ERR_CAST(new); } if (user_ns != ns->user_ns) { lock_mount_hash(); lock_mnt_tree(new); unlock_mount_hash(); } new_ns->root = new; list_add_tail(&new_ns->list, &new->mnt_list); /* * Second pass: switch the tsk->fs->* elements and mark new vfsmounts * as belonging to new namespace. We have already acquired a private * fs_struct, so tsk->fs->lock is not needed. */ p = old; q = new; while (p) { q->mnt_ns = new_ns; new_ns->mounts++; if (new_fs) { if (&p->mnt == new_fs->root.mnt) { new_fs->root.mnt = mntget(&q->mnt); rootmnt = &p->mnt; } if (&p->mnt == new_fs->pwd.mnt) { new_fs->pwd.mnt = mntget(&q->mnt); pwdmnt = &p->mnt; } } p = next_mnt(p, old); q = next_mnt(q, new); if (!q) break; while (p->mnt.mnt_root != q->mnt.mnt_root) p = next_mnt(p, old); } namespace_unlock(); if (rootmnt) mntput(rootmnt); if (pwdmnt) mntput(pwdmnt); return new_ns; } struct dentry *mount_subtree(struct vfsmount *m, const char *name) { struct mount *mnt = real_mount(m); struct mnt_namespace *ns; struct super_block *s; struct path path; int err; ns = alloc_mnt_ns(&init_user_ns, true); if (IS_ERR(ns)) { mntput(m); return ERR_CAST(ns); } mnt->mnt_ns = ns; ns->root = mnt; ns->mounts++; list_add(&mnt->mnt_list, &ns->list); err = vfs_path_lookup(m->mnt_root, m, name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path); put_mnt_ns(ns); if (err) return ERR_PTR(err); /* trade a vfsmount reference for active sb one */ s = path.mnt->mnt_sb; atomic_inc(&s->s_active); mntput(path.mnt); /* lock the sucker */ down_write(&s->s_umount); /* ... and return the root of (sub)tree on it */ return path.dentry; } EXPORT_SYMBOL(mount_subtree); SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, char __user *, type, unsigned long, flags, void __user *, data) { int ret; char *kernel_type; char *kernel_dev; void *options; kernel_type = copy_mount_string(type); ret = PTR_ERR(kernel_type); if (IS_ERR(kernel_type)) goto out_type; kernel_dev = copy_mount_string(dev_name); ret = PTR_ERR(kernel_dev); if (IS_ERR(kernel_dev)) goto out_dev; options = copy_mount_options(data); ret = PTR_ERR(options); if (IS_ERR(options)) goto out_data; ret = do_mount(kernel_dev, dir_name, kernel_type, flags, options); kfree(options); out_data: kfree(kernel_dev); out_dev: kfree(kernel_type); out_type: return ret; } #define FSMOUNT_VALID_FLAGS \ (MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID | MOUNT_ATTR_NODEV | \ MOUNT_ATTR_NOEXEC | MOUNT_ATTR__ATIME | MOUNT_ATTR_NODIRATIME | \ MOUNT_ATTR_NOSYMFOLLOW) #define MOUNT_SETATTR_VALID_FLAGS (FSMOUNT_VALID_FLAGS | MOUNT_ATTR_IDMAP) #define MOUNT_SETATTR_PROPAGATION_FLAGS \ (MS_UNBINDABLE | MS_PRIVATE | MS_SLAVE | MS_SHARED) static unsigned int attr_flags_to_mnt_flags(u64 attr_flags) { unsigned int mnt_flags = 0; if (attr_flags & MOUNT_ATTR_RDONLY) mnt_flags |= MNT_READONLY; if (attr_flags & MOUNT_ATTR_NOSUID) mnt_flags |= MNT_NOSUID; if (attr_flags & MOUNT_ATTR_NODEV) mnt_flags |= MNT_NODEV; if (attr_flags & MOUNT_ATTR_NOEXEC) mnt_flags |= MNT_NOEXEC; if (attr_flags & MOUNT_ATTR_NODIRATIME) mnt_flags |= MNT_NODIRATIME; if (attr_flags & MOUNT_ATTR_NOSYMFOLLOW) mnt_flags |= MNT_NOSYMFOLLOW; return mnt_flags; } /* * Create a kernel mount representation for a new, prepared superblock * (specified by fs_fd) and attach to an open_tree-like file descriptor. */ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags, unsigned int, attr_flags) { struct mnt_namespace *ns; struct fs_context *fc; struct file *file; struct path newmount; struct mount *mnt; struct fd f; unsigned int mnt_flags = 0; long ret; if (!may_mount()) return -EPERM; if ((flags & ~(FSMOUNT_CLOEXEC)) != 0) return -EINVAL; if (attr_flags & ~FSMOUNT_VALID_FLAGS) return -EINVAL; mnt_flags = attr_flags_to_mnt_flags(attr_flags); switch (attr_flags & MOUNT_ATTR__ATIME) { case MOUNT_ATTR_STRICTATIME: break; case MOUNT_ATTR_NOATIME: mnt_flags |= MNT_NOATIME; break; case MOUNT_ATTR_RELATIME: mnt_flags |= MNT_RELATIME; break; default: return -EINVAL; } f = fdget(fs_fd); if (!f.file) return -EBADF; ret = -EINVAL; if (f.file->f_op != &fscontext_fops) goto err_fsfd; fc = f.file->private_data; ret = mutex_lock_interruptible(&fc->uapi_mutex); if (ret < 0) goto err_fsfd; /* There must be a valid superblock or we can't mount it */ ret = -EINVAL; if (!fc->root) goto err_unlock; ret = -EPERM; if (mount_too_revealing(fc->root->d_sb, &mnt_flags)) { pr_warn("VFS: Mount too revealing\n"); goto err_unlock; } ret = -EBUSY; if (fc->phase != FS_CONTEXT_AWAITING_MOUNT) goto err_unlock; if (fc->sb_flags & SB_MANDLOCK) warn_mandlock(); newmount.mnt = vfs_create_mount(fc); if (IS_ERR(newmount.mnt)) { ret = PTR_ERR(newmount.mnt); goto err_unlock; } newmount.dentry = dget(fc->root); newmount.mnt->mnt_flags = mnt_flags; /* We've done the mount bit - now move the file context into more or * less the same state as if we'd done an fspick(). We don't want to * do any memory allocation or anything like that at this point as we * don't want to have to handle any errors incurred. */ vfs_clean_context(fc); ns = alloc_mnt_ns(current->nsproxy->mnt_ns->user_ns, true); if (IS_ERR(ns)) { ret = PTR_ERR(ns); goto err_path; } mnt = real_mount(newmount.mnt); mnt->mnt_ns = ns; ns->root = mnt; ns->mounts = 1; list_add(&mnt->mnt_list, &ns->list); mntget(newmount.mnt); /* Attach to an apparent O_PATH fd with a note that we need to unmount * it, not just simply put it. */ file = dentry_open(&newmount, O_PATH, fc->cred); if (IS_ERR(file)) { dissolve_on_fput(newmount.mnt); ret = PTR_ERR(file); goto err_path; } file->f_mode |= FMODE_NEED_UNMOUNT; ret = get_unused_fd_flags((flags & FSMOUNT_CLOEXEC) ? O_CLOEXEC : 0); if (ret >= 0) fd_install(ret, file); else fput(file); err_path: path_put(&newmount); err_unlock: mutex_unlock(&fc->uapi_mutex); err_fsfd: fdput(f); return ret; } /* * Move a mount from one place to another. In combination with * fsopen()/fsmount() this is used to install a new mount and in combination * with open_tree(OPEN_TREE_CLONE [| AT_RECURSIVE]) it can be used to copy * a mount subtree. * * Note the flags value is a combination of MOVE_MOUNT_* flags. */ SYSCALL_DEFINE5(move_mount, int, from_dfd, const char __user *, from_pathname, int, to_dfd, const char __user *, to_pathname, unsigned int, flags) { struct path from_path, to_path; unsigned int lflags; int ret = 0; if (!may_mount()) return -EPERM; if (flags & ~MOVE_MOUNT__MASK) return -EINVAL; /* If someone gives a pathname, they aren't permitted to move * from an fd that requires unmount as we can't get at the flag * to clear it afterwards. */ lflags = 0; if (flags & MOVE_MOUNT_F_SYMLINKS) lflags |= LOOKUP_FOLLOW; if (flags & MOVE_MOUNT_F_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; if (flags & MOVE_MOUNT_F_EMPTY_PATH) lflags |= LOOKUP_EMPTY; ret = user_path_at(from_dfd, from_pathname, lflags, &from_path); if (ret < 0) return ret; lflags = 0; if (flags & MOVE_MOUNT_T_SYMLINKS) lflags |= LOOKUP_FOLLOW; if (flags & MOVE_MOUNT_T_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; if (flags & MOVE_MOUNT_T_EMPTY_PATH) lflags |= LOOKUP_EMPTY; ret = user_path_at(to_dfd, to_pathname, lflags, &to_path); if (ret < 0) goto out_from; ret = security_move_mount(&from_path, &to_path); if (ret < 0) goto out_to; if (flags & MOVE_MOUNT_SET_GROUP) ret = do_set_group(&from_path, &to_path); else ret = do_move_mount(&from_path, &to_path); out_to: path_put(&to_path); out_from: path_put(&from_path); return ret; } /* * Return true if path is reachable from root * * namespace_sem or mount_lock is held */ bool is_path_reachable(struct mount *mnt, struct dentry *dentry, const struct path *root) { while (&mnt->mnt != root->mnt && mnt_has_parent(mnt)) { dentry = mnt->mnt_mountpoint; mnt = mnt->mnt_parent; } return &mnt->mnt == root->mnt && is_subdir(dentry, root->dentry); } bool path_is_under(const struct path *path1, const struct path *path2) { bool res; read_seqlock_excl(&mount_lock); res = is_path_reachable(real_mount(path1->mnt), path1->dentry, path2); read_sequnlock_excl(&mount_lock); return res; } EXPORT_SYMBOL(path_is_under); /* * pivot_root Semantics: * Moves the root file system of the current process to the directory put_old, * makes new_root as the new root file system of the current process, and sets * root/cwd of all processes which had them on the current root to new_root. * * Restrictions: * The new_root and put_old must be directories, and must not be on the * same file system as the current process root. The put_old must be * underneath new_root, i.e. adding a non-zero number of /.. to the string * pointed to by put_old must yield the same directory as new_root. No other * file system may be mounted on put_old. After all, new_root is a mountpoint. * * Also, the current root cannot be on the 'rootfs' (initial ramfs) filesystem. * See Documentation/filesystems/ramfs-rootfs-initramfs.rst for alternatives * in this situation. * * Notes: * - we don't move root/cwd if they are not at the root (reason: if something * cared enough to change them, it's probably wrong to force them elsewhere) * - it's okay to pick a root that isn't the root of a file system, e.g. * /nfs/my_root where /nfs is the mount point. It must be a mountpoint, * though, so you may need to say mount --bind /nfs/my_root /nfs/my_root * first. */ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, const char __user *, put_old) { struct path new, old, root; struct mount *new_mnt, *root_mnt, *old_mnt, *root_parent, *ex_parent; struct mountpoint *old_mp, *root_mp; int error; if (!may_mount()) return -EPERM; error = user_path_at(AT_FDCWD, new_root, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &new); if (error) goto out0; error = user_path_at(AT_FDCWD, put_old, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &old); if (error) goto out1; error = security_sb_pivotroot(&old, &new); if (error) goto out2; get_fs_root(current->fs, &root); old_mp = lock_mount(&old); error = PTR_ERR(old_mp); if (IS_ERR(old_mp)) goto out3; error = -EINVAL; new_mnt = real_mount(new.mnt); root_mnt = real_mount(root.mnt); old_mnt = real_mount(old.mnt); ex_parent = new_mnt->mnt_parent; root_parent = root_mnt->mnt_parent; if (IS_MNT_SHARED(old_mnt) || IS_MNT_SHARED(ex_parent) || IS_MNT_SHARED(root_parent)) goto out4; if (!check_mnt(root_mnt) || !check_mnt(new_mnt)) goto out4; if (new_mnt->mnt.mnt_flags & MNT_LOCKED) goto out4; error = -ENOENT; if (d_unlinked(new.dentry)) goto out4; error = -EBUSY; if (new_mnt == root_mnt || old_mnt == root_mnt) goto out4; /* loop, on the same file system */ error = -EINVAL; if (root.mnt->mnt_root != root.dentry) goto out4; /* not a mountpoint */ if (!mnt_has_parent(root_mnt)) goto out4; /* not attached */ if (new.mnt->mnt_root != new.dentry) goto out4; /* not a mountpoint */ if (!mnt_has_parent(new_mnt)) goto out4; /* not attached */ /* make sure we can reach put_old from new_root */ if (!is_path_reachable(old_mnt, old.dentry, &new)) goto out4; /* make certain new is below the root */ if (!is_path_reachable(new_mnt, new.dentry, &root)) goto out4; lock_mount_hash(); umount_mnt(new_mnt); root_mp = unhash_mnt(root_mnt); /* we'll need its mountpoint */ if (root_mnt->mnt.mnt_flags & MNT_LOCKED) { new_mnt->mnt.mnt_flags |= MNT_LOCKED; root_mnt->mnt.mnt_flags &= ~MNT_LOCKED; } /* mount old root on put_old */ attach_mnt(root_mnt, old_mnt, old_mp); /* mount new_root on / */ attach_mnt(new_mnt, root_parent, root_mp); mnt_add_count(root_parent, -1); touch_mnt_namespace(current->nsproxy->mnt_ns); /* A moved mount should not expire automatically */ list_del_init(&new_mnt->mnt_expire); put_mountpoint(root_mp); unlock_mount_hash(); chroot_fs_refs(&root, &new); error = 0; out4: unlock_mount(old_mp); if (!error) mntput_no_expire(ex_parent); out3: path_put(&root); out2: path_put(&old); out1: path_put(&new); out0: return error; } static unsigned int recalc_flags(struct mount_kattr *kattr, struct mount *mnt) { unsigned int flags = mnt->mnt.mnt_flags; /* flags to clear */ flags &= ~kattr->attr_clr; /* flags to raise */ flags |= kattr->attr_set; return flags; } static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) { struct vfsmount *m = &mnt->mnt; struct user_namespace *fs_userns = m->mnt_sb->s_user_ns; if (!kattr->mnt_userns) return 0; /* * Creating an idmapped mount with the filesystem wide idmapping * doesn't make sense so block that. We don't allow mushy semantics. */ if (kattr->mnt_userns == fs_userns) return -EINVAL; /* * Once a mount has been idmapped we don't allow it to change its * mapping. It makes things simpler and callers can just create * another bind-mount they can idmap if they want to. */ if (is_idmapped_mnt(m)) return -EPERM; /* The underlying filesystem doesn't support idmapped mounts yet. */ if (!(m->mnt_sb->s_type->fs_flags & FS_ALLOW_IDMAP)) return -EINVAL; /* We're not controlling the superblock. */ if (!ns_capable(fs_userns, CAP_SYS_ADMIN)) return -EPERM; /* Mount has already been visible in the filesystem hierarchy. */ if (!is_anon_ns(mnt->mnt_ns)) return -EINVAL; return 0; } /** * mnt_allow_writers() - check whether the attribute change allows writers * @kattr: the new mount attributes * @mnt: the mount to which @kattr will be applied * * Check whether thew new mount attributes in @kattr allow concurrent writers. * * Return: true if writers need to be held, false if not */ static inline bool mnt_allow_writers(const struct mount_kattr *kattr, const struct mount *mnt) { return (!(kattr->attr_set & MNT_READONLY) || (mnt->mnt.mnt_flags & MNT_READONLY)) && !kattr->mnt_userns; } static int mount_setattr_prepare(struct mount_kattr *kattr, struct mount *mnt) { struct mount *m; int err; for (m = mnt; m; m = next_mnt(m, mnt)) { if (!can_change_locked_flags(m, recalc_flags(kattr, m))) { err = -EPERM; break; } err = can_idmap_mount(kattr, m); if (err) break; if (!mnt_allow_writers(kattr, m)) { err = mnt_hold_writers(m); if (err) break; } if (!kattr->recurse) return 0; } if (err) { struct mount *p; /* * If we had to call mnt_hold_writers() MNT_WRITE_HOLD will * be set in @mnt_flags. The loop unsets MNT_WRITE_HOLD for all * mounts and needs to take care to include the first mount. */ for (p = mnt; p; p = next_mnt(p, mnt)) { /* If we had to hold writers unblock them. */ if (p->mnt.mnt_flags & MNT_WRITE_HOLD) mnt_unhold_writers(p); /* * We're done once the first mount we changed got * MNT_WRITE_HOLD unset. */ if (p == m) break; } } return err; } static void do_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) { struct user_namespace *mnt_userns, *old_mnt_userns; if (!kattr->mnt_userns) return; /* * We're the only ones able to change the mount's idmapping. So * mnt->mnt.mnt_userns is stable and we can retrieve it directly. */ old_mnt_userns = mnt->mnt.mnt_userns; mnt_userns = get_user_ns(kattr->mnt_userns); /* Pairs with smp_load_acquire() in mnt_user_ns(). */ smp_store_release(&mnt->mnt.mnt_userns, mnt_userns); /* * If this is an idmapped filesystem drop the reference we've taken * in vfs_create_mount() before. */ if (!initial_idmapping(old_mnt_userns)) put_user_ns(old_mnt_userns); } static void mount_setattr_commit(struct mount_kattr *kattr, struct mount *mnt) { struct mount *m; for (m = mnt; m; m = next_mnt(m, mnt)) { unsigned int flags; do_idmap_mount(kattr, m); flags = recalc_flags(kattr, m); WRITE_ONCE(m->mnt.mnt_flags, flags); /* If we had to hold writers unblock them. */ if (m->mnt.mnt_flags & MNT_WRITE_HOLD) mnt_unhold_writers(m); if (kattr->propagation) change_mnt_propagation(m, kattr->propagation); if (!kattr->recurse) break; } touch_mnt_namespace(mnt->mnt_ns); } static int do_mount_setattr(struct path *path, struct mount_kattr *kattr) { struct mount *mnt = real_mount(path->mnt); int err = 0; if (path->dentry != mnt->mnt.mnt_root) return -EINVAL; if (kattr->propagation) { /* * Only take namespace_lock() if we're actually changing * propagation. */ namespace_lock(); if (kattr->propagation == MS_SHARED) { err = invent_group_ids(mnt, kattr->recurse); if (err) { namespace_unlock(); return err; } } } err = -EINVAL; lock_mount_hash(); /* Ensure that this isn't anything purely vfs internal. */ if (!is_mounted(&mnt->mnt)) goto out; /* * If this is an attached mount make sure it's located in the callers * mount namespace. If it's not don't let the caller interact with it. * * If this mount doesn't have a parent it's most often simply a * detached mount with an anonymous mount namespace. IOW, something * that's simply not attached yet. But there are apparently also users * that do change mount properties on the rootfs itself. That obviously * neither has a parent nor is it a detached mount so we cannot * unconditionally check for detached mounts. */ if ((mnt_has_parent(mnt) || !is_anon_ns(mnt->mnt_ns)) && !check_mnt(mnt)) goto out; /* * First, we get the mount tree in a shape where we can change mount * properties without failure. If we succeeded to do so we commit all * changes and if we failed we clean up. */ err = mount_setattr_prepare(kattr, mnt); if (!err) mount_setattr_commit(kattr, mnt); out: unlock_mount_hash(); if (kattr->propagation) { if (err) cleanup_group_ids(mnt, NULL); namespace_unlock(); } return err; } static int build_mount_idmapped(const struct mount_attr *attr, size_t usize, struct mount_kattr *kattr, unsigned int flags) { int err = 0; struct ns_common *ns; struct user_namespace *mnt_userns; struct file *file; if (!((attr->attr_set | attr->attr_clr) & MOUNT_ATTR_IDMAP)) return 0; /* * We currently do not support clearing an idmapped mount. If this ever * is a use-case we can revisit this but for now let's keep it simple * and not allow it. */ if (attr->attr_clr & MOUNT_ATTR_IDMAP) return -EINVAL; if (attr->userns_fd > INT_MAX) return -EINVAL; file = fget(attr->userns_fd); if (!file) return -EBADF; if (!proc_ns_file(file)) { err = -EINVAL; goto out_fput; } ns = get_proc_ns(file_inode(file)); if (ns->ops->type != CLONE_NEWUSER) { err = -EINVAL; goto out_fput; } /* * The initial idmapping cannot be used to create an idmapped * mount. We use the initial idmapping as an indicator of a mount * that is not idmapped. It can simply be passed into helpers that * are aware of idmapped mounts as a convenient shortcut. A user * can just create a dedicated identity mapping to achieve the same * result. */ mnt_userns = container_of(ns, struct user_namespace, ns); if (initial_idmapping(mnt_userns)) { err = -EPERM; goto out_fput; } /* We're not controlling the target namespace. */ if (!ns_capable(mnt_userns, CAP_SYS_ADMIN)) { err = -EPERM; goto out_fput; } kattr->mnt_userns = get_user_ns(mnt_userns); out_fput: fput(file); return err; } static int build_mount_kattr(const struct mount_attr *attr, size_t usize, struct mount_kattr *kattr, unsigned int flags) { unsigned int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW; if (flags & AT_NO_AUTOMOUNT) lookup_flags &= ~LOOKUP_AUTOMOUNT; if (flags & AT_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; *kattr = (struct mount_kattr) { .lookup_flags = lookup_flags, .recurse = !!(flags & AT_RECURSIVE), }; if (attr->propagation & ~MOUNT_SETATTR_PROPAGATION_FLAGS) return -EINVAL; if (hweight32(attr->propagation & MOUNT_SETATTR_PROPAGATION_FLAGS) > 1) return -EINVAL; kattr->propagation = attr->propagation; if ((attr->attr_set | attr->attr_clr) & ~MOUNT_SETATTR_VALID_FLAGS) return -EINVAL; kattr->attr_set = attr_flags_to_mnt_flags(attr->attr_set); kattr->attr_clr = attr_flags_to_mnt_flags(attr->attr_clr); /* * Since the MOUNT_ATTR_<atime> values are an enum, not a bitmap, * users wanting to transition to a different atime setting cannot * simply specify the atime setting in @attr_set, but must also * specify MOUNT_ATTR__ATIME in the @attr_clr field. * So ensure that MOUNT_ATTR__ATIME can't be partially set in * @attr_clr and that @attr_set can't have any atime bits set if * MOUNT_ATTR__ATIME isn't set in @attr_clr. */ if (attr->attr_clr & MOUNT_ATTR__ATIME) { if ((attr->attr_clr & MOUNT_ATTR__ATIME) != MOUNT_ATTR__ATIME) return -EINVAL; /* * Clear all previous time settings as they are mutually * exclusive. */ kattr->attr_clr |= MNT_RELATIME | MNT_NOATIME; switch (attr->attr_set & MOUNT_ATTR__ATIME) { case MOUNT_ATTR_RELATIME: kattr->attr_set |= MNT_RELATIME; break; case MOUNT_ATTR_NOATIME: kattr->attr_set |= MNT_NOATIME; break; case MOUNT_ATTR_STRICTATIME: break; default: return -EINVAL; } } else { if (attr->attr_set & MOUNT_ATTR__ATIME) return -EINVAL; } return build_mount_idmapped(attr, usize, kattr, flags); } static void finish_mount_kattr(struct mount_kattr *kattr) { put_user_ns(kattr->mnt_userns); kattr->mnt_userns = NULL; } SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path, unsigned int, flags, struct mount_attr __user *, uattr, size_t, usize) { int err; struct path target; struct mount_attr attr; struct mount_kattr kattr; BUILD_BUG_ON(sizeof(struct mount_attr) != MOUNT_ATTR_SIZE_VER0); if (flags & ~(AT_EMPTY_PATH | AT_RECURSIVE | AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT)) return -EINVAL; if (unlikely(usize > PAGE_SIZE)) return -E2BIG; if (unlikely(usize < MOUNT_ATTR_SIZE_VER0)) return -EINVAL; if (!may_mount()) return -EPERM; err = copy_struct_from_user(&attr, sizeof(attr), uattr, usize); if (err) return err; /* Don't bother walking through the mounts if this is a nop. */ if (attr.attr_set == 0 && attr.attr_clr == 0 && attr.propagation == 0) return 0; err = build_mount_kattr(&attr, usize, &kattr, flags); if (err) return err; err = user_path_at(dfd, path, kattr.lookup_flags, &target); if (!err) { err = do_mount_setattr(&target, &kattr); path_put(&target); } finish_mount_kattr(&kattr); return err; } static void __init init_mount_tree(void) { struct vfsmount *mnt; struct mount *m; struct mnt_namespace *ns; struct path root; mnt = vfs_kern_mount(&rootfs_fs_type, 0, "rootfs", NULL); if (IS_ERR(mnt)) panic("Can't create rootfs"); ns = alloc_mnt_ns(&init_user_ns, false); if (IS_ERR(ns)) panic("Can't allocate initial namespace"); m = real_mount(mnt); m->mnt_ns = ns; ns->root = m; ns->mounts = 1; list_add(&m->mnt_list, &ns->list); init_task.nsproxy->mnt_ns = ns; get_mnt_ns(ns); root.mnt = mnt; root.dentry = mnt->mnt_root; mnt->mnt_flags |= MNT_LOCKED; set_fs_pwd(current->fs, &root); set_fs_root(current->fs, &root); } void __init mnt_init(void) { int err; mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); mount_hashtable = alloc_large_system_hash("Mount-cache", sizeof(struct hlist_head), mhash_entries, 19, HASH_ZERO, &m_hash_shift, &m_hash_mask, 0, 0); mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache", sizeof(struct hlist_head), mphash_entries, 19, HASH_ZERO, &mp_hash_shift, &mp_hash_mask, 0, 0); if (!mount_hashtable || !mountpoint_hashtable) panic("Failed to allocate mount hash table\n"); kernfs_init(); err = sysfs_init(); if (err) printk(KERN_WARNING "%s: sysfs_init error: %d\n", __func__, err); fs_kobj = kobject_create_and_add("fs", NULL); if (!fs_kobj) printk(KERN_WARNING "%s: kobj create error\n", __func__); shmem_init(); init_rootfs(); init_mount_tree(); } void put_mnt_ns(struct mnt_namespace *ns) { if (!refcount_dec_and_test(&ns->ns.count)) return; drop_collected_mounts(&ns->root->mnt); free_mnt_ns(ns); } struct vfsmount *kern_mount(struct file_system_type *type) { struct vfsmount *mnt; mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL); if (!IS_ERR(mnt)) { /* * it is a longterm mount, don't release mnt until * we unmount before file sys is unregistered */ real_mount(mnt)->mnt_ns = MNT_NS_INTERNAL; } return mnt; } EXPORT_SYMBOL_GPL(kern_mount); void kern_unmount(struct vfsmount *mnt) { /* release long term mount so mount point can be released */ if (!IS_ERR_OR_NULL(mnt)) { real_mount(mnt)->mnt_ns = NULL; synchronize_rcu(); /* yecchhh... */ mntput(mnt); } } EXPORT_SYMBOL(kern_unmount); void kern_unmount_array(struct vfsmount *mnt[], unsigned int num) { unsigned int i; for (i = 0; i < num; i++) if (mnt[i]) real_mount(mnt[i])->mnt_ns = NULL; synchronize_rcu_expedited(); for (i = 0; i < num; i++) mntput(mnt[i]); } EXPORT_SYMBOL(kern_unmount_array); bool our_mnt(struct vfsmount *mnt) { return check_mnt(real_mount(mnt)); } bool current_chrooted(void) { /* Does the current process have a non-standard root */ struct path ns_root; struct path fs_root; bool chrooted; /* Find the namespace root */ ns_root.mnt = ¤t->nsproxy->mnt_ns->root->mnt; ns_root.dentry = ns_root.mnt->mnt_root; path_get(&ns_root); while (d_mountpoint(ns_root.dentry) && follow_down_one(&ns_root)) ; get_fs_root(current->fs, &fs_root); chrooted = !path_equal(&fs_root, &ns_root); path_put(&fs_root); path_put(&ns_root); return chrooted; } static bool mnt_already_visible(struct mnt_namespace *ns, const struct super_block *sb, int *new_mnt_flags) { int new_flags = *new_mnt_flags; struct mount *mnt; bool visible = false; down_read(&namespace_sem); lock_ns_list(ns); list_for_each_entry(mnt, &ns->list, mnt_list) { struct mount *child; int mnt_flags; if (mnt_is_cursor(mnt)) continue; if (mnt->mnt.mnt_sb->s_type != sb->s_type) continue; /* This mount is not fully visible if it's root directory * is not the root directory of the filesystem. */ if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root) continue; /* A local view of the mount flags */ mnt_flags = mnt->mnt.mnt_flags; /* Don't miss readonly hidden in the superblock flags */ if (sb_rdonly(mnt->mnt.mnt_sb)) mnt_flags |= MNT_LOCK_READONLY; /* Verify the mount flags are equal to or more permissive * than the proposed new mount. */ if ((mnt_flags & MNT_LOCK_READONLY) && !(new_flags & MNT_READONLY)) continue; if ((mnt_flags & MNT_LOCK_ATIME) && ((mnt_flags & MNT_ATIME_MASK) != (new_flags & MNT_ATIME_MASK))) continue; /* This mount is not fully visible if there are any * locked child mounts that cover anything except for * empty directories. */ list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { struct inode *inode = child->mnt_mountpoint->d_inode; /* Only worry about locked mounts */ if (!(child->mnt.mnt_flags & MNT_LOCKED)) continue; /* Is the directory permanetly empty? */ if (!is_empty_dir_inode(inode)) goto next; } /* Preserve the locked attributes */ *new_mnt_flags |= mnt_flags & (MNT_LOCK_READONLY | \ MNT_LOCK_ATIME); visible = true; goto found; next: ; } found: unlock_ns_list(ns); up_read(&namespace_sem); return visible; } static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags) { const unsigned long required_iflags = SB_I_NOEXEC | SB_I_NODEV; struct mnt_namespace *ns = current->nsproxy->mnt_ns; unsigned long s_iflags; if (ns->user_ns == &init_user_ns) return false; /* Can this filesystem be too revealing? */ s_iflags = sb->s_iflags; if (!(s_iflags & SB_I_USERNS_VISIBLE)) return false; if ((s_iflags & required_iflags) != required_iflags) { WARN_ONCE(1, "Expected s_iflags to contain 0x%lx\n", required_iflags); return true; } return !mnt_already_visible(ns, sb, new_mnt_flags); } bool mnt_may_suid(struct vfsmount *mnt) { /* * Foreign mounts (accessed via fchdir or through /proc * symlinks) are always treated as if they are nosuid. This * prevents namespaces from trusting potentially unsafe * suid/sgid bits, file caps, or security labels that originate * in other namespaces. */ return !(mnt->mnt_flags & MNT_NOSUID) && check_mnt(real_mount(mnt)) && current_in_userns(mnt->mnt_sb->s_user_ns); } static struct ns_common *mntns_get(struct task_struct *task) { struct ns_common *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) { ns = &nsproxy->mnt_ns->ns; get_mnt_ns(to_mnt_ns(ns)); } task_unlock(task); return ns; } static void mntns_put(struct ns_common *ns) { put_mnt_ns(to_mnt_ns(ns)); } static int mntns_install(struct nsset *nsset, struct ns_common *ns) { struct nsproxy *nsproxy = nsset->nsproxy; struct fs_struct *fs = nsset->fs; struct mnt_namespace *mnt_ns = to_mnt_ns(ns), *old_mnt_ns; struct user_namespace *user_ns = nsset->cred->user_ns; struct path root; int err; if (!ns_capable(mnt_ns->user_ns, CAP_SYS_ADMIN) || !ns_capable(user_ns, CAP_SYS_CHROOT) || !ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; if (is_anon_ns(mnt_ns)) return -EINVAL; if (fs->users != 1) return -EINVAL; get_mnt_ns(mnt_ns); old_mnt_ns = nsproxy->mnt_ns; nsproxy->mnt_ns = mnt_ns; /* Find the root */ err = vfs_path_lookup(mnt_ns->root->mnt.mnt_root, &mnt_ns->root->mnt, "/", LOOKUP_DOWN, &root); if (err) { /* revert to old namespace */ nsproxy->mnt_ns = old_mnt_ns; put_mnt_ns(mnt_ns); return err; } put_mnt_ns(old_mnt_ns); /* Update the pwd and root */ set_fs_pwd(fs, &root); set_fs_root(fs, &root); path_put(&root); return 0; } static struct user_namespace *mntns_owner(struct ns_common *ns) { return to_mnt_ns(ns)->user_ns; } const struct proc_ns_operations mntns_operations = { .name = "mnt", .type = CLONE_NEWNS, .get = mntns_get, .put = mntns_put, .install = mntns_install, .owner = mntns_owner, }; #ifdef CONFIG_SYSCTL static struct ctl_table fs_namespace_sysctls[] = { { .procname = "mount-max", .data = &sysctl_mount_max, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, }, { } }; static int __init init_fs_namespace_sysctls(void) { register_sysctl_init("fs", fs_namespace_sysctls); return 0; } fs_initcall(init_fs_namespace_sysctls); #endif /* CONFIG_SYSCTL */ |
| 12 19 5 12 12 12 999 2074 2074 2074 2074 2074 566 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 | // SPDX-License-Identifier: GPL-2.0-only /* -*- linux-c -*- * sysctl_net.c: sysctl interface to net subsystem. * * Begun April 1, 1996, Mike Shaver. * Added /proc/sys/net directories for each protocol family. [MS] * * Revision 1.2 1996/05/08 20:24:40 shaver * Added bits for NET_BRIDGE and the NET_IPV4_ARP stuff and * NET_IPV4_IP_FORWARD. * * */ #include <linux/mm.h> #include <linux/export.h> #include <linux/sysctl.h> #include <linux/nsproxy.h> #include <net/sock.h> #ifdef CONFIG_INET #include <net/ip.h> #endif #ifdef CONFIG_NET #include <linux/if_ether.h> #endif static struct ctl_table_set * net_ctl_header_lookup(struct ctl_table_root *root) { return ¤t->nsproxy->net_ns->sysctls; } static int is_seen(struct ctl_table_set *set) { return ¤t->nsproxy->net_ns->sysctls == set; } /* Return standard mode bits for table entry. */ static int net_ctl_permissions(struct ctl_table_header *head, struct ctl_table *table) { struct net *net = container_of(head->set, struct net, sysctls); /* Allow network administrator to have same access as root. */ if (ns_capable_noaudit(net->user_ns, CAP_NET_ADMIN)) { int mode = (table->mode >> 6) & 7; return (mode << 6) | (mode << 3) | mode; } return table->mode; } static void net_ctl_set_ownership(struct ctl_table_header *head, struct ctl_table *table, kuid_t *uid, kgid_t *gid) { struct net *net = container_of(head->set, struct net, sysctls); kuid_t ns_root_uid; kgid_t ns_root_gid; ns_root_uid = make_kuid(net->user_ns, 0); if (uid_valid(ns_root_uid)) *uid = ns_root_uid; ns_root_gid = make_kgid(net->user_ns, 0); if (gid_valid(ns_root_gid)) *gid = ns_root_gid; } static struct ctl_table_root net_sysctl_root = { .lookup = net_ctl_header_lookup, .permissions = net_ctl_permissions, .set_ownership = net_ctl_set_ownership, }; static int __net_init sysctl_net_init(struct net *net) { setup_sysctl_set(&net->sysctls, &net_sysctl_root, is_seen); return 0; } static void __net_exit sysctl_net_exit(struct net *net) { retire_sysctl_set(&net->sysctls); } static struct pernet_operations sysctl_pernet_ops = { .init = sysctl_net_init, .exit = sysctl_net_exit, }; static struct ctl_table_header *net_header; __init int net_sysctl_init(void) { static struct ctl_table empty[1]; int ret = -ENOMEM; /* Avoid limitations in the sysctl implementation by * registering "/proc/sys/net" as an empty directory not in a * network namespace. */ net_header = register_sysctl("net", empty); if (!net_header) goto out; ret = register_pernet_subsys(&sysctl_pernet_ops); if (ret) goto out1; out: return ret; out1: unregister_sysctl_table(net_header); net_header = NULL; goto out; } /* Verify that sysctls for non-init netns are safe by either: * 1) being read-only, or * 2) having a data pointer which points outside of the global kernel/module * data segment, and rather into the heap where a per-net object was * allocated. */ static void ensure_safe_net_sysctl(struct net *net, const char *path, struct ctl_table *table) { struct ctl_table *ent; pr_debug("Registering net sysctl (net %p): %s\n", net, path); for (ent = table; ent->procname; ent++) { unsigned long addr; const char *where; pr_debug(" procname=%s mode=%o proc_handler=%ps data=%p\n", ent->procname, ent->mode, ent->proc_handler, ent->data); /* If it's not writable inside the netns, then it can't hurt. */ if ((ent->mode & 0222) == 0) { pr_debug(" Not writable by anyone\n"); continue; } /* Where does data point? */ addr = (unsigned long)ent->data; if (is_module_address(addr)) where = "module"; else if (is_kernel_core_data(addr)) where = "kernel"; else continue; /* If it is writable and points to kernel/module global * data, then it's probably a netns leak. */ WARN(1, "sysctl %s/%s: data points to %s global data: %ps\n", path, ent->procname, where, ent->data); /* Make it "safe" by dropping writable perms */ ent->mode &= ~0222; } } struct ctl_table_header *register_net_sysctl(struct net *net, const char *path, struct ctl_table *table) { if (!net_eq(net, &init_net)) ensure_safe_net_sysctl(net, path, table); return __register_sysctl_table(&net->sysctls, path, table); } EXPORT_SYMBOL_GPL(register_net_sysctl); void unregister_net_sysctl_table(struct ctl_table_header *header) { unregister_sysctl_table(header); } EXPORT_SYMBOL_GPL(unregister_net_sysctl_table); |
| 2320 2322 1327 1183 1183 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 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 #include <linux/export.h> #include <linux/spinlock.h> #include <linux/atomic.h> /* * This is an implementation of the notion of "decrement a * reference count, and return locked if it decremented to zero". * * NOTE NOTE NOTE! This is _not_ equivalent to * * if (atomic_dec_and_test(&atomic)) { * spin_lock(&lock); * return 1; * } * return 0; * * because the spin-lock and the decrement must be * "atomic". */ int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock) { /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ if (atomic_add_unless(atomic, -1, 1)) return 0; /* Otherwise do it the slow way */ spin_lock(lock); if (atomic_dec_and_test(atomic)) return 1; spin_unlock(lock); return 0; } EXPORT_SYMBOL(_atomic_dec_and_lock); int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, unsigned long *flags) { /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ if (atomic_add_unless(atomic, -1, 1)) return 0; /* Otherwise do it the slow way */ spin_lock_irqsave(lock, *flags); if (atomic_dec_and_test(atomic)) return 1; spin_unlock_irqrestore(lock, *flags); return 0; } EXPORT_SYMBOL(_atomic_dec_and_lock_irqsave); |
| 49 49 49 49 49 49 49 57 2 6 49 49 49 49 999 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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); |
| 498 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Because linux/module.h has tracepoints in the header, and ftrace.h * used to include this file, define_trace.h includes linux/module.h * But we do not want the module.h to override the TRACE_SYSTEM macro * variable that define_trace.h is processing, so we only set it * when module events are being processed, which would happen when * CREATE_TRACE_POINTS is defined. */ #ifdef CREATE_TRACE_POINTS #undef TRACE_SYSTEM #define TRACE_SYSTEM module #endif #if !defined(_TRACE_MODULE_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_MODULE_H #include <linux/tracepoint.h> #ifdef CONFIG_MODULES struct module; #define show_module_flags(flags) __print_flags(flags, "", \ { (1UL << TAINT_PROPRIETARY_MODULE), "P" }, \ { (1UL << TAINT_OOT_MODULE), "O" }, \ { (1UL << TAINT_FORCED_MODULE), "F" }, \ { (1UL << TAINT_CRAP), "C" }, \ { (1UL << TAINT_UNSIGNED_MODULE), "E" }) TRACE_EVENT(module_load, TP_PROTO(struct module *mod), TP_ARGS(mod), TP_STRUCT__entry( __field( unsigned int, taints ) __string( name, mod->name ) ), TP_fast_assign( __entry->taints = mod->taints; __assign_str(name, mod->name); ), TP_printk("%s %s", __get_str(name), show_module_flags(__entry->taints)) ); TRACE_EVENT(module_free, TP_PROTO(struct module *mod), TP_ARGS(mod), TP_STRUCT__entry( __string( name, mod->name ) ), TP_fast_assign( __assign_str(name, mod->name); ), TP_printk("%s", __get_str(name)) ); #ifdef CONFIG_MODULE_UNLOAD /* trace_module_get/put are only used if CONFIG_MODULE_UNLOAD is defined */ DECLARE_EVENT_CLASS(module_refcnt, TP_PROTO(struct module *mod, unsigned long ip), TP_ARGS(mod, ip), TP_STRUCT__entry( __field( unsigned long, ip ) __field( int, refcnt ) __string( name, mod->name ) ), TP_fast_assign( __entry->ip = ip; __entry->refcnt = atomic_read(&mod->refcnt); __assign_str(name, mod->name); ), TP_printk("%s call_site=%ps refcnt=%d", __get_str(name), (void *)__entry->ip, __entry->refcnt) ); DEFINE_EVENT(module_refcnt, module_get, TP_PROTO(struct module *mod, unsigned long ip), TP_ARGS(mod, ip) ); DEFINE_EVENT(module_refcnt, module_put, TP_PROTO(struct module *mod, unsigned long ip), TP_ARGS(mod, ip) ); #endif /* CONFIG_MODULE_UNLOAD */ TRACE_EVENT(module_request, TP_PROTO(char *name, bool wait, unsigned long ip), TP_ARGS(name, wait, ip), TP_STRUCT__entry( __field( unsigned long, ip ) __field( bool, wait ) __string( name, name ) ), TP_fast_assign( __entry->ip = ip; __entry->wait = wait; __assign_str(name, name); ), TP_printk("%s wait=%d call_site=%ps", __get_str(name), (int)__entry->wait, (void *)__entry->ip) ); #endif /* CONFIG_MODULES */ #endif /* _TRACE_MODULE_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 7 5 5 1 1 2 2 5 42 5 4 40 27 26 5 3 1 1 1 1 2 1 1 1 1 1 1 1 1 1 2 4 4 5 2 18 4 1 7 3 4 1 1 1 4 157 157 18 3 73 51 48 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Ioctl handler * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> */ #include <linux/capability.h> #include <linux/compat.h> #include <linux/kernel.h> #include <linux/if_bridge.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/times.h> #include <net/net_namespace.h> #include <linux/uaccess.h> #include "br_private.h" static int get_bridge_ifindices(struct net *net, int *indices, int num) { struct net_device *dev; int i = 0; rcu_read_lock(); for_each_netdev_rcu(net, dev) { if (i >= num) break; if (netif_is_bridge_master(dev)) indices[i++] = dev->ifindex; } rcu_read_unlock(); return i; } /* called with RTNL */ static void get_port_ifindices(struct net_bridge *br, int *ifindices, int num) { struct net_bridge_port *p; list_for_each_entry(p, &br->port_list, list) { if (p->port_no < num) ifindices[p->port_no] = p->dev->ifindex; } } /* * Format up to a page worth of forwarding table entries * userbuf -- where to copy result * maxnum -- maximum number of entries desired * (limited to a page for sanity) * offset -- number of records to skip */ static int get_fdb_entries(struct net_bridge *br, void __user *userbuf, unsigned long maxnum, unsigned long offset) { int num; void *buf; size_t size; /* Clamp size to PAGE_SIZE, test maxnum to avoid overflow */ if (maxnum > PAGE_SIZE/sizeof(struct __fdb_entry)) maxnum = PAGE_SIZE/sizeof(struct __fdb_entry); size = maxnum * sizeof(struct __fdb_entry); buf = kmalloc(size, GFP_USER); if (!buf) return -ENOMEM; num = br_fdb_fillbuf(br, buf, maxnum, offset); if (num > 0) { if (copy_to_user(userbuf, buf, array_size(num, sizeof(struct __fdb_entry)))) num = -EFAULT; } kfree(buf); return num; } /* called with RTNL */ static int add_del_if(struct net_bridge *br, int ifindex, int isadd) { struct net *net = dev_net(br->dev); struct net_device *dev; int ret; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; dev = __dev_get_by_index(net, ifindex); if (dev == NULL) return -EINVAL; if (isadd) ret = br_add_if(br, dev, NULL); else ret = br_del_if(br, dev); return ret; } #define BR_UARGS_MAX 4 static int br_dev_read_uargs(unsigned long *args, size_t nr_args, void __user **argp, void __user *data) { int ret; if (nr_args < 2 || nr_args > BR_UARGS_MAX) return -EINVAL; if (in_compat_syscall()) { unsigned int cargs[BR_UARGS_MAX]; int i; ret = copy_from_user(cargs, data, nr_args * sizeof(*cargs)); if (ret) goto fault; for (i = 0; i < nr_args; ++i) args[i] = cargs[i]; *argp = compat_ptr(args[1]); } else { ret = copy_from_user(args, data, nr_args * sizeof(*args)); if (ret) goto fault; *argp = (void __user *)args[1]; } return 0; fault: return -EFAULT; } /* * Legacy ioctl's through SIOCDEVPRIVATE * This interface is deprecated because it was too difficult * to do the translation for 32/64bit ioctl compatibility. */ int br_dev_siocdevprivate(struct net_device *dev, struct ifreq *rq, void __user *data, int cmd) { struct net_bridge *br = netdev_priv(dev); struct net_bridge_port *p = NULL; unsigned long args[4]; void __user *argp; int ret; ret = br_dev_read_uargs(args, ARRAY_SIZE(args), &argp, data); if (ret) return ret; switch (args[0]) { case BRCTL_ADD_IF: case BRCTL_DEL_IF: return add_del_if(br, args[1], args[0] == BRCTL_ADD_IF); case BRCTL_GET_BRIDGE_INFO: { struct __bridge_info b; memset(&b, 0, sizeof(struct __bridge_info)); rcu_read_lock(); memcpy(&b.designated_root, &br->designated_root, 8); memcpy(&b.bridge_id, &br->bridge_id, 8); b.root_path_cost = br->root_path_cost; b.max_age = jiffies_to_clock_t(br->max_age); b.hello_time = jiffies_to_clock_t(br->hello_time); b.forward_delay = br->forward_delay; b.bridge_max_age = br->bridge_max_age; b.bridge_hello_time = br->bridge_hello_time; b.bridge_forward_delay = jiffies_to_clock_t(br->bridge_forward_delay); b.topology_change = br->topology_change; b.topology_change_detected = br->topology_change_detected; b.root_port = br->root_port; b.stp_enabled = (br->stp_enabled != BR_NO_STP); b.ageing_time = jiffies_to_clock_t(br->ageing_time); b.hello_timer_value = br_timer_value(&br->hello_timer); b.tcn_timer_value = br_timer_value(&br->tcn_timer); b.topology_change_timer_value = br_timer_value(&br->topology_change_timer); b.gc_timer_value = br_timer_value(&br->gc_work.timer); rcu_read_unlock(); if (copy_to_user((void __user *)args[1], &b, sizeof(b))) return -EFAULT; return 0; } case BRCTL_GET_PORT_LIST: { int num, *indices; num = args[2]; if (num < 0) return -EINVAL; if (num == 0) num = 256; if (num > BR_MAX_PORTS) num = BR_MAX_PORTS; indices = kcalloc(num, sizeof(int), GFP_KERNEL); if (indices == NULL) return -ENOMEM; get_port_ifindices(br, indices, num); if (copy_to_user(argp, indices, array_size(num, sizeof(int)))) num = -EFAULT; kfree(indices); return num; } case BRCTL_SET_BRIDGE_FORWARD_DELAY: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = br_set_forward_delay(br, args[1]); break; case BRCTL_SET_BRIDGE_HELLO_TIME: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = br_set_hello_time(br, args[1]); break; case BRCTL_SET_BRIDGE_MAX_AGE: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = br_set_max_age(br, args[1]); break; case BRCTL_SET_AGEING_TIME: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = br_set_ageing_time(br, args[1]); break; case BRCTL_GET_PORT_INFO: { struct __port_info p; struct net_bridge_port *pt; rcu_read_lock(); if ((pt = br_get_port(br, args[2])) == NULL) { rcu_read_unlock(); return -EINVAL; } memset(&p, 0, sizeof(struct __port_info)); memcpy(&p.designated_root, &pt->designated_root, 8); memcpy(&p.designated_bridge, &pt->designated_bridge, 8); p.port_id = pt->port_id; p.designated_port = pt->designated_port; p.path_cost = pt->path_cost; p.designated_cost = pt->designated_cost; p.state = pt->state; p.top_change_ack = pt->topology_change_ack; p.config_pending = pt->config_pending; p.message_age_timer_value = br_timer_value(&pt->message_age_timer); p.forward_delay_timer_value = br_timer_value(&pt->forward_delay_timer); p.hold_timer_value = br_timer_value(&pt->hold_timer); rcu_read_unlock(); if (copy_to_user(argp, &p, sizeof(p))) return -EFAULT; return 0; } case BRCTL_SET_BRIDGE_STP_STATE: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = br_stp_set_enabled(br, args[1], NULL); break; case BRCTL_SET_BRIDGE_PRIORITY: if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; br_stp_set_bridge_priority(br, args[1]); ret = 0; break; case BRCTL_SET_PORT_PRIORITY: { if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; spin_lock_bh(&br->lock); if ((p = br_get_port(br, args[1])) == NULL) ret = -EINVAL; else ret = br_stp_set_port_priority(p, args[2]); spin_unlock_bh(&br->lock); break; } case BRCTL_SET_PATH_COST: { if (!ns_capable(dev_net(dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; spin_lock_bh(&br->lock); if ((p = br_get_port(br, args[1])) == NULL) ret = -EINVAL; else ret = br_stp_set_path_cost(p, args[2]); spin_unlock_bh(&br->lock); break; } case BRCTL_GET_FDB_ENTRIES: return get_fdb_entries(br, argp, args[2], args[3]); default: ret = -EOPNOTSUPP; } if (!ret) { if (p) br_ifinfo_notify(RTM_NEWLINK, NULL, p); else netdev_state_change(br->dev); } return ret; } static int old_deviceless(struct net *net, void __user *data) { unsigned long args[3]; void __user *argp; int ret; ret = br_dev_read_uargs(args, ARRAY_SIZE(args), &argp, data); if (ret) return ret; switch (args[0]) { case BRCTL_GET_VERSION: return BRCTL_VERSION; case BRCTL_GET_BRIDGES: { int *indices; int ret = 0; if (args[2] >= 2048) return -ENOMEM; indices = kcalloc(args[2], sizeof(int), GFP_KERNEL); if (indices == NULL) return -ENOMEM; args[2] = get_bridge_ifindices(net, indices, args[2]); ret = copy_to_user(argp, indices, array_size(args[2], sizeof(int))) ? -EFAULT : args[2]; kfree(indices); return ret; } case BRCTL_ADD_BRIDGE: case BRCTL_DEL_BRIDGE: { char buf[IFNAMSIZ]; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(buf, argp, IFNAMSIZ)) return -EFAULT; buf[IFNAMSIZ-1] = 0; if (args[0] == BRCTL_ADD_BRIDGE) return br_add_bridge(net, buf); return br_del_bridge(net, buf); } } return -EOPNOTSUPP; } int br_ioctl_stub(struct net *net, struct net_bridge *br, unsigned int cmd, struct ifreq *ifr, void __user *uarg) { int ret = -EOPNOTSUPP; rtnl_lock(); switch (cmd) { case SIOCGIFBR: case SIOCSIFBR: ret = old_deviceless(net, uarg); break; case SIOCBRADDBR: case SIOCBRDELBR: { char buf[IFNAMSIZ]; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; break; } if (copy_from_user(buf, uarg, IFNAMSIZ)) { ret = -EFAULT; break; } buf[IFNAMSIZ-1] = 0; if (cmd == SIOCBRADDBR) ret = br_add_bridge(net, buf); else ret = br_del_bridge(net, buf); } break; case SIOCBRADDIF: case SIOCBRDELIF: ret = add_del_if(br, ifr->ifr_ifindex, cmd == SIOCBRADDIF); break; } rtnl_unlock(); return ret; } |
| 6459 6430 44 19 6 3005 8 2940 781 80 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 | #ifndef _LINUX_JHASH_H #define _LINUX_JHASH_H /* jhash.h: Jenkins hash support. * * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net) * * https://burtleburtle.net/bob/hash/ * * These are the credits from Bob's sources: * * lookup3.c, by Bob Jenkins, May 2006, Public Domain. * * These are functions for producing 32-bit hashes for hash table lookup. * hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() * are externally useful functions. Routines to test the hash are included * if SELF_TEST is defined. You can use this free for any purpose. It's in * the public domain. It has no warranty. * * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@netfilter.org) * * I've modified Bob's hash to be useful in the Linux kernel, and * any bugs present are my fault. * Jozsef */ #include <linux/bitops.h> #include <linux/unaligned/packed_struct.h> /* Best hash sizes are of power of two */ #define jhash_size(n) ((u32)1<<(n)) /* Mask the hash value, i.e (value & jhash_mask(n)) instead of (value % n) */ #define jhash_mask(n) (jhash_size(n)-1) /* __jhash_mix -- mix 3 32-bit values reversibly. */ #define __jhash_mix(a, b, c) \ { \ a -= c; a ^= rol32(c, 4); c += b; \ b -= a; b ^= rol32(a, 6); a += c; \ c -= b; c ^= rol32(b, 8); b += a; \ a -= c; a ^= rol32(c, 16); c += b; \ b -= a; b ^= rol32(a, 19); a += c; \ c -= b; c ^= rol32(b, 4); b += a; \ } /* __jhash_final - final mixing of 3 32-bit values (a,b,c) into c */ #define __jhash_final(a, b, c) \ { \ c ^= b; c -= rol32(b, 14); \ a ^= c; a -= rol32(c, 11); \ b ^= a; b -= rol32(a, 25); \ c ^= b; c -= rol32(b, 16); \ a ^= c; a -= rol32(c, 4); \ b ^= a; b -= rol32(a, 14); \ c ^= b; c -= rol32(b, 24); \ } /* An arbitrary initial parameter */ #define JHASH_INITVAL 0xdeadbeef /* jhash - hash an arbitrary key * @k: sequence of bytes as key * @length: the length of the key * @initval: the previous hash, or an arbitray value * * The generic version, hashes an arbitrary sequence of bytes. * No alignment or length assumptions are made about the input key. * * Returns the hash value of the key. The result depends on endianness. */ static inline u32 jhash(const void *key, u32 length, u32 initval) { u32 a, b, c; const u8 *k = key; /* Set up the internal state */ a = b = c = JHASH_INITVAL + length + initval; /* All but the last block: affect some 32 bits of (a,b,c) */ while (length > 12) { a += __get_unaligned_cpu32(k); b += __get_unaligned_cpu32(k + 4); c += __get_unaligned_cpu32(k + 8); __jhash_mix(a, b, c); length -= 12; k += 12; } /* Last block: affect all 32 bits of (c) */ switch (length) { case 12: c += (u32)k[11]<<24; fallthrough; case 11: c += (u32)k[10]<<16; fallthrough; case 10: c += (u32)k[9]<<8; fallthrough; case 9: c += k[8]; fallthrough; case 8: b += (u32)k[7]<<24; fallthrough; case 7: b += (u32)k[6]<<16; fallthrough; case 6: b += (u32)k[5]<<8; fallthrough; case 5: b += k[4]; fallthrough; case 4: a += (u32)k[3]<<24; fallthrough; case 3: a += (u32)k[2]<<16; fallthrough; case 2: a += (u32)k[1]<<8; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; case 0: /* Nothing left to add */ break; } return c; } /* jhash2 - hash an array of u32's * @k: the key which must be an array of u32's * @length: the number of u32's in the key * @initval: the previous hash, or an arbitray value * * Returns the hash value of the key. */ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) { u32 a, b, c; /* Set up the internal state */ a = b = c = JHASH_INITVAL + (length<<2) + initval; /* Handle most of the key */ while (length > 3) { a += k[0]; b += k[1]; c += k[2]; __jhash_mix(a, b, c); length -= 3; k += 3; } /* Handle the last 3 u32's */ switch (length) { case 3: c += k[2]; fallthrough; case 2: b += k[1]; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; case 0: /* Nothing left to add */ break; } return c; } /* __jhash_nwords - hash exactly 3, 2 or 1 word(s) */ static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) { a += initval; b += initval; c += initval; __jhash_final(a, b, c); return c; } static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval) { return __jhash_nwords(a, b, c, initval + JHASH_INITVAL + (3 << 2)); } static inline u32 jhash_2words(u32 a, u32 b, u32 initval) { return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); } static inline u32 jhash_1word(u32 a, u32 initval) { return __jhash_nwords(a, 0, 0, initval + JHASH_INITVAL + (1 << 2)); } #endif /* _LINUX_JHASH_H */ |
| 526 207 56 241 21 241 580 565 565 568 76 22 567 25 369 4 9 7 287 298 298 285 9 12 6 258 222 7 215 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 | // 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); |
| 86 10 1 1 4 2 163 1 3327 3319 163 1 3321 580 3317 156 86 86 11 8 11 5 1 4 4 4 112 1 112 112 112 112 86 86 86 63 3 61 49 11 2 999 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET 802.1Q VLAN * Ethernet-type device handling. * * Authors: Ben Greear <greearb@candelatech.com> * Please send support related email to: netdev@vger.kernel.org * VLAN Home Page: http://www.candelatech.com/~greear/vlan.html * * Fixes: * Fix for packet capture - Nick Eggleston <nick@dccinc.com>; * Add HW acceleration hooks - David S. Miller <davem@redhat.com>; * Correct all the locking - David S. Miller <davem@redhat.com>; * Use hash table for VLAN groups - David S. Miller <davem@redhat.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/capability.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/rculist.h> #include <net/p8022.h> #include <net/arp.h> #include <linux/rtnetlink.h> #include <linux/notifier.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/uaccess.h> #include <linux/if_vlan.h> #include "vlan.h" #include "vlanproc.h" #define DRV_VERSION "1.8" /* Global VLAN variables */ unsigned int vlan_net_id __read_mostly; const char vlan_fullname[] = "802.1Q VLAN Support"; const char vlan_version[] = DRV_VERSION; /* End of global variables definitions. */ static int vlan_group_prealloc_vid(struct vlan_group *vg, __be16 vlan_proto, u16 vlan_id) { struct net_device **array; unsigned int vidx; unsigned int size; int pidx; ASSERT_RTNL(); pidx = vlan_proto_idx(vlan_proto); if (pidx < 0) return -EINVAL; vidx = vlan_id / VLAN_GROUP_ARRAY_PART_LEN; array = vg->vlan_devices_arrays[pidx][vidx]; if (array != NULL) return 0; size = sizeof(struct net_device *) * VLAN_GROUP_ARRAY_PART_LEN; array = kzalloc(size, GFP_KERNEL_ACCOUNT); if (array == NULL) return -ENOBUFS; /* paired with smp_rmb() in __vlan_group_get_device() */ smp_wmb(); vg->vlan_devices_arrays[pidx][vidx] = array; return 0; } static void vlan_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev, struct vlan_dev_priv *vlan) { if (!(vlan->flags & VLAN_FLAG_BRIDGE_BINDING)) netif_stacked_transfer_operstate(rootdev, dev); } void unregister_vlan_dev(struct net_device *dev, struct list_head *head) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; struct vlan_info *vlan_info; struct vlan_group *grp; u16 vlan_id = vlan->vlan_id; ASSERT_RTNL(); vlan_info = rtnl_dereference(real_dev->vlan_info); BUG_ON(!vlan_info); grp = &vlan_info->grp; grp->nr_vlan_devs--; if (vlan->flags & VLAN_FLAG_MVRP) vlan_mvrp_request_leave(dev); if (vlan->flags & VLAN_FLAG_GVRP) vlan_gvrp_request_leave(dev); vlan_group_set_device(grp, vlan->vlan_proto, vlan_id, NULL); netdev_upper_dev_unlink(real_dev, dev); /* Because unregister_netdevice_queue() makes sure at least one rcu * grace period is respected before device freeing, * we dont need to call synchronize_net() here. */ unregister_netdevice_queue(dev, head); if (grp->nr_vlan_devs == 0) { vlan_mvrp_uninit_applicant(real_dev); vlan_gvrp_uninit_applicant(real_dev); } vlan_vid_del(real_dev, vlan->vlan_proto, vlan_id); } int vlan_check_real_dev(struct net_device *real_dev, __be16 protocol, u16 vlan_id, struct netlink_ext_ack *extack) { const char *name = real_dev->name; if (real_dev->features & NETIF_F_VLAN_CHALLENGED || real_dev->type != ARPHRD_ETHER) { pr_info("VLANs not supported on %s\n", name); NL_SET_ERR_MSG_MOD(extack, "VLANs not supported on device"); return -EOPNOTSUPP; } if (vlan_find_dev(real_dev, protocol, vlan_id) != NULL) { NL_SET_ERR_MSG_MOD(extack, "VLAN device already exists"); return -EEXIST; } return 0; } int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; u16 vlan_id = vlan->vlan_id; struct vlan_info *vlan_info; struct vlan_group *grp; int err; err = vlan_vid_add(real_dev, vlan->vlan_proto, vlan_id); if (err) return err; vlan_info = rtnl_dereference(real_dev->vlan_info); /* vlan_info should be there now. vlan_vid_add took care of it */ BUG_ON(!vlan_info); grp = &vlan_info->grp; if (grp->nr_vlan_devs == 0) { err = vlan_gvrp_init_applicant(real_dev); if (err < 0) goto out_vid_del; err = vlan_mvrp_init_applicant(real_dev); if (err < 0) goto out_uninit_gvrp; } err = vlan_group_prealloc_vid(grp, vlan->vlan_proto, vlan_id); if (err < 0) goto out_uninit_mvrp; err = register_netdevice(dev); if (err < 0) goto out_uninit_mvrp; err = netdev_upper_dev_link(real_dev, dev, extack); if (err) goto out_unregister_netdev; vlan_stacked_transfer_operstate(real_dev, dev, vlan); linkwatch_fire_event(dev); /* _MUST_ call rfc2863_policy() */ /* So, got the sucker initialized, now lets place * it into our local structure. */ vlan_group_set_device(grp, vlan->vlan_proto, vlan_id, dev); grp->nr_vlan_devs++; return 0; out_unregister_netdev: unregister_netdevice(dev); out_uninit_mvrp: if (grp->nr_vlan_devs == 0) vlan_mvrp_uninit_applicant(real_dev); out_uninit_gvrp: if (grp->nr_vlan_devs == 0) vlan_gvrp_uninit_applicant(real_dev); out_vid_del: vlan_vid_del(real_dev, vlan->vlan_proto, vlan_id); return err; } /* Attach a VLAN device to a mac address (ie Ethernet Card). * Returns 0 if the device was created or a negative error code otherwise. */ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id) { struct net_device *new_dev; struct vlan_dev_priv *vlan; struct net *net = dev_net(real_dev); struct vlan_net *vn = net_generic(net, vlan_net_id); char name[IFNAMSIZ]; int err; if (vlan_id >= VLAN_VID_MASK) return -ERANGE; err = vlan_check_real_dev(real_dev, htons(ETH_P_8021Q), vlan_id, NULL); if (err < 0) return err; /* Gotta set up the fields for the device. */ switch (vn->name_type) { case VLAN_NAME_TYPE_RAW_PLUS_VID: /* name will look like: eth1.0005 */ snprintf(name, IFNAMSIZ, "%s.%.4i", real_dev->name, vlan_id); break; case VLAN_NAME_TYPE_PLUS_VID_NO_PAD: /* Put our vlan.VID in the name. * Name will look like: vlan5 */ snprintf(name, IFNAMSIZ, "vlan%i", vlan_id); break; case VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD: /* Put our vlan.VID in the name. * Name will look like: eth0.5 */ snprintf(name, IFNAMSIZ, "%s.%i", real_dev->name, vlan_id); break; case VLAN_NAME_TYPE_PLUS_VID: /* Put our vlan.VID in the name. * Name will look like: vlan0005 */ default: snprintf(name, IFNAMSIZ, "vlan%.4i", vlan_id); } new_dev = alloc_netdev(sizeof(struct vlan_dev_priv), name, NET_NAME_UNKNOWN, vlan_setup); if (new_dev == NULL) return -ENOBUFS; dev_net_set(new_dev, net); /* need 4 bytes for extra VLAN header info, * hope the underlying device can handle it. */ new_dev->mtu = real_dev->mtu; vlan = vlan_dev_priv(new_dev); vlan->vlan_proto = htons(ETH_P_8021Q); vlan->vlan_id = vlan_id; vlan->real_dev = real_dev; vlan->dent = NULL; vlan->flags = VLAN_FLAG_REORDER_HDR; new_dev->rtnl_link_ops = &vlan_link_ops; err = register_vlan_dev(new_dev, NULL); if (err < 0) goto out_free_newdev; return 0; out_free_newdev: free_netdev(new_dev); return err; } static void vlan_sync_address(struct net_device *dev, struct net_device *vlandev) { struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev); /* May be called without an actual change */ if (ether_addr_equal(vlan->real_dev_addr, dev->dev_addr)) return; /* vlan continues to inherit address of lower device */ if (vlan_dev_inherit_address(vlandev, dev)) goto out; /* vlan address was different from the old address and is equal to * the new address */ if (!ether_addr_equal(vlandev->dev_addr, vlan->real_dev_addr) && ether_addr_equal(vlandev->dev_addr, dev->dev_addr)) dev_uc_del(dev, vlandev->dev_addr); /* vlan address was equal to the old address and is different from * the new address */ if (ether_addr_equal(vlandev->dev_addr, vlan->real_dev_addr) && !ether_addr_equal(vlandev->dev_addr, dev->dev_addr)) dev_uc_add(dev, vlandev->dev_addr); out: ether_addr_copy(vlan->real_dev_addr, dev->dev_addr); } static void vlan_transfer_features(struct net_device *dev, struct net_device *vlandev) { struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev); netif_inherit_tso_max(vlandev, dev); if (vlan_hw_offload_capable(dev->features, vlan->vlan_proto)) vlandev->hard_header_len = dev->hard_header_len; else vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN; #if IS_ENABLED(CONFIG_FCOE) vlandev->fcoe_ddp_xid = dev->fcoe_ddp_xid; #endif vlandev->priv_flags &= ~IFF_XMIT_DST_RELEASE; vlandev->priv_flags |= (vlan->real_dev->priv_flags & IFF_XMIT_DST_RELEASE); vlandev->hw_enc_features = vlan_tnl_features(vlan->real_dev); netdev_update_features(vlandev); } static int __vlan_device_event(struct net_device *dev, unsigned long event) { int err = 0; switch (event) { case NETDEV_CHANGENAME: vlan_proc_rem_dev(dev); err = vlan_proc_add_dev(dev); break; case NETDEV_REGISTER: err = vlan_proc_add_dev(dev); break; case NETDEV_UNREGISTER: vlan_proc_rem_dev(dev); break; } return err; } static int vlan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr); struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct vlan_group *grp; struct vlan_info *vlan_info; int i, flgs; struct net_device *vlandev; struct vlan_dev_priv *vlan; bool last = false; LIST_HEAD(list); int err; if (is_vlan_dev(dev)) { int err = __vlan_device_event(dev, event); if (err) return notifier_from_errno(err); } if ((event == NETDEV_UP) && (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) { pr_info("adding VLAN 0 to HW filter on device %s\n", dev->name); vlan_vid_add(dev, htons(ETH_P_8021Q), 0); } if (event == NETDEV_DOWN && (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) vlan_vid_del(dev, htons(ETH_P_8021Q), 0); vlan_info = rtnl_dereference(dev->vlan_info); if (!vlan_info) goto out; grp = &vlan_info->grp; /* It is OK that we do not hold the group lock right now, * as we run under the RTNL lock. */ switch (event) { case NETDEV_CHANGE: /* Propagate real device state to vlan devices */ vlan_group_for_each_dev(grp, i, vlandev) vlan_stacked_transfer_operstate(dev, vlandev, vlan_dev_priv(vlandev)); break; case NETDEV_CHANGEADDR: /* Adjust unicast filters on underlying device */ vlan_group_for_each_dev(grp, i, vlandev) { flgs = vlandev->flags; if (!(flgs & IFF_UP)) continue; vlan_sync_address(dev, vlandev); } break; case NETDEV_CHANGEMTU: vlan_group_for_each_dev(grp, i, vlandev) { if (vlandev->mtu <= dev->mtu) continue; dev_set_mtu(vlandev, dev->mtu); } break; case NETDEV_FEAT_CHANGE: /* Propagate device features to underlying device */ vlan_group_for_each_dev(grp, i, vlandev) vlan_transfer_features(dev, vlandev); break; case NETDEV_DOWN: { struct net_device *tmp; LIST_HEAD(close_list); /* Put all VLANs for this dev in the down state too. */ vlan_group_for_each_dev(grp, i, vlandev) { flgs = vlandev->flags; if (!(flgs & IFF_UP)) continue; vlan = vlan_dev_priv(vlandev); if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) list_add(&vlandev->close_list, &close_list); } dev_close_many(&close_list, false); list_for_each_entry_safe(vlandev, tmp, &close_list, close_list) { vlan_stacked_transfer_operstate(dev, vlandev, vlan_dev_priv(vlandev)); list_del_init(&vlandev->close_list); } list_del(&close_list); break; } case NETDEV_UP: /* Put all VLANs for this dev in the up state too. */ vlan_group_for_each_dev(grp, i, vlandev) { flgs = dev_get_flags(vlandev); if (flgs & IFF_UP) continue; vlan = vlan_dev_priv(vlandev); if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) dev_change_flags(vlandev, flgs | IFF_UP, extack); vlan_stacked_transfer_operstate(dev, vlandev, vlan); } break; case NETDEV_UNREGISTER: /* twiddle thumbs on netns device moves */ if (dev->reg_state != NETREG_UNREGISTERING) break; vlan_group_for_each_dev(grp, i, vlandev) { /* removal of last vid destroys vlan_info, abort * afterwards */ if (vlan_info->nr_vids == 1) last = true; unregister_vlan_dev(vlandev, &list); if (last) break; } unregister_netdevice_many(&list); break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlaying device to change its type. */ if (vlan_uses_dev(dev)) return NOTIFY_BAD; break; case NETDEV_NOTIFY_PEERS: case NETDEV_BONDING_FAILOVER: case NETDEV_RESEND_IGMP: /* Propagate to vlan devices */ vlan_group_for_each_dev(grp, i, vlandev) call_netdevice_notifiers(event, vlandev); break; case NETDEV_CVLAN_FILTER_PUSH_INFO: err = vlan_filter_push_vids(vlan_info, htons(ETH_P_8021Q)); if (err) return notifier_from_errno(err); break; case NETDEV_CVLAN_FILTER_DROP_INFO: vlan_filter_drop_vids(vlan_info, htons(ETH_P_8021Q)); break; case NETDEV_SVLAN_FILTER_PUSH_INFO: err = vlan_filter_push_vids(vlan_info, htons(ETH_P_8021AD)); if (err) return notifier_from_errno(err); break; case NETDEV_SVLAN_FILTER_DROP_INFO: vlan_filter_drop_vids(vlan_info, htons(ETH_P_8021AD)); break; } out: return NOTIFY_DONE; } static struct notifier_block vlan_notifier_block __read_mostly = { .notifier_call = vlan_device_event, }; /* * VLAN IOCTL handler. * o execute requested action or pass command to the device driver * arg is really a struct vlan_ioctl_args __user *. */ static int vlan_ioctl_handler(struct net *net, void __user *arg) { int err; struct vlan_ioctl_args args; struct net_device *dev = NULL; if (copy_from_user(&args, arg, sizeof(struct vlan_ioctl_args))) return -EFAULT; /* Null terminate this sucker, just in case. */ args.device1[sizeof(args.device1) - 1] = 0; args.u.device2[sizeof(args.u.device2) - 1] = 0; rtnl_lock(); switch (args.cmd) { case SET_VLAN_INGRESS_PRIORITY_CMD: case SET_VLAN_EGRESS_PRIORITY_CMD: case SET_VLAN_FLAG_CMD: case ADD_VLAN_CMD: case DEL_VLAN_CMD: case GET_VLAN_REALDEV_NAME_CMD: case GET_VLAN_VID_CMD: err = -ENODEV; dev = __dev_get_by_name(net, args.device1); if (!dev) goto out; err = -EINVAL; if (args.cmd != ADD_VLAN_CMD && !is_vlan_dev(dev)) goto out; } switch (args.cmd) { case SET_VLAN_INGRESS_PRIORITY_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; vlan_dev_set_ingress_priority(dev, args.u.skb_priority, args.vlan_qos); err = 0; break; case SET_VLAN_EGRESS_PRIORITY_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = vlan_dev_set_egress_priority(dev, args.u.skb_priority, args.vlan_qos); break; case SET_VLAN_FLAG_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = vlan_dev_change_flags(dev, args.vlan_qos ? args.u.flag : 0, args.u.flag); break; case SET_VLAN_NAME_TYPE_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; if (args.u.name_type < VLAN_NAME_TYPE_HIGHEST) { struct vlan_net *vn; vn = net_generic(net, vlan_net_id); vn->name_type = args.u.name_type; err = 0; } else { err = -EINVAL; } break; case ADD_VLAN_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = register_vlan_device(dev, args.u.VID); break; case DEL_VLAN_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; unregister_vlan_dev(dev, NULL); err = 0; break; case GET_VLAN_REALDEV_NAME_CMD: err = 0; vlan_dev_get_realdev_name(dev, args.u.device2, sizeof(args.u.device2)); if (copy_to_user(arg, &args, sizeof(struct vlan_ioctl_args))) err = -EFAULT; break; case GET_VLAN_VID_CMD: err = 0; args.u.VID = vlan_dev_vlan_id(dev); if (copy_to_user(arg, &args, sizeof(struct vlan_ioctl_args))) err = -EFAULT; break; default: err = -EOPNOTSUPP; break; } out: rtnl_unlock(); return err; } static int __net_init vlan_init_net(struct net *net) { struct vlan_net *vn = net_generic(net, vlan_net_id); int err; vn->name_type = VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD; err = vlan_proc_init(net); return err; } static void __net_exit vlan_exit_net(struct net *net) { vlan_proc_cleanup(net); } static struct pernet_operations vlan_net_ops = { .init = vlan_init_net, .exit = vlan_exit_net, .id = &vlan_net_id, .size = sizeof(struct vlan_net), }; static int __init vlan_proto_init(void) { int err; pr_info("%s v%s\n", vlan_fullname, vlan_version); err = register_pernet_subsys(&vlan_net_ops); if (err < 0) goto err0; err = register_netdevice_notifier(&vlan_notifier_block); if (err < 0) goto err2; err = vlan_gvrp_init(); if (err < 0) goto err3; err = vlan_mvrp_init(); if (err < 0) goto err4; err = vlan_netlink_init(); if (err < 0) goto err5; vlan_ioctl_set(vlan_ioctl_handler); return 0; err5: vlan_mvrp_uninit(); err4: vlan_gvrp_uninit(); err3: unregister_netdevice_notifier(&vlan_notifier_block); err2: unregister_pernet_subsys(&vlan_net_ops); err0: return err; } static void __exit vlan_cleanup_module(void) { vlan_ioctl_set(NULL); vlan_netlink_fini(); unregister_netdevice_notifier(&vlan_notifier_block); unregister_pernet_subsys(&vlan_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ vlan_mvrp_uninit(); vlan_gvrp_uninit(); } module_init(vlan_proto_init); module_exit(vlan_cleanup_module); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); |
| 1463 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef IOCONTEXT_H #define IOCONTEXT_H #include <linux/radix-tree.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> enum { ICQ_EXITED = 1 << 2, ICQ_DESTROYED = 1 << 3, }; /* * An io_cq (icq) is association between an io_context (ioc) and a * request_queue (q). This is used by elevators which need to track * information per ioc - q pair. * * Elevator can request use of icq by setting elevator_type->icq_size and * ->icq_align. Both size and align must be larger than that of struct * io_cq and elevator can use the tail area for private information. The * recommended way to do this is defining a struct which contains io_cq as * the first member followed by private members and using its size and * align. For example, * * struct snail_io_cq { * struct io_cq icq; * int poke_snail; * int feed_snail; * }; * * struct elevator_type snail_elv_type { * .ops = { ... }, * .icq_size = sizeof(struct snail_io_cq), * .icq_align = __alignof__(struct snail_io_cq), * ... * }; * * If icq_size is set, block core will manage icq's. All requests will * have its ->elv.icq field set before elevator_ops->elevator_set_req_fn() * is called and be holding a reference to the associated io_context. * * Whenever a new icq is created, elevator_ops->elevator_init_icq_fn() is * called and, on destruction, ->elevator_exit_icq_fn(). Both functions * are called with both the associated io_context and queue locks held. * * Elevator is allowed to lookup icq using ioc_lookup_icq() while holding * queue lock but the returned icq is valid only until the queue lock is * released. Elevators can not and should not try to create or destroy * icq's. * * As icq's are linked from both ioc and q, the locking rules are a bit * complex. * * - ioc lock nests inside q lock. * * - ioc->icq_list and icq->ioc_node are protected by ioc lock. * q->icq_list and icq->q_node by q lock. * * - ioc->icq_tree and ioc->icq_hint are protected by ioc lock, while icq * itself is protected by q lock. However, both the indexes and icq * itself are also RCU managed and lookup can be performed holding only * the q lock. * * - icq's are not reference counted. They are destroyed when either the * ioc or q goes away. Each request with icq set holds an extra * reference to ioc to ensure it stays until the request is completed. * * - Linking and unlinking icq's are performed while holding both ioc and q * locks. Due to the lock ordering, q exit is simple but ioc exit * requires reverse-order double lock dance. */ struct io_cq { struct request_queue *q; struct io_context *ioc; /* * q_node and ioc_node link io_cq through icq_list of q and ioc * respectively. Both fields are unused once ioc_exit_icq() is * called and shared with __rcu_icq_cache and __rcu_head which are * used for RCU free of io_cq. */ union { struct list_head q_node; struct kmem_cache *__rcu_icq_cache; }; union { struct hlist_node ioc_node; struct rcu_head __rcu_head; }; unsigned int flags; }; /* * I/O subsystem state of the associated processes. It is refcounted * and kmalloc'ed. These could be shared between processes. */ struct io_context { atomic_long_t refcount; atomic_t active_ref; unsigned short ioprio; #ifdef CONFIG_BLK_ICQ /* all the fields below are protected by this lock */ spinlock_t lock; struct radix_tree_root icq_tree; struct io_cq __rcu *icq_hint; struct hlist_head icq_list; struct work_struct release_work; #endif /* CONFIG_BLK_ICQ */ }; struct task_struct; #ifdef CONFIG_BLOCK void put_io_context(struct io_context *ioc); void exit_io_context(struct task_struct *task); int __copy_io(unsigned long clone_flags, struct task_struct *tsk); static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk) { if (!current->io_context) return 0; return __copy_io(clone_flags, tsk); } #else struct io_context; static inline void put_io_context(struct io_context *ioc) { } static inline void exit_io_context(struct task_struct *task) { } static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk) { return 0; } #endif /* CONFIG_BLOCK */ #endif /* IOCONTEXT_H */ |
| 63 63 63 63 60 60 52 53 53 53 63 63 5 4 4 1499 1499 63 63 63 63 63 63 63 63 63 63 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 | // SPDX-License-Identifier: GPL-2.0-or-later #include <net/gro.h> #include <net/dst_metadata.h> #include <net/busy_poll.h> #include <trace/events/net.h> #define MAX_GRO_SKBS 8 /* This should be increased if a protocol with a bigger head is added. */ #define GRO_MAX_HEAD (MAX_HEADER + 128) static DEFINE_SPINLOCK(offload_lock); static struct list_head offload_base __read_mostly = LIST_HEAD_INIT(offload_base); /* Maximum number of GRO_NORMAL skbs to batch up for list-RX */ int gro_normal_batch __read_mostly = 8; /** * dev_add_offload - register offload handlers * @po: protocol offload declaration * * Add protocol offload handlers to the networking stack. The passed * &proto_offload is linked into kernel lists and may not be freed until * it has been removed from the kernel lists. * * This call does not sleep therefore it can not * guarantee all CPU's that are in middle of receiving packets * will see the new offload handlers (until the next received packet). */ void dev_add_offload(struct packet_offload *po) { struct packet_offload *elem; spin_lock(&offload_lock); list_for_each_entry(elem, &offload_base, list) { if (po->priority < elem->priority) break; } list_add_rcu(&po->list, elem->list.prev); spin_unlock(&offload_lock); } EXPORT_SYMBOL(dev_add_offload); /** * __dev_remove_offload - remove offload handler * @po: packet offload declaration * * Remove a protocol offload handler that was previously added to the * kernel offload handlers by dev_add_offload(). The passed &offload_type * is removed from the kernel lists and can be freed or reused once this * function returns. * * The packet type might still be in use by receivers * and must not be freed until after all the CPU's have gone * through a quiescent state. */ static void __dev_remove_offload(struct packet_offload *po) { struct list_head *head = &offload_base; struct packet_offload *po1; spin_lock(&offload_lock); list_for_each_entry(po1, head, list) { if (po == po1) { list_del_rcu(&po->list); goto out; } } pr_warn("dev_remove_offload: %p not found\n", po); out: spin_unlock(&offload_lock); } /** * dev_remove_offload - remove packet offload handler * @po: packet offload declaration * * Remove a packet offload handler that was previously added to the kernel * offload handlers by dev_add_offload(). The passed &offload_type is * removed from the kernel lists and can be freed or reused once this * function returns. * * This call sleeps to guarantee that no CPU is looking at the packet * type after return. */ void dev_remove_offload(struct packet_offload *po) { __dev_remove_offload(po); synchronize_net(); } EXPORT_SYMBOL(dev_remove_offload); /** * skb_eth_gso_segment - segmentation handler for ethernet protocols. * @skb: buffer to segment * @features: features for the output path (see dev->features) * @type: Ethernet Protocol ID */ struct sk_buff *skb_eth_gso_segment(struct sk_buff *skb, netdev_features_t features, __be16 type) { struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); struct packet_offload *ptype; rcu_read_lock(); list_for_each_entry_rcu(ptype, &offload_base, list) { if (ptype->type == type && ptype->callbacks.gso_segment) { segs = ptype->callbacks.gso_segment(skb, features); break; } } rcu_read_unlock(); return segs; } EXPORT_SYMBOL(skb_eth_gso_segment); /** * skb_mac_gso_segment - mac layer segmentation handler. * @skb: buffer to segment * @features: features for the output path (see dev->features) */ struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); struct packet_offload *ptype; int vlan_depth = skb->mac_len; __be16 type = skb_network_protocol(skb, &vlan_depth); if (unlikely(!type)) return ERR_PTR(-EINVAL); __skb_pull(skb, vlan_depth); rcu_read_lock(); list_for_each_entry_rcu(ptype, &offload_base, list) { if (ptype->type == type && ptype->callbacks.gso_segment) { segs = ptype->callbacks.gso_segment(skb, features); break; } } rcu_read_unlock(); __skb_push(skb, skb->data - skb_mac_header(skb)); return segs; } EXPORT_SYMBOL(skb_mac_gso_segment); int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) { struct skb_shared_info *pinfo, *skbinfo = skb_shinfo(skb); unsigned int offset = skb_gro_offset(skb); unsigned int headlen = skb_headlen(skb); unsigned int len = skb_gro_len(skb); unsigned int delta_truesize; unsigned int gro_max_size; unsigned int new_truesize; struct sk_buff *lp; int segs; /* Do not splice page pool based packets w/ non-page pool * packets. This can result in reference count issues as page * pool pages will not decrement the reference count and will * instead be immediately returned to the pool or have frag * count decremented. */ if (p->pp_recycle != skb->pp_recycle) return -ETOOMANYREFS; /* pairs with WRITE_ONCE() in netif_set_gro_max_size() */ gro_max_size = READ_ONCE(p->dev->gro_max_size); if (unlikely(p->len + len >= gro_max_size || NAPI_GRO_CB(skb)->flush)) return -E2BIG; if (unlikely(p->len + len >= GRO_LEGACY_MAX_SIZE)) { if (p->protocol != htons(ETH_P_IPV6) || skb_headroom(p) < sizeof(struct hop_jumbo_hdr) || ipv6_hdr(p)->nexthdr != IPPROTO_TCP || p->encapsulation) return -E2BIG; } segs = NAPI_GRO_CB(skb)->count; lp = NAPI_GRO_CB(p)->last; pinfo = skb_shinfo(lp); if (headlen <= offset) { skb_frag_t *frag; skb_frag_t *frag2; int i = skbinfo->nr_frags; int nr_frags = pinfo->nr_frags + i; if (nr_frags > MAX_SKB_FRAGS) goto merge; offset -= headlen; pinfo->nr_frags = nr_frags; skbinfo->nr_frags = 0; frag = pinfo->frags + nr_frags; frag2 = skbinfo->frags + i; do { *--frag = *--frag2; } while (--i); skb_frag_off_add(frag, offset); skb_frag_size_sub(frag, offset); /* all fragments truesize : remove (head size + sk_buff) */ new_truesize = SKB_TRUESIZE(skb_end_offset(skb)); delta_truesize = skb->truesize - new_truesize; skb->truesize = new_truesize; skb->len -= skb->data_len; skb->data_len = 0; NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE; goto done; } else if (skb->head_frag) { int nr_frags = pinfo->nr_frags; skb_frag_t *frag = pinfo->frags + nr_frags; struct page *page = virt_to_head_page(skb->head); unsigned int first_size = headlen - offset; unsigned int first_offset; if (nr_frags + 1 + skbinfo->nr_frags > MAX_SKB_FRAGS) goto merge; first_offset = skb->data - (unsigned char *)page_address(page) + offset; pinfo->nr_frags = nr_frags + 1 + skbinfo->nr_frags; __skb_frag_set_page(frag, page); skb_frag_off_set(frag, first_offset); skb_frag_size_set(frag, first_size); memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags); /* We dont need to clear skbinfo->nr_frags here */ new_truesize = SKB_DATA_ALIGN(sizeof(struct sk_buff)); delta_truesize = skb->truesize - new_truesize; skb->truesize = new_truesize; NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD; goto done; } merge: /* sk ownership - if any - completely transferred to the aggregated packet */ skb->destructor = NULL; skb->sk = NULL; delta_truesize = skb->truesize; if (offset > headlen) { unsigned int eat = offset - headlen; skb_frag_off_add(&skbinfo->frags[0], eat); skb_frag_size_sub(&skbinfo->frags[0], eat); skb->data_len -= eat; skb->len -= eat; offset = headlen; } __skb_pull(skb, offset); if (NAPI_GRO_CB(p)->last == p) skb_shinfo(p)->frag_list = skb; else NAPI_GRO_CB(p)->last->next = skb; NAPI_GRO_CB(p)->last = skb; __skb_header_release(skb); lp = p; done: NAPI_GRO_CB(p)->count += segs; p->data_len += len; p->truesize += delta_truesize; p->len += len; if (lp != p) { lp->data_len += len; lp->truesize += delta_truesize; lp->len += len; } NAPI_GRO_CB(skb)->same_flow = 1; return 0; } static void napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb) { struct packet_offload *ptype; __be16 type = skb->protocol; struct list_head *head = &offload_base; int err = -ENOENT; BUILD_BUG_ON(sizeof(struct napi_gro_cb) > sizeof(skb->cb)); if (NAPI_GRO_CB(skb)->count == 1) { skb_shinfo(skb)->gso_size = 0; goto out; } rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { if (ptype->type != type || !ptype->callbacks.gro_complete) continue; err = INDIRECT_CALL_INET(ptype->callbacks.gro_complete, ipv6_gro_complete, inet_gro_complete, skb, 0); break; } rcu_read_unlock(); if (err) { WARN_ON(&ptype->list == head); kfree_skb(skb); return; } out: gro_normal_one(napi, skb, NAPI_GRO_CB(skb)->count); } static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, bool flush_old) { struct list_head *head = &napi->gro_hash[index].list; struct sk_buff *skb, *p; list_for_each_entry_safe_reverse(skb, p, head, list) { if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) return; skb_list_del_init(skb); napi_gro_complete(napi, skb); napi->gro_hash[index].count--; } if (!napi->gro_hash[index].count) __clear_bit(index, &napi->gro_bitmask); } /* napi->gro_hash[].list contains packets ordered by age. * youngest packets at the head of it. * Complete skbs in reverse order to reduce latencies. */ void napi_gro_flush(struct napi_struct *napi, bool flush_old) { unsigned long bitmask = napi->gro_bitmask; unsigned int i, base = ~0U; while ((i = ffs(bitmask)) != 0) { bitmask >>= i; base += i; __napi_gro_flush_chain(napi, base, flush_old); } } EXPORT_SYMBOL(napi_gro_flush); static void gro_list_prepare(const struct list_head *head, const struct sk_buff *skb) { unsigned int maclen = skb->dev->hard_header_len; u32 hash = skb_get_hash_raw(skb); struct sk_buff *p; list_for_each_entry(p, head, list) { unsigned long diffs; NAPI_GRO_CB(p)->flush = 0; if (hash != skb_get_hash_raw(p)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; diffs |= skb_vlan_tag_present(p) ^ skb_vlan_tag_present(skb); if (skb_vlan_tag_present(p)) diffs |= skb_vlan_tag_get(p) ^ skb_vlan_tag_get(skb); diffs |= skb_metadata_differs(p, skb); if (maclen == ETH_HLEN) diffs |= compare_ether_header(skb_mac_header(p), skb_mac_header(skb)); else if (!diffs) diffs = memcmp(skb_mac_header(p), skb_mac_header(skb), maclen); /* in most common scenarions 'slow_gro' is 0 * otherwise we are already on some slower paths * either skip all the infrequent tests altogether or * avoid trying too hard to skip each of them individually */ if (!diffs && unlikely(skb->slow_gro | p->slow_gro)) { #if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT) struct tc_skb_ext *skb_ext; struct tc_skb_ext *p_ext; #endif diffs |= p->sk != skb->sk; diffs |= skb_metadata_dst_cmp(p, skb); diffs |= skb_get_nfct(p) ^ skb_get_nfct(skb); #if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT) skb_ext = skb_ext_find(skb, TC_SKB_EXT); p_ext = skb_ext_find(p, TC_SKB_EXT); diffs |= (!!p_ext) ^ (!!skb_ext); if (!diffs && unlikely(skb_ext)) diffs |= p_ext->chain ^ skb_ext->chain; #endif } NAPI_GRO_CB(p)->same_flow = !diffs; } } static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff) { const struct skb_shared_info *pinfo = skb_shinfo(skb); const skb_frag_t *frag0 = &pinfo->frags[0]; NAPI_GRO_CB(skb)->data_offset = 0; NAPI_GRO_CB(skb)->frag0 = NULL; NAPI_GRO_CB(skb)->frag0_len = 0; if (!skb_headlen(skb) && pinfo->nr_frags && !PageHighMem(skb_frag_page(frag0)) && (!NET_IP_ALIGN || !((skb_frag_off(frag0) + nhoff) & 3))) { NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int, skb_frag_size(frag0), skb->end - skb->tail); } } static void gro_pull_from_frag0(struct sk_buff *skb, int grow) { struct skb_shared_info *pinfo = skb_shinfo(skb); BUG_ON(skb->end - skb->tail < grow); memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow); skb->data_len -= grow; skb->tail += grow; skb_frag_off_add(&pinfo->frags[0], grow); skb_frag_size_sub(&pinfo->frags[0], grow); if (unlikely(!skb_frag_size(&pinfo->frags[0]))) { skb_frag_unref(skb, 0); memmove(pinfo->frags, pinfo->frags + 1, --pinfo->nr_frags * sizeof(pinfo->frags[0])); } } static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head) { struct sk_buff *oldest; oldest = list_last_entry(head, struct sk_buff, list); /* We are called with head length >= MAX_GRO_SKBS, so this is * impossible. */ if (WARN_ON_ONCE(!oldest)) return; /* Do not adjust napi->gro_hash[].count, caller is adding a new * SKB to the chain. */ skb_list_del_init(oldest); napi_gro_complete(napi, oldest); } static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { u32 bucket = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1); struct gro_list *gro_list = &napi->gro_hash[bucket]; struct list_head *head = &offload_base; struct packet_offload *ptype; __be16 type = skb->protocol; struct sk_buff *pp = NULL; enum gro_result ret; int same_flow; int grow; if (netif_elide_gro(skb->dev)) goto normal; gro_list_prepare(&gro_list->list, skb); rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { if (ptype->type == type && ptype->callbacks.gro_receive) goto found_ptype; } rcu_read_unlock(); goto normal; found_ptype: skb_set_network_header(skb, skb_gro_offset(skb)); skb_reset_mac_len(skb); BUILD_BUG_ON(sizeof_field(struct napi_gro_cb, zeroed) != sizeof(u32)); BUILD_BUG_ON(!IS_ALIGNED(offsetof(struct napi_gro_cb, zeroed), sizeof(u32))); /* Avoid slow unaligned acc */ *(u32 *)&NAPI_GRO_CB(skb)->zeroed = 0; NAPI_GRO_CB(skb)->flush = skb_has_frag_list(skb); NAPI_GRO_CB(skb)->is_atomic = 1; NAPI_GRO_CB(skb)->count = 1; if (unlikely(skb_is_gso(skb))) { NAPI_GRO_CB(skb)->count = skb_shinfo(skb)->gso_segs; /* Only support TCP and non DODGY users. */ if (!skb_is_gso_tcp(skb) || (skb_shinfo(skb)->gso_type & SKB_GSO_DODGY)) NAPI_GRO_CB(skb)->flush = 1; } /* Setup for GRO checksum validation */ switch (skb->ip_summed) { case CHECKSUM_COMPLETE: NAPI_GRO_CB(skb)->csum = skb->csum; NAPI_GRO_CB(skb)->csum_valid = 1; break; case CHECKSUM_UNNECESSARY: NAPI_GRO_CB(skb)->csum_cnt = skb->csum_level + 1; break; } pp = INDIRECT_CALL_INET(ptype->callbacks.gro_receive, ipv6_gro_receive, inet_gro_receive, &gro_list->list, skb); rcu_read_unlock(); if (PTR_ERR(pp) == -EINPROGRESS) { ret = GRO_CONSUMED; goto ok; } same_flow = NAPI_GRO_CB(skb)->same_flow; ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED; if (pp) { skb_list_del_init(pp); napi_gro_complete(napi, pp); gro_list->count--; } if (same_flow) goto ok; if (NAPI_GRO_CB(skb)->flush) goto normal; if (unlikely(gro_list->count >= MAX_GRO_SKBS)) gro_flush_oldest(napi, &gro_list->list); else gro_list->count++; NAPI_GRO_CB(skb)->age = jiffies; NAPI_GRO_CB(skb)->last = skb; if (!skb_is_gso(skb)) skb_shinfo(skb)->gso_size = skb_gro_len(skb); list_add(&skb->list, &gro_list->list); ret = GRO_HELD; pull: grow = skb_gro_offset(skb) - skb_headlen(skb); if (grow > 0) gro_pull_from_frag0(skb, grow); ok: if (gro_list->count) { if (!test_bit(bucket, &napi->gro_bitmask)) __set_bit(bucket, &napi->gro_bitmask); } else if (test_bit(bucket, &napi->gro_bitmask)) { __clear_bit(bucket, &napi->gro_bitmask); } return ret; normal: ret = GRO_NORMAL; goto pull; } struct packet_offload *gro_find_receive_by_type(__be16 type) { struct list_head *offload_head = &offload_base; struct packet_offload *ptype; list_for_each_entry_rcu(ptype, offload_head, list) { if (ptype->type != type || !ptype->callbacks.gro_receive) continue; return ptype; } return NULL; } EXPORT_SYMBOL(gro_find_receive_by_type); struct packet_offload *gro_find_complete_by_type(__be16 type) { struct list_head *offload_head = &offload_base; struct packet_offload *ptype; list_for_each_entry_rcu(ptype, offload_head, list) { if (ptype->type != type || !ptype->callbacks.gro_complete) continue; return ptype; } return NULL; } EXPORT_SYMBOL(gro_find_complete_by_type); static gro_result_t napi_skb_finish(struct napi_struct *napi, struct sk_buff *skb, gro_result_t ret) { switch (ret) { case GRO_NORMAL: gro_normal_one(napi, skb, 1); break; case GRO_MERGED_FREE: if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) napi_skb_free_stolen_head(skb); else if (skb->fclone != SKB_FCLONE_UNAVAILABLE) __kfree_skb(skb); else __kfree_skb_defer(skb); break; case GRO_HELD: case GRO_MERGED: case GRO_CONSUMED: break; } return ret; } gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { gro_result_t ret; skb_mark_napi_id(skb, napi); trace_napi_gro_receive_entry(skb); skb_gro_reset_offset(skb, 0); ret = napi_skb_finish(napi, skb, dev_gro_receive(napi, skb)); trace_napi_gro_receive_exit(ret); return ret; } EXPORT_SYMBOL(napi_gro_receive); static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) { if (unlikely(skb->pfmemalloc)) { consume_skb(skb); return; } __skb_pull(skb, skb_headlen(skb)); /* restore the reserve we had after netdev_alloc_skb_ip_align() */ skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN - skb_headroom(skb)); __vlan_hwaccel_clear_tag(skb); skb->dev = napi->dev; skb->skb_iif = 0; /* eth_type_trans() assumes pkt_type is PACKET_HOST */ skb->pkt_type = PACKET_HOST; skb->encapsulation = 0; skb->ip_summed = CHECKSUM_NONE; skb_shinfo(skb)->gso_type = 0; skb_shinfo(skb)->gso_size = 0; if (unlikely(skb->slow_gro)) { skb_orphan(skb); skb_ext_reset(skb); nf_reset_ct(skb); skb->slow_gro = 0; } napi->skb = skb; } struct sk_buff *napi_get_frags(struct napi_struct *napi) { struct sk_buff *skb = napi->skb; if (!skb) { skb = napi_alloc_skb(napi, GRO_MAX_HEAD); if (skb) { napi->skb = skb; skb_mark_napi_id(skb, napi); } } return skb; } EXPORT_SYMBOL(napi_get_frags); static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, gro_result_t ret) { switch (ret) { case GRO_NORMAL: case GRO_HELD: __skb_push(skb, ETH_HLEN); skb->protocol = eth_type_trans(skb, skb->dev); if (ret == GRO_NORMAL) gro_normal_one(napi, skb, 1); break; case GRO_MERGED_FREE: if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) napi_skb_free_stolen_head(skb); else napi_reuse_skb(napi, skb); break; case GRO_MERGED: case GRO_CONSUMED: break; } return ret; } /* Upper GRO stack assumes network header starts at gro_offset=0 * Drivers could call both napi_gro_frags() and napi_gro_receive() * We copy ethernet header into skb->data to have a common layout. */ static struct sk_buff *napi_frags_skb(struct napi_struct *napi) { struct sk_buff *skb = napi->skb; const struct ethhdr *eth; unsigned int hlen = sizeof(*eth); napi->skb = NULL; skb_reset_mac_header(skb); skb_gro_reset_offset(skb, hlen); if (unlikely(skb_gro_header_hard(skb, hlen))) { eth = skb_gro_header_slow(skb, hlen, 0); if (unlikely(!eth)) { net_warn_ratelimited("%s: dropping impossible skb from %s\n", __func__, napi->dev->name); napi_reuse_skb(napi, skb); return NULL; } } else { eth = (const struct ethhdr *)skb->data; gro_pull_from_frag0(skb, hlen); NAPI_GRO_CB(skb)->frag0 += hlen; NAPI_GRO_CB(skb)->frag0_len -= hlen; } __skb_pull(skb, hlen); /* * This works because the only protocols we care about don't require * special handling. * We'll fix it up properly in napi_frags_finish() */ skb->protocol = eth->h_proto; return skb; } gro_result_t napi_gro_frags(struct napi_struct *napi) { gro_result_t ret; struct sk_buff *skb = napi_frags_skb(napi); trace_napi_gro_frags_entry(skb); ret = napi_frags_finish(napi, skb, dev_gro_receive(napi, skb)); trace_napi_gro_frags_exit(ret); return ret; } EXPORT_SYMBOL(napi_gro_frags); /* Compute the checksum from gro_offset and return the folded value * after adding in any pseudo checksum. */ __sum16 __skb_gro_checksum_complete(struct sk_buff *skb) { __wsum wsum; __sum16 sum; wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb), 0); /* NAPI_GRO_CB(skb)->csum holds pseudo checksum */ sum = csum_fold(csum_add(NAPI_GRO_CB(skb)->csum, wsum)); /* See comments in __skb_checksum_complete(). */ if (likely(!sum)) { if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && !skb->csum_complete_sw) netdev_rx_csum_fault(skb->dev, skb); } NAPI_GRO_CB(skb)->csum = wsum; NAPI_GRO_CB(skb)->csum_valid = 1; return sum; } EXPORT_SYMBOL(__skb_gro_checksum_complete); |
| 3268 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PID_NS_H #define _LINUX_PID_NS_H #include <linux/sched.h> #include <linux/bug.h> #include <linux/mm.h> #include <linux/workqueue.h> #include <linux/threads.h> #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/idr.h> /* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */ #define MAX_PID_NS_LEVEL 32 struct fs_pin; struct pid_namespace { struct idr idr; struct rcu_head rcu; unsigned int pid_allocated; struct task_struct *child_reaper; struct kmem_cache *pid_cachep; unsigned int level; struct pid_namespace *parent; #ifdef CONFIG_BSD_PROCESS_ACCT struct fs_pin *bacct; #endif struct user_namespace *user_ns; struct ucounts *ucounts; int reboot; /* group exit code if this pidns was rebooted */ struct ns_common ns; } __randomize_layout; extern struct pid_namespace init_pid_ns; #define PIDNS_ADDING (1U << 31) #ifdef CONFIG_PID_NS static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns) { if (ns != &init_pid_ns) refcount_inc(&ns->ns.count); return ns; } extern struct pid_namespace *copy_pid_ns(unsigned long flags, struct user_namespace *user_ns, struct pid_namespace *ns); extern void zap_pid_ns_processes(struct pid_namespace *pid_ns); extern int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd); extern void put_pid_ns(struct pid_namespace *ns); #else /* !CONFIG_PID_NS */ #include <linux/err.h> static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns) { return ns; } static inline struct pid_namespace *copy_pid_ns(unsigned long flags, struct user_namespace *user_ns, struct pid_namespace *ns) { if (flags & CLONE_NEWPID) ns = ERR_PTR(-EINVAL); return ns; } static inline void put_pid_ns(struct pid_namespace *ns) { } static inline void zap_pid_ns_processes(struct pid_namespace *ns) { BUG(); } static inline int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd) { return 0; } #endif /* CONFIG_PID_NS */ extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk); void pidhash_init(void); void pid_idr_init(void); static inline bool task_is_in_init_pid_ns(struct task_struct *tsk) { return task_active_pid_ns(tsk) == &init_pid_ns; } #endif /* _LINUX_PID_NS_H */ |
| 2281 1062 1062 1373 1677 1959 1960 1921 60 1373 671 1676 1677 1675 1645 31 1677 544 543 407 192 542 3 151 153 265 264 265 265 1880 109 1649 402 133 290 1960 1713 345 1857 154 1960 1964 1644 404 1649 400 1963 1963 3 3 2085 2085 1882 255 427 543 10 423 1960 1962 1646 404 3 3749 2977 1266 1759 1738 3779 2519 2994 569 12 92 92 530 1 49 49 12 60 49 12 28 3 25 319 319 2 2 2 2 2 2 2 2 2 2 2 2 2 157 155 2 7942 353 7882 118 7948 271 1359 351 2 2 7440 7441 7946 7950 7946 1005 7914 7909 14 7716 733 7920 7600 1060 7882 351 7917 534 6790 232 2434 1037 7436 7869 7701 7706 7699 7703 7700 7700 7695 7700 755 13 13 13 3 2114 2115 13 1207 310 1676 1580 1580 669 1208 1750 1750 1267 285 1220 31 31 1307 1307 1303 1303 1129 1130 1130 1 1173 1173 1173 3 1173 1 1 1 1 1 1 1173 1174 1174 1173 1174 128 1307 258 1128 838 645 644 645 259 1130 837 645 658 659 734 194 444 485 319 319 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/dcache.c * * Complete reimplementation * (C) 1997 Thomas Schoebel-Theuer, * with heavy changes by Linus Torvalds */ /* * Notes on the allocation strategy: * * The dcache is a master of the icache - whenever a dcache entry * exists, the inode will always exist. "iput()" is done either when * the dcache entry is deleted or garbage collected. */ #include <linux/ratelimit.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/fs.h> #include <linux/fscrypt.h> #include <linux/fsnotify.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/hash.h> #include <linux/cache.h> #include <linux/export.h> #include <linux/security.h> #include <linux/seqlock.h> #include <linux/memblock.h> #include <linux/bit_spinlock.h> #include <linux/rculist_bl.h> #include <linux/list_lru.h> #include "internal.h" #include "mount.h" /* * Usage: * dcache->d_inode->i_lock protects: * - i_dentry, d_u.d_alias, d_inode of aliases * dcache_hash_bucket lock protects: * - the dcache hash table * s_roots bl list spinlock protects: * - the s_roots list (see __d_drop) * dentry->d_sb->s_dentry_lru_lock protects: * - the dcache lru lists and counters * d_lock protects: * - d_flags * - d_name * - d_lru * - d_count * - d_unhashed() * - d_parent and d_subdirs * - childrens' d_child and d_parent * - d_u.d_alias, d_inode * * Ordering: * dentry->d_inode->i_lock * dentry->d_lock * dentry->d_sb->s_dentry_lru_lock * dcache_hash_bucket lock * s_roots lock * * If there is an ancestor relationship: * dentry->d_parent->...->d_parent->d_lock * ... * dentry->d_parent->d_lock * dentry->d_lock * * If no ancestor relationship: * arbitrary, since it's serialized on rename_lock */ int sysctl_vfs_cache_pressure __read_mostly = 100; EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure); __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock); EXPORT_SYMBOL(rename_lock); static struct kmem_cache *dentry_cache __read_mostly; const struct qstr empty_name = QSTR_INIT("", 0); EXPORT_SYMBOL(empty_name); const struct qstr slash_name = QSTR_INIT("/", 1); EXPORT_SYMBOL(slash_name); const struct qstr dotdot_name = QSTR_INIT("..", 2); EXPORT_SYMBOL(dotdot_name); /* * This is the single most critical data structure when it comes * to the dcache: the hashtable for lookups. Somebody should try * to make this good - I've just made it work. * * This hash-function tries to avoid losing too many bits of hash * information, yet avoid using a prime hash-size or similar. */ static unsigned int d_hash_shift __read_mostly; static struct hlist_bl_head *dentry_hashtable __read_mostly; static inline struct hlist_bl_head *d_hash(unsigned int hash) { return dentry_hashtable + (hash >> d_hash_shift); } #define IN_LOOKUP_SHIFT 10 static struct hlist_bl_head in_lookup_hashtable[1 << IN_LOOKUP_SHIFT]; static inline struct hlist_bl_head *in_lookup_hash(const struct dentry *parent, unsigned int hash) { hash += (unsigned long) parent / L1_CACHE_BYTES; return in_lookup_hashtable + hash_32(hash, IN_LOOKUP_SHIFT); } struct dentry_stat_t { long nr_dentry; long nr_unused; long age_limit; /* age in seconds */ long want_pages; /* pages requested by system */ long nr_negative; /* # of unused negative dentries */ long dummy; /* Reserved for future use */ }; static DEFINE_PER_CPU(long, nr_dentry); static DEFINE_PER_CPU(long, nr_dentry_unused); static DEFINE_PER_CPU(long, nr_dentry_negative); #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) /* Statistics gathering. */ static struct dentry_stat_t dentry_stat = { .age_limit = 45, }; /* * Here we resort to our own counters instead of using generic per-cpu counters * for consistency with what the vfs inode code does. We are expected to harvest * better code and performance by having our own specialized counters. * * Please note that the loop is done over all possible CPUs, not over all online * CPUs. The reason for this is that we don't want to play games with CPUs going * on and off. If one of them goes off, we will just keep their counters. * * glommer: See cffbc8a for details, and if you ever intend to change this, * please update all vfs counters to match. */ static long get_nr_dentry(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry, i); return sum < 0 ? 0 : sum; } static long get_nr_dentry_unused(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry_unused, i); return sum < 0 ? 0 : sum; } static long get_nr_dentry_negative(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry_negative, i); return sum < 0 ? 0 : sum; } static int proc_nr_dentry(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { dentry_stat.nr_dentry = get_nr_dentry(); dentry_stat.nr_unused = get_nr_dentry_unused(); dentry_stat.nr_negative = get_nr_dentry_negative(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static struct ctl_table fs_dcache_sysctls[] = { { .procname = "dentry-state", .data = &dentry_stat, .maxlen = 6*sizeof(long), .mode = 0444, .proc_handler = proc_nr_dentry, }, { } }; static int __init init_fs_dcache_sysctls(void) { register_sysctl_init("fs", fs_dcache_sysctls); return 0; } fs_initcall(init_fs_dcache_sysctls); #endif /* * Compare 2 name strings, return 0 if they match, otherwise non-zero. * The strings are both count bytes long, and count is non-zero. */ #ifdef CONFIG_DCACHE_WORD_ACCESS #include <asm/word-at-a-time.h> /* * NOTE! 'cs' and 'scount' come from a dentry, so it has a * aligned allocation for this particular component. We don't * strictly need the load_unaligned_zeropad() safety, but it * doesn't hurt either. * * In contrast, 'ct' and 'tcount' can be from a pathname, and do * need the careful unaligned handling. */ static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) { unsigned long a,b,mask; for (;;) { a = read_word_at_a_time(cs); b = load_unaligned_zeropad(ct); if (tcount < sizeof(unsigned long)) break; if (unlikely(a != b)) return 1; cs += sizeof(unsigned long); ct += sizeof(unsigned long); tcount -= sizeof(unsigned long); if (!tcount) return 0; } mask = bytemask_from_count(tcount); return unlikely(!!((a ^ b) & mask)); } #else static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) { do { if (*cs != *ct) return 1; cs++; ct++; tcount--; } while (tcount); return 0; } #endif static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *ct, unsigned tcount) { /* * Be careful about RCU walk racing with rename: * use 'READ_ONCE' to fetch the name pointer. * * NOTE! Even if a rename will mean that the length * was not loaded atomically, we don't care. The * RCU walk will check the sequence count eventually, * and catch it. And we won't overrun the buffer, * because we're reading the name pointer atomically, * and a dentry name is guaranteed to be properly * terminated with a NUL byte. * * End result: even if 'len' is wrong, we'll exit * early because the data cannot match (there can * be no NUL in the ct/tcount data) */ const unsigned char *cs = READ_ONCE(dentry->d_name.name); return dentry_string_cmp(cs, ct, tcount); } struct external_name { union { atomic_t count; struct rcu_head head; } u; unsigned char name[]; }; static inline struct external_name *external_name(struct dentry *dentry) { return container_of(dentry->d_name.name, struct external_name, name[0]); } static void __d_free(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); kmem_cache_free(dentry_cache, dentry); } static void __d_free_external(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); kfree(external_name(dentry)); kmem_cache_free(dentry_cache, dentry); } static inline int dname_external(const struct dentry *dentry) { return dentry->d_name.name != dentry->d_iname; } void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry) { spin_lock(&dentry->d_lock); name->name = dentry->d_name; if (unlikely(dname_external(dentry))) { atomic_inc(&external_name(dentry)->u.count); } else { memcpy(name->inline_name, dentry->d_iname, dentry->d_name.len + 1); name->name.name = name->inline_name; } spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(take_dentry_name_snapshot); void release_dentry_name_snapshot(struct name_snapshot *name) { if (unlikely(name->name.name != name->inline_name)) { struct external_name *p; p = container_of(name->name.name, struct external_name, name[0]); if (unlikely(atomic_dec_and_test(&p->u.count))) kfree_rcu(p, u.head); } } EXPORT_SYMBOL(release_dentry_name_snapshot); static inline void __d_set_inode_and_type(struct dentry *dentry, struct inode *inode, unsigned type_flags) { unsigned flags; dentry->d_inode = inode; flags = READ_ONCE(dentry->d_flags); flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); flags |= type_flags; smp_store_release(&dentry->d_flags, flags); } static inline void __d_clear_type_and_inode(struct dentry *dentry) { unsigned flags = READ_ONCE(dentry->d_flags); flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); WRITE_ONCE(dentry->d_flags, flags); dentry->d_inode = NULL; /* * The negative counter only tracks dentries on the LRU. Don't inc if * d_lru is on another list. */ if ((flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_inc(nr_dentry_negative); } static void dentry_free(struct dentry *dentry) { WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias)); if (unlikely(dname_external(dentry))) { struct external_name *p = external_name(dentry); if (likely(atomic_dec_and_test(&p->u.count))) { call_rcu(&dentry->d_u.d_rcu, __d_free_external); return; } } /* if dentry was never visible to RCU, immediate free is OK */ if (dentry->d_flags & DCACHE_NORCU) __d_free(&dentry->d_u.d_rcu); else call_rcu(&dentry->d_u.d_rcu, __d_free); } /* * Release the dentry's inode, using the filesystem * d_iput() operation if defined. */ static void dentry_unlink_inode(struct dentry * dentry) __releases(dentry->d_lock) __releases(dentry->d_inode->i_lock) { struct inode *inode = dentry->d_inode; raw_write_seqcount_begin(&dentry->d_seq); __d_clear_type_and_inode(dentry); hlist_del_init(&dentry->d_u.d_alias); raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) fsnotify_inoderemove(inode); if (dentry->d_op && dentry->d_op->d_iput) dentry->d_op->d_iput(dentry, inode); else iput(inode); } /* * The DCACHE_LRU_LIST bit is set whenever the 'd_lru' entry * is in use - which includes both the "real" per-superblock * LRU list _and_ the DCACHE_SHRINK_LIST use. * * The DCACHE_SHRINK_LIST bit is set whenever the dentry is * on the shrink list (ie not on the superblock LRU list). * * The per-cpu "nr_dentry_unused" counters are updated with * the DCACHE_LRU_LIST bit. * * The per-cpu "nr_dentry_negative" counters are only updated * when deleted from or added to the per-superblock LRU list, not * from/to the shrink list. That is to avoid an unneeded dec/inc * pair when moving from LRU to shrink list in select_collect(). * * These helper functions make sure we always follow the * rules. d_lock must be held by the caller. */ #define D_FLAG_VERIFY(dentry,x) WARN_ON_ONCE(((dentry)->d_flags & (DCACHE_LRU_LIST | DCACHE_SHRINK_LIST)) != (x)) static void d_lru_add(struct dentry *dentry) { D_FLAG_VERIFY(dentry, 0); dentry->d_flags |= DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_inc(nr_dentry_negative); WARN_ON_ONCE(!list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } static void d_lru_del(struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); WARN_ON_ONCE(!list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } static void d_shrink_del(struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_SHRINK_LIST | DCACHE_LRU_LIST); list_del_init(&dentry->d_lru); dentry->d_flags &= ~(DCACHE_SHRINK_LIST | DCACHE_LRU_LIST); this_cpu_dec(nr_dentry_unused); } static void d_shrink_add(struct dentry *dentry, struct list_head *list) { D_FLAG_VERIFY(dentry, 0); list_add(&dentry->d_lru, list); dentry->d_flags |= DCACHE_SHRINK_LIST | DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); } /* * These can only be called under the global LRU lock, ie during the * callback for freeing the LRU list. "isolate" removes it from the * LRU lists entirely, while shrink_move moves it to the indicated * private list. */ static void d_lru_isolate(struct list_lru_one *lru, struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); list_lru_isolate(lru, &dentry->d_lru); } static void d_lru_shrink_move(struct list_lru_one *lru, struct dentry *dentry, struct list_head *list) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags |= DCACHE_SHRINK_LIST; if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); list_lru_isolate_move(lru, &dentry->d_lru, list); } static void ___d_drop(struct dentry *dentry) { struct hlist_bl_head *b; /* * Hashed dentries are normally on the dentry hashtable, * with the exception of those newly allocated by * d_obtain_root, which are always IS_ROOT: */ if (unlikely(IS_ROOT(dentry))) b = &dentry->d_sb->s_roots; else b = d_hash(dentry->d_name.hash); hlist_bl_lock(b); __hlist_bl_del(&dentry->d_hash); hlist_bl_unlock(b); } void __d_drop(struct dentry *dentry) { if (!d_unhashed(dentry)) { ___d_drop(dentry); dentry->d_hash.pprev = NULL; write_seqcount_invalidate(&dentry->d_seq); } } EXPORT_SYMBOL(__d_drop); /** * d_drop - drop a dentry * @dentry: dentry to drop * * d_drop() unhashes the entry from the parent dentry hashes, so that it won't * be found through a VFS lookup any more. Note that this is different from * deleting the dentry - d_delete will try to mark the dentry negative if * possible, giving a successful _negative_ lookup, while d_drop will * just make the cache lookup fail. * * d_drop() is used mainly for stuff that wants to invalidate a dentry for some * reason (NFS timeouts or autofs deletes). * * __d_drop requires dentry->d_lock * * ___d_drop doesn't mark dentry as "unhashed" * (dentry->d_hash.pprev will be LIST_POISON2, not NULL). */ void d_drop(struct dentry *dentry) { spin_lock(&dentry->d_lock); __d_drop(dentry); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(d_drop); static inline void dentry_unlist(struct dentry *dentry, struct dentry *parent) { struct dentry *next; /* * Inform d_walk() and shrink_dentry_list() that we are no longer * attached to the dentry tree */ dentry->d_flags |= DCACHE_DENTRY_KILLED; if (unlikely(list_empty(&dentry->d_child))) return; __list_del_entry(&dentry->d_child); /* * Cursors can move around the list of children. While we'd been * a normal list member, it didn't matter - ->d_child.next would've * been updated. However, from now on it won't be and for the * things like d_walk() it might end up with a nasty surprise. * Normally d_walk() doesn't care about cursors moving around - * ->d_lock on parent prevents that and since a cursor has no children * of its own, we get through it without ever unlocking the parent. * There is one exception, though - if we ascend from a child that * gets killed as soon as we unlock it, the next sibling is found * using the value left in its ->d_child.next. And if _that_ * pointed to a cursor, and cursor got moved (e.g. by lseek()) * before d_walk() regains parent->d_lock, we'll end up skipping * everything the cursor had been moved past. * * Solution: make sure that the pointer left behind in ->d_child.next * points to something that won't be moving around. I.e. skip the * cursors. */ while (dentry->d_child.next != &parent->d_subdirs) { next = list_entry(dentry->d_child.next, struct dentry, d_child); if (likely(!(next->d_flags & DCACHE_DENTRY_CURSOR))) break; dentry->d_child.next = next->d_child.next; } } static void __dentry_kill(struct dentry *dentry) { struct dentry *parent = NULL; bool can_free = true; if (!IS_ROOT(dentry)) parent = dentry->d_parent; /* * The dentry is now unrecoverably dead to the world. */ lockref_mark_dead(&dentry->d_lockref); /* * inform the fs via d_prune that this dentry is about to be * unhashed and destroyed. */ if (dentry->d_flags & DCACHE_OP_PRUNE) dentry->d_op->d_prune(dentry); if (dentry->d_flags & DCACHE_LRU_LIST) { if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) d_lru_del(dentry); } /* if it was on the hash then remove it */ __d_drop(dentry); dentry_unlist(dentry, parent); if (parent) spin_unlock(&parent->d_lock); if (dentry->d_inode) dentry_unlink_inode(dentry); else spin_unlock(&dentry->d_lock); this_cpu_dec(nr_dentry); if (dentry->d_op && dentry->d_op->d_release) dentry->d_op->d_release(dentry); spin_lock(&dentry->d_lock); if (dentry->d_flags & DCACHE_SHRINK_LIST) { dentry->d_flags |= DCACHE_MAY_FREE; can_free = false; } spin_unlock(&dentry->d_lock); if (likely(can_free)) dentry_free(dentry); cond_resched(); } static struct dentry *__lock_parent(struct dentry *dentry) { struct dentry *parent; rcu_read_lock(); spin_unlock(&dentry->d_lock); again: parent = READ_ONCE(dentry->d_parent); spin_lock(&parent->d_lock); /* * We can't blindly lock dentry until we are sure * that we won't violate the locking order. * Any changes of dentry->d_parent must have * been done with parent->d_lock held, so * spin_lock() above is enough of a barrier * for checking if it's still our child. */ if (unlikely(parent != dentry->d_parent)) { spin_unlock(&parent->d_lock); goto again; } rcu_read_unlock(); if (parent != dentry) spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); else parent = NULL; return parent; } static inline struct dentry *lock_parent(struct dentry *dentry) { struct dentry *parent = dentry->d_parent; if (IS_ROOT(dentry)) return NULL; if (likely(spin_trylock(&parent->d_lock))) return parent; return __lock_parent(dentry); } static inline bool retain_dentry(struct dentry *dentry) { WARN_ON(d_in_lookup(dentry)); /* Unreachable? Get rid of it */ if (unlikely(d_unhashed(dentry))) return false; if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED)) return false; if (unlikely(dentry->d_flags & DCACHE_OP_DELETE)) { if (dentry->d_op->d_delete(dentry)) return false; } if (unlikely(dentry->d_flags & DCACHE_DONTCACHE)) return false; /* retain; LRU fodder */ dentry->d_lockref.count--; if (unlikely(!(dentry->d_flags & DCACHE_LRU_LIST))) d_lru_add(dentry); else if (unlikely(!(dentry->d_flags & DCACHE_REFERENCED))) dentry->d_flags |= DCACHE_REFERENCED; return true; } void d_mark_dontcache(struct inode *inode) { struct dentry *de; spin_lock(&inode->i_lock); hlist_for_each_entry(de, &inode->i_dentry, d_u.d_alias) { spin_lock(&de->d_lock); de->d_flags |= DCACHE_DONTCACHE; spin_unlock(&de->d_lock); } inode->i_state |= I_DONTCACHE; spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_mark_dontcache); /* * Finish off a dentry we've decided to kill. * dentry->d_lock must be held, returns with it unlocked. * Returns dentry requiring refcount drop, or NULL if we're done. */ static struct dentry *dentry_kill(struct dentry *dentry) __releases(dentry->d_lock) { struct inode *inode = dentry->d_inode; struct dentry *parent = NULL; if (inode && unlikely(!spin_trylock(&inode->i_lock))) goto slow_positive; if (!IS_ROOT(dentry)) { parent = dentry->d_parent; if (unlikely(!spin_trylock(&parent->d_lock))) { parent = __lock_parent(dentry); if (likely(inode || !dentry->d_inode)) goto got_locks; /* negative that became positive */ if (parent) spin_unlock(&parent->d_lock); inode = dentry->d_inode; goto slow_positive; } } __dentry_kill(dentry); return parent; slow_positive: spin_unlock(&dentry->d_lock); spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); parent = lock_parent(dentry); got_locks: if (unlikely(dentry->d_lockref.count != 1)) { dentry->d_lockref.count--; } else if (likely(!retain_dentry(dentry))) { __dentry_kill(dentry); return parent; } /* we are keeping it, after all */ if (inode) spin_unlock(&inode->i_lock); if (parent) spin_unlock(&parent->d_lock); spin_unlock(&dentry->d_lock); return NULL; } /* * Try to do a lockless dput(), and return whether that was successful. * * If unsuccessful, we return false, having already taken the dentry lock. * * The caller needs to hold the RCU read lock, so that the dentry is * guaranteed to stay around even if the refcount goes down to zero! */ static inline bool fast_dput(struct dentry *dentry) { int ret; unsigned int d_flags; /* * If we have a d_op->d_delete() operation, we sould not * let the dentry count go to zero, so use "put_or_lock". */ if (unlikely(dentry->d_flags & DCACHE_OP_DELETE)) return lockref_put_or_lock(&dentry->d_lockref); /* * .. otherwise, we can try to just decrement the * lockref optimistically. */ ret = lockref_put_return(&dentry->d_lockref); /* * If the lockref_put_return() failed due to the lock being held * by somebody else, the fast path has failed. We will need to * get the lock, and then check the count again. */ if (unlikely(ret < 0)) { spin_lock(&dentry->d_lock); if (WARN_ON_ONCE(dentry->d_lockref.count <= 0)) { spin_unlock(&dentry->d_lock); return true; } dentry->d_lockref.count--; goto locked; } /* * If we weren't the last ref, we're done. */ if (ret) return true; /* * Careful, careful. The reference count went down * to zero, but we don't hold the dentry lock, so * somebody else could get it again, and do another * dput(), and we need to not race with that. * * However, there is a very special and common case * where we don't care, because there is nothing to * do: the dentry is still hashed, it does not have * a 'delete' op, and it's referenced and already on * the LRU list. * * NOTE! Since we aren't locked, these values are * not "stable". However, it is sufficient that at * some point after we dropped the reference the * dentry was hashed and the flags had the proper * value. Other dentry users may have re-gotten * a reference to the dentry and change that, but * our work is done - we can leave the dentry * around with a zero refcount. * * Nevertheless, there are two cases that we should kill * the dentry anyway. * 1. free disconnected dentries as soon as their refcount * reached zero. * 2. free dentries if they should not be cached. */ smp_rmb(); d_flags = READ_ONCE(dentry->d_flags); d_flags &= DCACHE_REFERENCED | DCACHE_LRU_LIST | DCACHE_DISCONNECTED | DCACHE_DONTCACHE; /* Nothing to do? Dropping the reference was all we needed? */ if (d_flags == (DCACHE_REFERENCED | DCACHE_LRU_LIST) && !d_unhashed(dentry)) return true; /* * Not the fast normal case? Get the lock. We've already decremented * the refcount, but we'll need to re-check the situation after * getting the lock. */ spin_lock(&dentry->d_lock); /* * Did somebody else grab a reference to it in the meantime, and * we're no longer the last user after all? Alternatively, somebody * else could have killed it and marked it dead. Either way, we * don't need to do anything else. */ locked: if (dentry->d_lockref.count) { spin_unlock(&dentry->d_lock); return true; } /* * Re-get the reference we optimistically dropped. We hold the * lock, and we just tested that it was zero, so we can just * set it to 1. */ dentry->d_lockref.count = 1; return false; } /* * This is dput * * This is complicated by the fact that we do not want to put * dentries that are no longer on any hash chain on the unused * list: we'd much rather just get rid of them immediately. * * However, that implies that we have to traverse the dentry * tree upwards to the parents which might _also_ now be * scheduled for deletion (it may have been only waiting for * its last child to go away). * * This tail recursion is done by hand as we don't want to depend * on the compiler to always get this right (gcc generally doesn't). * Real recursion would eat up our stack space. */ /* * dput - release a dentry * @dentry: dentry to release * * Release a dentry. This will drop the usage count and if appropriate * call the dentry unlink method as well as removing it from the queues and * releasing its resources. If the parent dentries were scheduled for release * they too may now get deleted. */ void dput(struct dentry *dentry) { while (dentry) { might_sleep(); rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); return; } /* Slow case: now with the dentry lock held */ rcu_read_unlock(); if (likely(retain_dentry(dentry))) { spin_unlock(&dentry->d_lock); return; } dentry = dentry_kill(dentry); } } EXPORT_SYMBOL(dput); static void __dput_to_list(struct dentry *dentry, struct list_head *list) __must_hold(&dentry->d_lock) { if (dentry->d_flags & DCACHE_SHRINK_LIST) { /* let the owner of the list it's on deal with it */ --dentry->d_lockref.count; } else { if (dentry->d_flags & DCACHE_LRU_LIST) d_lru_del(dentry); if (!--dentry->d_lockref.count) d_shrink_add(dentry, list); } } void dput_to_list(struct dentry *dentry, struct list_head *list) { rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); return; } rcu_read_unlock(); if (!retain_dentry(dentry)) __dput_to_list(dentry, list); spin_unlock(&dentry->d_lock); } /* This must be called with d_lock held */ static inline void __dget_dlock(struct dentry *dentry) { dentry->d_lockref.count++; } static inline void __dget(struct dentry *dentry) { lockref_get(&dentry->d_lockref); } struct dentry *dget_parent(struct dentry *dentry) { int gotref; struct dentry *ret; unsigned seq; /* * Do optimistic parent lookup without any * locking. */ rcu_read_lock(); seq = raw_seqcount_begin(&dentry->d_seq); ret = READ_ONCE(dentry->d_parent); gotref = lockref_get_not_zero(&ret->d_lockref); rcu_read_unlock(); if (likely(gotref)) { if (!read_seqcount_retry(&dentry->d_seq, seq)) return ret; dput(ret); } repeat: /* * Don't need rcu_dereference because we re-check it was correct under * the lock. */ rcu_read_lock(); ret = dentry->d_parent; spin_lock(&ret->d_lock); if (unlikely(ret != dentry->d_parent)) { spin_unlock(&ret->d_lock); rcu_read_unlock(); goto repeat; } rcu_read_unlock(); BUG_ON(!ret->d_lockref.count); ret->d_lockref.count++; spin_unlock(&ret->d_lock); return ret; } EXPORT_SYMBOL(dget_parent); static struct dentry * __d_find_any_alias(struct inode *inode) { struct dentry *alias; if (hlist_empty(&inode->i_dentry)) return NULL; alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); __dget(alias); return alias; } /** * d_find_any_alias - find any alias for a given inode * @inode: inode to find an alias for * * If any aliases exist for the given inode, take and return a * reference for one of them. If no aliases exist, return %NULL. */ struct dentry *d_find_any_alias(struct inode *inode) { struct dentry *de; spin_lock(&inode->i_lock); de = __d_find_any_alias(inode); spin_unlock(&inode->i_lock); return de; } EXPORT_SYMBOL(d_find_any_alias); static struct dentry *__d_find_alias(struct inode *inode) { struct dentry *alias; if (S_ISDIR(inode->i_mode)) return __d_find_any_alias(inode); hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { spin_lock(&alias->d_lock); if (!d_unhashed(alias)) { __dget_dlock(alias); spin_unlock(&alias->d_lock); return alias; } spin_unlock(&alias->d_lock); } return NULL; } /** * d_find_alias - grab a hashed alias of inode * @inode: inode in question * * If inode has a hashed alias, or is a directory and has any alias, * acquire the reference to alias and return it. Otherwise return NULL. * Notice that if inode is a directory there can be only one alias and * it can be unhashed only if it has no children, or if it is the root * of a filesystem, or if the directory was renamed and d_revalidate * was the first vfs operation to notice. * * If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer * any other hashed alias over that one. */ struct dentry *d_find_alias(struct inode *inode) { struct dentry *de = NULL; if (!hlist_empty(&inode->i_dentry)) { spin_lock(&inode->i_lock); de = __d_find_alias(inode); spin_unlock(&inode->i_lock); } return de; } EXPORT_SYMBOL(d_find_alias); /* * Caller MUST be holding rcu_read_lock() and be guaranteed * that inode won't get freed until rcu_read_unlock(). */ struct dentry *d_find_alias_rcu(struct inode *inode) { struct hlist_head *l = &inode->i_dentry; struct dentry *de = NULL; spin_lock(&inode->i_lock); // ->i_dentry and ->i_rcu are colocated, but the latter won't be // used without having I_FREEING set, which means no aliases left if (likely(!(inode->i_state & I_FREEING) && !hlist_empty(l))) { if (S_ISDIR(inode->i_mode)) { de = hlist_entry(l->first, struct dentry, d_u.d_alias); } else { hlist_for_each_entry(de, l, d_u.d_alias) if (!d_unhashed(de)) break; } } spin_unlock(&inode->i_lock); return de; } /* * Try to kill dentries associated with this inode. * WARNING: you must own a reference to inode. */ void d_prune_aliases(struct inode *inode) { struct dentry *dentry; restart: spin_lock(&inode->i_lock); hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { spin_lock(&dentry->d_lock); if (!dentry->d_lockref.count) { struct dentry *parent = lock_parent(dentry); if (likely(!dentry->d_lockref.count)) { __dentry_kill(dentry); dput(parent); goto restart; } if (parent) spin_unlock(&parent->d_lock); } spin_unlock(&dentry->d_lock); } spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_prune_aliases); /* * Lock a dentry from shrink list. * Called under rcu_read_lock() and dentry->d_lock; the former * guarantees that nothing we access will be freed under us. * Note that dentry is *not* protected from concurrent dentry_kill(), * d_delete(), etc. * * Return false if dentry has been disrupted or grabbed, leaving * the caller to kick it off-list. Otherwise, return true and have * that dentry's inode and parent both locked. */ static bool shrink_lock_dentry(struct dentry *dentry) { struct inode *inode; struct dentry *parent; if (dentry->d_lockref.count) return false; inode = dentry->d_inode; if (inode && unlikely(!spin_trylock(&inode->i_lock))) { spin_unlock(&dentry->d_lock); spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); if (unlikely(dentry->d_lockref.count)) goto out; /* changed inode means that somebody had grabbed it */ if (unlikely(inode != dentry->d_inode)) goto out; } parent = dentry->d_parent; if (IS_ROOT(dentry) || likely(spin_trylock(&parent->d_lock))) return true; spin_unlock(&dentry->d_lock); spin_lock(&parent->d_lock); if (unlikely(parent != dentry->d_parent)) { spin_unlock(&parent->d_lock); spin_lock(&dentry->d_lock); goto out; } spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); if (likely(!dentry->d_lockref.count)) return true; spin_unlock(&parent->d_lock); out: if (inode) spin_unlock(&inode->i_lock); return false; } void shrink_dentry_list(struct list_head *list) { while (!list_empty(list)) { struct dentry *dentry, *parent; dentry = list_entry(list->prev, struct dentry, d_lru); spin_lock(&dentry->d_lock); rcu_read_lock(); if (!shrink_lock_dentry(dentry)) { bool can_free = false; rcu_read_unlock(); d_shrink_del(dentry); if (dentry->d_lockref.count < 0) can_free = dentry->d_flags & DCACHE_MAY_FREE; spin_unlock(&dentry->d_lock); if (can_free) dentry_free(dentry); continue; } rcu_read_unlock(); d_shrink_del(dentry); parent = dentry->d_parent; if (parent != dentry) __dput_to_list(parent, list); __dentry_kill(dentry); } } static enum lru_status dentry_lru_isolate(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); /* * we are inverting the lru lock/dentry->d_lock here, * so use a trylock. If we fail to get the lock, just skip * it */ if (!spin_trylock(&dentry->d_lock)) return LRU_SKIP; /* * Referenced dentries are still in use. If they have active * counts, just remove them from the LRU. Otherwise give them * another pass through the LRU. */ if (dentry->d_lockref.count) { d_lru_isolate(lru, dentry); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } if (dentry->d_flags & DCACHE_REFERENCED) { dentry->d_flags &= ~DCACHE_REFERENCED; spin_unlock(&dentry->d_lock); /* * The list move itself will be made by the common LRU code. At * this point, we've dropped the dentry->d_lock but keep the * lru lock. This is safe to do, since every list movement is * protected by the lru lock even if both locks are held. * * This is guaranteed by the fact that all LRU management * functions are intermediated by the LRU API calls like * list_lru_add and list_lru_del. List movement in this file * only ever occur through this functions or through callbacks * like this one, that are called from the LRU API. * * The only exceptions to this are functions like * shrink_dentry_list, and code that first checks for the * DCACHE_SHRINK_LIST flag. Those are guaranteed to be * operating only with stack provided lists after they are * properly isolated from the main list. It is thus, always a * local access. */ return LRU_ROTATE; } d_lru_shrink_move(lru, dentry, freeable); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } /** * prune_dcache_sb - shrink the dcache * @sb: superblock * @sc: shrink control, passed to list_lru_shrink_walk() * * Attempt to shrink the superblock dcache LRU by @sc->nr_to_scan entries. This * is done when we need more memory and called from the superblock shrinker * function. * * This function may fail to free any resources if all the dentries are in * use. */ long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc) { LIST_HEAD(dispose); long freed; freed = list_lru_shrink_walk(&sb->s_dentry_lru, sc, dentry_lru_isolate, &dispose); shrink_dentry_list(&dispose); return freed; } static enum lru_status dentry_lru_isolate_shrink(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); /* * we are inverting the lru lock/dentry->d_lock here, * so use a trylock. If we fail to get the lock, just skip * it */ if (!spin_trylock(&dentry->d_lock)) return LRU_SKIP; d_lru_shrink_move(lru, dentry, freeable); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } /** * shrink_dcache_sb - shrink dcache for a superblock * @sb: superblock * * Shrink the dcache for the specified super block. This is used to free * the dcache before unmounting a file system. */ void shrink_dcache_sb(struct super_block *sb) { do { LIST_HEAD(dispose); list_lru_walk(&sb->s_dentry_lru, dentry_lru_isolate_shrink, &dispose, 1024); shrink_dentry_list(&dispose); } while (list_lru_count(&sb->s_dentry_lru) > 0); } EXPORT_SYMBOL(shrink_dcache_sb); /** * enum d_walk_ret - action to talke during tree walk * @D_WALK_CONTINUE: contrinue walk * @D_WALK_QUIT: quit walk * @D_WALK_NORETRY: quit when retry is needed * @D_WALK_SKIP: skip this dentry and its children */ enum d_walk_ret { D_WALK_CONTINUE, D_WALK_QUIT, D_WALK_NORETRY, D_WALK_SKIP, }; /** * d_walk - walk the dentry tree * @parent: start of walk * @data: data passed to @enter() and @finish() * @enter: callback when first entering the dentry * * The @enter() callbacks are called with d_lock held. */ static void d_walk(struct dentry *parent, void *data, enum d_walk_ret (*enter)(void *, struct dentry *)) { struct dentry *this_parent; struct list_head *next; unsigned seq = 0; enum d_walk_ret ret; bool retry = true; again: read_seqbegin_or_lock(&rename_lock, &seq); this_parent = parent; spin_lock(&this_parent->d_lock); ret = enter(data, this_parent); switch (ret) { case D_WALK_CONTINUE: break; case D_WALK_QUIT: case D_WALK_SKIP: goto out_unlock; case D_WALK_NORETRY: retry = false; break; } repeat: next = this_parent->d_subdirs.next; resume: while (next != &this_parent->d_subdirs) { struct list_head *tmp = next; struct dentry *dentry = list_entry(tmp, struct dentry, d_child); next = tmp->next; if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR)) continue; spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); ret = enter(data, dentry); switch (ret) { case D_WALK_CONTINUE: break; case D_WALK_QUIT: spin_unlock(&dentry->d_lock); goto out_unlock; case D_WALK_NORETRY: retry = false; break; case D_WALK_SKIP: spin_unlock(&dentry->d_lock); continue; } if (!list_empty(&dentry->d_subdirs)) { spin_unlock(&this_parent->d_lock); spin_release(&dentry->d_lock.dep_map, _RET_IP_); this_parent = dentry; spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_); goto repeat; } spin_unlock(&dentry->d_lock); } /* * All done at this level ... ascend and resume the search. */ rcu_read_lock(); ascend: if (this_parent != parent) { struct dentry *child = this_parent; this_parent = child->d_parent; spin_unlock(&child->d_lock); spin_lock(&this_parent->d_lock); /* might go back up the wrong parent if we have had a rename. */ if (need_seqretry(&rename_lock, seq)) goto rename_retry; /* go into the first sibling still alive */ do { next = child->d_child.next; if (next == &this_parent->d_subdirs) goto ascend; child = list_entry(next, struct dentry, d_child); } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)); rcu_read_unlock(); goto resume; } if (need_seqretry(&rename_lock, seq)) goto rename_retry; rcu_read_unlock(); out_unlock: spin_unlock(&this_parent->d_lock); done_seqretry(&rename_lock, seq); return; rename_retry: spin_unlock(&this_parent->d_lock); rcu_read_unlock(); BUG_ON(seq & 1); if (!retry) return; seq = 1; goto again; } struct check_mount { struct vfsmount *mnt; unsigned int mounted; }; static enum d_walk_ret path_check_mount(void *data, struct dentry *dentry) { struct check_mount *info = data; struct path path = { .mnt = info->mnt, .dentry = dentry }; if (likely(!d_mountpoint(dentry))) return D_WALK_CONTINUE; if (__path_is_mountpoint(&path)) { info->mounted = 1; return D_WALK_QUIT; } return D_WALK_CONTINUE; } /** * path_has_submounts - check for mounts over a dentry in the * current namespace. * @parent: path to check. * * Return true if the parent or its subdirectories contain * a mount point in the current namespace. */ int path_has_submounts(const struct path *parent) { struct check_mount data = { .mnt = parent->mnt, .mounted = 0 }; read_seqlock_excl(&mount_lock); d_walk(parent->dentry, &data, path_check_mount); read_sequnlock_excl(&mount_lock); return data.mounted; } EXPORT_SYMBOL(path_has_submounts); /* * Called by mount code to set a mountpoint and check if the mountpoint is * reachable (e.g. NFS can unhash a directory dentry and then the complete * subtree can become unreachable). * * Only one of d_invalidate() and d_set_mounted() must succeed. For * this reason take rename_lock and d_lock on dentry and ancestors. */ int d_set_mounted(struct dentry *dentry) { struct dentry *p; int ret = -ENOENT; write_seqlock(&rename_lock); for (p = dentry->d_parent; !IS_ROOT(p); p = p->d_parent) { /* Need exclusion wrt. d_invalidate() */ spin_lock(&p->d_lock); if (unlikely(d_unhashed(p))) { spin_unlock(&p->d_lock); goto out; } spin_unlock(&p->d_lock); } spin_lock(&dentry->d_lock); if (!d_unlinked(dentry)) { ret = -EBUSY; if (!d_mountpoint(dentry)) { dentry->d_flags |= DCACHE_MOUNTED; ret = 0; } } spin_unlock(&dentry->d_lock); out: write_sequnlock(&rename_lock); return ret; } /* * Search the dentry child list of the specified parent, * and move any unused dentries to the end of the unused * list for prune_dcache(). We descend to the next level * whenever the d_subdirs list is non-empty and continue * searching. * * It returns zero iff there are no unused children, * otherwise it returns the number of children moved to * the end of the unused list. This may not be the total * number of unused children, because select_parent can * drop the lock and return early due to latency * constraints. */ struct select_data { struct dentry *start; union { long found; struct dentry *victim; }; struct list_head dispose; }; static enum d_walk_ret select_collect(void *_data, struct dentry *dentry) { struct select_data *data = _data; enum d_walk_ret ret = D_WALK_CONTINUE; if (data->start == dentry) goto out; if (dentry->d_flags & DCACHE_SHRINK_LIST) { data->found++; } else { if (dentry->d_flags & DCACHE_LRU_LIST) d_lru_del(dentry); if (!dentry->d_lockref.count) { d_shrink_add(dentry, &data->dispose); data->found++; } } /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ if (!list_empty(&data->dispose)) ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; out: return ret; } static enum d_walk_ret select_collect2(void *_data, struct dentry *dentry) { struct select_data *data = _data; enum d_walk_ret ret = D_WALK_CONTINUE; if (data->start == dentry) goto out; if (dentry->d_flags & DCACHE_SHRINK_LIST) { if (!dentry->d_lockref.count) { rcu_read_lock(); data->victim = dentry; return D_WALK_QUIT; } } else { if (dentry->d_flags & DCACHE_LRU_LIST) d_lru_del(dentry); if (!dentry->d_lockref.count) d_shrink_add(dentry, &data->dispose); } /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ if (!list_empty(&data->dispose)) ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; out: return ret; } /** * shrink_dcache_parent - prune dcache * @parent: parent of entries to prune * * Prune the dcache to remove unused children of the parent dentry. */ void shrink_dcache_parent(struct dentry *parent) { for (;;) { struct select_data data = {.start = parent}; INIT_LIST_HEAD(&data.dispose); d_walk(parent, &data, select_collect); if (!list_empty(&data.dispose)) { shrink_dentry_list(&data.dispose); continue; } cond_resched(); if (!data.found) break; data.victim = NULL; d_walk(parent, &data, select_collect2); if (data.victim) { struct dentry *parent; spin_lock(&data.victim->d_lock); if (!shrink_lock_dentry(data.victim)) { spin_unlock(&data.victim->d_lock); rcu_read_unlock(); } else { rcu_read_unlock(); parent = data.victim->d_parent; if (parent != data.victim) __dput_to_list(parent, &data.dispose); __dentry_kill(data.victim); } } if (!list_empty(&data.dispose)) shrink_dentry_list(&data.dispose); } } EXPORT_SYMBOL(shrink_dcache_parent); static enum d_walk_ret umount_check(void *_data, struct dentry *dentry) { /* it has busy descendents; complain about those instead */ if (!list_empty(&dentry->d_subdirs)) return D_WALK_CONTINUE; /* root with refcount 1 is fine */ if (dentry == _data && dentry->d_lockref.count == 1) return D_WALK_CONTINUE; printk(KERN_ERR "BUG: Dentry %p{i=%lx,n=%pd} " " still in use (%d) [unmount of %s %s]\n", dentry, dentry->d_inode ? dentry->d_inode->i_ino : 0UL, dentry, dentry->d_lockref.count, dentry->d_sb->s_type->name, dentry->d_sb->s_id); WARN_ON(1); return D_WALK_CONTINUE; } static void do_one_tree(struct dentry *dentry) { shrink_dcache_parent(dentry); d_walk(dentry, dentry, umount_check); d_drop(dentry); dput(dentry); } /* * destroy the dentries attached to a superblock on unmounting */ void shrink_dcache_for_umount(struct super_block *sb) { struct dentry *dentry; WARN(down_read_trylock(&sb->s_umount), "s_umount should've been locked"); dentry = sb->s_root; sb->s_root = NULL; do_one_tree(dentry); while (!hlist_bl_empty(&sb->s_roots)) { dentry = dget(hlist_bl_entry(hlist_bl_first(&sb->s_roots), struct dentry, d_hash)); do_one_tree(dentry); } } static enum d_walk_ret find_submount(void *_data, struct dentry *dentry) { struct dentry **victim = _data; if (d_mountpoint(dentry)) { __dget_dlock(dentry); *victim = dentry; return D_WALK_QUIT; } return D_WALK_CONTINUE; } /** * d_invalidate - detach submounts, prune dcache, and drop * @dentry: dentry to invalidate (aka detach, prune and drop) */ void d_invalidate(struct dentry *dentry) { bool had_submounts = false; spin_lock(&dentry->d_lock); if (d_unhashed(dentry)) { spin_unlock(&dentry->d_lock); return; } __d_drop(dentry); spin_unlock(&dentry->d_lock); /* Negative dentries can be dropped without further checks */ if (!dentry->d_inode) return; shrink_dcache_parent(dentry); for (;;) { struct dentry *victim = NULL; d_walk(dentry, &victim, find_submount); if (!victim) { if (had_submounts) shrink_dcache_parent(dentry); return; } had_submounts = true; detach_mounts(victim); dput(victim); } } EXPORT_SYMBOL(d_invalidate); /** * __d_alloc - allocate a dcache entry * @sb: filesystem it will belong to * @name: qstr of the name * * Allocates a dentry. It returns %NULL if there is insufficient memory * available. On a success the dentry is returned. The name passed in is * copied and the copy passed in may be reused after this call. */ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) { struct dentry *dentry; char *dname; int err; dentry = kmem_cache_alloc_lru(dentry_cache, &sb->s_dentry_lru, GFP_KERNEL); if (!dentry) return NULL; /* * We guarantee that the inline name is always NUL-terminated. * This way the memcpy() done by the name switching in rename * will still always have a NUL at the end, even if we might * be overwriting an internal NUL character */ dentry->d_iname[DNAME_INLINE_LEN-1] = 0; if (unlikely(!name)) { name = &slash_name; dname = dentry->d_iname; } else if (name->len > DNAME_INLINE_LEN-1) { size_t size = offsetof(struct external_name, name[1]); struct external_name *p = kmalloc(size + name->len, GFP_KERNEL_ACCOUNT | __GFP_RECLAIMABLE); if (!p) { kmem_cache_free(dentry_cache, dentry); return NULL; } atomic_set(&p->u.count, 1); dname = p->name; } else { dname = dentry->d_iname; } dentry->d_name.len = name->len; dentry->d_name.hash = name->hash; memcpy(dname, name->name, name->len); dname[name->len] = 0; /* Make sure we always see the terminating NUL character */ smp_store_release(&dentry->d_name.name, dname); /* ^^^ */ dentry->d_lockref.count = 1; dentry->d_flags = 0; spin_lock_init(&dentry->d_lock); seqcount_spinlock_init(&dentry->d_seq, &dentry->d_lock); dentry->d_inode = NULL; dentry->d_parent = dentry; dentry->d_sb = sb; dentry->d_op = NULL; dentry->d_fsdata = NULL; INIT_HLIST_BL_NODE(&dentry->d_hash); INIT_LIST_HEAD(&dentry->d_lru); INIT_LIST_HEAD(&dentry->d_subdirs); INIT_HLIST_NODE(&dentry->d_u.d_alias); INIT_LIST_HEAD(&dentry->d_child); d_set_d_op(dentry, dentry->d_sb->s_d_op); if (dentry->d_op && dentry->d_op->d_init) { err = dentry->d_op->d_init(dentry); if (err) { if (dname_external(dentry)) kfree(external_name(dentry)); kmem_cache_free(dentry_cache, dentry); return NULL; } } this_cpu_inc(nr_dentry); return dentry; } /** * d_alloc - allocate a dcache entry * @parent: parent of entry to allocate * @name: qstr of the name * * Allocates a dentry. It returns %NULL if there is insufficient memory * available. On a success the dentry is returned. The name passed in is * copied and the copy passed in may be reused after this call. */ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) { struct dentry *dentry = __d_alloc(parent->d_sb, name); if (!dentry) return NULL; spin_lock(&parent->d_lock); /* * don't need child lock because it is not subject * to concurrency here */ __dget_dlock(parent); dentry->d_parent = parent; list_add(&dentry->d_child, &parent->d_subdirs); spin_unlock(&parent->d_lock); return dentry; } EXPORT_SYMBOL(d_alloc); struct dentry *d_alloc_anon(struct super_block *sb) { return __d_alloc(sb, NULL); } EXPORT_SYMBOL(d_alloc_anon); struct dentry *d_alloc_cursor(struct dentry * parent) { struct dentry *dentry = d_alloc_anon(parent->d_sb); if (dentry) { dentry->d_flags |= DCACHE_DENTRY_CURSOR; dentry->d_parent = dget(parent); } return dentry; } /** * d_alloc_pseudo - allocate a dentry (for lookup-less filesystems) * @sb: the superblock * @name: qstr of the name * * For a filesystem that just pins its dentries in memory and never * performs lookups at all, return an unhashed IS_ROOT dentry. * This is used for pipes, sockets et.al. - the stuff that should * never be anyone's children or parents. Unlike all other * dentries, these will not have RCU delay between dropping the * last reference and freeing them. * * The only user is alloc_file_pseudo() and that's what should * be considered a public interface. Don't use directly. */ struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name) { struct dentry *dentry = __d_alloc(sb, name); if (likely(dentry)) dentry->d_flags |= DCACHE_NORCU; return dentry; } struct dentry *d_alloc_name(struct dentry *parent, const char *name) { struct qstr q; q.name = name; q.hash_len = hashlen_string(parent, name); return d_alloc(parent, &q); } EXPORT_SYMBOL(d_alloc_name); void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op) { WARN_ON_ONCE(dentry->d_op); WARN_ON_ONCE(dentry->d_flags & (DCACHE_OP_HASH | DCACHE_OP_COMPARE | DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE | DCACHE_OP_DELETE | DCACHE_OP_REAL)); dentry->d_op = op; if (!op) return; if (op->d_hash) dentry->d_flags |= DCACHE_OP_HASH; if (op->d_compare) dentry->d_flags |= DCACHE_OP_COMPARE; if (op->d_revalidate) dentry->d_flags |= DCACHE_OP_REVALIDATE; if (op->d_weak_revalidate) dentry->d_flags |= DCACHE_OP_WEAK_REVALIDATE; if (op->d_delete) dentry->d_flags |= DCACHE_OP_DELETE; if (op->d_prune) dentry->d_flags |= DCACHE_OP_PRUNE; if (op->d_real) dentry->d_flags |= DCACHE_OP_REAL; } EXPORT_SYMBOL(d_set_d_op); /* * d_set_fallthru - Mark a dentry as falling through to a lower layer * @dentry - The dentry to mark * * Mark a dentry as falling through to the lower layer (as set with * d_pin_lower()). This flag may be recorded on the medium. */ void d_set_fallthru(struct dentry *dentry) { spin_lock(&dentry->d_lock); dentry->d_flags |= DCACHE_FALLTHRU; spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(d_set_fallthru); static unsigned d_flags_for_inode(struct inode *inode) { unsigned add_flags = DCACHE_REGULAR_TYPE; if (!inode) return DCACHE_MISS_TYPE; if (S_ISDIR(inode->i_mode)) { add_flags = DCACHE_DIRECTORY_TYPE; if (unlikely(!(inode->i_opflags & IOP_LOOKUP))) { if (unlikely(!inode->i_op->lookup)) add_flags = DCACHE_AUTODIR_TYPE; else inode->i_opflags |= IOP_LOOKUP; } goto type_determined; } if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) { if (unlikely(inode->i_op->get_link)) { add_flags = DCACHE_SYMLINK_TYPE; goto type_determined; } inode->i_opflags |= IOP_NOFOLLOW; } if (unlikely(!S_ISREG(inode->i_mode))) add_flags = DCACHE_SPECIAL_TYPE; type_determined: if (unlikely(IS_AUTOMOUNT(inode))) add_flags |= DCACHE_NEED_AUTOMOUNT; return add_flags; } static void __d_instantiate(struct dentry *dentry, struct inode *inode) { unsigned add_flags = d_flags_for_inode(inode); WARN_ON(d_in_lookup(dentry)); spin_lock(&dentry->d_lock); /* * The negative counter only tracks dentries on the LRU. Don't dec if * d_lru is on another list. */ if ((dentry->d_flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_dec(nr_dentry_negative); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); fsnotify_update_flags(dentry); spin_unlock(&dentry->d_lock); } /** * d_instantiate - fill in inode information for a dentry * @entry: dentry to complete * @inode: inode to attach to this dentry * * Fill in inode information in the entry. * * This turns negative dentries into productive full members * of society. * * NOTE! This assumes that the inode count has been incremented * (or otherwise set) by the caller to indicate that it is now * in use by the dcache. */ void d_instantiate(struct dentry *entry, struct inode * inode) { BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); if (inode) { security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); __d_instantiate(entry, inode); spin_unlock(&inode->i_lock); } } EXPORT_SYMBOL(d_instantiate); /* * This should be equivalent to d_instantiate() + unlock_new_inode(), * with lockdep-related part of unlock_new_inode() done before * anything else. Use that instead of open-coding d_instantiate()/ * unlock_new_inode() combinations. */ void d_instantiate_new(struct dentry *entry, struct inode *inode) { BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); BUG_ON(!inode); lockdep_annotate_inode_mutex_key(inode); security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); __d_instantiate(entry, inode); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW & ~I_CREATING; smp_mb(); wake_up_bit(&inode->i_state, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_instantiate_new); struct dentry *d_make_root(struct inode *root_inode) { struct dentry *res = NULL; if (root_inode) { res = d_alloc_anon(root_inode->i_sb); if (res) d_instantiate(res, root_inode); else iput(root_inode); } return res; } EXPORT_SYMBOL(d_make_root); static struct dentry *__d_instantiate_anon(struct dentry *dentry, struct inode *inode, bool disconnected) { struct dentry *res; unsigned add_flags; security_d_instantiate(dentry, inode); spin_lock(&inode->i_lock); res = __d_find_any_alias(inode); if (res) { spin_unlock(&inode->i_lock); dput(dentry); goto out_iput; } /* attach a disconnected dentry */ add_flags = d_flags_for_inode(inode); if (disconnected) add_flags |= DCACHE_DISCONNECTED; spin_lock(&dentry->d_lock); __d_set_inode_and_type(dentry, inode, add_flags); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); if (!disconnected) { hlist_bl_lock(&dentry->d_sb->s_roots); hlist_bl_add_head(&dentry->d_hash, &dentry->d_sb->s_roots); hlist_bl_unlock(&dentry->d_sb->s_roots); } spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); return dentry; out_iput: iput(inode); return res; } struct dentry *d_instantiate_anon(struct dentry *dentry, struct inode *inode) { return __d_instantiate_anon(dentry, inode, true); } EXPORT_SYMBOL(d_instantiate_anon); static struct dentry *__d_obtain_alias(struct inode *inode, bool disconnected) { struct dentry *tmp; struct dentry *res; if (!inode) return ERR_PTR(-ESTALE); if (IS_ERR(inode)) return ERR_CAST(inode); res = d_find_any_alias(inode); if (res) goto out_iput; tmp = d_alloc_anon(inode->i_sb); if (!tmp) { res = ERR_PTR(-ENOMEM); goto out_iput; } return __d_instantiate_anon(tmp, inode, disconnected); out_iput: iput(inode); return res; } /** * d_obtain_alias - find or allocate a DISCONNECTED dentry for a given inode * @inode: inode to allocate the dentry for * * Obtain a dentry for an inode resulting from NFS filehandle conversion or * similar open by handle operations. The returned dentry may be anonymous, * or may have a full name (if the inode was already in the cache). * * When called on a directory inode, we must ensure that the inode only ever * has one dentry. If a dentry is found, that is returned instead of * allocating a new one. * * On successful return, the reference to the inode has been transferred * to the dentry. In case of an error the reference on the inode is released. * To make it easier to use in export operations a %NULL or IS_ERR inode may * be passed in and the error will be propagated to the return value, * with a %NULL @inode replaced by ERR_PTR(-ESTALE). */ struct dentry *d_obtain_alias(struct inode *inode) { return __d_obtain_alias(inode, true); } EXPORT_SYMBOL(d_obtain_alias); /** * d_obtain_root - find or allocate a dentry for a given inode * @inode: inode to allocate the dentry for * * Obtain an IS_ROOT dentry for the root of a filesystem. * * We must ensure that directory inodes only ever have one dentry. If a * dentry is found, that is returned instead of allocating a new one. * * On successful return, the reference to the inode has been transferred * to the dentry. In case of an error the reference on the inode is * released. A %NULL or IS_ERR inode may be passed in and will be the * error will be propagate to the return value, with a %NULL @inode * replaced by ERR_PTR(-ESTALE). */ struct dentry *d_obtain_root(struct inode *inode) { return __d_obtain_alias(inode, false); } EXPORT_SYMBOL(d_obtain_root); /** * d_add_ci - lookup or allocate new dentry with case-exact name * @inode: the inode case-insensitive lookup has found * @dentry: the negative dentry that was passed to the parent's lookup func * @name: the case-exact name to be associated with the returned dentry * * This is to avoid filling the dcache with case-insensitive names to the * same inode, only the actual correct case is stored in the dcache for * case-insensitive filesystems. * * For a case-insensitive lookup match and if the case-exact dentry * already exists in the dcache, use it and return it. * * If no entry exists with the exact case name, allocate new dentry with * the exact case, and return the spliced entry. */ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode, struct qstr *name) { struct dentry *found, *res; /* * First check if a dentry matching the name already exists, * if not go ahead and create it now. */ found = d_hash_and_lookup(dentry->d_parent, name); if (found) { iput(inode); return found; } if (d_in_lookup(dentry)) { found = d_alloc_parallel(dentry->d_parent, name, dentry->d_wait); if (IS_ERR(found) || !d_in_lookup(found)) { iput(inode); return found; } } else { found = d_alloc(dentry->d_parent, name); if (!found) { iput(inode); return ERR_PTR(-ENOMEM); } } res = d_splice_alias(inode, found); if (res) { d_lookup_done(found); dput(found); return res; } return found; } EXPORT_SYMBOL(d_add_ci); /** * d_same_name - compare dentry name with case-exact name * @parent: parent dentry * @dentry: the negative dentry that was passed to the parent's lookup func * @name: the case-exact name to be associated with the returned dentry * * Return: true if names are same, or false */ bool d_same_name(const struct dentry *dentry, const struct dentry *parent, const struct qstr *name) { if (likely(!(parent->d_flags & DCACHE_OP_COMPARE))) { if (dentry->d_name.len != name->len) return false; return dentry_cmp(dentry, name->name, name->len) == 0; } return parent->d_op->d_compare(dentry, dentry->d_name.len, dentry->d_name.name, name) == 0; } EXPORT_SYMBOL_GPL(d_same_name); /* * This is __d_lookup_rcu() when the parent dentry has * DCACHE_OP_COMPARE, which makes things much nastier. */ static noinline struct dentry *__d_lookup_rcu_op_compare( const struct dentry *parent, const struct qstr *name, unsigned *seqp) { u64 hashlen = name->hash_len; struct hlist_bl_head *b = d_hash(hashlen_hash(hashlen)); struct hlist_bl_node *node; struct dentry *dentry; hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { int tlen; const char *tname; unsigned seq; seqretry: seq = raw_seqcount_begin(&dentry->d_seq); if (dentry->d_parent != parent) continue; if (d_unhashed(dentry)) continue; if (dentry->d_name.hash != hashlen_hash(hashlen)) continue; tlen = dentry->d_name.len; tname = dentry->d_name.name; /* we want a consistent (name,len) pair */ if (read_seqcount_retry(&dentry->d_seq, seq)) { cpu_relax(); goto seqretry; } if (parent->d_op->d_compare(dentry, tlen, tname, name) != 0) continue; *seqp = seq; return dentry; } return NULL; } /** * __d_lookup_rcu - search for a dentry (racy, store-free) * @parent: parent dentry * @name: qstr of name we wish to find * @seqp: returns d_seq value at the point where the dentry was found * Returns: dentry, or NULL * * __d_lookup_rcu is the dcache lookup function for rcu-walk name * resolution (store-free path walking) design described in * Documentation/filesystems/path-lookup.txt. * * This is not to be used outside core vfs. * * __d_lookup_rcu must only be used in rcu-walk mode, ie. with vfsmount lock * held, and rcu_read_lock held. The returned dentry must not be stored into * without taking d_lock and checking d_seq sequence count against @seq * returned here. * * A refcount may be taken on the found dentry with the d_rcu_to_refcount * function. * * Alternatively, __d_lookup_rcu may be called again to look up the child of * the returned dentry, so long as its parent's seqlock is checked after the * child is looked up. Thus, an interlocking stepping of sequence lock checks * is formed, giving integrity down the path walk. * * NOTE! The caller *has* to check the resulting dentry against the sequence * number we've returned before using any of the resulting dentry state! */ struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, unsigned *seqp) { u64 hashlen = name->hash_len; const unsigned char *str = name->name; struct hlist_bl_head *b = d_hash(hashlen_hash(hashlen)); struct hlist_bl_node *node; struct dentry *dentry; /* * Note: There is significant duplication with __d_lookup_rcu which is * required to prevent single threaded performance regressions * especially on architectures where smp_rmb (in seqcounts) are costly. * Keep the two functions in sync. */ if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) return __d_lookup_rcu_op_compare(parent, name, seqp); /* * The hash list is protected using RCU. * * Carefully use d_seq when comparing a candidate dentry, to avoid * races with d_move(). * * It is possible that concurrent renames can mess up our list * walk here and result in missing our dentry, resulting in the * false-negative result. d_lookup() protects against concurrent * renames using rename_lock seqlock. * * See Documentation/filesystems/path-lookup.txt for more details. */ hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { unsigned seq; /* * The dentry sequence count protects us from concurrent * renames, and thus protects parent and name fields. * * The caller must perform a seqcount check in order * to do anything useful with the returned dentry. * * NOTE! We do a "raw" seqcount_begin here. That means that * we don't wait for the sequence count to stabilize if it * is in the middle of a sequence change. If we do the slow * dentry compare, we will do seqretries until it is stable, * and if we end up with a successful lookup, we actually * want to exit RCU lookup anyway. * * Note that raw_seqcount_begin still *does* smp_rmb(), so * we are still guaranteed NUL-termination of ->d_name.name. */ seq = raw_seqcount_begin(&dentry->d_seq); if (dentry->d_parent != parent) continue; if (d_unhashed(dentry)) continue; if (dentry->d_name.hash_len != hashlen) continue; if (dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0) continue; *seqp = seq; return dentry; } return NULL; } /** * d_lookup - search for a dentry * @parent: parent dentry * @name: qstr of name we wish to find * Returns: dentry, or NULL * * d_lookup searches the children of the parent dentry for the name in * question. If the dentry is found its reference count is incremented and the * dentry is returned. The caller must use dput to free the entry when it has * finished using it. %NULL is returned if the dentry does not exist. */ struct dentry *d_lookup(const struct dentry *parent, const struct qstr *name) { struct dentry *dentry; unsigned seq; do { seq = read_seqbegin(&rename_lock); dentry = __d_lookup(parent, name); if (dentry) break; } while (read_seqretry(&rename_lock, seq)); return dentry; } EXPORT_SYMBOL(d_lookup); /** * __d_lookup - search for a dentry (racy) * @parent: parent dentry * @name: qstr of name we wish to find * Returns: dentry, or NULL * * __d_lookup is like d_lookup, however it may (rarely) return a * false-negative result due to unrelated rename activity. * * __d_lookup is slightly faster by avoiding rename_lock read seqlock, * however it must be used carefully, eg. with a following d_lookup in * the case of failure. * * __d_lookup callers must be commented. */ struct dentry *__d_lookup(const struct dentry *parent, const struct qstr *name) { unsigned int hash = name->hash; struct hlist_bl_head *b = d_hash(hash); struct hlist_bl_node *node; struct dentry *found = NULL; struct dentry *dentry; /* * Note: There is significant duplication with __d_lookup_rcu which is * required to prevent single threaded performance regressions * especially on architectures where smp_rmb (in seqcounts) are costly. * Keep the two functions in sync. */ /* * The hash list is protected using RCU. * * Take d_lock when comparing a candidate dentry, to avoid races * with d_move(). * * It is possible that concurrent renames can mess up our list * walk here and result in missing our dentry, resulting in the * false-negative result. d_lookup() protects against concurrent * renames using rename_lock seqlock. * * See Documentation/filesystems/path-lookup.txt for more details. */ rcu_read_lock(); hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { if (dentry->d_name.hash != hash) continue; spin_lock(&dentry->d_lock); if (dentry->d_parent != parent) goto next; if (d_unhashed(dentry)) goto next; if (!d_same_name(dentry, parent, name)) goto next; dentry->d_lockref.count++; found = dentry; spin_unlock(&dentry->d_lock); break; next: spin_unlock(&dentry->d_lock); } rcu_read_unlock(); return found; } /** * d_hash_and_lookup - hash the qstr then search for a dentry * @dir: Directory to search in * @name: qstr of name we wish to find * * On lookup failure NULL is returned; on bad name - ERR_PTR(-error) */ struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name) { /* * Check for a fs-specific hash function. Note that we must * calculate the standard hash first, as the d_op->d_hash() * routine may choose to leave the hash value unchanged. */ name->hash = full_name_hash(dir, name->name, name->len); if (dir->d_flags & DCACHE_OP_HASH) { int err = dir->d_op->d_hash(dir, name); if (unlikely(err < 0)) return ERR_PTR(err); } return d_lookup(dir, name); } EXPORT_SYMBOL(d_hash_and_lookup); /* * When a file is deleted, we have two options: * - turn this dentry into a negative dentry * - unhash this dentry and free it. * * Usually, we want to just turn this into * a negative dentry, but if anybody else is * currently using the dentry or the inode * we can't do that and we fall back on removing * it from the hash queues and waiting for * it to be deleted later when it has no users */ /** * d_delete - delete a dentry * @dentry: The dentry to delete * * Turn the dentry into a negative dentry if possible, otherwise * remove it from the hash queues so it can be deleted later */ void d_delete(struct dentry * dentry) { struct inode *inode = dentry->d_inode; spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); /* * Are we the only user? */ if (dentry->d_lockref.count == 1) { dentry->d_flags &= ~DCACHE_CANT_MOUNT; dentry_unlink_inode(dentry); } else { __d_drop(dentry); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); } } EXPORT_SYMBOL(d_delete); static void __d_rehash(struct dentry *entry) { struct hlist_bl_head *b = d_hash(entry->d_name.hash); hlist_bl_lock(b); hlist_bl_add_head_rcu(&entry->d_hash, b); hlist_bl_unlock(b); } /** * d_rehash - add an entry back to the hash * @entry: dentry to add to the hash * * Adds a dentry to the hash according to its name. */ void d_rehash(struct dentry * entry) { spin_lock(&entry->d_lock); __d_rehash(entry); spin_unlock(&entry->d_lock); } EXPORT_SYMBOL(d_rehash); static inline unsigned start_dir_add(struct inode *dir) { preempt_disable_nested(); for (;;) { unsigned n = dir->i_dir_seq; if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n) return n; cpu_relax(); } } static inline void end_dir_add(struct inode *dir, unsigned int n, wait_queue_head_t *d_wait) { smp_store_release(&dir->i_dir_seq, n + 2); preempt_enable_nested(); wake_up_all(d_wait); } static void d_wait_lookup(struct dentry *dentry) { if (d_in_lookup(dentry)) { DECLARE_WAITQUEUE(wait, current); add_wait_queue(dentry->d_wait, &wait); do { set_current_state(TASK_UNINTERRUPTIBLE); spin_unlock(&dentry->d_lock); schedule(); spin_lock(&dentry->d_lock); } while (d_in_lookup(dentry)); } } struct dentry *d_alloc_parallel(struct dentry *parent, const struct qstr *name, wait_queue_head_t *wq) { unsigned int hash = name->hash; struct hlist_bl_head *b = in_lookup_hash(parent, hash); struct hlist_bl_node *node; struct dentry *new = d_alloc(parent, name); struct dentry *dentry; unsigned seq, r_seq, d_seq; if (unlikely(!new)) return ERR_PTR(-ENOMEM); retry: rcu_read_lock(); seq = smp_load_acquire(&parent->d_inode->i_dir_seq); r_seq = read_seqbegin(&rename_lock); dentry = __d_lookup_rcu(parent, name, &d_seq); if (unlikely(dentry)) { if (!lockref_get_not_dead(&dentry->d_lockref)) { rcu_read_unlock(); goto retry; } if (read_seqcount_retry(&dentry->d_seq, d_seq)) { rcu_read_unlock(); dput(dentry); goto retry; } rcu_read_unlock(); dput(new); return dentry; } if (unlikely(read_seqretry(&rename_lock, r_seq))) { rcu_read_unlock(); goto retry; } if (unlikely(seq & 1)) { rcu_read_unlock(); goto retry; } hlist_bl_lock(b); if (unlikely(READ_ONCE(parent->d_inode->i_dir_seq) != seq)) { hlist_bl_unlock(b); rcu_read_unlock(); goto retry; } /* * No changes for the parent since the beginning of d_lookup(). * Since all removals from the chain happen with hlist_bl_lock(), * any potential in-lookup matches are going to stay here until * we unlock the chain. All fields are stable in everything * we encounter. */ hlist_bl_for_each_entry(dentry, node, b, d_u.d_in_lookup_hash) { if (dentry->d_name.hash != hash) continue; if (dentry->d_parent != parent) continue; if (!d_same_name(dentry, parent, name)) continue; hlist_bl_unlock(b); /* now we can try to grab a reference */ if (!lockref_get_not_dead(&dentry->d_lockref)) { rcu_read_unlock(); goto retry; } rcu_read_unlock(); /* * somebody is likely to be still doing lookup for it; * wait for them to finish */ spin_lock(&dentry->d_lock); d_wait_lookup(dentry); /* * it's not in-lookup anymore; in principle we should repeat * everything from dcache lookup, but it's likely to be what * d_lookup() would've found anyway. If it is, just return it; * otherwise we really have to repeat the whole thing. */ if (unlikely(dentry->d_name.hash != hash)) goto mismatch; if (unlikely(dentry->d_parent != parent)) goto mismatch; if (unlikely(d_unhashed(dentry))) goto mismatch; if (unlikely(!d_same_name(dentry, parent, name))) goto mismatch; /* OK, it *is* a hashed match; return it */ spin_unlock(&dentry->d_lock); dput(new); return dentry; } rcu_read_unlock(); /* we can't take ->d_lock here; it's OK, though. */ new->d_flags |= DCACHE_PAR_LOOKUP; new->d_wait = wq; hlist_bl_add_head_rcu(&new->d_u.d_in_lookup_hash, b); hlist_bl_unlock(b); return new; mismatch: spin_unlock(&dentry->d_lock); dput(dentry); goto retry; } EXPORT_SYMBOL(d_alloc_parallel); /* * - Unhash the dentry * - Retrieve and clear the waitqueue head in dentry * - Return the waitqueue head */ static wait_queue_head_t *__d_lookup_unhash(struct dentry *dentry) { wait_queue_head_t *d_wait; struct hlist_bl_head *b; lockdep_assert_held(&dentry->d_lock); b = in_lookup_hash(dentry->d_parent, dentry->d_name.hash); hlist_bl_lock(b); dentry->d_flags &= ~DCACHE_PAR_LOOKUP; __hlist_bl_del(&dentry->d_u.d_in_lookup_hash); d_wait = dentry->d_wait; dentry->d_wait = NULL; hlist_bl_unlock(b); INIT_HLIST_NODE(&dentry->d_u.d_alias); INIT_LIST_HEAD(&dentry->d_lru); return d_wait; } void __d_lookup_unhash_wake(struct dentry *dentry) { spin_lock(&dentry->d_lock); wake_up_all(__d_lookup_unhash(dentry)); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(__d_lookup_unhash_wake); /* inode->i_lock held if inode is non-NULL */ static inline void __d_add(struct dentry *dentry, struct inode *inode) { wait_queue_head_t *d_wait; struct inode *dir = NULL; unsigned n; spin_lock(&dentry->d_lock); if (unlikely(d_in_lookup(dentry))) { dir = dentry->d_parent->d_inode; n = start_dir_add(dir); d_wait = __d_lookup_unhash(dentry); } if (inode) { unsigned add_flags = d_flags_for_inode(inode); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); fsnotify_update_flags(dentry); } __d_rehash(dentry); if (dir) end_dir_add(dir, n, d_wait); spin_unlock(&dentry->d_lock); if (inode) spin_unlock(&inode->i_lock); } /** * d_add - add dentry to hash queues * @entry: dentry to add * @inode: The inode to attach to this dentry * * This adds the entry to the hash queues and initializes @inode. * The entry was actually filled in earlier during d_alloc(). */ void d_add(struct dentry *entry, struct inode *inode) { if (inode) { security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); } __d_add(entry, inode); } EXPORT_SYMBOL(d_add); /** * d_exact_alias - find and hash an exact unhashed alias * @entry: dentry to add * @inode: The inode to go with this dentry * * If an unhashed dentry with the same name/parent and desired * inode already exists, hash and return it. Otherwise, return * NULL. * * Parent directory should be locked. */ struct dentry *d_exact_alias(struct dentry *entry, struct inode *inode) { struct dentry *alias; unsigned int hash = entry->d_name.hash; spin_lock(&inode->i_lock); hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { /* * Don't need alias->d_lock here, because aliases with * d_parent == entry->d_parent are not subject to name or * parent changes, because the parent inode i_mutex is held. */ if (alias->d_name.hash != hash) continue; if (alias->d_parent != entry->d_parent) continue; if (!d_same_name(alias, entry->d_parent, &entry->d_name)) continue; spin_lock(&alias->d_lock); if (!d_unhashed(alias)) { spin_unlock(&alias->d_lock); alias = NULL; } else { __dget_dlock(alias); __d_rehash(alias); spin_unlock(&alias->d_lock); } spin_unlock(&inode->i_lock); return alias; } spin_unlock(&inode->i_lock); return NULL; } EXPORT_SYMBOL(d_exact_alias); static void swap_names(struct dentry *dentry, struct dentry *target) { if (unlikely(dname_external(target))) { if (unlikely(dname_external(dentry))) { /* * Both external: swap the pointers */ swap(target->d_name.name, dentry->d_name.name); } else { /* * dentry:internal, target:external. Steal target's * storage and make target internal. */ memcpy(target->d_iname, dentry->d_name.name, dentry->d_name.len + 1); dentry->d_name.name = target->d_name.name; target->d_name.name = target->d_iname; } } else { if (unlikely(dname_external(dentry))) { /* * dentry:external, target:internal. Give dentry's * storage to target and make dentry internal */ memcpy(dentry->d_iname, target->d_name.name, target->d_name.len + 1); target->d_name.name = dentry->d_name.name; dentry->d_name.name = dentry->d_iname; } else { /* * Both are internal. */ unsigned int i; BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long))); for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) { swap(((long *) &dentry->d_iname)[i], ((long *) &target->d_iname)[i]); } } } swap(dentry->d_name.hash_len, target->d_name.hash_len); } static void copy_name(struct dentry *dentry, struct dentry *target) { struct external_name *old_name = NULL; if (unlikely(dname_external(dentry))) old_name = external_name(dentry); if (unlikely(dname_external(target))) { atomic_inc(&external_name(target)->u.count); dentry->d_name = target->d_name; } else { memcpy(dentry->d_iname, target->d_name.name, target->d_name.len + 1); dentry->d_name.name = dentry->d_iname; dentry->d_name.hash_len = target->d_name.hash_len; } if (old_name && likely(atomic_dec_and_test(&old_name->u.count))) kfree_rcu(old_name, u.head); } /* * __d_move - move a dentry * @dentry: entry to move * @target: new dentry * @exchange: exchange the two dentries * * Update the dcache to reflect the move of a file name. Negative * dcache entries should not be moved in this way. Caller must hold * rename_lock, the i_mutex of the source and target directories, * and the sb->s_vfs_rename_mutex if they differ. See lock_rename(). */ static void __d_move(struct dentry *dentry, struct dentry *target, bool exchange) { struct dentry *old_parent, *p; wait_queue_head_t *d_wait; struct inode *dir = NULL; unsigned n; WARN_ON(!dentry->d_inode); if (WARN_ON(dentry == target)) return; BUG_ON(d_ancestor(target, dentry)); old_parent = dentry->d_parent; p = d_ancestor(old_parent, target); if (IS_ROOT(dentry)) { BUG_ON(p); spin_lock(&target->d_parent->d_lock); } else if (!p) { /* target is not a descendent of dentry->d_parent */ spin_lock(&target->d_parent->d_lock); spin_lock_nested(&old_parent->d_lock, DENTRY_D_LOCK_NESTED); } else { BUG_ON(p == dentry); spin_lock(&old_parent->d_lock); if (p != target) spin_lock_nested(&target->d_parent->d_lock, DENTRY_D_LOCK_NESTED); } spin_lock_nested(&dentry->d_lock, 2); spin_lock_nested(&target->d_lock, 3); if (unlikely(d_in_lookup(target))) { dir = target->d_parent->d_inode; n = start_dir_add(dir); d_wait = __d_lookup_unhash(target); } write_seqcount_begin(&dentry->d_seq); write_seqcount_begin_nested(&target->d_seq, DENTRY_D_LOCK_NESTED); /* unhash both */ if (!d_unhashed(dentry)) ___d_drop(dentry); if (!d_unhashed(target)) ___d_drop(target); /* ... and switch them in the tree */ dentry->d_parent = target->d_parent; if (!exchange) { copy_name(dentry, target); target->d_hash.pprev = NULL; dentry->d_parent->d_lockref.count++; if (dentry != old_parent) /* wasn't IS_ROOT */ WARN_ON(!--old_parent->d_lockref.count); } else { target->d_parent = old_parent; swap_names(dentry, target); list_move(&target->d_child, &target->d_parent->d_subdirs); __d_rehash(target); fsnotify_update_flags(target); } list_move(&dentry->d_child, &dentry->d_parent->d_subdirs); __d_rehash(dentry); fsnotify_update_flags(dentry); fscrypt_handle_d_move(dentry); write_seqcount_end(&target->d_seq); write_seqcount_end(&dentry->d_seq); if (dir) end_dir_add(dir, n, d_wait); if (dentry->d_parent != old_parent) spin_unlock(&dentry->d_parent->d_lock); if (dentry != old_parent) spin_unlock(&old_parent->d_lock); spin_unlock(&target->d_lock); spin_unlock(&dentry->d_lock); } /* * d_move - move a dentry * @dentry: entry to move * @target: new dentry * * Update the dcache to reflect the move of a file name. Negative * dcache entries should not be moved in this way. See the locking * requirements for __d_move. */ void d_move(struct dentry *dentry, struct dentry *target) { write_seqlock(&rename_lock); __d_move(dentry, target, false); write_sequnlock(&rename_lock); } EXPORT_SYMBOL(d_move); /* * d_exchange - exchange two dentries * @dentry1: first dentry * @dentry2: second dentry */ void d_exchange(struct dentry *dentry1, struct dentry *dentry2) { write_seqlock(&rename_lock); WARN_ON(!dentry1->d_inode); WARN_ON(!dentry2->d_inode); WARN_ON(IS_ROOT(dentry1)); WARN_ON(IS_ROOT(dentry2)); __d_move(dentry1, dentry2, true); write_sequnlock(&rename_lock); } /** * d_ancestor - search for an ancestor * @p1: ancestor dentry * @p2: child dentry * * Returns the ancestor dentry of p2 which is a child of p1, if p1 is * an ancestor of p2, else NULL. */ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2) { struct dentry *p; for (p = p2; !IS_ROOT(p); p = p->d_parent) { if (p->d_parent == p1) return p; } return NULL; } /* * This helper attempts to cope with remotely renamed directories * * It assumes that the caller is already holding * dentry->d_parent->d_inode->i_mutex, and rename_lock * * Note: If ever the locking in lock_rename() changes, then please * remember to update this too... */ static int __d_unalias(struct inode *inode, struct dentry *dentry, struct dentry *alias) { struct mutex *m1 = NULL; struct rw_semaphore *m2 = NULL; int ret = -ESTALE; /* If alias and dentry share a parent, then no extra locks required */ if (alias->d_parent == dentry->d_parent) goto out_unalias; /* See lock_rename() */ if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex)) goto out_err; m1 = &dentry->d_sb->s_vfs_rename_mutex; if (!inode_trylock_shared(alias->d_parent->d_inode)) goto out_err; m2 = &alias->d_parent->d_inode->i_rwsem; out_unalias: __d_move(alias, dentry, false); ret = 0; out_err: if (m2) up_read(m2); if (m1) mutex_unlock(m1); return ret; } /** * d_splice_alias - splice a disconnected dentry into the tree if one exists * @inode: the inode which may have a disconnected dentry * @dentry: a negative dentry which we want to point to the inode. * * If inode is a directory and has an IS_ROOT alias, then d_move that in * place of the given dentry and return it, else simply d_add the inode * to the dentry and return NULL. * * If a non-IS_ROOT directory is found, the filesystem is corrupt, and * we should error out: directories can't have multiple aliases. * * This is needed in the lookup routine of any filesystem that is exportable * (via knfsd) so that we can build dcache paths to directories effectively. * * If a dentry was found and moved, then it is returned. Otherwise NULL * is returned. This matches the expected return value of ->lookup. * * Cluster filesystems may call this function with a negative, hashed dentry. * In that case, we know that the inode will be a regular file, and also this * will only occur during atomic_open. So we need to check for the dentry * being already hashed only in the final case. */ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) { if (IS_ERR(inode)) return ERR_CAST(inode); BUG_ON(!d_unhashed(dentry)); if (!inode) goto out; security_d_instantiate(dentry, inode); spin_lock(&inode->i_lock); if (S_ISDIR(inode->i_mode)) { struct dentry *new = __d_find_any_alias(inode); if (unlikely(new)) { /* The reference to new ensures it remains an alias */ spin_unlock(&inode->i_lock); write_seqlock(&rename_lock); if (unlikely(d_ancestor(new, dentry))) { write_sequnlock(&rename_lock); dput(new); new = ERR_PTR(-ELOOP); pr_warn_ratelimited( "VFS: Lookup of '%s' in %s %s" " would have caused loop\n", dentry->d_name.name, inode->i_sb->s_type->name, inode->i_sb->s_id); } else if (!IS_ROOT(new)) { struct dentry *old_parent = dget(new->d_parent); int err = __d_unalias(inode, dentry, new); write_sequnlock(&rename_lock); if (err) { dput(new); new = ERR_PTR(err); } dput(old_parent); } else { __d_move(new, dentry, false); write_sequnlock(&rename_lock); } iput(inode); return new; } } out: __d_add(dentry, inode); return NULL; } EXPORT_SYMBOL(d_splice_alias); /* * Test whether new_dentry is a subdirectory of old_dentry. * * Trivially implemented using the dcache structure */ /** * is_subdir - is new dentry a subdirectory of old_dentry * @new_dentry: new dentry * @old_dentry: old dentry * * Returns true if new_dentry is a subdirectory of the parent (at any depth). * Returns false otherwise. * Caller must ensure that "new_dentry" is pinned before calling is_subdir() */ bool is_subdir(struct dentry *new_dentry, struct dentry *old_dentry) { bool subdir; unsigned seq; if (new_dentry == old_dentry) return true; /* Access d_parent under rcu as d_move() may change it. */ rcu_read_lock(); seq = read_seqbegin(&rename_lock); subdir = d_ancestor(old_dentry, new_dentry); /* Try lockless once... */ if (read_seqretry(&rename_lock, seq)) { /* ...else acquire lock for progress even on deep chains. */ read_seqlock_excl(&rename_lock); subdir = d_ancestor(old_dentry, new_dentry); read_sequnlock_excl(&rename_lock); } rcu_read_unlock(); return subdir; } EXPORT_SYMBOL(is_subdir); static enum d_walk_ret d_genocide_kill(void *data, struct dentry *dentry) { struct dentry *root = data; if (dentry != root) { if (d_unhashed(dentry) || !dentry->d_inode) return D_WALK_SKIP; if (!(dentry->d_flags & DCACHE_GENOCIDE)) { dentry->d_flags |= DCACHE_GENOCIDE; dentry->d_lockref.count--; } } return D_WALK_CONTINUE; } void d_genocide(struct dentry *parent) { d_walk(parent, parent, d_genocide_kill); } EXPORT_SYMBOL(d_genocide); void d_tmpfile(struct file *file, struct inode *inode) { struct dentry *dentry = file->f_path.dentry; inode_dec_link_count(inode); BUG_ON(dentry->d_name.name != dentry->d_iname || !hlist_unhashed(&dentry->d_u.d_alias) || !d_unlinked(dentry)); spin_lock(&dentry->d_parent->d_lock); spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); dentry->d_name.len = sprintf(dentry->d_iname, "#%llu", (unsigned long long)inode->i_ino); spin_unlock(&dentry->d_lock); spin_unlock(&dentry->d_parent->d_lock); d_instantiate(dentry, inode); } EXPORT_SYMBOL(d_tmpfile); static __initdata unsigned long dhash_entries; static int __init set_dhash_entries(char *str) { if (!str) return 0; dhash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("dhash_entries=", set_dhash_entries); static void __init dcache_init_early(void) { /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. */ if (hashdist) return; dentry_hashtable = alloc_large_system_hash("Dentry cache", sizeof(struct hlist_bl_head), dhash_entries, 13, HASH_EARLY | HASH_ZERO, &d_hash_shift, NULL, 0, 0); d_hash_shift = 32 - d_hash_shift; } static void __init dcache_init(void) { /* * A constructor could be added for stable state like the lists, * but it is probably not worth it because of the cache nature * of the dcache. */ dentry_cache = KMEM_CACHE_USERCOPY(dentry, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD|SLAB_ACCOUNT, d_iname); /* Hash may have been set up in dcache_init_early */ if (!hashdist) return; dentry_hashtable = alloc_large_system_hash("Dentry cache", sizeof(struct hlist_bl_head), dhash_entries, 13, HASH_ZERO, &d_hash_shift, NULL, 0, 0); d_hash_shift = 32 - d_hash_shift; } /* SLAB cache for __getname() consumers */ struct kmem_cache *names_cachep __read_mostly; EXPORT_SYMBOL(names_cachep); void __init vfs_caches_init_early(void) { int i; for (i = 0; i < ARRAY_SIZE(in_lookup_hashtable); i++) INIT_HLIST_BL_HEAD(&in_lookup_hashtable[i]); dcache_init_early(); inode_init_early(); } void __init vfs_caches_init(void) { names_cachep = kmem_cache_create_usercopy("names_cache", PATH_MAX, 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, 0, PATH_MAX, NULL); dcache_init(); inode_init(); files_init(); files_maxfiles_init(); mnt_init(); bdev_cache_init(); chrdev_init(); } |
| 272 272 272 270 271 270 270 4 4 3 2 1 3 3 4 4 3 3 1 1 20 20 4 8 9 7 1 37 37 37 1 1 1002 2 1000 1002 1002 1002 1000 999 998 998 995 998 1016 1016 1016 1003 1003 1003 995 999 997 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux NET3: GRE over IP protocol decoder. * * Authors: Alexey Kuznetsov (kuznet@ms2.inr.ac.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/if_vlan.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 <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/protocol.h> #include <net/ip_tunnels.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/gre.h> #include <net/dst_metadata.h> #include <net/erspan.h> /* Problems & solutions -------------------- 1. The most important issue is detecting local dead loops. They would cause complete host lockup in transmit, which would be "resolved" by stack overflow or, if queueing is enabled, with infinite looping in net_bh. We cannot track such dead loops during route installation, it is infeasible task. The most general solutions would be to keep skb->encapsulation counter (sort of local ttl), and silently drop packet when it expires. It is a good solution, but it supposes maintaining new variable in ALL skb, even if no tunneling is used. Current solution: xmit_recursion breaks dead loops. This is a percpu counter, since when we enter the first ndo_xmit(), cpu migration is forbidden. We force an exit if this counter reaches RECURSION_LIMIT 2. Networking dead loops would not kill routers, but would really kill network. IP hop limit plays role of "t->recursion" in this case, if we copy it from packet being encapsulated to upper header. It is very good solution, but it introduces two problems: - Routing protocols, using packets with ttl=1 (OSPF, RIP2), do not work over tunnels. - traceroute does not work. I planned to relay ICMP from tunnel, so that this problem would be solved and traceroute output would even more informative. This idea appeared to be wrong: only Linux complies to rfc1812 now (yes, guys, Linux is the only true router now :-)), all routers (at least, in neighbourhood of mine) return only 8 bytes of payload. It is the end. Hence, if we want that OSPF worked or traceroute said something reasonable, we should search for another solution. One of them is to parse packet trying to detect inner encapsulation made by our node. It is difficult or even impossible, especially, taking into account fragmentation. TO be short, ttl is not solution at all. Current solution: The solution was UNEXPECTEDLY SIMPLE. We force DF flag on tunnels with preconfigured hop limit, that is ALL. :-) Well, it does not remove the problem completely, but exponential growth of network traffic is changed to linear (branches, that exceed pmtu are pruned) and tunnel mtu rapidly degrades to value <68, where looping stops. Yes, it is not good if there exists a router in the loop, which does not force DF, even when encapsulating packets have DF set. But it is not our problem! Nobody could accuse us, we made all that we could make. Even if it is your gated who injected fatal route to network, even if it were you who configured fatal static route: you are innocent. :-) Alexey Kuznetsov. */ 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 struct rtnl_link_ops ipgre_link_ops __read_mostly; static const struct header_ops ipgre_header_ops; static int ipgre_tunnel_init(struct net_device *dev); static void erspan_build_header(struct sk_buff *skb, u32 id, u32 index, bool truncate, bool is_ipv4); static unsigned int ipgre_net_id __read_mostly; static unsigned int gre_tap_net_id __read_mostly; static unsigned int erspan_net_id __read_mostly; static int ipgre_err(struct sk_buff *skb, u32 info, const struct tnl_ptk_info *tpi) { /* 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. Moreover, Cisco "wise men" put GRE key to the third word in GRE header. It makes impossible maintaining even soft state for keyed GRE tunnels with enabled checksum. Tell them "thank you". Well, I wonder, rfc1812 was written by Cisco employee, what the hell these idiots break standards established by themselves??? */ struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn; const struct iphdr *iph; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; unsigned int data_len = 0; struct ip_tunnel *t; if (tpi->proto == htons(ETH_P_TEB)) itn = net_generic(net, gre_tap_net_id); else if (tpi->proto == htons(ETH_P_ERSPAN) || tpi->proto == htons(ETH_P_ERSPAN2)) itn = net_generic(net, erspan_net_id); else itn = net_generic(net, ipgre_net_id); iph = (const struct iphdr *)(icmp_hdr(skb) + 1); t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags, iph->daddr, iph->saddr, tpi->key); if (!t) return -ENOENT; switch (type) { default: case ICMP_PARAMETERPROB: return 0; case ICMP_DEST_UNREACH: switch (code) { case ICMP_SR_FAILED: case ICMP_PORT_UNREACH: /* Impossible event. */ return 0; 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) return 0; data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */ break; case ICMP_REDIRECT: break; } #if IS_ENABLED(CONFIG_IPV6) if (tpi->proto == htons(ETH_P_IPV6) && !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len, type, data_len)) return 0; #endif if (t->parms.iph.daddr == 0 || ipv4_is_multicast(t->parms.iph.daddr)) return 0; if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) return 0; if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO)) t->err_count++; else t->err_count = 1; t->err_time = jiffies; return 0; } static void gre_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. * * Moreover, Cisco "wise men" put GRE key to the third word * in GRE header. It makes impossible maintaining even soft * state for keyed * GRE tunnels with enabled checksum. Tell them "thank you". * * Well, I wonder, rfc1812 was written by Cisco employee, * what the hell these idiots break standards established * by themselves??? */ const struct iphdr *iph = (struct iphdr *)skb->data; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct tnl_ptk_info tpi; if (gre_parse_header(skb, &tpi, NULL, htons(ETH_P_IP), iph->ihl * 4) < 0) return; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, skb->dev->ifindex, IPPROTO_GRE); return; } if (type == ICMP_REDIRECT) { ipv4_redirect(skb, dev_net(skb->dev), skb->dev->ifindex, IPPROTO_GRE); return; } ipgre_err(skb, info, &tpi); } static bool is_erspan_type1(int gre_hdr_len) { /* Both ERSPAN type I (version 0) and type II (version 1) use * protocol 0x88BE, but the type I has only 4-byte GRE header, * while type II has 8-byte. */ return gre_hdr_len == 4; } static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, int gre_hdr_len) { struct net *net = dev_net(skb->dev); struct metadata_dst *tun_dst = NULL; struct erspan_base_hdr *ershdr; struct ip_tunnel_net *itn; struct ip_tunnel *tunnel; const struct iphdr *iph; struct erspan_md2 *md2; int ver; int len; itn = net_generic(net, erspan_net_id); iph = ip_hdr(skb); if (is_erspan_type1(gre_hdr_len)) { ver = 0; tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags | TUNNEL_NO_KEY, iph->saddr, iph->daddr, 0); } else { if (unlikely(!pskb_may_pull(skb, gre_hdr_len + sizeof(*ershdr)))) return PACKET_REJECT; ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); ver = ershdr->ver; iph = ip_hdr(skb); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags | TUNNEL_KEY, iph->saddr, iph->daddr, tpi->key); } if (tunnel) { if (is_erspan_type1(gre_hdr_len)) len = gre_hdr_len; else len = gre_hdr_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) goto drop; if (tunnel->collect_md) { struct erspan_metadata *pkt_md, *md; 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 = ip_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)); md = ip_tunnel_info_opts(&tun_dst->u.tun_info); md->version = ver; md2 = &md->u.md2; memcpy(md2, pkt_md, ver == 1 ? ERSPAN_V1_MDSIZE : ERSPAN_V2_MDSIZE); info = &tun_dst->u.tun_info; info->key.tun_flags |= TUNNEL_ERSPAN_OPT; info->options_len = sizeof(*md); } skb_reset_mac_header(skb); ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); return PACKET_RCVD; } return PACKET_REJECT; drop: kfree_skb(skb); return PACKET_RCVD; } static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct ip_tunnel_net *itn, int hdr_len, bool raw_proto) { struct metadata_dst *tun_dst = NULL; const struct iphdr *iph; struct ip_tunnel *tunnel; iph = ip_hdr(skb); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags, iph->saddr, iph->daddr, tpi->key); if (tunnel) { const struct iphdr *tnl_params; if (__iptunnel_pull_header(skb, hdr_len, tpi->proto, raw_proto, false) < 0) goto drop; /* Special case for ipgre_header_parse(), which expects the * mac_header to point to the outer IP header. */ if (tunnel->dev->header_ops == &ipgre_header_ops) skb_pop_mac_header(skb); else skb_reset_mac_header(skb); tnl_params = &tunnel->parms.iph; if (tunnel->collect_md || tnl_params->daddr == 0) { __be16 flags; __be64 tun_id; flags = tpi->flags & (TUNNEL_CSUM | TUNNEL_KEY); tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, tun_id, 0); if (!tun_dst) return PACKET_REJECT; } ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); return PACKET_RCVD; } return PACKET_NEXT; drop: kfree_skb(skb); return PACKET_RCVD; } static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, int hdr_len) { struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn; int res; if (tpi->proto == htons(ETH_P_TEB)) itn = net_generic(net, gre_tap_net_id); else itn = net_generic(net, ipgre_net_id); res = __ipgre_rcv(skb, tpi, itn, hdr_len, false); if (res == PACKET_NEXT && tpi->proto == htons(ETH_P_TEB)) { /* ipgre tunnels in collect metadata mode should receive * also ETH_P_TEB traffic. */ itn = net_generic(net, ipgre_net_id); res = __ipgre_rcv(skb, tpi, itn, hdr_len, true); } return res; } static int gre_rcv(struct sk_buff *skb) { struct tnl_ptk_info tpi; bool csum_err = false; int hdr_len; #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(ip_hdr(skb)->daddr)) { /* Looped back packet, drop it! */ if (rt_is_output_route(skb_rtable(skb))) goto drop; } #endif hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP), 0); if (hdr_len < 0) goto drop; if (unlikely(tpi.proto == htons(ETH_P_ERSPAN) || tpi.proto == htons(ETH_P_ERSPAN2))) { if (erspan_rcv(skb, &tpi, hdr_len) == PACKET_RCVD) return 0; goto out; } if (ipgre_rcv(skb, &tpi, hdr_len) == PACKET_RCVD) return 0; out: icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); drop: kfree_skb(skb); return 0; } static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); __be16 flags = tunnel->parms.o_flags; /* Push GRE header. */ gre_build_header(skb, tunnel->tun_hlen, flags, proto, tunnel->parms.o_key, (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } 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 gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; int tunnel_hlen; __be16 flags; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET)) goto err_free_skb; key = &tun_info->key; tunnel_hlen = gre_calc_hlen(key->tun_flags); if (skb_cow_head(skb, dev->needed_headroom)) goto err_free_skb; /* Push Tunnel header. */ if (gre_handle_offloads(skb, !!(tun_info->key.tun_flags & TUNNEL_CSUM))) goto err_free_skb; flags = tun_info->key.tun_flags & (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); gre_build_header(skb, tunnel_hlen, flags, proto, tunnel_id_to_key32(tun_info->key.tun_id), (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); return; err_free_skb: kfree_skb(skb); dev->stats.tx_dropped++; } static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; struct erspan_metadata *md; bool truncate = false; __be16 proto; int tunnel_hlen; int version; int nhoff; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET)) goto err_free_skb; key = &tun_info->key; if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) goto err_free_skb; if (tun_info->options_len < sizeof(*md)) goto err_free_skb; md = ip_tunnel_info_opts(tun_info); /* ERSPAN has fixed 8 byte GRE header */ version = md->version; tunnel_hlen = 8 + erspan_hdr_len(version); if (skb_cow_head(skb, dev->needed_headroom)) goto err_free_skb; if (gre_handle_offloads(skb, false)) goto err_free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { pskb_trim(skb, dev->mtu + dev->hard_header_len); 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 (version == 1) { erspan_build_header(skb, ntohl(tunnel_id_to_key32(key->tun_id)), ntohl(md->u.index), truncate, true); proto = htons(ETH_P_ERSPAN); } else if (version == 2) { erspan_build_header_v2(skb, ntohl(tunnel_id_to_key32(key->tun_id)), md->u.md2.dir, get_hwid(&md->u.md2), truncate, true); proto = htons(ETH_P_ERSPAN2); } else { goto err_free_skb; } gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(atomic_fetch_inc(&tunnel->o_seqno))); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); return; err_free_skb: kfree_skb(skb); dev->stats.tx_dropped++; } static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info = skb_tunnel_info(skb); const struct ip_tunnel_key *key; struct rtable *rt; struct flowi4 fl4; if (ip_tunnel_info_af(info) != AF_INET) return -EINVAL; key = &info->key; ip_tunnel_init_flow(&fl4, IPPROTO_GRE, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), key->tos & ~INET_ECN_MASK, dev_net(dev), 0, skb->mark, skb_get_hash(skb), key->flow_flags); rt = ip_route_output_key(dev_net(dev), &fl4); if (IS_ERR(rt)) return PTR_ERR(rt); ip_rt_put(rt); info->key.u.ipv4.src = fl4.saddr; return 0; } static netdev_tx_t ipgre_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tnl_params; if (!pskb_inet_may_pull(skb)) goto free_skb; if (tunnel->collect_md) { gre_fb_xmit(skb, dev, skb->protocol); return NETDEV_TX_OK; } if (dev->header_ops) { int pull_len = tunnel->hlen + sizeof(struct iphdr); if (skb_cow_head(skb, 0)) goto free_skb; if (!pskb_may_pull(skb, pull_len)) goto free_skb; tnl_params = (const struct iphdr *)skb->data; /* ip_tunnel_xmit() needs skb->data pointing to gre header. */ skb_pull(skb, pull_len); skb_reset_mac_header(skb); if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start(skb) < skb->data) goto free_skb; } else { if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; tnl_params = &tunnel->parms.iph; } if (gre_handle_offloads(skb, !!(tunnel->parms.o_flags & TUNNEL_CSUM))) goto free_skb; __gre_xmit(skb, dev, tnl_params, skb->protocol); return NETDEV_TX_OK; free_skb: kfree_skb(skb); dev->stats.tx_dropped++; return NETDEV_TX_OK; } static netdev_tx_t erspan_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); bool truncate = false; __be16 proto; if (!pskb_inet_may_pull(skb)) goto free_skb; if (tunnel->collect_md) { erspan_fb_xmit(skb, dev); return NETDEV_TX_OK; } if (gre_handle_offloads(skb, false)) goto free_skb; if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { pskb_trim(skb, dev->mtu + dev->hard_header_len); truncate = true; } /* Push ERSPAN header */ if (tunnel->erspan_ver == 0) { proto = htons(ETH_P_ERSPAN); tunnel->parms.o_flags &= ~TUNNEL_SEQ; } else if (tunnel->erspan_ver == 1) { erspan_build_header(skb, ntohl(tunnel->parms.o_key), tunnel->index, truncate, true); proto = htons(ETH_P_ERSPAN); } else if (tunnel->erspan_ver == 2) { erspan_build_header_v2(skb, ntohl(tunnel->parms.o_key), tunnel->dir, tunnel->hwid, truncate, true); proto = htons(ETH_P_ERSPAN2); } else { goto free_skb; } tunnel->parms.o_flags &= ~TUNNEL_KEY; __gre_xmit(skb, dev, &tunnel->parms.iph, proto); return NETDEV_TX_OK; free_skb: kfree_skb(skb); dev->stats.tx_dropped++; return NETDEV_TX_OK; } static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); if (!pskb_inet_may_pull(skb)) goto free_skb; if (tunnel->collect_md) { gre_fb_xmit(skb, dev, htons(ETH_P_TEB)); return NETDEV_TX_OK; } if (gre_handle_offloads(skb, !!(tunnel->parms.o_flags & TUNNEL_CSUM))) goto free_skb; if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; __gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_TEB)); return NETDEV_TX_OK; free_skb: kfree_skb(skb); dev->stats.tx_dropped++; return NETDEV_TX_OK; } static void ipgre_link_update(struct net_device *dev, bool set_mtu) { struct ip_tunnel *tunnel = netdev_priv(dev); __be16 flags; int len; len = tunnel->tun_hlen; tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); len = tunnel->tun_hlen - len; tunnel->hlen = tunnel->hlen + len; if (dev->header_ops) dev->hard_header_len += len; else dev->needed_headroom += len; if (set_mtu) dev->mtu = max_t(int, dev->mtu - len, 68); flags = tunnel->parms.o_flags; if (flags & TUNNEL_SEQ || (flags & TUNNEL_CSUM && tunnel->encap.type != TUNNEL_ENCAP_NONE)) { dev->features &= ~NETIF_F_GSO_SOFTWARE; dev->hw_features &= ~NETIF_F_GSO_SOFTWARE; } else { dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_GSO_SOFTWARE; } } static int ipgre_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) { int err; if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { if (p->iph.version != 4 || p->iph.protocol != IPPROTO_GRE || p->iph.ihl != 5 || (p->iph.frag_off & htons(~IP_DF)) || ((p->i_flags | p->o_flags) & (GRE_VERSION | GRE_ROUTING))) return -EINVAL; } p->i_flags = gre_flags_to_tnl_flags(p->i_flags); p->o_flags = gre_flags_to_tnl_flags(p->o_flags); err = ip_tunnel_ctl(dev, p, cmd); if (err) return err; if (cmd == SIOCCHGTUNNEL) { struct ip_tunnel *t = netdev_priv(dev); t->parms.i_flags = p->i_flags; t->parms.o_flags = p->o_flags; if (strcmp(dev->rtnl_link_ops->kind, "erspan")) ipgre_link_update(dev, true); } p->i_flags = gre_tnl_flags_to_gre_flags(p->i_flags); p->o_flags = gre_tnl_flags_to_gre_flags(p->o_flags); return 0; } /* Nice toy. Unfortunately, useless in real life :-) It allows to construct virtual multiprotocol broadcast "LAN" over the Internet, provided multicast routing is tuned. I have no idea was this bicycle invented before me, so that I had to set ARPHRD_IPGRE to a random value. I have an impression, that Cisco could make something similar, but this feature is apparently missing in IOS<=11.2(8). I set up 10.66.66/24 and fec0:6666:6666::0/96 as virtual networks with broadcast 224.66.66.66. If you have access to mbone, play with me :-) ping -t 255 224.66.66.66 If nobody answers, mbone does not work. ip tunnel add Universe mode gre remote 224.66.66.66 local <Your_real_addr> ttl 255 ip addr add 10.66.66.<somewhat>/24 dev Universe ifconfig Universe up ifconfig Universe add fe80::<Your_real_addr>/10 ifconfig Universe add fec0:6666:6666::<Your_real_addr>/96 ftp 10.66.66.66 ... ftp fec0:6666:6666::193.233.7.65 ... */ static int ipgre_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { struct ip_tunnel *t = netdev_priv(dev); struct iphdr *iph; struct gre_base_hdr *greh; iph = skb_push(skb, t->hlen + sizeof(*iph)); greh = (struct gre_base_hdr *)(iph+1); greh->flags = gre_tnl_flags_to_gre_flags(t->parms.o_flags); greh->protocol = htons(type); memcpy(iph, &t->parms.iph, sizeof(struct iphdr)); /* Set the source hardware address. */ if (saddr) memcpy(&iph->saddr, saddr, 4); if (daddr) memcpy(&iph->daddr, daddr, 4); if (iph->daddr) return t->hlen + sizeof(*iph); return -(t->hlen + sizeof(*iph)); } static int ipgre_header_parse(const struct sk_buff *skb, unsigned char *haddr) { const struct iphdr *iph = (const struct iphdr *) skb_mac_header(skb); memcpy(haddr, &iph->saddr, 4); return 4; } static const struct header_ops ipgre_header_ops = { .create = ipgre_header, .parse = ipgre_header_parse, }; #ifdef CONFIG_NET_IPGRE_BROADCAST static int ipgre_open(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); if (ipv4_is_multicast(t->parms.iph.daddr)) { struct flowi4 fl4; struct rtable *rt; rt = ip_route_output_gre(t->net, &fl4, t->parms.iph.daddr, t->parms.iph.saddr, t->parms.o_key, RT_TOS(t->parms.iph.tos), t->parms.link); if (IS_ERR(rt)) return -EADDRNOTAVAIL; dev = rt->dst.dev; ip_rt_put(rt); if (!__in_dev_get_rtnl(dev)) return -EADDRNOTAVAIL; t->mlink = dev->ifindex; ip_mc_inc_group(__in_dev_get_rtnl(dev), t->parms.iph.daddr); } return 0; } static int ipgre_close(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); if (ipv4_is_multicast(t->parms.iph.daddr) && t->mlink) { struct in_device *in_dev; in_dev = inetdev_by_index(t->net, t->mlink); if (in_dev) ip_mc_dec_group(in_dev, t->parms.iph.daddr); } return 0; } #endif static const struct net_device_ops ipgre_netdev_ops = { .ndo_init = ipgre_tunnel_init, .ndo_uninit = ip_tunnel_uninit, #ifdef CONFIG_NET_IPGRE_BROADCAST .ndo_open = ipgre_open, .ndo_stop = ipgre_close, #endif .ndo_start_xmit = ipgre_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 = ipgre_tunnel_ctl, }; #define GRE_FEATURES (NETIF_F_SG | \ NETIF_F_FRAGLIST | \ NETIF_F_HIGHDMA | \ NETIF_F_HW_CSUM) static void ipgre_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipgre_netdev_ops; dev->type = ARPHRD_IPGRE; ip_tunnel_setup(dev, ipgre_net_id); } static void __gre_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel; __be16 flags; tunnel = netdev_priv(dev); tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); tunnel->parms.iph.protocol = IPPROTO_GRE; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; dev->needed_headroom = tunnel->hlen + sizeof(tunnel->parms.iph); dev->features |= GRE_FEATURES | NETIF_F_LLTX; dev->hw_features |= GRE_FEATURES; flags = tunnel->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 && tunnel->encap.type != TUNNEL_ENCAP_NONE) return; dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_GSO_SOFTWARE; } static int ipgre_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; __gre_tunnel_init(dev); __dev_addr_set(dev, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); dev->flags = IFF_NOARP; netif_keep_dst(dev); dev->addr_len = 4; if (iph->daddr && !tunnel->collect_md) { #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { if (!iph->saddr) return -EINVAL; dev->flags = IFF_BROADCAST; dev->header_ops = &ipgre_header_ops; dev->hard_header_len = tunnel->hlen + sizeof(*iph); dev->needed_headroom = 0; } #endif } else if (!tunnel->collect_md) { dev->header_ops = &ipgre_header_ops; dev->hard_header_len = tunnel->hlen + sizeof(*iph); dev->needed_headroom = 0; } return ip_tunnel_init(dev); } static const struct gre_protocol ipgre_protocol = { .handler = gre_rcv, .err_handler = gre_err, }; static int __net_init ipgre_init_net(struct net *net) { return ip_tunnel_init_net(net, ipgre_net_id, &ipgre_link_ops, NULL); } static void __net_exit ipgre_exit_batch_net(struct list_head *list_net) { ip_tunnel_delete_nets(list_net, ipgre_net_id, &ipgre_link_ops); } static struct pernet_operations ipgre_net_ops = { .init = ipgre_init_net, .exit_batch = ipgre_exit_batch_net, .id = &ipgre_net_id, .size = sizeof(struct ip_tunnel_net), }; static int ipgre_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; if (data[IFLA_GRE_COLLECT_METADATA] && data[IFLA_GRE_ENCAP_TYPE] && nla_get_u16(data[IFLA_GRE_ENCAP_TYPE]) != TUNNEL_ENCAP_NONE) return -EINVAL; return 0; } static int ipgre_tap_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { __be32 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]) { memcpy(&daddr, nla_data(data[IFLA_GRE_REMOTE]), 4); if (!daddr) return -EINVAL; } out: return ipgre_tunnel_validate(tb, data, extack); } static int erspan_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { __be16 flags = 0; int ret; if (!data) return 0; ret = ipgre_tap_validate(tb, data, extack); if (ret) return ret; if (data[IFLA_GRE_ERSPAN_VER] && nla_get_u8(data[IFLA_GRE_ERSPAN_VER]) == 0) return 0; /* ERSPAN type II/III 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; return 0; } static int ipgre_netlink_parms(struct net_device *dev, struct nlattr *data[], struct nlattr *tb[], struct ip_tunnel_parm *parms, __u32 *fwmark) { struct ip_tunnel *t = netdev_priv(dev); memset(parms, 0, sizeof(*parms)); parms->iph.protocol = IPPROTO_GRE; if (!data) return 0; 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->iph.saddr = nla_get_in_addr(data[IFLA_GRE_LOCAL]); if (data[IFLA_GRE_REMOTE]) parms->iph.daddr = nla_get_in_addr(data[IFLA_GRE_REMOTE]); if (data[IFLA_GRE_TTL]) parms->iph.ttl = nla_get_u8(data[IFLA_GRE_TTL]); if (data[IFLA_GRE_TOS]) parms->iph.tos = nla_get_u8(data[IFLA_GRE_TOS]); if (!data[IFLA_GRE_PMTUDISC] || nla_get_u8(data[IFLA_GRE_PMTUDISC])) { if (t->ignore_df) return -EINVAL; parms->iph.frag_off = htons(IP_DF); } if (data[IFLA_GRE_COLLECT_METADATA]) { t->collect_md = true; if (dev->type == ARPHRD_IPGRE) dev->type = ARPHRD_NONE; } if (data[IFLA_GRE_IGNORE_DF]) { if (nla_get_u8(data[IFLA_GRE_IGNORE_DF]) && (parms->iph.frag_off & htons(IP_DF))) return -EINVAL; t->ignore_df = !!nla_get_u8(data[IFLA_GRE_IGNORE_DF]); } if (data[IFLA_GRE_FWMARK]) *fwmark = nla_get_u32(data[IFLA_GRE_FWMARK]); return 0; } static int erspan_netlink_parms(struct net_device *dev, struct nlattr *data[], struct nlattr *tb[], struct ip_tunnel_parm *parms, __u32 *fwmark) { struct ip_tunnel *t = netdev_priv(dev); int err; err = ipgre_netlink_parms(dev, data, tb, parms, fwmark); if (err) return err; if (!data) return 0; if (data[IFLA_GRE_ERSPAN_VER]) { t->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); if (t->erspan_ver > 2) return -EINVAL; } if (t->erspan_ver == 1) { if (data[IFLA_GRE_ERSPAN_INDEX]) { t->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]); if (t->index & ~INDEX_MASK) return -EINVAL; } } else if (t->erspan_ver == 2) { if (data[IFLA_GRE_ERSPAN_DIR]) { t->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]); if (t->dir & ~(DIR_MASK >> DIR_OFFSET)) return -EINVAL; } if (data[IFLA_GRE_ERSPAN_HWID]) { t->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]); if (t->hwid & ~(HWID_MASK >> HWID_OFFSET)) return -EINVAL; } } return 0; } /* This function returns true when ENCAP attributes are present in the nl msg */ static bool ipgre_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 gre_tap_init(struct net_device *dev) { __gre_tunnel_init(dev); dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); return ip_tunnel_init(dev); } static const struct net_device_ops gre_tap_netdev_ops = { .ndo_init = gre_tap_init, .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = gre_tap_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_fill_metadata_dst = gre_fill_metadata_dst, }; static int erspan_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); if (tunnel->erspan_ver == 0) tunnel->tun_hlen = 4; /* 4-byte GRE hdr. */ else tunnel->tun_hlen = 8; /* 8-byte GRE hdr. */ tunnel->parms.iph.protocol = IPPROTO_GRE; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen + erspan_hdr_len(tunnel->erspan_ver); dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); return ip_tunnel_init(dev); } static const struct net_device_ops erspan_netdev_ops = { .ndo_init = erspan_tunnel_init, .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = erspan_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_fill_metadata_dst = gre_fill_metadata_dst, }; static void ipgre_tap_setup(struct net_device *dev) { ether_setup(dev); dev->max_mtu = 0; dev->netdev_ops = &gre_tap_netdev_ops; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip_tunnel_setup(dev, gre_tap_net_id); } static int ipgre_newlink_encap_setup(struct net_device *dev, struct nlattr *data[]) { struct ip_tunnel_encap ipencap; if (ipgre_netlink_encap_parms(data, &ipencap)) { struct ip_tunnel *t = netdev_priv(dev); int err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) return err; } return 0; } static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel_parm p; __u32 fwmark = 0; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; return ip_tunnel_newlink(dev, tb, &p, fwmark); } static int erspan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel_parm p; __u32 fwmark = 0; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = erspan_netlink_parms(dev, data, tb, &p, &fwmark); if (err) return err; return ip_tunnel_newlink(dev, tb, &p, fwmark); } static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); __u32 fwmark = t->fwmark; struct ip_tunnel_parm p; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; err = ip_tunnel_changelink(dev, tb, &p, fwmark); if (err < 0) return err; t->parms.i_flags = p.i_flags; t->parms.o_flags = p.o_flags; ipgre_link_update(dev, !tb[IFLA_MTU]); return 0; } static int erspan_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); __u32 fwmark = t->fwmark; struct ip_tunnel_parm p; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = erspan_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; err = ip_tunnel_changelink(dev, tb, &p, fwmark); if (err < 0) return err; t->parms.i_flags = p.i_flags; t->parms.o_flags = p.o_flags; return 0; } static size_t ipgre_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(4) + /* IFLA_GRE_REMOTE */ nla_total_size(4) + /* IFLA_GRE_TTL */ nla_total_size(1) + /* IFLA_GRE_TOS */ nla_total_size(1) + /* IFLA_GRE_PMTUDISC */ nla_total_size(1) + /* 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_IGNORE_DF */ nla_total_size(1) + /* IFLA_GRE_FWMARK */ nla_total_size(4) + /* IFLA_GRE_ERSPAN_INDEX */ nla_total_size(4) + /* IFLA_GRE_ERSPAN_VER */ nla_total_size(1) + /* IFLA_GRE_ERSPAN_DIR */ nla_total_size(1) + /* IFLA_GRE_ERSPAN_HWID */ nla_total_size(2) + 0; } static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm *p = &t->parms; __be16 o_flags = p->o_flags; 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_in_addr(skb, IFLA_GRE_LOCAL, p->iph.saddr) || nla_put_in_addr(skb, IFLA_GRE_REMOTE, p->iph.daddr) || nla_put_u8(skb, IFLA_GRE_TTL, p->iph.ttl) || nla_put_u8(skb, IFLA_GRE_TOS, p->iph.tos) || nla_put_u8(skb, IFLA_GRE_PMTUDISC, !!(p->iph.frag_off & htons(IP_DF))) || nla_put_u32(skb, IFLA_GRE_FWMARK, t->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 (nla_put_u8(skb, IFLA_GRE_IGNORE_DF, t->ignore_df)) goto nla_put_failure; if (t->collect_md) { if (nla_put_flag(skb, IFLA_GRE_COLLECT_METADATA)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static int erspan_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); if (t->erspan_ver <= 2) { if (t->erspan_ver != 0 && !t->collect_md) t->parms.o_flags |= TUNNEL_KEY; if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) goto nla_put_failure; if (t->erspan_ver == 1) { if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index)) goto nla_put_failure; } else if (t->erspan_ver == 2) { if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid)) goto nla_put_failure; } } return ipgre_fill_info(skb, dev); nla_put_failure: return -EMSGSIZE; } static void erspan_setup(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); ether_setup(dev); dev->max_mtu = 0; dev->netdev_ops = &erspan_netdev_ops; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip_tunnel_setup(dev, erspan_net_id); t->erspan_ver = 1; } static const struct nla_policy ipgre_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 iphdr, saddr) }, [IFLA_GRE_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_GRE_TTL] = { .type = NLA_U8 }, [IFLA_GRE_TOS] = { .type = NLA_U8 }, [IFLA_GRE_PMTUDISC] = { .type = NLA_U8 }, [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_IGNORE_DF] = { .type = NLA_U8 }, [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 struct rtnl_link_ops ipgre_link_ops __read_mostly = { .kind = "gre", .maxtype = IFLA_GRE_MAX, .policy = ipgre_policy, .priv_size = sizeof(struct ip_tunnel), .setup = ipgre_tunnel_setup, .validate = ipgre_tunnel_validate, .newlink = ipgre_newlink, .changelink = ipgre_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, .fill_info = ipgre_fill_info, .get_link_net = ip_tunnel_get_link_net, }; static struct rtnl_link_ops ipgre_tap_ops __read_mostly = { .kind = "gretap", .maxtype = IFLA_GRE_MAX, .policy = ipgre_policy, .priv_size = sizeof(struct ip_tunnel), .setup = ipgre_tap_setup, .validate = ipgre_tap_validate, .newlink = ipgre_newlink, .changelink = ipgre_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, .fill_info = ipgre_fill_info, .get_link_net = ip_tunnel_get_link_net, }; static struct rtnl_link_ops erspan_link_ops __read_mostly = { .kind = "erspan", .maxtype = IFLA_GRE_MAX, .policy = ipgre_policy, .priv_size = sizeof(struct ip_tunnel), .setup = erspan_setup, .validate = erspan_validate, .newlink = erspan_newlink, .changelink = erspan_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, .fill_info = erspan_fill_info, .get_link_net = ip_tunnel_get_link_net, }; struct net_device *gretap_fb_dev_create(struct net *net, const char *name, u8 name_assign_type) { struct nlattr *tb[IFLA_MAX + 1]; struct net_device *dev; LIST_HEAD(list_kill); struct ip_tunnel *t; int err; memset(&tb, 0, sizeof(tb)); dev = rtnl_create_link(net, name, name_assign_type, &ipgre_tap_ops, tb, NULL); if (IS_ERR(dev)) return dev; /* Configure flow based GRE device. */ t = netdev_priv(dev); t->collect_md = true; err = ipgre_newlink(net, dev, tb, NULL, NULL); if (err < 0) { free_netdev(dev); return ERR_PTR(err); } /* openvswitch users expect packet sizes to be unrestricted, * so set the largest MTU we can. */ err = __ip_tunnel_change_mtu(dev, IP_MAX_MTU, false); if (err) goto out; err = rtnl_configure_link(dev, NULL); if (err < 0) goto out; return dev; out: ip_tunnel_dellink(dev, &list_kill); unregister_netdevice_many(&list_kill); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(gretap_fb_dev_create); static int __net_init ipgre_tap_init_net(struct net *net) { return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, "gretap0"); } static void __net_exit ipgre_tap_exit_batch_net(struct list_head *list_net) { ip_tunnel_delete_nets(list_net, gre_tap_net_id, &ipgre_tap_ops); } static struct pernet_operations ipgre_tap_net_ops = { .init = ipgre_tap_init_net, .exit_batch = ipgre_tap_exit_batch_net, .id = &gre_tap_net_id, .size = sizeof(struct ip_tunnel_net), }; static int __net_init erspan_init_net(struct net *net) { return ip_tunnel_init_net(net, erspan_net_id, &erspan_link_ops, "erspan0"); } static void __net_exit erspan_exit_batch_net(struct list_head *net_list) { ip_tunnel_delete_nets(net_list, erspan_net_id, &erspan_link_ops); } static struct pernet_operations erspan_net_ops = { .init = erspan_init_net, .exit_batch = erspan_exit_batch_net, .id = &erspan_net_id, .size = sizeof(struct ip_tunnel_net), }; static int __init ipgre_init(void) { int err; pr_info("GRE over IPv4 tunneling driver\n"); err = register_pernet_device(&ipgre_net_ops); if (err < 0) return err; err = register_pernet_device(&ipgre_tap_net_ops); if (err < 0) goto pnet_tap_failed; err = register_pernet_device(&erspan_net_ops); if (err < 0) goto pnet_erspan_failed; err = gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO); if (err < 0) { pr_info("%s: can't add protocol\n", __func__); goto add_proto_failed; } err = rtnl_link_register(&ipgre_link_ops); if (err < 0) goto rtnl_link_failed; err = rtnl_link_register(&ipgre_tap_ops); if (err < 0) goto tap_ops_failed; err = rtnl_link_register(&erspan_link_ops); if (err < 0) goto erspan_link_failed; return 0; erspan_link_failed: rtnl_link_unregister(&ipgre_tap_ops); tap_ops_failed: rtnl_link_unregister(&ipgre_link_ops); rtnl_link_failed: gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); add_proto_failed: unregister_pernet_device(&erspan_net_ops); pnet_erspan_failed: unregister_pernet_device(&ipgre_tap_net_ops); pnet_tap_failed: unregister_pernet_device(&ipgre_net_ops); return err; } static void __exit ipgre_fini(void) { rtnl_link_unregister(&ipgre_tap_ops); rtnl_link_unregister(&ipgre_link_ops); rtnl_link_unregister(&erspan_link_ops); gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); unregister_pernet_device(&ipgre_tap_net_ops); unregister_pernet_device(&ipgre_net_ops); unregister_pernet_device(&erspan_net_ops); } module_init(ipgre_init); module_exit(ipgre_fini); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("gre"); MODULE_ALIAS_RTNL_LINK("gretap"); MODULE_ALIAS_RTNL_LINK("erspan"); MODULE_ALIAS_NETDEV("gre0"); MODULE_ALIAS_NETDEV("gretap0"); MODULE_ALIAS_NETDEV("erspan0"); |
| 15192 11593 14084 11590 8394 6055 9 8420 6993 210 1912 15358 1676 14042 11621 11590 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 | // SPDX-License-Identifier: GPL-2.0-only /* * This implements the various checks for CONFIG_HARDENED_USERCOPY*, * which are designed to protect kernel memory from needless exposure * and overwrite under many unintended conditions. This code is based * on PAX_USERCOPY, which is: * * Copyright (C) 2001-2016 PaX Team, Bradley Spengler, Open Source * Security Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/highmem.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/thread_info.h> #include <linux/vmalloc.h> #include <linux/atomic.h> #include <linux/jump_label.h> #include <asm/sections.h> #include "slab.h" /* * Checks if a given pointer and length is contained by the current * stack frame (if possible). * * Returns: * NOT_STACK: not at all on the stack * GOOD_FRAME: fully within a valid stack frame * GOOD_STACK: within the current stack (when can't frame-check exactly) * BAD_STACK: error condition (invalid stack position or bad stack frame) */ static noinline int check_stack_object(const void *obj, unsigned long len) { const void * const stack = task_stack_page(current); const void * const stackend = stack + THREAD_SIZE; int ret; /* Object is not on the stack at all. */ if (obj + len <= stack || stackend <= obj) return NOT_STACK; /* * Reject: object partially overlaps the stack (passing the * check above means at least one end is within the stack, * so if this check fails, the other end is outside the stack). */ if (obj < stack || stackend < obj + len) return BAD_STACK; /* Check if object is safely within a valid frame. */ ret = arch_within_stack_frames(stack, stackend, obj, len); if (ret) return ret; /* Finally, check stack depth if possible. */ #ifdef CONFIG_ARCH_HAS_CURRENT_STACK_POINTER if (IS_ENABLED(CONFIG_STACK_GROWSUP)) { if ((void *)current_stack_pointer < obj + len) return BAD_STACK; } else { if (obj < (void *)current_stack_pointer) return BAD_STACK; } #endif return GOOD_STACK; } /* * If these functions are reached, then CONFIG_HARDENED_USERCOPY has found * an unexpected state during a copy_from_user() or copy_to_user() call. * There are several checks being performed on the buffer by the * __check_object_size() function. Normal stack buffer usage should never * trip the checks, and kernel text addressing will always trip the check. * For cache objects, it is checking that only the whitelisted range of * bytes for a given cache is being accessed (via the cache's usersize and * useroffset fields). To adjust a cache whitelist, use the usercopy-aware * kmem_cache_create_usercopy() function to create the cache (and * carefully audit the whitelist range). */ void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len) { pr_emerg("Kernel memory %s attempt detected %s %s%s%s%s (offset %lu, size %lu)!\n", to_user ? "exposure" : "overwrite", to_user ? "from" : "to", name ? : "unknown?!", detail ? " '" : "", detail ? : "", detail ? "'" : "", offset, len); /* * For greater effect, it would be nice to do do_group_exit(), * but BUG() actually hooks all the lock-breaking and per-arch * Oops code, so that is used here instead. */ BUG(); } /* Returns true if any portion of [ptr,ptr+n) over laps with [low,high). */ static bool overlaps(const unsigned long ptr, unsigned long n, unsigned long low, unsigned long high) { const unsigned long check_low = ptr; unsigned long check_high = check_low + n; /* Does not overlap if entirely above or entirely below. */ if (check_low >= high || check_high <= low) return false; return true; } /* Is this address range in the kernel text area? */ static inline void check_kernel_text_object(const unsigned long ptr, unsigned long n, bool to_user) { unsigned long textlow = (unsigned long)_stext; unsigned long texthigh = (unsigned long)_etext; unsigned long textlow_linear, texthigh_linear; if (overlaps(ptr, n, textlow, texthigh)) usercopy_abort("kernel text", NULL, to_user, ptr - textlow, n); /* * Some architectures have virtual memory mappings with a secondary * mapping of the kernel text, i.e. there is more than one virtual * kernel address that points to the kernel image. It is usually * when there is a separate linear physical memory mapping, in that * __pa() is not just the reverse of __va(). This can be detected * and checked: */ textlow_linear = (unsigned long)lm_alias(textlow); /* No different mapping: we're done. */ if (textlow_linear == textlow) return; /* Check the secondary mapping... */ texthigh_linear = (unsigned long)lm_alias(texthigh); if (overlaps(ptr, n, textlow_linear, texthigh_linear)) usercopy_abort("linear kernel text", NULL, to_user, ptr - textlow_linear, n); } static inline void check_bogus_address(const unsigned long ptr, unsigned long n, bool to_user) { /* Reject if object wraps past end of memory. */ if (ptr + (n - 1) < ptr) usercopy_abort("wrapped address", NULL, to_user, 0, ptr + n); /* Reject if NULL or ZERO-allocation. */ if (ZERO_OR_NULL_PTR(ptr)) usercopy_abort("null address", NULL, to_user, ptr, n); } static inline void check_heap_object(const void *ptr, unsigned long n, bool to_user) { unsigned long addr = (unsigned long)ptr; unsigned long offset; struct folio *folio; if (is_kmap_addr(ptr)) { offset = offset_in_page(ptr); if (n > PAGE_SIZE - offset) usercopy_abort("kmap", NULL, to_user, offset, n); return; } if (is_vmalloc_addr(ptr) && !pagefault_disabled()) { struct vmap_area *area = find_vmap_area(addr); if (!area) usercopy_abort("vmalloc", "no area", to_user, 0, n); if (n > area->va_end - addr) { offset = addr - area->va_start; usercopy_abort("vmalloc", NULL, to_user, offset, n); } return; } if (!virt_addr_valid(ptr)) return; folio = virt_to_folio(ptr); if (folio_test_slab(folio)) { /* Check slab allocator for flags and size. */ __check_heap_object(ptr, n, folio_slab(folio), to_user); } else if (folio_test_large(folio)) { offset = ptr - folio_address(folio); if (n > folio_size(folio) - offset) usercopy_abort("page alloc", NULL, to_user, offset, n); } } static DEFINE_STATIC_KEY_FALSE_RO(bypass_usercopy_checks); /* * Validates that the given object is: * - not bogus address * - fully contained by stack (or stack frame, when available) * - fully within SLAB object (or object whitelist area, when available) * - not in kernel text */ void __check_object_size(const void *ptr, unsigned long n, bool to_user) { if (static_branch_unlikely(&bypass_usercopy_checks)) return; /* Skip all tests if size is zero. */ if (!n) return; /* Check for invalid addresses. */ check_bogus_address((const unsigned long)ptr, n, to_user); /* Check for bad stack object. */ switch (check_stack_object(ptr, n)) { case NOT_STACK: /* Object is not touching the current process stack. */ break; case GOOD_FRAME: case GOOD_STACK: /* * Object is either in the correct frame (when it * is possible to check) or just generally on the * process stack (when frame checking not available). */ return; default: usercopy_abort("process stack", NULL, to_user, #ifdef CONFIG_ARCH_HAS_CURRENT_STACK_POINTER IS_ENABLED(CONFIG_STACK_GROWSUP) ? ptr - (void *)current_stack_pointer : (void *)current_stack_pointer - ptr, #else 0, #endif n); } /* Check for bad heap object. */ check_heap_object(ptr, n, to_user); /* Check for object in kernel to avoid text exposure. */ check_kernel_text_object((const unsigned long)ptr, n, to_user); } EXPORT_SYMBOL(__check_object_size); static bool enable_checks __initdata = true; static int __init parse_hardened_usercopy(char *str) { if (strtobool(str, &enable_checks)) pr_warn("Invalid option string for hardened_usercopy: '%s'\n", str); return 1; } __setup("hardened_usercopy=", parse_hardened_usercopy); static int __init set_hardened_usercopy(void) { if (enable_checks == false) static_branch_enable(&bypass_usercopy_checks); return 1; } late_initcall(set_hardened_usercopy); |
| 215 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 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 */ |
| 1042 1040 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 | /* 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 */ |
| 597 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _X_TABLES_H #define _X_TABLES_H #include <linux/netdevice.h> #include <linux/static_key.h> #include <linux/netfilter.h> #include <uapi/linux/netfilter/x_tables.h> /* Test a struct->invflags and a boolean for inequality */ #define NF_INVF(ptr, flag, boolean) \ ((boolean) ^ !!((ptr)->invflags & (flag))) /** * struct xt_action_param - parameters for matches/targets * * @match: the match extension * @target: the target extension * @matchinfo: per-match data * @targetinfo: per-target data * @state: pointer to hook state this packet came from * @fragoff: packet is a fragment, this is the data offset * @thoff: position of transport header relative to skb->data * * Fields written to by extensions: * * @hotdrop: drop packet if we had inspection problems */ struct xt_action_param { union { const struct xt_match *match; const struct xt_target *target; }; union { const void *matchinfo, *targinfo; }; const struct nf_hook_state *state; unsigned int thoff; u16 fragoff; bool hotdrop; }; static inline struct net *xt_net(const struct xt_action_param *par) { return par->state->net; } static inline struct net_device *xt_in(const struct xt_action_param *par) { return par->state->in; } static inline const char *xt_inname(const struct xt_action_param *par) { return par->state->in->name; } static inline struct net_device *xt_out(const struct xt_action_param *par) { return par->state->out; } static inline const char *xt_outname(const struct xt_action_param *par) { return par->state->out->name; } static inline unsigned int xt_hooknum(const struct xt_action_param *par) { return par->state->hook; } static inline u_int8_t xt_family(const struct xt_action_param *par) { return par->state->pf; } /** * struct xt_mtchk_param - parameters for match extensions' * checkentry functions * * @net: network namespace through which the check was invoked * @table: table the rule is tried to be inserted into * @entryinfo: the family-specific rule data * (struct ipt_ip, ip6t_ip, arpt_arp or (note) ebt_entry) * @match: struct xt_match through which this function was invoked * @matchinfo: per-match data * @hook_mask: via which hooks the new rule is reachable * Other fields as above. */ struct xt_mtchk_param { struct net *net; const char *table; const void *entryinfo; const struct xt_match *match; void *matchinfo; unsigned int hook_mask; u_int8_t family; bool nft_compat; }; /** * struct xt_mdtor_param - match destructor parameters * Fields as above. */ struct xt_mtdtor_param { struct net *net; const struct xt_match *match; void *matchinfo; u_int8_t family; }; /** * struct xt_tgchk_param - parameters for target extensions' * checkentry functions * * @entryinfo: the family-specific rule data * (struct ipt_entry, ip6t_entry, arpt_entry, ebt_entry) * * Other fields see above. */ struct xt_tgchk_param { struct net *net; const char *table; const void *entryinfo; const struct xt_target *target; void *targinfo; unsigned int hook_mask; u_int8_t family; bool nft_compat; }; /* Target destructor parameters */ struct xt_tgdtor_param { struct net *net; const struct xt_target *target; void *targinfo; u_int8_t family; }; struct xt_match { struct list_head list; const char name[XT_EXTENSION_MAXNAMELEN]; u_int8_t revision; /* Return true or false: return FALSE and set *hotdrop = 1 to force immediate packet drop. */ /* Arguments changed since 2.6.9, as this must now handle non-linear skb, using skb_header_pointer and skb_ip_make_writable. */ bool (*match)(const struct sk_buff *skb, struct xt_action_param *); /* Called when user tries to insert an entry of this type. */ int (*checkentry)(const struct xt_mtchk_param *); /* Called when entry of this type deleted. */ void (*destroy)(const struct xt_mtdtor_param *); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT /* Called when userspace align differs from kernel space one */ void (*compat_from_user)(void *dst, const void *src); int (*compat_to_user)(void __user *dst, const void *src); #endif /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; const char *table; unsigned int matchsize; unsigned int usersize; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT unsigned int compatsize; #endif unsigned int hooks; unsigned short proto; unsigned short family; }; /* Registration hooks for targets. */ struct xt_target { struct list_head list; const char name[XT_EXTENSION_MAXNAMELEN]; u_int8_t revision; /* Returns verdict. Argument order changed since 2.6.9, as this must now handle non-linear skbs, using skb_copy_bits and skb_ip_make_writable. */ unsigned int (*target)(struct sk_buff *skb, const struct xt_action_param *); /* Called when user tries to insert an entry of this type: hook_mask is a bitmask of hooks from which it can be called. */ /* Should return 0 on success or an error code otherwise (-Exxxx). */ int (*checkentry)(const struct xt_tgchk_param *); /* Called when entry of this type deleted. */ void (*destroy)(const struct xt_tgdtor_param *); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT /* Called when userspace align differs from kernel space one */ void (*compat_from_user)(void *dst, const void *src); int (*compat_to_user)(void __user *dst, const void *src); #endif /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; const char *table; unsigned int targetsize; unsigned int usersize; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT unsigned int compatsize; #endif unsigned int hooks; unsigned short proto; unsigned short family; }; /* Furniture shopping... */ struct xt_table { struct list_head list; /* What hooks you will enter on */ unsigned int valid_hooks; /* Man behind the curtain... */ struct xt_table_info *private; /* hook ops that register the table with the netfilter core */ struct nf_hook_ops *ops; /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; u_int8_t af; /* address/protocol family */ int priority; /* hook order */ /* A unique name... */ const char name[XT_TABLE_MAXNAMELEN]; }; #include <linux/netfilter_ipv4.h> /* The table itself */ struct xt_table_info { /* Size per table */ unsigned int size; /* Number of entries: FIXME. --RR */ unsigned int number; /* Initial number of entries. Needed for module usage count */ unsigned int initial_entries; /* Entry points and underflows */ unsigned int hook_entry[NF_INET_NUMHOOKS]; unsigned int underflow[NF_INET_NUMHOOKS]; /* * Number of user chains. Since tables cannot have loops, at most * @stacksize jumps (number of user chains) can possibly be made. */ unsigned int stacksize; void ***jumpstack; unsigned char entries[] __aligned(8); }; int xt_register_target(struct xt_target *target); void xt_unregister_target(struct xt_target *target); int xt_register_targets(struct xt_target *target, unsigned int n); void xt_unregister_targets(struct xt_target *target, unsigned int n); int xt_register_match(struct xt_match *target); void xt_unregister_match(struct xt_match *target); int xt_register_matches(struct xt_match *match, unsigned int n); void xt_unregister_matches(struct xt_match *match, unsigned int n); int xt_check_entry_offsets(const void *base, const char *elems, unsigned int target_offset, unsigned int next_offset); int xt_check_table_hooks(const struct xt_table_info *info, unsigned int valid_hooks); unsigned int *xt_alloc_entry_offsets(unsigned int size); bool xt_find_jump_offset(const unsigned int *offsets, unsigned int target, unsigned int size); int xt_check_proc_name(const char *name, unsigned int size); int xt_check_match(struct xt_mtchk_param *, unsigned int size, u16 proto, bool inv_proto); int xt_check_target(struct xt_tgchk_param *, unsigned int size, u16 proto, bool inv_proto); int xt_match_to_user(const struct xt_entry_match *m, struct xt_entry_match __user *u); int xt_target_to_user(const struct xt_entry_target *t, struct xt_entry_target __user *u); int xt_data_to_user(void __user *dst, const void *src, int usersize, int size, int aligned_size); void *xt_copy_counters(sockptr_t arg, unsigned int len, struct xt_counters_info *info); struct xt_counters *xt_counters_alloc(unsigned int counters); struct xt_table *xt_register_table(struct net *net, const struct xt_table *table, struct xt_table_info *bootstrap, struct xt_table_info *newinfo); void *xt_unregister_table(struct xt_table *table); struct xt_table_info *xt_replace_table(struct xt_table *table, unsigned int num_counters, struct xt_table_info *newinfo, int *error); struct xt_match *xt_find_match(u8 af, const char *name, u8 revision); struct xt_match *xt_request_find_match(u8 af, const char *name, u8 revision); struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision); int xt_find_revision(u8 af, const char *name, u8 revision, int target, int *err); struct xt_table *xt_find_table(struct net *net, u8 af, const char *name); struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af, const char *name); struct xt_table *xt_request_find_table_lock(struct net *net, u_int8_t af, const char *name); void xt_table_unlock(struct xt_table *t); int xt_proto_init(struct net *net, u_int8_t af); void xt_proto_fini(struct net *net, u_int8_t af); struct xt_table_info *xt_alloc_table_info(unsigned int size); void xt_free_table_info(struct xt_table_info *info); /** * xt_recseq - recursive seqcount for netfilter use * * Packet processing changes the seqcount only if no recursion happened * get_counters() can use read_seqcount_begin()/read_seqcount_retry(), * because we use the normal seqcount convention : * Low order bit set to 1 if a writer is active. */ DECLARE_PER_CPU(seqcount_t, xt_recseq); /* xt_tee_enabled - true if x_tables needs to handle reentrancy * * Enabled if current ip(6)tables ruleset has at least one -j TEE rule. */ extern struct static_key xt_tee_enabled; /** * xt_write_recseq_begin - start of a write section * * Begin packet processing : all readers must wait the end * 1) Must be called with preemption disabled * 2) softirqs must be disabled too (or we should use this_cpu_add()) * Returns : * 1 if no recursion on this cpu * 0 if recursion detected */ static inline unsigned int xt_write_recseq_begin(void) { unsigned int addend; /* * Low order bit of sequence is set if we already * called xt_write_recseq_begin(). */ addend = (__this_cpu_read(xt_recseq.sequence) + 1) & 1; /* * This is kind of a write_seqcount_begin(), but addend is 0 or 1 * We dont check addend value to avoid a test and conditional jump, * since addend is most likely 1 */ __this_cpu_add(xt_recseq.sequence, addend); smp_mb(); return addend; } /** * xt_write_recseq_end - end of a write section * @addend: return value from previous xt_write_recseq_begin() * * End packet processing : all readers can proceed * 1) Must be called with preemption disabled * 2) softirqs must be disabled too (or we should use this_cpu_add()) */ static inline void xt_write_recseq_end(unsigned int addend) { /* this is kind of a write_seqcount_end(), but addend is 0 or 1 */ smp_wmb(); __this_cpu_add(xt_recseq.sequence, addend); } /* * This helper is performance critical and must be inlined */ static inline unsigned long ifname_compare_aligned(const char *_a, const char *_b, const char *_mask) { const unsigned long *a = (const unsigned long *)_a; const unsigned long *b = (const unsigned long *)_b; const unsigned long *mask = (const unsigned long *)_mask; unsigned long ret; ret = (a[0] ^ b[0]) & mask[0]; if (IFNAMSIZ > sizeof(unsigned long)) ret |= (a[1] ^ b[1]) & mask[1]; if (IFNAMSIZ > 2 * sizeof(unsigned long)) ret |= (a[2] ^ b[2]) & mask[2]; if (IFNAMSIZ > 3 * sizeof(unsigned long)) ret |= (a[3] ^ b[3]) & mask[3]; BUILD_BUG_ON(IFNAMSIZ > 4 * sizeof(unsigned long)); return ret; } struct xt_percpu_counter_alloc_state { unsigned int off; const char __percpu *mem; }; bool xt_percpu_counter_alloc(struct xt_percpu_counter_alloc_state *state, struct xt_counters *counter); void xt_percpu_counter_free(struct xt_counters *cnt); static inline struct xt_counters * xt_get_this_cpu_counter(struct xt_counters *cnt) { if (nr_cpu_ids > 1) return this_cpu_ptr((void __percpu *) (unsigned long) cnt->pcnt); return cnt; } static inline struct xt_counters * xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu) { if (nr_cpu_ids > 1) return per_cpu_ptr((void __percpu *) (unsigned long) cnt->pcnt, cpu); return cnt; } struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *); int xt_register_template(const struct xt_table *t, int(*table_init)(struct net *net)); void xt_unregister_template(const struct xt_table *t); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT #include <net/compat.h> struct compat_xt_entry_match { union { struct { u_int16_t match_size; char name[XT_FUNCTION_MAXNAMELEN - 1]; u_int8_t revision; } user; struct { u_int16_t match_size; compat_uptr_t match; } kernel; u_int16_t match_size; } u; unsigned char data[]; }; struct compat_xt_entry_target { union { struct { u_int16_t target_size; char name[XT_FUNCTION_MAXNAMELEN - 1]; u_int8_t revision; } user; struct { u_int16_t target_size; compat_uptr_t target; } kernel; u_int16_t target_size; } u; unsigned char data[]; }; /* FIXME: this works only on 32 bit tasks * need to change whole approach in order to calculate align as function of * current task alignment */ struct compat_xt_counters { compat_u64 pcnt, bcnt; /* Packet and byte counters */ }; struct compat_xt_counters_info { char name[XT_TABLE_MAXNAMELEN]; compat_uint_t num_counters; struct compat_xt_counters counters[]; }; struct _compat_xt_align { __u8 u8; __u16 u16; __u32 u32; compat_u64 u64; }; #define COMPAT_XT_ALIGN(s) __ALIGN_KERNEL((s), __alignof__(struct _compat_xt_align)) void xt_compat_lock(u_int8_t af); void xt_compat_unlock(u_int8_t af); int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta); void xt_compat_flush_offsets(u_int8_t af); int xt_compat_init_offsets(u8 af, unsigned int number); int xt_compat_calc_jump(u_int8_t af, unsigned int offset); int xt_compat_match_offset(const struct xt_match *match); void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, unsigned int *size); int xt_compat_match_to_user(const struct xt_entry_match *m, void __user **dstptr, unsigned int *size); int xt_compat_target_offset(const struct xt_target *target); void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, unsigned int *size); int xt_compat_target_to_user(const struct xt_entry_target *t, void __user **dstptr, unsigned int *size); int xt_compat_check_entry_offsets(const void *base, const char *elems, unsigned int target_offset, unsigned int next_offset); #endif /* CONFIG_NETFILTER_XTABLES_COMPAT */ #endif /* _X_TABLES_H */ |
| 2163 2163 666 667 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 | // 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); |
| 4646 1634 7865 2152 117 8568 4 8573 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 | // SPDX-License-Identifier: GPL-2.0 #include <linux/compiler.h> #include <linux/export.h> #include <linux/fault-inject-usercopy.h> #include <linux/kasan-checks.h> #include <linux/thread_info.h> #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/mm.h> #include <asm/byteorder.h> #include <asm/word-at-a-time.h> #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS #define IS_UNALIGNED(src, dst) 0 #else #define IS_UNALIGNED(src, dst) \ (((long) dst | (long) src) & (sizeof(long) - 1)) #endif /* * Do a strncpy, return length of string without final '\0'. * 'count' is the user-supplied count (return 'count' if we * hit it), 'max' is the address space maximum (and we return * -EFAULT if we hit it). */ static __always_inline long do_strncpy_from_user(char *dst, const char __user *src, unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; unsigned long res = 0; if (IS_UNALIGNED(src, dst)) goto byte_at_a_time; while (max >= sizeof(unsigned long)) { unsigned long c, data, mask; /* Fall back to byte-at-a-time if we get a page fault */ unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time); /* * Note that we mask out the bytes following the NUL. This is * important to do because string oblivious code may read past * the NUL. For those routines, we don't want to give them * potentially random bytes after the NUL in `src`. * * One example of such code is BPF map keys. BPF treats map keys * as an opaque set of bytes. Without the post-NUL mask, any BPF * maps keyed by strings returned from strncpy_from_user() may * have multiple entries for semantically identical strings. */ if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); data = create_zero_mask(data); mask = zero_bytemask(data); *(unsigned long *)(dst+res) = c & mask; return res + find_zero(data); } *(unsigned long *)(dst+res) = c; res += sizeof(unsigned long); max -= sizeof(unsigned long); } byte_at_a_time: while (max) { char c; unsafe_get_user(c,src+res, efault); dst[res] = c; if (!c) return res; res++; max--; } /* * Uhhuh. We hit 'max'. But was that the user-specified maximum * too? If so, that's ok - we got as much as the user asked for. */ if (res >= count) return res; /* * Nope: we hit the address space limit, and we still had more * characters the caller would have wanted. That's an EFAULT. */ efault: return -EFAULT; } /** * strncpy_from_user: - Copy a NUL terminated string from userspace. * @dst: Destination address, in kernel space. This buffer must be at * least @count bytes long. * @src: Source address, in user space. * @count: Maximum number of bytes to copy, including the trailing NUL. * * Copies a NUL-terminated string from userspace to kernel space. * * On success, returns the length of the string (not including the trailing * NUL). * * If access to userspace fails, returns -EFAULT (some data may have been * copied). * * If @count is smaller than the length of the string, copies @count bytes * and returns @count. */ long strncpy_from_user(char *dst, const char __user *src, long count) { unsigned long max_addr, src_addr; might_fault(); if (should_fail_usercopy()) return -EFAULT; if (unlikely(count <= 0)) return 0; max_addr = TASK_SIZE_MAX; src_addr = (unsigned long)untagged_addr(src); if (likely(src_addr < max_addr)) { unsigned long max = max_addr - src_addr; long retval; /* * Truncate 'max' to the user-specified limit, so that * we only have one limit we need to check in the loop */ if (max > count) max = count; kasan_check_write(dst, count); check_object_size(dst, count, false); if (user_read_access_begin(src, max)) { retval = do_strncpy_from_user(dst, src, count, max); user_read_access_end(); return retval; } } return -EFAULT; } EXPORT_SYMBOL(strncpy_from_user); |
| 5184 5184 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_PGTABLE_INVERT_H #define _ASM_PGTABLE_INVERT_H 1 #ifndef __ASSEMBLY__ /* * A clear pte value is special, and doesn't get inverted. * * Note that even users that only pass a pgprot_t (rather * than a full pte) won't trigger the special zero case, * because even PAGE_NONE has _PAGE_PROTNONE | _PAGE_ACCESSED * set. So the all zero case really is limited to just the * cleared page table entry case. */ static inline bool __pte_needs_invert(u64 val) { return val && !(val & _PAGE_PRESENT); } /* Get a mask to xor with the page table entry to get the correct pfn. */ static inline u64 protnone_mask(u64 val) { return __pte_needs_invert(val) ? ~0ull : 0; } static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask) { /* * When a PTE transitions from NONE to !NONE or vice-versa * invert the PFN part to stop speculation. * pte_pfn undoes this when needed. */ if (__pte_needs_invert(oldval) != __pte_needs_invert(val)) val = (val & ~mask) | (~val & mask); return val; } #endif /* __ASSEMBLY__ */ #endif |
| 2 2 74 74 62 3 11 21 3 8 10 14 54 2 3 5 6 25 4 27 21 8 25 23 42 2 4 2 4 4 1 3 3 2 1 19 347 74 414 350 74 73 74 54 423 14 14 14 14 9 5 14 9 5 110 110 4 834 63 836 64 833 838 3 14 14 835 835 309 8 61 12 46 54 41 12 1 40 451 405 96 404 19 56 423 4 32 5 30 31 31 2 7 25 2 6 5 1 2 2 10 10 2 9 8 4 3 10 6 2 6 1 6 586 31 346 69 14 17 242 1 13 52 12 52 6 22 3 19 21 3 65 414 271 80 260 833 523 524 227 26 16 39 4 217 237 266 3 525 524 234 235 235 325 326 29 29 29 326 324 324 38 1 26 2 4 1 1 1 1 1 210 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/export.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/if_vlan.h> #include <linux/filter.h> #include <net/dsa.h> #include <net/dst_metadata.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/gre.h> #include <net/pptp.h> #include <net/tipc.h> #include <linux/igmp.h> #include <linux/icmp.h> #include <linux/sctp.h> #include <linux/dccp.h> #include <linux/if_tunnel.h> #include <linux/if_pppox.h> #include <linux/ppp_defs.h> #include <linux/stddef.h> #include <linux/if_ether.h> #include <linux/if_hsr.h> #include <linux/mpls.h> #include <linux/tcp.h> #include <linux/ptp_classify.h> #include <net/flow_dissector.h> #include <scsi/fc/fc_fcoe.h> #include <uapi/linux/batadv_packet.h> #include <linux/bpf.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_labels.h> #endif #include <linux/bpf-netns.h> static void dissector_set_key(struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id) { flow_dissector->used_keys |= (1 << key_id); } void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count) { unsigned int i; memset(flow_dissector, 0, sizeof(*flow_dissector)); for (i = 0; i < key_count; i++, key++) { /* User should make sure that every key target offset is within * boundaries of unsigned short. */ BUG_ON(key->offset > USHRT_MAX); BUG_ON(dissector_uses_key(flow_dissector, key->key_id)); dissector_set_key(flow_dissector, key->key_id); flow_dissector->offset[key->key_id] = key->offset; } /* Ensure that the dissector always includes control and basic key. * That way we are able to avoid handling lack of these in fast path. */ BUG_ON(!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_CONTROL)); BUG_ON(!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_BASIC)); } EXPORT_SYMBOL(skb_flow_dissector_init); #ifdef CONFIG_BPF_SYSCALL int flow_dissector_bpf_prog_attach_check(struct net *net, struct bpf_prog *prog) { enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; if (net == &init_net) { /* BPF flow dissector in the root namespace overrides * any per-net-namespace one. When attaching to root, * make sure we don't have any BPF program attached * to the non-root namespaces. */ struct net *ns; for_each_net(ns) { if (ns == &init_net) continue; if (rcu_access_pointer(ns->bpf.run_array[type])) return -EEXIST; } } else { /* Make sure root flow dissector is not attached * when attaching to the non-root namespace. */ if (rcu_access_pointer(init_net.bpf.run_array[type])) return -EEXIST; } return 0; } #endif /* CONFIG_BPF_SYSCALL */ /** * __skb_flow_get_ports - extract the upper layer ports and return them * @skb: sk_buff to extract the ports from * @thoff: transport header offset * @ip_proto: protocol for which to get port offset * @data: raw buffer pointer to the packet, if NULL use skb->data * @hlen: packet header length, if @data is NULL use skb_headlen(skb) * * The function will try to retrieve the ports at offset thoff + poff where poff * is the protocol port offset returned from proto_ports_offset */ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, const void *data, int hlen) { int poff = proto_ports_offset(ip_proto); if (!data) { data = skb->data; hlen = skb_headlen(skb); } if (poff >= 0) { __be32 *ports, _ports; ports = __skb_header_pointer(skb, thoff + poff, sizeof(_ports), data, hlen, &_ports); if (ports) return *ports; } return 0; } EXPORT_SYMBOL(__skb_flow_get_ports); static bool icmp_has_id(u8 type) { switch (type) { case ICMP_ECHO: case ICMP_ECHOREPLY: case ICMP_TIMESTAMP: case ICMP_TIMESTAMPREPLY: case ICMPV6_ECHO_REQUEST: case ICMPV6_ECHO_REPLY: return true; } return false; } /** * skb_flow_get_icmp_tci - extract ICMP(6) Type, Code and Identifier fields * @skb: sk_buff to extract from * @key_icmp: struct flow_dissector_key_icmp to fill * @data: raw buffer pointer to the packet * @thoff: offset to extract at * @hlen: packet header length */ void skb_flow_get_icmp_tci(const struct sk_buff *skb, struct flow_dissector_key_icmp *key_icmp, const void *data, int thoff, int hlen) { struct icmphdr *ih, _ih; ih = __skb_header_pointer(skb, thoff, sizeof(_ih), data, hlen, &_ih); if (!ih) return; key_icmp->type = ih->type; key_icmp->code = ih->code; /* As we use 0 to signal that the Id field is not present, * avoid confusion with packets without such field */ if (icmp_has_id(ih->type)) key_icmp->id = ih->un.echo.id ? ntohs(ih->un.echo.id) : 1; else key_icmp->id = 0; } EXPORT_SYMBOL(skb_flow_get_icmp_tci); /* If FLOW_DISSECTOR_KEY_ICMP is set, dissect an ICMP packet * using skb_flow_get_icmp_tci(). */ static void __skb_flow_dissect_icmp(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int thoff, int hlen) { struct flow_dissector_key_icmp *key_icmp; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ICMP)) return; key_icmp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ICMP, target_container); skb_flow_get_icmp_tci(skb, key_icmp, data, thoff, hlen); } static void __skb_flow_dissect_l2tpv3(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen) { struct flow_dissector_key_l2tpv3 *key_l2tpv3; struct { __be32 session_id; } *hdr, _hdr; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_L2TPV3)) return; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) return; key_l2tpv3 = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_L2TPV3, target_container); key_l2tpv3->session_id = hdr->session_id; } void skb_flow_dissect_meta(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container) { struct flow_dissector_key_meta *meta; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_META)) return; meta = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_META, target_container); meta->ingress_ifindex = skb->skb_iif; } EXPORT_SYMBOL(skb_flow_dissect_meta); static void skb_flow_dissect_set_enc_addr_type(enum flow_dissector_key_id type, struct flow_dissector *flow_dissector, void *target_container) { struct flow_dissector_key_control *ctrl; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL)) return; ctrl = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL, target_container); ctrl->addr_type = type; } void skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, u16 *ctinfo_map, size_t mapsize, bool post_ct, u16 zone) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) struct flow_dissector_key_ct *key; enum ip_conntrack_info ctinfo; struct nf_conn_labels *cl; struct nf_conn *ct; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_CT)) return; ct = nf_ct_get(skb, &ctinfo); if (!ct && !post_ct) return; key = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CT, target_container); if (!ct) { key->ct_state = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | TCA_FLOWER_KEY_CT_FLAGS_INVALID; key->ct_zone = zone; return; } if (ctinfo < mapsize) key->ct_state = ctinfo_map[ctinfo]; #if IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) key->ct_zone = ct->zone.id; #endif #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) key->ct_mark = READ_ONCE(ct->mark); #endif cl = nf_ct_labels_find(ct); if (cl) memcpy(key->ct_labels, cl->bits, sizeof(key->ct_labels)); #endif /* CONFIG_NF_CONNTRACK */ } EXPORT_SYMBOL(skb_flow_dissect_ct); void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container) { struct ip_tunnel_info *info; struct ip_tunnel_key *key; /* A quick check to see if there might be something to do. */ if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_KEYID) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_PORTS) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IP) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS)) return; info = skb_tunnel_info(skb); if (!info) return; key = &info->key; switch (ip_tunnel_info_af(info)) { case AF_INET: skb_flow_dissect_set_enc_addr_type(FLOW_DISSECTOR_KEY_IPV4_ADDRS, flow_dissector, target_container); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { struct flow_dissector_key_ipv4_addrs *ipv4; ipv4 = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, target_container); ipv4->src = key->u.ipv4.src; ipv4->dst = key->u.ipv4.dst; } break; case AF_INET6: skb_flow_dissect_set_enc_addr_type(FLOW_DISSECTOR_KEY_IPV6_ADDRS, flow_dissector, target_container); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) { struct flow_dissector_key_ipv6_addrs *ipv6; ipv6 = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, target_container); ipv6->src = key->u.ipv6.src; ipv6->dst = key->u.ipv6.dst; } break; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { struct flow_dissector_key_keyid *keyid; keyid = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_KEYID, target_container); keyid->keyid = tunnel_id_to_key32(key->tun_id); } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) { struct flow_dissector_key_ports *tp; tp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_PORTS, target_container); tp->src = key->tp_src; tp->dst = key->tp_dst; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IP)) { struct flow_dissector_key_ip *ip; ip = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IP, target_container); ip->tos = key->tos; ip->ttl = key->ttl; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS)) { struct flow_dissector_key_enc_opts *enc_opt; enc_opt = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS, target_container); if (info->options_len) { enc_opt->len = info->options_len; ip_tunnel_info_opts_get(enc_opt->data, info); enc_opt->dst_opt_type = info->key.tun_flags & TUNNEL_OPTIONS_PRESENT; } } } EXPORT_SYMBOL(skb_flow_dissect_tunnel_info); void skb_flow_dissect_hash(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container) { struct flow_dissector_key_hash *key; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_HASH)) return; key = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_HASH, target_container); key->hash = skb_get_hash_raw(skb); } EXPORT_SYMBOL(skb_flow_dissect_hash); static enum flow_dissect_ret __skb_flow_dissect_mpls(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen, int lse_index, bool *entropy_label) { struct mpls_label *hdr, _hdr; u32 entry, label, bos; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS_ENTROPY) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS)) return FLOW_DISSECT_RET_OUT_GOOD; if (lse_index >= FLOW_DIS_MPLS_MAX) return FLOW_DISSECT_RET_OUT_GOOD; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) return FLOW_DISSECT_RET_OUT_BAD; entry = ntohl(hdr->entry); label = (entry & MPLS_LS_LABEL_MASK) >> MPLS_LS_LABEL_SHIFT; bos = (entry & MPLS_LS_S_MASK) >> MPLS_LS_S_SHIFT; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS)) { struct flow_dissector_key_mpls *key_mpls; struct flow_dissector_mpls_lse *lse; key_mpls = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_MPLS, target_container); lse = &key_mpls->ls[lse_index]; lse->mpls_ttl = (entry & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT; lse->mpls_bos = bos; lse->mpls_tc = (entry & MPLS_LS_TC_MASK) >> MPLS_LS_TC_SHIFT; lse->mpls_label = label; dissector_set_mpls_lse(key_mpls, lse_index); } if (*entropy_label && dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) { struct flow_dissector_key_keyid *key_keyid; key_keyid = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_MPLS_ENTROPY, target_container); key_keyid->keyid = cpu_to_be32(label); } *entropy_label = label == MPLS_LABEL_ENTROPY; return bos ? FLOW_DISSECT_RET_OUT_GOOD : FLOW_DISSECT_RET_PROTO_AGAIN; } static enum flow_dissect_ret __skb_flow_dissect_arp(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen) { struct flow_dissector_key_arp *key_arp; struct { unsigned char ar_sha[ETH_ALEN]; unsigned char ar_sip[4]; unsigned char ar_tha[ETH_ALEN]; unsigned char ar_tip[4]; } *arp_eth, _arp_eth; const struct arphdr *arp; struct arphdr _arp; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ARP)) return FLOW_DISSECT_RET_OUT_GOOD; arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data, hlen, &_arp); if (!arp) return FLOW_DISSECT_RET_OUT_BAD; if (arp->ar_hrd != htons(ARPHRD_ETHER) || arp->ar_pro != htons(ETH_P_IP) || arp->ar_hln != ETH_ALEN || arp->ar_pln != 4 || (arp->ar_op != htons(ARPOP_REPLY) && arp->ar_op != htons(ARPOP_REQUEST))) return FLOW_DISSECT_RET_OUT_BAD; arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp), sizeof(_arp_eth), data, hlen, &_arp_eth); if (!arp_eth) return FLOW_DISSECT_RET_OUT_BAD; key_arp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ARP, target_container); memcpy(&key_arp->sip, arp_eth->ar_sip, sizeof(key_arp->sip)); memcpy(&key_arp->tip, arp_eth->ar_tip, sizeof(key_arp->tip)); /* Only store the lower byte of the opcode; * this covers ARPOP_REPLY and ARPOP_REQUEST. */ key_arp->op = ntohs(arp->ar_op) & 0xff; ether_addr_copy(key_arp->sha, arp_eth->ar_sha); ether_addr_copy(key_arp->tha, arp_eth->ar_tha); return FLOW_DISSECT_RET_OUT_GOOD; } static enum flow_dissect_ret __skb_flow_dissect_gre(const struct sk_buff *skb, struct flow_dissector_key_control *key_control, struct flow_dissector *flow_dissector, void *target_container, const void *data, __be16 *p_proto, int *p_nhoff, int *p_hlen, unsigned int flags) { struct flow_dissector_key_keyid *key_keyid; struct gre_base_hdr *hdr, _hdr; int offset = 0; u16 gre_ver; hdr = __skb_header_pointer(skb, *p_nhoff, sizeof(_hdr), data, *p_hlen, &_hdr); if (!hdr) return FLOW_DISSECT_RET_OUT_BAD; /* Only look inside GRE without routing */ if (hdr->flags & GRE_ROUTING) return FLOW_DISSECT_RET_OUT_GOOD; /* Only look inside GRE for version 0 and 1 */ gre_ver = ntohs(hdr->flags & GRE_VERSION); if (gre_ver > 1) return FLOW_DISSECT_RET_OUT_GOOD; *p_proto = hdr->protocol; if (gre_ver) { /* Version1 must be PPTP, and check the flags */ if (!(*p_proto == GRE_PROTO_PPP && (hdr->flags & GRE_KEY))) return FLOW_DISSECT_RET_OUT_GOOD; } offset += sizeof(struct gre_base_hdr); if (hdr->flags & GRE_CSUM) offset += sizeof_field(struct gre_full_hdr, csum) + sizeof_field(struct gre_full_hdr, reserved1); if (hdr->flags & GRE_KEY) { const __be32 *keyid; __be32 _keyid; keyid = __skb_header_pointer(skb, *p_nhoff + offset, sizeof(_keyid), data, *p_hlen, &_keyid); if (!keyid) return FLOW_DISSECT_RET_OUT_BAD; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_GRE_KEYID)) { key_keyid = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_GRE_KEYID, target_container); if (gre_ver == 0) key_keyid->keyid = *keyid; else key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK; } offset += sizeof_field(struct gre_full_hdr, key); } if (hdr->flags & GRE_SEQ) offset += sizeof_field(struct pptp_gre_header, seq); if (gre_ver == 0) { if (*p_proto == htons(ETH_P_TEB)) { const struct ethhdr *eth; struct ethhdr _eth; eth = __skb_header_pointer(skb, *p_nhoff + offset, sizeof(_eth), data, *p_hlen, &_eth); if (!eth) return FLOW_DISSECT_RET_OUT_BAD; *p_proto = eth->h_proto; offset += sizeof(*eth); /* Cap headers that we access via pointers at the * end of the Ethernet header as our maximum alignment * at that point is only 2 bytes. */ if (NET_IP_ALIGN) *p_hlen = *p_nhoff + offset; } } else { /* version 1, must be PPTP */ u8 _ppp_hdr[PPP_HDRLEN]; u8 *ppp_hdr; if (hdr->flags & GRE_ACK) offset += sizeof_field(struct pptp_gre_header, ack); ppp_hdr = __skb_header_pointer(skb, *p_nhoff + offset, sizeof(_ppp_hdr), data, *p_hlen, _ppp_hdr); if (!ppp_hdr) return FLOW_DISSECT_RET_OUT_BAD; switch (PPP_PROTOCOL(ppp_hdr)) { case PPP_IP: *p_proto = htons(ETH_P_IP); break; case PPP_IPV6: *p_proto = htons(ETH_P_IPV6); break; default: /* Could probably catch some more like MPLS */ break; } offset += PPP_HDRLEN; } *p_nhoff += offset; key_control->flags |= FLOW_DIS_ENCAPSULATION; if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) return FLOW_DISSECT_RET_OUT_GOOD; return FLOW_DISSECT_RET_PROTO_AGAIN; } /** * __skb_flow_dissect_batadv() - dissect batman-adv header * @skb: sk_buff to with the batman-adv header * @key_control: flow dissectors control key * @data: raw buffer pointer to the packet, if NULL use skb->data * @p_proto: pointer used to update the protocol to process next * @p_nhoff: pointer used to update inner network header offset * @hlen: packet header length * @flags: any combination of FLOW_DISSECTOR_F_* * * ETH_P_BATMAN packets are tried to be dissected. Only * &struct batadv_unicast packets are actually processed because they contain an * inner ethernet header and are usually followed by actual network header. This * allows the flow dissector to continue processing the packet. * * Return: FLOW_DISSECT_RET_PROTO_AGAIN when &struct batadv_unicast was found, * FLOW_DISSECT_RET_OUT_GOOD when dissector should stop after encapsulation, * otherwise FLOW_DISSECT_RET_OUT_BAD */ static enum flow_dissect_ret __skb_flow_dissect_batadv(const struct sk_buff *skb, struct flow_dissector_key_control *key_control, const void *data, __be16 *p_proto, int *p_nhoff, int hlen, unsigned int flags) { struct { struct batadv_unicast_packet batadv_unicast; struct ethhdr eth; } *hdr, _hdr; hdr = __skb_header_pointer(skb, *p_nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) return FLOW_DISSECT_RET_OUT_BAD; if (hdr->batadv_unicast.version != BATADV_COMPAT_VERSION) return FLOW_DISSECT_RET_OUT_BAD; if (hdr->batadv_unicast.packet_type != BATADV_UNICAST) return FLOW_DISSECT_RET_OUT_BAD; *p_proto = hdr->eth.h_proto; *p_nhoff += sizeof(*hdr); key_control->flags |= FLOW_DIS_ENCAPSULATION; if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) return FLOW_DISSECT_RET_OUT_GOOD; return FLOW_DISSECT_RET_PROTO_AGAIN; } static void __skb_flow_dissect_tcp(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int thoff, int hlen) { struct flow_dissector_key_tcp *key_tcp; struct tcphdr *th, _th; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_TCP)) return; th = __skb_header_pointer(skb, thoff, sizeof(_th), data, hlen, &_th); if (!th) return; if (unlikely(__tcp_hdrlen(th) < sizeof(_th))) return; key_tcp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_TCP, target_container); key_tcp->flags = (*(__be16 *) &tcp_flag_word(th) & htons(0x0FFF)); } static void __skb_flow_dissect_ports(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, u8 ip_proto, int hlen) { struct flow_dissector_key_ports_range *key_ports_range = NULL; struct flow_dissector_key_ports *key_ports = NULL; __be32 ports; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS, target_container); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE)) key_ports_range = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE, target_container); if (!key_ports && !key_ports_range) return; ports = __skb_flow_get_ports(skb, nhoff, ip_proto, data, hlen); if (key_ports) key_ports->ports = ports; if (key_ports_range) key_ports_range->tp.ports = ports; } static void __skb_flow_dissect_ipv4(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, const struct iphdr *iph) { struct flow_dissector_key_ip *key_ip; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IP)) return; key_ip = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IP, target_container); key_ip->tos = iph->tos; key_ip->ttl = iph->ttl; } static void __skb_flow_dissect_ipv6(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, const struct ipv6hdr *iph) { struct flow_dissector_key_ip *key_ip; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IP)) return; key_ip = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IP, target_container); key_ip->tos = ipv6_get_dsfield(iph); key_ip->ttl = iph->hop_limit; } /* Maximum number of protocol headers that can be parsed in * __skb_flow_dissect */ #define MAX_FLOW_DISSECT_HDRS 15 static bool skb_flow_dissect_allowed(int *num_hdrs) { ++*num_hdrs; return (*num_hdrs <= MAX_FLOW_DISSECT_HDRS); } static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, struct flow_dissector *flow_dissector, void *target_container) { struct flow_dissector_key_ports_range *key_ports_range = NULL; struct flow_dissector_key_ports *key_ports = NULL; struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; struct flow_dissector_key_addrs *key_addrs; struct flow_dissector_key_tags *key_tags; key_control = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CONTROL, target_container); key_control->thoff = flow_keys->thoff; if (flow_keys->is_frag) key_control->flags |= FLOW_DIS_IS_FRAGMENT; if (flow_keys->is_first_frag) key_control->flags |= FLOW_DIS_FIRST_FRAG; if (flow_keys->is_encap) key_control->flags |= FLOW_DIS_ENCAPSULATION; key_basic = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_BASIC, target_container); key_basic->n_proto = flow_keys->n_proto; key_basic->ip_proto = flow_keys->ip_proto; if (flow_keys->addr_proto == ETH_P_IP && dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS, target_container); key_addrs->v4addrs.src = flow_keys->ipv4_src; key_addrs->v4addrs.dst = flow_keys->ipv4_dst; key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; } else if (flow_keys->addr_proto == ETH_P_IPV6 && dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS, target_container); memcpy(&key_addrs->v6addrs.src, &flow_keys->ipv6_src, sizeof(key_addrs->v6addrs.src)); memcpy(&key_addrs->v6addrs.dst, &flow_keys->ipv6_dst, sizeof(key_addrs->v6addrs.dst)); key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) { key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS, target_container); key_ports->src = flow_keys->sport; key_ports->dst = flow_keys->dport; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE)) { key_ports_range = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE, target_container); key_ports_range->tp.src = flow_keys->sport; key_ports_range->tp.dst = flow_keys->dport; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL)) { key_tags = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL, target_container); key_tags->flow_label = ntohl(flow_keys->flow_label); } } u32 bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, __be16 proto, int nhoff, int hlen, unsigned int flags) { struct bpf_flow_keys *flow_keys = ctx->flow_keys; u32 result; /* Pass parameters to the BPF program */ memset(flow_keys, 0, sizeof(*flow_keys)); flow_keys->n_proto = proto; flow_keys->nhoff = nhoff; flow_keys->thoff = flow_keys->nhoff; BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG != (int)FLOW_DISSECTOR_F_PARSE_1ST_FRAG); BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL != (int)FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP != (int)FLOW_DISSECTOR_F_STOP_AT_ENCAP); flow_keys->flags = flags; result = bpf_prog_run_pin_on_cpu(prog, ctx); flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, nhoff, hlen); flow_keys->thoff = clamp_t(u16, flow_keys->thoff, flow_keys->nhoff, hlen); return result; } static bool is_pppoe_ses_hdr_valid(const struct pppoe_hdr *hdr) { return hdr->ver == 1 && hdr->type == 1 && hdr->code == 0; } /** * __skb_flow_dissect - extract the flow_keys struct and return it * @net: associated network namespace, derived from @skb if NULL * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified * @flow_dissector: list of keys to dissect * @target_container: target structure to put dissected values into * @data: raw buffer pointer to the packet, if NULL use skb->data * @proto: protocol for which to get the flow, if @data is NULL use skb->protocol * @nhoff: network header offset, if @data is NULL use skb_network_offset(skb) * @hlen: packet header length, if @data is NULL use skb_headlen(skb) * @flags: flags that control the dissection process, e.g. * FLOW_DISSECTOR_F_STOP_AT_ENCAP. * * The function will try to retrieve individual keys into target specified * by flow_dissector from either the skbuff or a raw buffer specified by the * rest parameters. * * Caller must take care of zeroing target container memory. */ bool __skb_flow_dissect(const struct net *net, const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, __be16 proto, int nhoff, int hlen, unsigned int flags) { struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; struct flow_dissector_key_addrs *key_addrs; struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_vlan *key_vlan; enum flow_dissect_ret fdret; enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX; bool mpls_el = false; int mpls_lse = 0; int num_hdrs = 0; u8 ip_proto = 0; bool ret; if (!data) { data = skb->data; proto = skb_vlan_tag_present(skb) ? skb->vlan_proto : skb->protocol; nhoff = skb_network_offset(skb); hlen = skb_headlen(skb); #if IS_ENABLED(CONFIG_NET_DSA) if (unlikely(skb->dev && netdev_uses_dsa(skb->dev) && proto == htons(ETH_P_XDSA))) { const struct dsa_device_ops *ops; int offset = 0; ops = skb->dev->dsa_ptr->tag_ops; /* Only DSA header taggers break flow dissection */ if (ops->needed_headroom) { if (ops->flow_dissect) ops->flow_dissect(skb, &proto, &offset); else dsa_tag_generic_flow_dissect(skb, &proto, &offset); hlen -= offset; nhoff += offset; } } #endif } /* It is ensured by skb_flow_dissector_init() that control key will * be always present. */ key_control = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CONTROL, target_container); /* It is ensured by skb_flow_dissector_init() that basic key will * be always present. */ key_basic = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_BASIC, target_container); rcu_read_lock(); if (skb) { if (!net) { if (skb->dev) net = dev_net_rcu(skb->dev); else if (skb->sk) net = sock_net(skb->sk); } } DEBUG_NET_WARN_ON_ONCE(!net); if (net) { enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; struct bpf_prog_array *run_array; run_array = rcu_dereference(init_net.bpf.run_array[type]); if (!run_array) run_array = rcu_dereference(net->bpf.run_array[type]); if (run_array) { struct bpf_flow_keys flow_keys; struct bpf_flow_dissector ctx = { .flow_keys = &flow_keys, .data = data, .data_end = data + hlen, }; __be16 n_proto = proto; struct bpf_prog *prog; u32 result; if (skb) { ctx.skb = skb; /* we can't use 'proto' in the skb case * because it might be set to skb->vlan_proto * which has been pulled from the data */ n_proto = skb->protocol; } prog = READ_ONCE(run_array->items[0].prog); result = bpf_flow_dissect(prog, &ctx, n_proto, nhoff, hlen, flags); if (result != BPF_FLOW_DISSECTOR_CONTINUE) { __skb_flow_bpf_to_target(&flow_keys, flow_dissector, target_container); rcu_read_unlock(); return result == BPF_OK; } } } rcu_read_unlock(); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct ethhdr *eth = eth_hdr(skb); struct flow_dissector_key_eth_addrs *key_eth_addrs; key_eth_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS, target_container); memcpy(key_eth_addrs, eth, sizeof(*key_eth_addrs)); } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_NUM_OF_VLANS)) { struct flow_dissector_key_num_of_vlans *key_num_of_vlans; key_num_of_vlans = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_NUM_OF_VLANS, target_container); key_num_of_vlans->num_of_vlans = 0; } proto_again: fdret = FLOW_DISSECT_RET_CONTINUE; switch (proto) { case htons(ETH_P_IP): { const struct iphdr *iph; struct iphdr _iph; iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph); if (!iph || iph->ihl < 5) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } nhoff += iph->ihl * 4; ip_proto = iph->protocol; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS, target_container); memcpy(&key_addrs->v4addrs.src, &iph->saddr, sizeof(key_addrs->v4addrs.src)); memcpy(&key_addrs->v4addrs.dst, &iph->daddr, sizeof(key_addrs->v4addrs.dst)); key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; } __skb_flow_dissect_ipv4(skb, flow_dissector, target_container, data, iph); if (ip_is_fragment(iph)) { key_control->flags |= FLOW_DIS_IS_FRAGMENT; if (iph->frag_off & htons(IP_OFFSET)) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } else { key_control->flags |= FLOW_DIS_FIRST_FRAG; if (!(flags & FLOW_DISSECTOR_F_PARSE_1ST_FRAG)) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } } } break; } case htons(ETH_P_IPV6): { const struct ipv6hdr *iph; struct ipv6hdr _iph; iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph); if (!iph) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } ip_proto = iph->nexthdr; nhoff += sizeof(struct ipv6hdr); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS, target_container); memcpy(&key_addrs->v6addrs.src, &iph->saddr, sizeof(key_addrs->v6addrs.src)); memcpy(&key_addrs->v6addrs.dst, &iph->daddr, sizeof(key_addrs->v6addrs.dst)); key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } if ((dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL) || (flags & FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL)) && ip6_flowlabel(iph)) { __be32 flow_label = ip6_flowlabel(iph); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL)) { key_tags = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL, target_container); key_tags->flow_label = ntohl(flow_label); } if (flags & FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } } __skb_flow_dissect_ipv6(skb, flow_dissector, target_container, data, iph); break; } case htons(ETH_P_8021AD): case htons(ETH_P_8021Q): { const struct vlan_hdr *vlan = NULL; struct vlan_hdr _vlan; __be16 saved_vlan_tpid = proto; if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX && skb && skb_vlan_tag_present(skb)) { proto = skb->protocol; } else { vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan), data, hlen, &_vlan); if (!vlan) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } proto = vlan->h_vlan_encapsulated_proto; nhoff += sizeof(*vlan); } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_NUM_OF_VLANS) && !(key_control->flags & FLOW_DIS_ENCAPSULATION)) { struct flow_dissector_key_num_of_vlans *key_nvs; key_nvs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_NUM_OF_VLANS, target_container); key_nvs->num_of_vlans++; } if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX) { dissector_vlan = FLOW_DISSECTOR_KEY_VLAN; } else if (dissector_vlan == FLOW_DISSECTOR_KEY_VLAN) { dissector_vlan = FLOW_DISSECTOR_KEY_CVLAN; } else { fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; } if (dissector_uses_key(flow_dissector, dissector_vlan)) { key_vlan = skb_flow_dissector_target(flow_dissector, dissector_vlan, target_container); if (!vlan) { key_vlan->vlan_id = skb_vlan_tag_get_id(skb); key_vlan->vlan_priority = skb_vlan_tag_get_prio(skb); } else { key_vlan->vlan_id = ntohs(vlan->h_vlan_TCI) & VLAN_VID_MASK; key_vlan->vlan_priority = (ntohs(vlan->h_vlan_TCI) & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; } key_vlan->vlan_tpid = saved_vlan_tpid; key_vlan->vlan_eth_type = proto; } fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; } case htons(ETH_P_PPP_SES): { struct { struct pppoe_hdr hdr; __be16 proto; } *hdr, _hdr; u16 ppp_proto; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } if (!is_pppoe_ses_hdr_valid(&hdr->hdr)) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } /* least significant bit of the most significant octet * indicates if protocol field was compressed */ ppp_proto = ntohs(hdr->proto); if (ppp_proto & 0x0100) { ppp_proto = ppp_proto >> 8; nhoff += PPPOE_SES_HLEN - 1; } else { nhoff += PPPOE_SES_HLEN; } if (ppp_proto == PPP_IP) { proto = htons(ETH_P_IP); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; } else if (ppp_proto == PPP_IPV6) { proto = htons(ETH_P_IPV6); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; } else if (ppp_proto == PPP_MPLS_UC) { proto = htons(ETH_P_MPLS_UC); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; } else if (ppp_proto == PPP_MPLS_MC) { proto = htons(ETH_P_MPLS_MC); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; } else if (ppp_proto_is_valid(ppp_proto)) { fdret = FLOW_DISSECT_RET_OUT_GOOD; } else { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PPPOE)) { struct flow_dissector_key_pppoe *key_pppoe; key_pppoe = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PPPOE, target_container); key_pppoe->session_id = hdr->hdr.sid; key_pppoe->ppp_proto = htons(ppp_proto); key_pppoe->type = htons(ETH_P_PPP_SES); } break; } case htons(ETH_P_TIPC): { struct tipc_basic_hdr *hdr, _hdr; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_TIPC)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_TIPC, target_container); key_addrs->tipckey.key = tipc_hdr_rps_key(hdr); key_control->addr_type = FLOW_DISSECTOR_KEY_TIPC; } fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } case htons(ETH_P_MPLS_UC): case htons(ETH_P_MPLS_MC): fdret = __skb_flow_dissect_mpls(skb, flow_dissector, target_container, data, nhoff, hlen, mpls_lse, &mpls_el); nhoff += sizeof(struct mpls_label); mpls_lse++; break; case htons(ETH_P_FCOE): if ((hlen - nhoff) < FCOE_HEADER_LEN) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } nhoff += FCOE_HEADER_LEN; fdret = FLOW_DISSECT_RET_OUT_GOOD; break; case htons(ETH_P_ARP): case htons(ETH_P_RARP): fdret = __skb_flow_dissect_arp(skb, flow_dissector, target_container, data, nhoff, hlen); break; case htons(ETH_P_BATMAN): fdret = __skb_flow_dissect_batadv(skb, key_control, data, &proto, &nhoff, hlen, flags); break; case htons(ETH_P_1588): { struct ptp_header *hdr, _hdr; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } nhoff += sizeof(struct ptp_header); fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } case htons(ETH_P_PRP): case htons(ETH_P_HSR): { struct hsr_tag *hdr, _hdr; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } proto = hdr->encap_proto; nhoff += HSR_HLEN; fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; } default: fdret = FLOW_DISSECT_RET_OUT_BAD; break; } /* Process result of proto processing */ switch (fdret) { case FLOW_DISSECT_RET_OUT_GOOD: goto out_good; case FLOW_DISSECT_RET_PROTO_AGAIN: if (skb_flow_dissect_allowed(&num_hdrs)) goto proto_again; goto out_good; case FLOW_DISSECT_RET_CONTINUE: case FLOW_DISSECT_RET_IPPROTO_AGAIN: break; case FLOW_DISSECT_RET_OUT_BAD: default: goto out_bad; } ip_proto_again: fdret = FLOW_DISSECT_RET_CONTINUE; switch (ip_proto) { case IPPROTO_GRE: if (flags & FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } fdret = __skb_flow_dissect_gre(skb, key_control, flow_dissector, target_container, data, &proto, &nhoff, &hlen, flags); break; case NEXTHDR_HOP: case NEXTHDR_ROUTING: case NEXTHDR_DEST: { u8 _opthdr[2], *opthdr; if (proto != htons(ETH_P_IPV6)) break; opthdr = __skb_header_pointer(skb, nhoff, sizeof(_opthdr), data, hlen, &_opthdr); if (!opthdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } ip_proto = opthdr[0]; nhoff += (opthdr[1] + 1) << 3; fdret = FLOW_DISSECT_RET_IPPROTO_AGAIN; break; } case NEXTHDR_FRAGMENT: { struct frag_hdr _fh, *fh; if (proto != htons(ETH_P_IPV6)) break; fh = __skb_header_pointer(skb, nhoff, sizeof(_fh), data, hlen, &_fh); if (!fh) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } key_control->flags |= FLOW_DIS_IS_FRAGMENT; nhoff += sizeof(_fh); ip_proto = fh->nexthdr; if (!(fh->frag_off & htons(IP6_OFFSET))) { key_control->flags |= FLOW_DIS_FIRST_FRAG; if (flags & FLOW_DISSECTOR_F_PARSE_1ST_FRAG) { fdret = FLOW_DISSECT_RET_IPPROTO_AGAIN; break; } } fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } case IPPROTO_IPIP: if (flags & FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } proto = htons(ETH_P_IP); key_control->flags |= FLOW_DIS_ENCAPSULATION; if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; case IPPROTO_IPV6: if (flags & FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } proto = htons(ETH_P_IPV6); key_control->flags |= FLOW_DIS_ENCAPSULATION; if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; case IPPROTO_MPLS: proto = htons(ETH_P_MPLS_UC); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; case IPPROTO_TCP: __skb_flow_dissect_tcp(skb, flow_dissector, target_container, data, nhoff, hlen); break; case IPPROTO_ICMP: case IPPROTO_ICMPV6: __skb_flow_dissect_icmp(skb, flow_dissector, target_container, data, nhoff, hlen); break; case IPPROTO_L2TP: __skb_flow_dissect_l2tpv3(skb, flow_dissector, target_container, data, nhoff, hlen); break; default: break; } if (!(key_control->flags & FLOW_DIS_IS_FRAGMENT)) __skb_flow_dissect_ports(skb, flow_dissector, target_container, data, nhoff, ip_proto, hlen); /* Process result of IP proto processing */ switch (fdret) { case FLOW_DISSECT_RET_PROTO_AGAIN: if (skb_flow_dissect_allowed(&num_hdrs)) goto proto_again; break; case FLOW_DISSECT_RET_IPPROTO_AGAIN: if (skb_flow_dissect_allowed(&num_hdrs)) goto ip_proto_again; break; case FLOW_DISSECT_RET_OUT_GOOD: case FLOW_DISSECT_RET_CONTINUE: break; case FLOW_DISSECT_RET_OUT_BAD: default: goto out_bad; } out_good: ret = true; out: key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen); key_basic->n_proto = proto; key_basic->ip_proto = ip_proto; return ret; out_bad: ret = false; goto out; } EXPORT_SYMBOL(__skb_flow_dissect); static siphash_aligned_key_t hashrnd; static __always_inline void __flow_hash_secret_init(void) { net_get_random_once(&hashrnd, sizeof(hashrnd)); } static const void *flow_keys_hash_start(const struct flow_keys *flow) { BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % SIPHASH_ALIGNMENT); return &flow->FLOW_KEYS_HASH_START_FIELD; } static inline size_t flow_keys_hash_length(const struct flow_keys *flow) { size_t diff = FLOW_KEYS_HASH_OFFSET + sizeof(flow->addrs); BUILD_BUG_ON((sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) % sizeof(u32)); switch (flow->control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: diff -= sizeof(flow->addrs.v4addrs); break; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: diff -= sizeof(flow->addrs.v6addrs); break; case FLOW_DISSECTOR_KEY_TIPC: diff -= sizeof(flow->addrs.tipckey); break; } return sizeof(*flow) - diff; } __be32 flow_get_u32_src(const struct flow_keys *flow) { switch (flow->control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: return flow->addrs.v4addrs.src; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: return (__force __be32)ipv6_addr_hash( &flow->addrs.v6addrs.src); case FLOW_DISSECTOR_KEY_TIPC: return flow->addrs.tipckey.key; default: return 0; } } EXPORT_SYMBOL(flow_get_u32_src); __be32 flow_get_u32_dst(const struct flow_keys *flow) { switch (flow->control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: return flow->addrs.v4addrs.dst; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: return (__force __be32)ipv6_addr_hash( &flow->addrs.v6addrs.dst); default: return 0; } } EXPORT_SYMBOL(flow_get_u32_dst); /* Sort the source and destination IP and the ports, * to have consistent hash within the two directions */ static inline void __flow_hash_consistentify(struct flow_keys *keys) { int addr_diff, i; switch (keys->control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: if ((__force u32)keys->addrs.v4addrs.dst < (__force u32)keys->addrs.v4addrs.src) swap(keys->addrs.v4addrs.src, keys->addrs.v4addrs.dst); if ((__force u16)keys->ports.dst < (__force u16)keys->ports.src) { swap(keys->ports.src, keys->ports.dst); } break; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: addr_diff = memcmp(&keys->addrs.v6addrs.dst, &keys->addrs.v6addrs.src, sizeof(keys->addrs.v6addrs.dst)); if (addr_diff < 0) { for (i = 0; i < 4; i++) swap(keys->addrs.v6addrs.src.s6_addr32[i], keys->addrs.v6addrs.dst.s6_addr32[i]); } if ((__force u16)keys->ports.dst < (__force u16)keys->ports.src) { swap(keys->ports.src, keys->ports.dst); } break; } } static inline u32 __flow_hash_from_keys(struct flow_keys *keys, const siphash_key_t *keyval) { u32 hash; __flow_hash_consistentify(keys); hash = siphash(flow_keys_hash_start(keys), flow_keys_hash_length(keys), keyval); if (!hash) hash = 1; return hash; } u32 flow_hash_from_keys(struct flow_keys *keys) { __flow_hash_secret_init(); return __flow_hash_from_keys(keys, &hashrnd); } EXPORT_SYMBOL(flow_hash_from_keys); static inline u32 ___skb_get_hash(const struct sk_buff *skb, struct flow_keys *keys, const siphash_key_t *keyval) { skb_flow_dissect_flow_keys(skb, keys, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); return __flow_hash_from_keys(keys, keyval); } struct _flow_keys_digest_data { __be16 n_proto; u8 ip_proto; u8 padding; __be32 ports; __be32 src; __be32 dst; }; void make_flow_keys_digest(struct flow_keys_digest *digest, const struct flow_keys *flow) { struct _flow_keys_digest_data *data = (struct _flow_keys_digest_data *)digest; BUILD_BUG_ON(sizeof(*data) > sizeof(*digest)); memset(digest, 0, sizeof(*digest)); data->n_proto = flow->basic.n_proto; data->ip_proto = flow->basic.ip_proto; data->ports = flow->ports.ports; data->src = flow->addrs.v4addrs.src; data->dst = flow->addrs.v4addrs.dst; } EXPORT_SYMBOL(make_flow_keys_digest); static struct flow_dissector flow_keys_dissector_symmetric __read_mostly; u32 __skb_get_hash_symmetric(const struct sk_buff *skb) { struct flow_keys keys; __flow_hash_secret_init(); memset(&keys, 0, sizeof(keys)); __skb_flow_dissect(NULL, skb, &flow_keys_dissector_symmetric, &keys, NULL, 0, 0, 0, 0); return __flow_hash_from_keys(&keys, &hashrnd); } EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric); /** * __skb_get_hash: calculate a flow hash * @skb: sk_buff to calculate flow hash from * * This function calculates a flow hash based on src/dst addresses * and src/dst port numbers. Sets hash in skb to non-zero hash value * on success, zero indicates no valid hash. Also, sets l4_hash in skb * if hash is a canonical 4-tuple hash over transport ports. */ void __skb_get_hash(struct sk_buff *skb) { struct flow_keys keys; u32 hash; __flow_hash_secret_init(); hash = ___skb_get_hash(skb, &keys, &hashrnd); __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } EXPORT_SYMBOL(__skb_get_hash); __u32 skb_get_hash_perturb(const struct sk_buff *skb, const siphash_key_t *perturb) { struct flow_keys keys; return ___skb_get_hash(skb, &keys, perturb); } EXPORT_SYMBOL(skb_get_hash_perturb); u32 __skb_get_poff(const struct sk_buff *skb, const void *data, const struct flow_keys_basic *keys, int hlen) { u32 poff = keys->control.thoff; /* skip L4 headers for fragments after the first */ if ((keys->control.flags & FLOW_DIS_IS_FRAGMENT) && !(keys->control.flags & FLOW_DIS_FIRST_FRAG)) return poff; switch (keys->basic.ip_proto) { case IPPROTO_TCP: { /* access doff as u8 to avoid unaligned access */ const u8 *doff; u8 _doff; doff = __skb_header_pointer(skb, poff + 12, sizeof(_doff), data, hlen, &_doff); if (!doff) return poff; poff += max_t(u32, sizeof(struct tcphdr), (*doff & 0xF0) >> 2); break; } case IPPROTO_UDP: case IPPROTO_UDPLITE: poff += sizeof(struct udphdr); break; /* For the rest, we do not really care about header * extensions at this point for now. */ case IPPROTO_ICMP: poff += sizeof(struct icmphdr); break; case IPPROTO_ICMPV6: poff += sizeof(struct icmp6hdr); break; case IPPROTO_IGMP: poff += sizeof(struct igmphdr); break; case IPPROTO_DCCP: poff += sizeof(struct dccp_hdr); break; case IPPROTO_SCTP: poff += sizeof(struct sctphdr); break; } return poff; } /** * skb_get_poff - get the offset to the payload * @skb: sk_buff to get the payload offset from * * The function will get the offset to the payload as far as it could * be dissected. The main user is currently BPF, so that we can dynamically * truncate packets without needing to push actual payload to the user * space and can analyze headers only, instead. */ u32 skb_get_poff(const struct sk_buff *skb) { struct flow_keys_basic keys; if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, NULL, 0, 0, 0, 0)) return 0; return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb)); } __u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys) { memset(keys, 0, sizeof(*keys)); memcpy(&keys->addrs.v6addrs.src, &fl6->saddr, sizeof(keys->addrs.v6addrs.src)); memcpy(&keys->addrs.v6addrs.dst, &fl6->daddr, sizeof(keys->addrs.v6addrs.dst)); keys->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; keys->ports.src = fl6->fl6_sport; keys->ports.dst = fl6->fl6_dport; keys->keyid.keyid = fl6->fl6_gre_key; keys->tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); keys->basic.ip_proto = fl6->flowi6_proto; return flow_hash_from_keys(keys); } EXPORT_SYMBOL(__get_hash_from_flowi6); static const struct flow_dissector_key flow_keys_dissector_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, .offset = offsetof(struct flow_keys, control), }, { .key_id = FLOW_DISSECTOR_KEY_BASIC, .offset = offsetof(struct flow_keys, basic), }, { .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, .offset = offsetof(struct flow_keys, addrs.v4addrs), }, { .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS, .offset = offsetof(struct flow_keys, addrs.v6addrs), }, { .key_id = FLOW_DISSECTOR_KEY_TIPC, .offset = offsetof(struct flow_keys, addrs.tipckey), }, { .key_id = FLOW_DISSECTOR_KEY_PORTS, .offset = offsetof(struct flow_keys, ports), }, { .key_id = FLOW_DISSECTOR_KEY_VLAN, .offset = offsetof(struct flow_keys, vlan), }, { .key_id = FLOW_DISSECTOR_KEY_FLOW_LABEL, .offset = offsetof(struct flow_keys, tags), }, { .key_id = FLOW_DISSECTOR_KEY_GRE_KEYID, .offset = offsetof(struct flow_keys, keyid), }, }; static const struct flow_dissector_key flow_keys_dissector_symmetric_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, .offset = offsetof(struct flow_keys, control), }, { .key_id = FLOW_DISSECTOR_KEY_BASIC, .offset = offsetof(struct flow_keys, basic), }, { .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, .offset = offsetof(struct flow_keys, addrs.v4addrs), }, { .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS, .offset = offsetof(struct flow_keys, addrs.v6addrs), }, { .key_id = FLOW_DISSECTOR_KEY_PORTS, .offset = offsetof(struct flow_keys, ports), }, }; static const struct flow_dissector_key flow_keys_basic_dissector_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, .offset = offsetof(struct flow_keys, control), }, { .key_id = FLOW_DISSECTOR_KEY_BASIC, .offset = offsetof(struct flow_keys, basic), }, }; struct flow_dissector flow_keys_dissector __read_mostly; EXPORT_SYMBOL(flow_keys_dissector); struct flow_dissector flow_keys_basic_dissector __read_mostly; EXPORT_SYMBOL(flow_keys_basic_dissector); static int __init init_default_flow_dissectors(void) { skb_flow_dissector_init(&flow_keys_dissector, flow_keys_dissector_keys, ARRAY_SIZE(flow_keys_dissector_keys)); skb_flow_dissector_init(&flow_keys_dissector_symmetric, flow_keys_dissector_symmetric_keys, ARRAY_SIZE(flow_keys_dissector_symmetric_keys)); skb_flow_dissector_init(&flow_keys_basic_dissector, flow_keys_basic_dissector_keys, ARRAY_SIZE(flow_keys_basic_dissector_keys)); return 0; } core_initcall(init_default_flow_dissectors); |
| 60 67 68 68 68 8 60 61 31 23 23 1530 1530 1532 683 683 683 528 148 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * event tracer * * Copyright (C) 2008 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> * * - Added format output of fields of the trace point. * This was based off of work by Tom Zanussi <tzanussi@gmail.com>. * */ #define pr_fmt(fmt) fmt #include <linux/workqueue.h> #include <linux/security.h> #include <linux/spinlock.h> #include <linux/kthread.h> #include <linux/tracefs.h> #include <linux/uaccess.h> #include <linux/module.h> #include <linux/ctype.h> #include <linux/sort.h> #include <linux/slab.h> #include <linux/delay.h> #include <trace/events/sched.h> #include <trace/syscall.h> #include <asm/setup.h> #include "trace_output.h" #undef TRACE_SYSTEM #define TRACE_SYSTEM "TRACE_SYSTEM" DEFINE_MUTEX(event_mutex); LIST_HEAD(ftrace_events); static LIST_HEAD(ftrace_generic_fields); static LIST_HEAD(ftrace_common_fields); static bool eventdir_initialized; static LIST_HEAD(module_strings); struct module_string { struct list_head next; struct module *module; char *str; }; #define GFP_TRACE (GFP_KERNEL | __GFP_ZERO) static struct kmem_cache *field_cachep; static struct kmem_cache *file_cachep; static inline int system_refcount(struct event_subsystem *system) { return system->ref_count; } static int system_refcount_inc(struct event_subsystem *system) { return system->ref_count++; } static int system_refcount_dec(struct event_subsystem *system) { return --system->ref_count; } /* Double loops, do not use break, only goto's work */ #define do_for_each_event_file(tr, file) \ list_for_each_entry(tr, &ftrace_trace_arrays, list) { \ list_for_each_entry(file, &tr->events, list) #define do_for_each_event_file_safe(tr, file) \ list_for_each_entry(tr, &ftrace_trace_arrays, list) { \ struct trace_event_file *___n; \ list_for_each_entry_safe(file, ___n, &tr->events, list) #define while_for_each_event_file() \ } static struct ftrace_event_field * __find_event_field(struct list_head *head, char *name) { struct ftrace_event_field *field; list_for_each_entry(field, head, link) { if (!strcmp(field->name, name)) return field; } return NULL; } struct ftrace_event_field * trace_find_event_field(struct trace_event_call *call, char *name) { struct ftrace_event_field *field; struct list_head *head; head = trace_get_fields(call); field = __find_event_field(head, name); if (field) return field; field = __find_event_field(&ftrace_generic_fields, name); if (field) return field; return __find_event_field(&ftrace_common_fields, name); } static int __trace_define_field(struct list_head *head, const char *type, const char *name, int offset, int size, int is_signed, int filter_type, int len) { struct ftrace_event_field *field; field = kmem_cache_alloc(field_cachep, GFP_TRACE); if (!field) return -ENOMEM; field->name = name; field->type = type; if (filter_type == FILTER_OTHER) field->filter_type = filter_assign_type(type); else field->filter_type = filter_type; field->offset = offset; field->size = size; field->is_signed = is_signed; field->len = len; list_add(&field->link, head); return 0; } int trace_define_field(struct trace_event_call *call, const char *type, const char *name, int offset, int size, int is_signed, int filter_type) { struct list_head *head; if (WARN_ON(!call->class)) return 0; head = trace_get_fields(call); return __trace_define_field(head, type, name, offset, size, is_signed, filter_type, 0); } EXPORT_SYMBOL_GPL(trace_define_field); static int trace_define_field_ext(struct trace_event_call *call, const char *type, const char *name, int offset, int size, int is_signed, int filter_type, int len) { struct list_head *head; if (WARN_ON(!call->class)) return 0; head = trace_get_fields(call); return __trace_define_field(head, type, name, offset, size, is_signed, filter_type, len); } #define __generic_field(type, item, filter_type) \ ret = __trace_define_field(&ftrace_generic_fields, #type, \ #item, 0, 0, is_signed_type(type), \ filter_type, 0); \ if (ret) \ return ret; #define __common_field(type, item) \ ret = __trace_define_field(&ftrace_common_fields, #type, \ "common_" #item, \ offsetof(typeof(ent), item), \ sizeof(ent.item), \ is_signed_type(type), FILTER_OTHER, 0); \ if (ret) \ return ret; static int trace_define_generic_fields(void) { int ret; __generic_field(int, CPU, FILTER_CPU); __generic_field(int, cpu, FILTER_CPU); __generic_field(int, common_cpu, FILTER_CPU); __generic_field(char *, COMM, FILTER_COMM); __generic_field(char *, comm, FILTER_COMM); return ret; } static int trace_define_common_fields(void) { int ret; struct trace_entry ent; __common_field(unsigned short, type); __common_field(unsigned char, flags); /* Holds both preempt_count and migrate_disable */ __common_field(unsigned char, preempt_count); __common_field(int, pid); return ret; } static void trace_destroy_fields(struct trace_event_call *call) { struct ftrace_event_field *field, *next; struct list_head *head; head = trace_get_fields(call); list_for_each_entry_safe(field, next, head, link) { list_del(&field->link); kmem_cache_free(field_cachep, field); } } /* * run-time version of trace_event_get_offsets_<call>() that returns the last * accessible offset of trace fields excluding __dynamic_array bytes */ int trace_event_get_offsets(struct trace_event_call *call) { struct ftrace_event_field *tail; struct list_head *head; head = trace_get_fields(call); /* * head->next points to the last field with the largest offset, * since it was added last by trace_define_field() */ tail = list_first_entry(head, struct ftrace_event_field, link); return tail->offset + tail->size; } static struct trace_event_fields *find_event_field(const char *fmt, struct trace_event_call *call) { struct trace_event_fields *field = call->class->fields_array; const char *p = fmt; int len; if (!(len = str_has_prefix(fmt, "REC->"))) return NULL; fmt += len; for (p = fmt; *p; p++) { if (!isalnum(*p) && *p != '_') break; } len = p - fmt; for (; field->type; field++) { if (strncmp(field->name, fmt, len) || field->name[len]) continue; return field; } return NULL; } /* * Check if the referenced field is an array and return true, * as arrays are OK to dereference. */ static bool test_field(const char *fmt, struct trace_event_call *call) { struct trace_event_fields *field; field = find_event_field(fmt, call); if (!field) return false; /* This is an array and is OK to dereference. */ return strchr(field->type, '[') != NULL; } /* Look for a string within an argument */ static bool find_print_string(const char *arg, const char *str, const char *end) { const char *r; r = strstr(arg, str); return r && r < end; } /* Return true if the argument pointer is safe */ static bool process_pointer(const char *fmt, int len, struct trace_event_call *call) { const char *r, *e, *a; e = fmt + len; /* Find the REC-> in the argument */ r = strstr(fmt, "REC->"); if (r && r < e) { /* * Addresses of events on the buffer, or an array on the buffer is * OK to dereference. There's ways to fool this, but * this is to catch common mistakes, not malicious code. */ a = strchr(fmt, '&'); if ((a && (a < r)) || test_field(r, call)) return true; } else if (find_print_string(fmt, "__get_dynamic_array(", e)) { return true; } else if (find_print_string(fmt, "__get_rel_dynamic_array(", e)) { return true; } else if (find_print_string(fmt, "__get_dynamic_array_len(", e)) { return true; } else if (find_print_string(fmt, "__get_rel_dynamic_array_len(", e)) { return true; } else if (find_print_string(fmt, "__get_sockaddr(", e)) { return true; } else if (find_print_string(fmt, "__get_rel_sockaddr(", e)) { return true; } return false; } /* Return true if the string is safe */ static bool process_string(const char *fmt, int len, struct trace_event_call *call) { const char *r, *e, *s; e = fmt + len; /* * There are several helper functions that return strings. * If the argument contains a function, then assume its field is valid. * It is considered that the argument has a function if it has: * alphanumeric or '_' before a parenthesis. */ s = fmt; do { r = strstr(s, "("); if (!r || r >= e) break; for (int i = 1; r - i >= s; i++) { char ch = *(r - i); if (isspace(ch)) continue; if (isalnum(ch) || ch == '_') return true; /* Anything else, this isn't a function */ break; } /* A function could be wrapped in parethesis, try the next one */ s = r + 1; } while (s < e); /* * Check for arrays. If the argument has: foo[REC->val] * then it is very likely that foo is an array of strings * that are safe to use. */ r = strstr(s, "["); if (r && r < e) { r = strstr(r, "REC->"); if (r && r < e) return true; } /* * If there's any strings in the argument consider this arg OK as it * could be: REC->field ? "foo" : "bar" and we don't want to get into * verifying that logic here. */ if (find_print_string(fmt, "\"", e)) return true; /* Dereferenced strings are also valid like any other pointer */ if (process_pointer(fmt, len, call)) return true; /* Make sure the field is found, and consider it OK for now if it is */ return find_event_field(fmt, call) != NULL; } /* * Examine the print fmt of the event looking for unsafe dereference * pointers using %p* that could be recorded in the trace event and * much later referenced after the pointer was freed. Dereferencing * pointers are OK, if it is dereferenced into the event itself. */ static void test_event_printk(struct trace_event_call *call) { u64 dereference_flags = 0; u64 string_flags = 0; bool first = true; const char *fmt; int parens = 0; char in_quote = 0; int start_arg = 0; int arg = 0; int i, e; fmt = call->print_fmt; if (!fmt) return; for (i = 0; fmt[i]; i++) { switch (fmt[i]) { case '\\': i++; if (!fmt[i]) return; continue; case '"': case '\'': /* * The print fmt starts with a string that * is processed first to find %p* usage, * then after the first string, the print fmt * contains arguments that are used to check * if the dereferenced %p* usage is safe. */ if (first) { if (fmt[i] == '\'') continue; if (in_quote) { arg = 0; first = false; /* * If there was no %p* uses * the fmt is OK. */ if (!dereference_flags) return; } } if (in_quote) { if (in_quote == fmt[i]) in_quote = 0; } else { in_quote = fmt[i]; } continue; case '%': if (!first || !in_quote) continue; i++; if (!fmt[i]) return; switch (fmt[i]) { case '%': continue; case 'p': do_pointer: /* Find dereferencing fields */ switch (fmt[i + 1]) { case 'B': case 'R': case 'r': case 'b': case 'M': case 'm': case 'I': case 'i': case 'E': case 'U': case 'V': case 'N': case 'a': case 'd': case 'D': case 'g': case 't': case 'C': case 'O': case 'f': if (WARN_ONCE(arg == 63, "Too many args for event: %s", trace_event_name(call))) return; dereference_flags |= 1ULL << arg; } break; default: { bool star = false; int j; /* Increment arg if %*s exists. */ for (j = 0; fmt[i + j]; j++) { if (isdigit(fmt[i + j]) || fmt[i + j] == '.') continue; if (fmt[i + j] == '*') { star = true; /* Handle %*pbl case */ if (!j && fmt[i + 1] == 'p') { arg++; i++; goto do_pointer; } continue; } if ((fmt[i + j] == 's')) { if (star) arg++; if (WARN_ONCE(arg == 63, "Too many args for event: %s", trace_event_name(call))) return; dereference_flags |= 1ULL << arg; string_flags |= 1ULL << arg; } break; } break; } /* default */ } /* switch */ arg++; continue; case '(': if (in_quote) continue; parens++; continue; case ')': if (in_quote) continue; parens--; if (WARN_ONCE(parens < 0, "Paren mismatch for event: %s\narg='%s'\n%*s", trace_event_name(call), fmt + start_arg, (i - start_arg) + 5, "^")) return; continue; case ',': if (in_quote || parens) continue; e = i; i++; while (isspace(fmt[i])) i++; /* * If start_arg is zero, then this is the start of the * first argument. The processing of the argument happens * when the end of the argument is found, as it needs to * handle paranthesis and such. */ if (!start_arg) { start_arg = i; /* Balance out the i++ in the for loop */ i--; continue; } if (dereference_flags & (1ULL << arg)) { if (string_flags & (1ULL << arg)) { if (process_string(fmt + start_arg, e - start_arg, call)) dereference_flags &= ~(1ULL << arg); } else if (process_pointer(fmt + start_arg, e - start_arg, call)) dereference_flags &= ~(1ULL << arg); } start_arg = i; arg++; /* Balance out the i++ in the for loop */ i--; } } if (dereference_flags & (1ULL << arg)) { if (string_flags & (1ULL << arg)) { if (process_string(fmt + start_arg, i - start_arg, call)) dereference_flags &= ~(1ULL << arg); } else if (process_pointer(fmt + start_arg, i - start_arg, call)) dereference_flags &= ~(1ULL << arg); } /* * If you triggered the below warning, the trace event reported * uses an unsafe dereference pointer %p*. As the data stored * at the trace event time may no longer exist when the trace * event is printed, dereferencing to the original source is * unsafe. The source of the dereference must be copied into the * event itself, and the dereference must access the copy instead. */ if (WARN_ON_ONCE(dereference_flags)) { arg = 1; while (!(dereference_flags & 1)) { dereference_flags >>= 1; arg++; } pr_warn("event %s has unsafe dereference of argument %d\n", trace_event_name(call), arg); pr_warn("print_fmt: %s\n", fmt); } } int trace_event_raw_init(struct trace_event_call *call) { int id; id = register_trace_event(&call->event); if (!id) return -ENODEV; test_event_printk(call); return 0; } EXPORT_SYMBOL_GPL(trace_event_raw_init); bool trace_event_ignore_this_pid(struct trace_event_file *trace_file) { struct trace_array *tr = trace_file->tr; struct trace_array_cpu *data; struct trace_pid_list *no_pid_list; struct trace_pid_list *pid_list; pid_list = rcu_dereference_raw(tr->filtered_pids); no_pid_list = rcu_dereference_raw(tr->filtered_no_pids); if (!pid_list && !no_pid_list) return false; data = this_cpu_ptr(tr->array_buffer.data); return data->ignore_pid; } EXPORT_SYMBOL_GPL(trace_event_ignore_this_pid); void *trace_event_buffer_reserve(struct trace_event_buffer *fbuffer, struct trace_event_file *trace_file, unsigned long len) { struct trace_event_call *event_call = trace_file->event_call; if ((trace_file->flags & EVENT_FILE_FL_PID_FILTER) && trace_event_ignore_this_pid(trace_file)) return NULL; /* * If CONFIG_PREEMPTION is enabled, then the tracepoint itself disables * preemption (adding one to the preempt_count). Since we are * interested in the preempt_count at the time the tracepoint was * hit, we need to subtract one to offset the increment. */ fbuffer->trace_ctx = tracing_gen_ctx_dec(); fbuffer->trace_file = trace_file; fbuffer->event = trace_event_buffer_lock_reserve(&fbuffer->buffer, trace_file, event_call->event.type, len, fbuffer->trace_ctx); if (!fbuffer->event) return NULL; fbuffer->regs = NULL; fbuffer->entry = ring_buffer_event_data(fbuffer->event); return fbuffer->entry; } EXPORT_SYMBOL_GPL(trace_event_buffer_reserve); int trace_event_reg(struct trace_event_call *call, enum trace_reg type, void *data) { struct trace_event_file *file = data; WARN_ON(!(call->flags & TRACE_EVENT_FL_TRACEPOINT)); switch (type) { case TRACE_REG_REGISTER: return tracepoint_probe_register(call->tp, call->class->probe, file); case TRACE_REG_UNREGISTER: tracepoint_probe_unregister(call->tp, call->class->probe, file); return 0; #ifdef CONFIG_PERF_EVENTS case TRACE_REG_PERF_REGISTER: return tracepoint_probe_register(call->tp, call->class->perf_probe, call); case TRACE_REG_PERF_UNREGISTER: tracepoint_probe_unregister(call->tp, call->class->perf_probe, call); return 0; case TRACE_REG_PERF_OPEN: case TRACE_REG_PERF_CLOSE: case TRACE_REG_PERF_ADD: case TRACE_REG_PERF_DEL: return 0; #endif } return 0; } EXPORT_SYMBOL_GPL(trace_event_reg); void trace_event_enable_cmd_record(bool enable) { struct trace_event_file *file; struct trace_array *tr; lockdep_assert_held(&event_mutex); do_for_each_event_file(tr, file) { if (!(file->flags & EVENT_FILE_FL_ENABLED)) continue; if (enable) { tracing_start_cmdline_record(); set_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags); } else { tracing_stop_cmdline_record(); clear_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags); } } while_for_each_event_file(); } void trace_event_enable_tgid_record(bool enable) { struct trace_event_file *file; struct trace_array *tr; lockdep_assert_held(&event_mutex); do_for_each_event_file(tr, file) { if (!(file->flags & EVENT_FILE_FL_ENABLED)) continue; if (enable) { tracing_start_tgid_record(); set_bit(EVENT_FILE_FL_RECORDED_TGID_BIT, &file->flags); } else { tracing_stop_tgid_record(); clear_bit(EVENT_FILE_FL_RECORDED_TGID_BIT, &file->flags); } } while_for_each_event_file(); } static int __ftrace_event_enable_disable(struct trace_event_file *file, int enable, int soft_disable) { struct trace_event_call *call = file->event_call; struct trace_array *tr = file->tr; int ret = 0; int disable; switch (enable) { case 0: /* * When soft_disable is set and enable is cleared, the sm_ref * reference counter is decremented. If it reaches 0, we want * to clear the SOFT_DISABLED flag but leave the event in the * state that it was. That is, if the event was enabled and * SOFT_DISABLED isn't set, then do nothing. But if SOFT_DISABLED * is set we do not want the event to be enabled before we * clear the bit. * * When soft_disable is not set but the SOFT_MODE flag is, * we do nothing. Do not disable the tracepoint, otherwise * "soft enable"s (clearing the SOFT_DISABLED bit) wont work. */ if (soft_disable) { if (atomic_dec_return(&file->sm_ref) > 0) break; disable = file->flags & EVENT_FILE_FL_SOFT_DISABLED; clear_bit(EVENT_FILE_FL_SOFT_MODE_BIT, &file->flags); /* Disable use of trace_buffered_event */ trace_buffered_event_disable(); } else disable = !(file->flags & EVENT_FILE_FL_SOFT_MODE); if (disable && (file->flags & EVENT_FILE_FL_ENABLED)) { clear_bit(EVENT_FILE_FL_ENABLED_BIT, &file->flags); if (file->flags & EVENT_FILE_FL_RECORDED_CMD) { tracing_stop_cmdline_record(); clear_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags); } if (file->flags & EVENT_FILE_FL_RECORDED_TGID) { tracing_stop_tgid_record(); clear_bit(EVENT_FILE_FL_RECORDED_TGID_BIT, &file->flags); } ret = call->class->reg(call, TRACE_REG_UNREGISTER, file); WARN_ON_ONCE(ret); } /* If in SOFT_MODE, just set the SOFT_DISABLE_BIT, else clear it */ if (file->flags & EVENT_FILE_FL_SOFT_MODE) set_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags); else clear_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags); break; case 1: /* * When soft_disable is set and enable is set, we want to * register the tracepoint for the event, but leave the event * as is. That means, if the event was already enabled, we do * nothing (but set SOFT_MODE). If the event is disabled, we * set SOFT_DISABLED before enabling the event tracepoint, so * it still seems to be disabled. */ if (!soft_disable) clear_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags); else { if (atomic_inc_return(&file->sm_ref) > 1) break; set_bit(EVENT_FILE_FL_SOFT_MODE_BIT, &file->flags); /* Enable use of trace_buffered_event */ trace_buffered_event_enable(); } if (!(file->flags & EVENT_FILE_FL_ENABLED)) { bool cmd = false, tgid = false; /* Keep the event disabled, when going to SOFT_MODE. */ if (soft_disable) set_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags); if (tr->trace_flags & TRACE_ITER_RECORD_CMD) { cmd = true; tracing_start_cmdline_record(); set_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags); } if (tr->trace_flags & TRACE_ITER_RECORD_TGID) { tgid = true; tracing_start_tgid_record(); set_bit(EVENT_FILE_FL_RECORDED_TGID_BIT, &file->flags); } ret = call->class->reg(call, TRACE_REG_REGISTER, file); if (ret) { if (cmd) tracing_stop_cmdline_record(); if (tgid) tracing_stop_tgid_record(); pr_info("event trace: Could not enable event " "%s\n", trace_event_name(call)); break; } set_bit(EVENT_FILE_FL_ENABLED_BIT, &file->flags); /* WAS_ENABLED gets set but never cleared. */ set_bit(EVENT_FILE_FL_WAS_ENABLED_BIT, &file->flags); } break; } return ret; } int trace_event_enable_disable(struct trace_event_file *file, int enable, int soft_disable) { return __ftrace_event_enable_disable(file, enable, soft_disable); } static int ftrace_event_enable_disable(struct trace_event_file *file, int enable) { return __ftrace_event_enable_disable(file, enable, 0); } static void ftrace_clear_events(struct trace_array *tr) { struct trace_event_file *file; mutex_lock(&event_mutex); list_for_each_entry(file, &tr->events, list) { ftrace_event_enable_disable(file, 0); } mutex_unlock(&event_mutex); } static void event_filter_pid_sched_process_exit(void *data, struct task_struct *task) { struct trace_pid_list *pid_list; struct trace_array *tr = data; pid_list = rcu_dereference_raw(tr->filtered_pids); trace_filter_add_remove_task(pid_list, NULL, task); pid_list = rcu_dereference_raw(tr->filtered_no_pids); trace_filter_add_remove_task(pid_list, NULL, task); } static void event_filter_pid_sched_process_fork(void *data, struct task_struct *self, struct task_struct *task) { struct trace_pid_list *pid_list; struct trace_array *tr = data; pid_list = rcu_dereference_sched(tr->filtered_pids); trace_filter_add_remove_task(pid_list, self, task); pid_list = rcu_dereference_sched(tr->filtered_no_pids); trace_filter_add_remove_task(pid_list, self, task); } void trace_event_follow_fork(struct trace_array *tr, bool enable) { if (enable) { register_trace_prio_sched_process_fork(event_filter_pid_sched_process_fork, tr, INT_MIN); register_trace_prio_sched_process_free(event_filter_pid_sched_process_exit, tr, INT_MAX); } else { unregister_trace_sched_process_fork(event_filter_pid_sched_process_fork, tr); unregister_trace_sched_process_free(event_filter_pid_sched_process_exit, tr); } } static void event_filter_pid_sched_switch_probe_pre(void *data, bool preempt, struct task_struct *prev, struct task_struct *next, unsigned int prev_state) { struct trace_array *tr = data; struct trace_pid_list *no_pid_list; struct trace_pid_list *pid_list; bool ret; pid_list = rcu_dereference_sched(tr->filtered_pids); no_pid_list = rcu_dereference_sched(tr->filtered_no_pids); /* * Sched switch is funny, as we only want to ignore it * in the notrace case if both prev and next should be ignored. */ ret = trace_ignore_this_task(NULL, no_pid_list, prev) && trace_ignore_this_task(NULL, no_pid_list, next); this_cpu_write(tr->array_buffer.data->ignore_pid, ret || (trace_ignore_this_task(pid_list, NULL, prev) && trace_ignore_this_task(pid_list, NULL, next))); } static void event_filter_pid_sched_switch_probe_post(void *data, bool preempt, struct task_struct *prev, struct task_struct *next, unsigned int prev_state) { struct trace_array *tr = data; struct trace_pid_list *no_pid_list; struct trace_pid_list *pid_list; pid_list = rcu_dereference_sched(tr->filtered_pids); no_pid_list = rcu_dereference_sched(tr->filtered_no_pids); this_cpu_write(tr->array_buffer.data->ignore_pid, trace_ignore_this_task(pid_list, no_pid_list, next)); } static void event_filter_pid_sched_wakeup_probe_pre(void *data, struct task_struct *task) { struct trace_array *tr = data; struct trace_pid_list *no_pid_list; struct trace_pid_list *pid_list; /* Nothing to do if we are already tracing */ if (!this_cpu_read(tr->array_buffer.data->ignore_pid)) return; pid_list = rcu_dereference_sched(tr->filtered_pids); no_pid_list = rcu_dereference_sched(tr->filtered_no_pids); this_cpu_write(tr->array_buffer.data->ignore_pid, trace_ignore_this_task(pid_list, no_pid_list, task)); } static void event_filter_pid_sched_wakeup_probe_post(void *data, struct task_struct *task) { struct trace_array *tr = data; struct trace_pid_list *no_pid_list; struct trace_pid_list *pid_list; /* Nothing to do if we are not tracing */ if (this_cpu_read(tr->array_buffer.data->ignore_pid)) return; pid_list = rcu_dereference_sched(tr->filtered_pids); no_pid_list = rcu_dereference_sched(tr->filtered_no_pids); /* Set tracing if current is enabled */ this_cpu_write(tr->array_buffer.data->ignore_pid, trace_ignore_this_task(pid_list, no_pid_list, current)); } static void unregister_pid_events(struct trace_array *tr) { unregister_trace_sched_switch(event_filter_pid_sched_switch_probe_pre, tr); unregister_trace_sched_switch(event_filter_pid_sched_switch_probe_post, tr); unregister_trace_sched_wakeup(event_filter_pid_sched_wakeup_probe_pre, tr); unregister_trace_sched_wakeup(event_filter_pid_sched_wakeup_probe_post, tr); unregister_trace_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_pre, tr); unregister_trace_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_post, tr); unregister_trace_sched_waking(event_filter_pid_sched_wakeup_probe_pre, tr); unregister_trace_sched_waking(event_filter_pid_sched_wakeup_probe_post, tr); } static void __ftrace_clear_event_pids(struct trace_array *tr, int type) { struct trace_pid_list *pid_list; struct trace_pid_list *no_pid_list; struct trace_event_file *file; int cpu; pid_list = rcu_dereference_protected(tr->filtered_pids, lockdep_is_held(&event_mutex)); no_pid_list = rcu_dereference_protected(tr->filtered_no_pids, lockdep_is_held(&event_mutex)); /* Make sure there's something to do */ if (!pid_type_enabled(type, pid_list, no_pid_list)) return; if (!still_need_pid_events(type, pid_list, no_pid_list)) { unregister_pid_events(tr); list_for_each_entry(file, &tr->events, list) { clear_bit(EVENT_FILE_FL_PID_FILTER_BIT, &file->flags); } for_each_possible_cpu(cpu) per_cpu_ptr(tr->array_buffer.data, cpu)->ignore_pid = false; } if (type & TRACE_PIDS) rcu_assign_pointer(tr->filtered_pids, NULL); if (type & TRACE_NO_PIDS) rcu_assign_pointer(tr->filtered_no_pids, NULL); /* Wait till all users are no longer using pid filtering */ tracepoint_synchronize_unregister(); if ((type & TRACE_PIDS) && pid_list) trace_pid_list_free(pid_list); if ((type & TRACE_NO_PIDS) && no_pid_list) trace_pid_list_free(no_pid_list); } static void ftrace_clear_event_pids(struct trace_array *tr, int type) { mutex_lock(&event_mutex); __ftrace_clear_event_pids(tr, type); mutex_unlock(&event_mutex); } static void __put_system(struct event_subsystem *system) { struct event_filter *filter = system->filter; WARN_ON_ONCE(system_refcount(system) == 0); if (system_refcount_dec(system)) return; list_del(&system->list); if (filter) { kfree(filter->filter_string); kfree(filter); } kfree_const(system->name); kfree(system); } static void __get_system(struct event_subsystem *system) { WARN_ON_ONCE(system_refcount(system) == 0); system_refcount_inc(system); } static void __get_system_dir(struct trace_subsystem_dir *dir) { WARN_ON_ONCE(dir->ref_count == 0); dir->ref_count++; __get_system(dir->subsystem); } static void __put_system_dir(struct trace_subsystem_dir *dir) { WARN_ON_ONCE(dir->ref_count == 0); /* If the subsystem is about to be freed, the dir must be too */ WARN_ON_ONCE(system_refcount(dir->subsystem) == 1 && dir->ref_count != 1); __put_system(dir->subsystem); if (!--dir->ref_count) kfree(dir); } static void put_system(struct trace_subsystem_dir *dir) { mutex_lock(&event_mutex); __put_system_dir(dir); mutex_unlock(&event_mutex); } static void remove_subsystem(struct trace_subsystem_dir *dir) { if (!dir) return; if (!--dir->nr_events) { tracefs_remove(dir->entry); list_del(&dir->list); __put_system_dir(dir); } } static void remove_event_file_dir(struct trace_event_file *file) { struct dentry *dir = file->dir; struct dentry *child; if (dir) { spin_lock(&dir->d_lock); /* probably unneeded */ list_for_each_entry(child, &dir->d_subdirs, d_child) { if (d_really_is_positive(child)) /* probably unneeded */ d_inode(child)->i_private = NULL; } spin_unlock(&dir->d_lock); tracefs_remove(dir); } list_del(&file->list); remove_subsystem(file->system); free_event_filter(file->filter); kmem_cache_free(file_cachep, file); } /* * __ftrace_set_clr_event(NULL, NULL, NULL, set) will set/unset all events. */ static int __ftrace_set_clr_event_nolock(struct trace_array *tr, const char *match, const char *sub, const char *event, int set) { struct trace_event_file *file; struct trace_event_call *call; const char *name; int ret = -EINVAL; int eret = 0; list_for_each_entry(file, &tr->events, list) { call = file->event_call; name = trace_event_name(call); if (!name || !call->class || !call->class->reg) continue; if (call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) continue; if (match && strcmp(match, name) != 0 && strcmp(match, call->class->system) != 0) continue; if (sub && strcmp(sub, call->class->system) != 0) continue; if (event && strcmp(event, name) != 0) continue; ret = ftrace_event_enable_disable(file, set); /* * Save the first error and return that. Some events * may still have been enabled, but let the user * know that something went wrong. */ if (ret && !eret) eret = ret; ret = eret; } return ret; } static int __ftrace_set_clr_event(struct trace_array *tr, const char *match, const char *sub, const char *event, int set) { int ret; mutex_lock(&event_mutex); ret = __ftrace_set_clr_event_nolock(tr, match, sub, event, set); mutex_unlock(&event_mutex); return ret; } int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set) { char *event = NULL, *sub = NULL, *match; int ret; if (!tr) return -ENOENT; /* * The buf format can be <subsystem>:<event-name> * *:<event-name> means any event by that name. * :<event-name> is the same. * * <subsystem>:* means all events in that subsystem * <subsystem>: means the same. * * <name> (no ':') means all events in a subsystem with * the name <name> or any event that matches <name> */ match = strsep(&buf, ":"); if (buf) { sub = match; event = buf; match = NULL; if (!strlen(sub) || strcmp(sub, "*") == 0) sub = NULL; if (!strlen(event) || strcmp(event, "*") == 0) event = NULL; } ret = __ftrace_set_clr_event(tr, match, sub, event, set); /* Put back the colon to allow this to be called again */ if (buf) *(buf - 1) = ':'; return ret; } /** * trace_set_clr_event - enable or disable an event * @system: system name to match (NULL for any system) * @event: event name to match (NULL for all events, within system) * @set: 1 to enable, 0 to disable * * This is a way for other parts of the kernel to enable or disable * event recording. * * Returns 0 on success, -EINVAL if the parameters do not match any * registered events. */ int trace_set_clr_event(const char *system, const char *event, int set) { struct trace_array *tr = top_trace_array(); if (!tr) return -ENODEV; return __ftrace_set_clr_event(tr, NULL, system, event, set); } EXPORT_SYMBOL_GPL(trace_set_clr_event); /** * trace_array_set_clr_event - enable or disable an event for a trace array. * @tr: concerned trace array. * @system: system name to match (NULL for any system) * @event: event name to match (NULL for all events, within system) * @enable: true to enable, false to disable * * This is a way for other parts of the kernel to enable or disable * event recording. * * Returns 0 on success, -EINVAL if the parameters do not match any * registered events. */ int trace_array_set_clr_event(struct trace_array *tr, const char *system, const char *event, bool enable) { int set; if (!tr) return -ENOENT; set = (enable == true) ? 1 : 0; return __ftrace_set_clr_event(tr, NULL, system, event, set); } EXPORT_SYMBOL_GPL(trace_array_set_clr_event); /* 128 should be much more than enough */ #define EVENT_BUF_SIZE 127 static ssize_t ftrace_event_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_parser parser; struct seq_file *m = file->private_data; struct trace_array *tr = m->private; ssize_t read, ret; if (!cnt) return 0; ret = tracing_update_buffers(); if (ret < 0) return ret; if (trace_parser_get_init(&parser, EVENT_BUF_SIZE + 1)) return -ENOMEM; read = trace_get_user(&parser, ubuf, cnt, ppos); if (read >= 0 && trace_parser_loaded((&parser))) { int set = 1; if (*parser.buffer == '!') set = 0; ret = ftrace_set_clr_event(tr, parser.buffer + !set, set); if (ret) goto out_put; } ret = read; out_put: trace_parser_put(&parser); return ret; } static void * t_next(struct seq_file *m, void *v, loff_t *pos) { struct trace_event_file *file = v; struct trace_event_call *call; struct trace_array *tr = m->private; (*pos)++; list_for_each_entry_continue(file, &tr->events, list) { call = file->event_call; /* * The ftrace subsystem is for showing formats only. * They can not be enabled or disabled via the event files. */ if (call->class && call->class->reg && !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) return file; } return NULL; } static void *t_start(struct seq_file *m, loff_t *pos) { struct trace_event_file *file; struct trace_array *tr = m->private; loff_t l; mutex_lock(&event_mutex); file = list_entry(&tr->events, struct trace_event_file, list); for (l = 0; l <= *pos; ) { file = t_next(m, file, &l); if (!file) break; } return file; } static void * s_next(struct seq_file *m, void *v, loff_t *pos) { struct trace_event_file *file = v; struct trace_array *tr = m->private; (*pos)++; list_for_each_entry_continue(file, &tr->events, list) { if (file->flags & EVENT_FILE_FL_ENABLED) return file; } return NULL; } static void *s_start(struct seq_file *m, loff_t *pos) { struct trace_event_file *file; struct trace_array *tr = m->private; loff_t l; mutex_lock(&event_mutex); file = list_entry(&tr->events, struct trace_event_file, list); for (l = 0; l <= *pos; ) { file = s_next(m, file, &l); if (!file) break; } return file; } static int t_show(struct seq_file *m, void *v) { struct trace_event_file *file = v; struct trace_event_call *call = file->event_call; if (strcmp(call->class->system, TRACE_SYSTEM) != 0) seq_printf(m, "%s:", call->class->system); seq_printf(m, "%s\n", trace_event_name(call)); return 0; } static void t_stop(struct seq_file *m, void *p) { mutex_unlock(&event_mutex); } static void * __next(struct seq_file *m, void *v, loff_t *pos, int type) { struct trace_array *tr = m->private; struct trace_pid_list *pid_list; if (type == TRACE_PIDS) pid_list = rcu_dereference_sched(tr->filtered_pids); else pid_list = rcu_dereference_sched(tr->filtered_no_pids); return trace_pid_next(pid_list, v, pos); } static void * p_next(struct seq_file *m, void *v, loff_t *pos) { return __next(m, v, pos, TRACE_PIDS); } static void * np_next(struct seq_file *m, void *v, loff_t *pos) { return __next(m, v, pos, TRACE_NO_PIDS); } static void *__start(struct seq_file *m, loff_t *pos, int type) __acquires(RCU) { struct trace_pid_list *pid_list; struct trace_array *tr = m->private; /* * Grab the mutex, to keep calls to p_next() having the same * tr->filtered_pids as p_start() has. * If we just passed the tr->filtered_pids around, then RCU would * have been enough, but doing that makes things more complex. */ mutex_lock(&event_mutex); rcu_read_lock_sched(); if (type == TRACE_PIDS) pid_list = rcu_dereference_sched(tr->filtered_pids); else pid_list = rcu_dereference_sched(tr->filtered_no_pids); if (!pid_list) return NULL; return trace_pid_start(pid_list, pos); } static void *p_start(struct seq_file *m, loff_t *pos) __acquires(RCU) { return __start(m, pos, TRACE_PIDS); } static void *np_start(struct seq_file *m, loff_t *pos) __acquires(RCU) { return __start(m, pos, TRACE_NO_PIDS); } static void p_stop(struct seq_file *m, void *p) __releases(RCU) { rcu_read_unlock_sched(); mutex_unlock(&event_mutex); } static ssize_t event_enable_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_event_file *file; unsigned long flags; char buf[4] = "0"; mutex_lock(&event_mutex); file = event_file_data(filp); if (likely(file)) flags = file->flags; mutex_unlock(&event_mutex); if (!file) return -ENODEV; if (flags & EVENT_FILE_FL_ENABLED && !(flags & EVENT_FILE_FL_SOFT_DISABLED)) strcpy(buf, "1"); if (flags & EVENT_FILE_FL_SOFT_DISABLED || flags & EVENT_FILE_FL_SOFT_MODE) strcat(buf, "*"); strcat(buf, "\n"); return simple_read_from_buffer(ubuf, cnt, ppos, buf, strlen(buf)); } static ssize_t event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_event_file *file; unsigned long val; int ret; ret = kstrtoul_from_user(ubuf, cnt, 10, &val); if (ret) return ret; ret = tracing_update_buffers(); if (ret < 0) return ret; switch (val) { case 0: case 1: ret = -ENODEV; mutex_lock(&event_mutex); file = event_file_data(filp); if (likely(file)) ret = ftrace_event_enable_disable(file, val); mutex_unlock(&event_mutex); break; default: return -EINVAL; } *ppos += cnt; return ret ? ret : cnt; } static ssize_t system_enable_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { const char set_to_char[4] = { '?', '0', '1', 'X' }; struct trace_subsystem_dir *dir = filp->private_data; struct event_subsystem *system = dir->subsystem; struct trace_event_call *call; struct trace_event_file *file; struct trace_array *tr = dir->tr; char buf[2]; int set = 0; int ret; mutex_lock(&event_mutex); list_for_each_entry(file, &tr->events, list) { call = file->event_call; if ((call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) || !trace_event_name(call) || !call->class || !call->class->reg) continue; if (system && strcmp(call->class->system, system->name) != 0) continue; /* * We need to find out if all the events are set * or if all events or cleared, or if we have * a mixture. */ set |= (1 << !!(file->flags & EVENT_FILE_FL_ENABLED)); /* * If we have a mixture, no need to look further. */ if (set == 3) break; } mutex_unlock(&event_mutex); buf[0] = set_to_char[set]; buf[1] = '\n'; ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, 2); return ret; } static ssize_t system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_subsystem_dir *dir = filp->private_data; struct event_subsystem *system = dir->subsystem; const char *name = NULL; unsigned long val; ssize_t ret; ret = kstrtoul_from_user(ubuf, cnt, 10, &val); if (ret) return ret; ret = tracing_update_buffers(); if (ret < 0) return ret; if (val != 0 && val != 1) return -EINVAL; /* * Opening of "enable" adds a ref count to system, * so the name is safe to use. */ if (system) name = system->name; ret = __ftrace_set_clr_event(dir->tr, NULL, name, NULL, val); if (ret) goto out; ret = cnt; out: *ppos += cnt; return ret; } enum { FORMAT_HEADER = 1, FORMAT_FIELD_SEPERATOR = 2, FORMAT_PRINTFMT = 3, }; static void *f_next(struct seq_file *m, void *v, loff_t *pos) { struct trace_event_call *call = event_file_data(m->private); struct list_head *common_head = &ftrace_common_fields; struct list_head *head = trace_get_fields(call); struct list_head *node = v; (*pos)++; switch ((unsigned long)v) { case FORMAT_HEADER: node = common_head; break; case FORMAT_FIELD_SEPERATOR: node = head; break; case FORMAT_PRINTFMT: /* all done */ return NULL; } node = node->prev; if (node == common_head) return (void *)FORMAT_FIELD_SEPERATOR; else if (node == head) return (void *)FORMAT_PRINTFMT; else return node; } static int f_show(struct seq_file *m, void *v) { struct trace_event_call *call = event_file_data(m->private); struct ftrace_event_field *field; const char *array_descriptor; switch ((unsigned long)v) { case FORMAT_HEADER: seq_printf(m, "name: %s\n", trace_event_name(call)); seq_printf(m, "ID: %d\n", call->event.type); seq_puts(m, "format:\n"); return 0; case FORMAT_FIELD_SEPERATOR: seq_putc(m, '\n'); return 0; case FORMAT_PRINTFMT: seq_printf(m, "\nprint fmt: %s\n", call->print_fmt); return 0; } field = list_entry(v, struct ftrace_event_field, link); /* * Smartly shows the array type(except dynamic array). * Normal: * field:TYPE VAR * If TYPE := TYPE[LEN], it is shown: * field:TYPE VAR[LEN] */ array_descriptor = strchr(field->type, '['); if (str_has_prefix(field->type, "__data_loc")) array_descriptor = NULL; if (!array_descriptor) seq_printf(m, "\tfield:%s %s;\toffset:%u;\tsize:%u;\tsigned:%d;\n", field->type, field->name, field->offset, field->size, !!field->is_signed); else if (field->len) seq_printf(m, "\tfield:%.*s %s[%d];\toffset:%u;\tsize:%u;\tsigned:%d;\n", (int)(array_descriptor - field->type), field->type, field->name, field->len, field->offset, field->size, !!field->is_signed); else seq_printf(m, "\tfield:%.*s %s[];\toffset:%u;\tsize:%u;\tsigned:%d;\n", (int)(array_descriptor - field->type), field->type, field->name, field->offset, field->size, !!field->is_signed); return 0; } static void *f_start(struct seq_file *m, loff_t *pos) { void *p = (void *)FORMAT_HEADER; loff_t l = 0; /* ->stop() is called even if ->start() fails */ mutex_lock(&event_mutex); if (!event_file_data(m->private)) return ERR_PTR(-ENODEV); while (l < *pos && p) p = f_next(m, p, &l); return p; } static void f_stop(struct seq_file *m, void *p) { mutex_unlock(&event_mutex); } static const struct seq_operations trace_format_seq_ops = { .start = f_start, .next = f_next, .stop = f_stop, .show = f_show, }; static int trace_format_open(struct inode *inode, struct file *file) { struct seq_file *m; int ret; /* Do we want to hide event format files on tracefs lockdown? */ ret = seq_open(file, &trace_format_seq_ops); if (ret < 0) return ret; m = file->private_data; m->private = file; return 0; } #ifdef CONFIG_PERF_EVENTS static ssize_t event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { int id = (long)event_file_data(filp); char buf[32]; int len; if (unlikely(!id)) return -ENODEV; len = sprintf(buf, "%d\n", id); return simple_read_from_buffer(ubuf, cnt, ppos, buf, len); } #endif static ssize_t event_filter_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_event_file *file; struct trace_seq *s; int r = -ENODEV; if (*ppos) return 0; s = kmalloc(sizeof(*s), GFP_KERNEL); if (!s) return -ENOMEM; trace_seq_init(s); mutex_lock(&event_mutex); file = event_file_data(filp); if (file) print_event_filter(file, s); mutex_unlock(&event_mutex); if (file) r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, trace_seq_used(s)); kfree(s); return r; } static ssize_t event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_event_file *file; char *buf; int err = -ENODEV; if (cnt >= PAGE_SIZE) return -EINVAL; buf = memdup_user_nul(ubuf, cnt); if (IS_ERR(buf)) return PTR_ERR(buf); mutex_lock(&event_mutex); file = event_file_data(filp); if (file) err = apply_event_filter(file, buf); mutex_unlock(&event_mutex); kfree(buf); if (err < 0) return err; *ppos += cnt; return cnt; } static LIST_HEAD(event_subsystems); static int subsystem_open(struct inode *inode, struct file *filp) { struct trace_subsystem_dir *dir = NULL, *iter_dir; struct trace_array *tr = NULL, *iter_tr; struct event_subsystem *system = NULL; int ret; if (tracing_is_disabled()) return -ENODEV; /* Make sure the system still exists */ mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); list_for_each_entry(iter_tr, &ftrace_trace_arrays, list) { list_for_each_entry(iter_dir, &iter_tr->systems, list) { if (iter_dir == inode->i_private) { /* Don't open systems with no events */ tr = iter_tr; dir = iter_dir; if (dir->nr_events) { __get_system_dir(dir); system = dir->subsystem; } goto exit_loop; } } } exit_loop: mutex_unlock(&trace_types_lock); mutex_unlock(&event_mutex); if (!system) return -ENODEV; /* Still need to increment the ref count of the system */ if (trace_array_get(tr) < 0) { put_system(dir); return -ENODEV; } ret = tracing_open_generic(inode, filp); if (ret < 0) { trace_array_put(tr); put_system(dir); } return ret; } static int system_tr_open(struct inode *inode, struct file *filp) { struct trace_subsystem_dir *dir; struct trace_array *tr = inode->i_private; int ret; /* Make a temporary dir that has no system but points to tr */ dir = kzalloc(sizeof(*dir), GFP_KERNEL); if (!dir) return -ENOMEM; ret = tracing_open_generic_tr(inode, filp); if (ret < 0) { kfree(dir); return ret; } dir->tr = tr; filp->private_data = dir; return 0; } static int subsystem_release(struct inode *inode, struct file *file) { struct trace_subsystem_dir *dir = file->private_data; trace_array_put(dir->tr); /* * If dir->subsystem is NULL, then this is a temporary * descriptor that was made for a trace_array to enable * all subsystems. */ if (dir->subsystem) put_system(dir); else kfree(dir); return 0; } static ssize_t subsystem_filter_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_subsystem_dir *dir = filp->private_data; struct event_subsystem *system = dir->subsystem; struct trace_seq *s; int r; if (*ppos) return 0; s = kmalloc(sizeof(*s), GFP_KERNEL); if (!s) return -ENOMEM; trace_seq_init(s); print_subsystem_event_filter(system, s); r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, trace_seq_used(s)); kfree(s); return r; } static ssize_t subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_subsystem_dir *dir = filp->private_data; char *buf; int err; if (cnt >= PAGE_SIZE) return -EINVAL; buf = memdup_user_nul(ubuf, cnt); if (IS_ERR(buf)) return PTR_ERR(buf); err = apply_subsystem_event_filter(dir, buf); kfree(buf); if (err < 0) return err; *ppos += cnt; return cnt; } static ssize_t show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { int (*func)(struct trace_seq *s) = filp->private_data; struct trace_seq *s; int r; if (*ppos) return 0; s = kmalloc(sizeof(*s), GFP_KERNEL); if (!s) return -ENOMEM; trace_seq_init(s); func(s); r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, trace_seq_used(s)); kfree(s); return r; } static void ignore_task_cpu(void *data) { struct trace_array *tr = data; struct trace_pid_list *pid_list; struct trace_pid_list *no_pid_list; /* * This function is called by on_each_cpu() while the * event_mutex is held. */ pid_list = rcu_dereference_protected(tr->filtered_pids, mutex_is_locked(&event_mutex)); no_pid_list = rcu_dereference_protected(tr->filtered_no_pids, mutex_is_locked(&event_mutex)); this_cpu_write(tr->array_buffer.data->ignore_pid, trace_ignore_this_task(pid_list, no_pid_list, current)); } static void register_pid_events(struct trace_array *tr) { /* * Register a probe that is called before all other probes * to set ignore_pid if next or prev do not match. * Register a probe this is called after all other probes * to only keep ignore_pid set if next pid matches. */ register_trace_prio_sched_switch(event_filter_pid_sched_switch_probe_pre, tr, INT_MAX); register_trace_prio_sched_switch(event_filter_pid_sched_switch_probe_post, tr, 0); register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_pre, tr, INT_MAX); register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_post, tr, 0); register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_pre, tr, INT_MAX); register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_post, tr, 0); register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_pre, tr, INT_MAX); register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_post, tr, 0); } static ssize_t event_pid_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos, int type) { struct seq_file *m = filp->private_data; struct trace_array *tr = m->private; struct trace_pid_list *filtered_pids = NULL; struct trace_pid_list *other_pids = NULL; struct trace_pid_list *pid_list; struct trace_event_file *file; ssize_t ret; if (!cnt) return 0; ret = tracing_update_buffers(); if (ret < 0) return ret; mutex_lock(&event_mutex); if (type == TRACE_PIDS) { filtered_pids = rcu_dereference_protected(tr->filtered_pids, lockdep_is_held(&event_mutex)); other_pids = rcu_dereference_protected(tr->filtered_no_pids, lockdep_is_held(&event_mutex)); } else { filtered_pids = rcu_dereference_protected(tr->filtered_no_pids, lockdep_is_held(&event_mutex)); other_pids = rcu_dereference_protected(tr->filtered_pids, lockdep_is_held(&event_mutex)); } ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt); if (ret < 0) goto out; if (type == TRACE_PIDS) rcu_assign_pointer(tr->filtered_pids, pid_list); else rcu_assign_pointer(tr->filtered_no_pids, pid_list); list_for_each_entry(file, &tr->events, list) { set_bit(EVENT_FILE_FL_PID_FILTER_BIT, &file->flags); } if (filtered_pids) { tracepoint_synchronize_unregister(); trace_pid_list_free(filtered_pids); } else if (pid_list && !other_pids) { register_pid_events(tr); } /* * Ignoring of pids is done at task switch. But we have to * check for those tasks that are currently running. * Always do this in case a pid was appended or removed. */ on_each_cpu(ignore_task_cpu, tr, 1); out: mutex_unlock(&event_mutex); if (ret > 0) *ppos += ret; return ret; } static ssize_t ftrace_event_pid_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { return event_pid_write(filp, ubuf, cnt, ppos, TRACE_PIDS); } static ssize_t ftrace_event_npid_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { return event_pid_write(filp, ubuf, cnt, ppos, TRACE_NO_PIDS); } static int ftrace_event_avail_open(struct inode *inode, struct file *file); static int ftrace_event_set_open(struct inode *inode, struct file *file); static int ftrace_event_set_pid_open(struct inode *inode, struct file *file); static int ftrace_event_set_npid_open(struct inode *inode, struct file *file); static int ftrace_event_release(struct inode *inode, struct file *file); static const struct seq_operations show_event_seq_ops = { .start = t_start, .next = t_next, .show = t_show, .stop = t_stop, }; static const struct seq_operations show_set_event_seq_ops = { .start = s_start, .next = s_next, .show = t_show, .stop = t_stop, }; static const struct seq_operations show_set_pid_seq_ops = { .start = p_start, .next = p_next, .show = trace_pid_show, .stop = p_stop, }; static const struct seq_operations show_set_no_pid_seq_ops = { .start = np_start, .next = np_next, .show = trace_pid_show, .stop = p_stop, }; static const struct file_operations ftrace_avail_fops = { .open = ftrace_event_avail_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; static const struct file_operations ftrace_set_event_fops = { .open = ftrace_event_set_open, .read = seq_read, .write = ftrace_event_write, .llseek = seq_lseek, .release = ftrace_event_release, }; static const struct file_operations ftrace_set_event_pid_fops = { .open = ftrace_event_set_pid_open, .read = seq_read, .write = ftrace_event_pid_write, .llseek = seq_lseek, .release = ftrace_event_release, }; static const struct file_operations ftrace_set_event_notrace_pid_fops = { .open = ftrace_event_set_npid_open, .read = seq_read, .write = ftrace_event_npid_write, .llseek = seq_lseek, .release = ftrace_event_release, }; static const struct file_operations ftrace_enable_fops = { .open = tracing_open_file_tr, .read = event_enable_read, .write = event_enable_write, .release = tracing_release_file_tr, .llseek = default_llseek, }; static const struct file_operations ftrace_event_format_fops = { .open = trace_format_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; #ifdef CONFIG_PERF_EVENTS static const struct file_operations ftrace_event_id_fops = { .read = event_id_read, .llseek = default_llseek, }; #endif static const struct file_operations ftrace_event_filter_fops = { .open = tracing_open_file_tr, .read = event_filter_read, .write = event_filter_write, .release = tracing_release_file_tr, .llseek = default_llseek, }; static const struct file_operations ftrace_subsystem_filter_fops = { .open = subsystem_open, .read = subsystem_filter_read, .write = subsystem_filter_write, .llseek = default_llseek, .release = subsystem_release, }; static const struct file_operations ftrace_system_enable_fops = { .open = subsystem_open, .read = system_enable_read, .write = system_enable_write, .llseek = default_llseek, .release = subsystem_release, }; static const struct file_operations ftrace_tr_enable_fops = { .open = system_tr_open, .read = system_enable_read, .write = system_enable_write, .llseek = default_llseek, .release = subsystem_release, }; static const struct file_operations ftrace_show_header_fops = { .open = tracing_open_generic, .read = show_header, .llseek = default_llseek, }; static int ftrace_event_open(struct inode *inode, struct file *file, const struct seq_operations *seq_ops) { struct seq_file *m; int ret; ret = security_locked_down(LOCKDOWN_TRACEFS); if (ret) return ret; ret = seq_open(file, seq_ops); if (ret < 0) return ret; m = file->private_data; /* copy tr over to seq ops */ m->private = inode->i_private; return ret; } static int ftrace_event_release(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; trace_array_put(tr); return seq_release(inode, file); } static int ftrace_event_avail_open(struct inode *inode, struct file *file) { const struct seq_operations *seq_ops = &show_event_seq_ops; /* Checks for tracefs lockdown */ return ftrace_event_open(inode, file, seq_ops); } static int ftrace_event_set_open(struct inode *inode, struct file *file) { const struct seq_operations *seq_ops = &show_set_event_seq_ops; struct trace_array *tr = inode->i_private; int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) ftrace_clear_events(tr); ret = ftrace_event_open(inode, file, seq_ops); if (ret < 0) trace_array_put(tr); return ret; } static int ftrace_event_set_pid_open(struct inode *inode, struct file *file) { const struct seq_operations *seq_ops = &show_set_pid_seq_ops; struct trace_array *tr = inode->i_private; int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) ftrace_clear_event_pids(tr, TRACE_PIDS); ret = ftrace_event_open(inode, file, seq_ops); if (ret < 0) trace_array_put(tr); return ret; } static int ftrace_event_set_npid_open(struct inode *inode, struct file *file) { const struct seq_operations *seq_ops = &show_set_no_pid_seq_ops; struct trace_array *tr = inode->i_private; int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) ftrace_clear_event_pids(tr, TRACE_NO_PIDS); ret = ftrace_event_open(inode, file, seq_ops); if (ret < 0) trace_array_put(tr); return ret; } static struct event_subsystem * create_new_subsystem(const char *name) { struct event_subsystem *system; /* need to create new entry */ system = kmalloc(sizeof(*system), GFP_KERNEL); if (!system) return NULL; system->ref_count = 1; /* Only allocate if dynamic (kprobes and modules) */ system->name = kstrdup_const(name, GFP_KERNEL); if (!system->name) goto out_free; system->filter = NULL; system->filter = kzalloc(sizeof(struct event_filter), GFP_KERNEL); if (!system->filter) goto out_free; list_add(&system->list, &event_subsystems); return system; out_free: kfree_const(system->name); kfree(system); return NULL; } static struct dentry * event_subsystem_dir(struct trace_array *tr, const char *name, struct trace_event_file *file, struct dentry *parent) { struct event_subsystem *system, *iter; struct trace_subsystem_dir *dir; struct dentry *entry; /* First see if we did not already create this dir */ list_for_each_entry(dir, &tr->systems, list) { system = dir->subsystem; if (strcmp(system->name, name) == 0) { dir->nr_events++; file->system = dir; return dir->entry; } } /* Now see if the system itself exists. */ system = NULL; list_for_each_entry(iter, &event_subsystems, list) { if (strcmp(iter->name, name) == 0) { system = iter; break; } } dir = kmalloc(sizeof(*dir), GFP_KERNEL); if (!dir) goto out_fail; if (!system) { system = create_new_subsystem(name); if (!system) goto out_free; } else __get_system(system); dir->entry = tracefs_create_dir(name, parent); if (!dir->entry) { pr_warn("Failed to create system directory %s\n", name); __put_system(system); goto out_free; } dir->tr = tr; dir->ref_count = 1; dir->nr_events = 1; dir->subsystem = system; file->system = dir; /* the ftrace system is special, do not create enable or filter files */ if (strcmp(name, "ftrace") != 0) { entry = tracefs_create_file("filter", TRACE_MODE_WRITE, dir->entry, dir, &ftrace_subsystem_filter_fops); if (!entry) { kfree(system->filter); system->filter = NULL; pr_warn("Could not create tracefs '%s/filter' entry\n", name); } trace_create_file("enable", TRACE_MODE_WRITE, dir->entry, dir, &ftrace_system_enable_fops); } list_add(&dir->list, &tr->systems); return dir->entry; out_free: kfree(dir); out_fail: /* Only print this message if failed on memory allocation */ if (!dir || !system) pr_warn("No memory to create event subsystem %s\n", name); return NULL; } static int event_define_fields(struct trace_event_call *call) { struct list_head *head; int ret = 0; /* * Other events may have the same class. Only update * the fields if they are not already defined. */ head = trace_get_fields(call); if (list_empty(head)) { struct trace_event_fields *field = call->class->fields_array; unsigned int offset = sizeof(struct trace_entry); for (; field->type; field++) { if (field->type == TRACE_FUNCTION_TYPE) { field->define_fields(call); break; } offset = ALIGN(offset, field->align); ret = trace_define_field_ext(call, field->type, field->name, offset, field->size, field->is_signed, field->filter_type, field->len); if (WARN_ON_ONCE(ret)) { pr_err("error code is %d\n", ret); break; } offset += field->size; } } return ret; } static int event_create_dir(struct dentry *parent, struct trace_event_file *file) { struct trace_event_call *call = file->event_call; struct trace_array *tr = file->tr; struct dentry *d_events; const char *name; int ret; /* * If the trace point header did not define TRACE_SYSTEM * then the system would be called "TRACE_SYSTEM". */ if (strcmp(call->class->system, TRACE_SYSTEM) != 0) { d_events = event_subsystem_dir(tr, call->class->system, file, parent); if (!d_events) return -ENOMEM; } else d_events = parent; name = trace_event_name(call); file->dir = tracefs_create_dir(name, d_events); if (!file->dir) { pr_warn("Could not create tracefs '%s' directory\n", name); return -1; } if (call->class->reg && !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) trace_create_file("enable", TRACE_MODE_WRITE, file->dir, file, &ftrace_enable_fops); #ifdef CONFIG_PERF_EVENTS if (call->event.type && call->class->reg) trace_create_file("id", TRACE_MODE_READ, file->dir, (void *)(long)call->event.type, &ftrace_event_id_fops); #endif ret = event_define_fields(call); if (ret < 0) { pr_warn("Could not initialize trace point events/%s\n", name); return ret; } /* * Only event directories that can be enabled should have * triggers or filters. */ if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) { trace_create_file("filter", TRACE_MODE_WRITE, file->dir, file, &ftrace_event_filter_fops); trace_create_file("trigger", TRACE_MODE_WRITE, file->dir, file, &event_trigger_fops); } #ifdef CONFIG_HIST_TRIGGERS trace_create_file("hist", TRACE_MODE_READ, file->dir, file, &event_hist_fops); #endif #ifdef CONFIG_HIST_TRIGGERS_DEBUG trace_create_file("hist_debug", TRACE_MODE_READ, file->dir, file, &event_hist_debug_fops); #endif trace_create_file("format", TRACE_MODE_READ, file->dir, call, &ftrace_event_format_fops); #ifdef CONFIG_TRACE_EVENT_INJECT if (call->event.type && call->class->reg) trace_create_file("inject", 0200, file->dir, file, &event_inject_fops); #endif return 0; } static void remove_event_from_tracers(struct trace_event_call *call) { struct trace_event_file *file; struct trace_array *tr; do_for_each_event_file_safe(tr, file) { if (file->event_call != call) continue; remove_event_file_dir(file); /* * The do_for_each_event_file_safe() is * a double loop. After finding the call for this * trace_array, we use break to jump to the next * trace_array. */ break; } while_for_each_event_file(); } static void event_remove(struct trace_event_call *call) { struct trace_array *tr; struct trace_event_file *file; do_for_each_event_file(tr, file) { if (file->event_call != call) continue; if (file->flags & EVENT_FILE_FL_WAS_ENABLED) tr->clear_trace = true; ftrace_event_enable_disable(file, 0); /* * The do_for_each_event_file() is * a double loop. After finding the call for this * trace_array, we use break to jump to the next * trace_array. */ break; } while_for_each_event_file(); if (call->event.funcs) __unregister_trace_event(&call->event); remove_event_from_tracers(call); list_del(&call->list); } static int event_init(struct trace_event_call *call) { int ret = 0; const char *name; name = trace_event_name(call); if (WARN_ON(!name)) return -EINVAL; if (call->class->raw_init) { ret = call->class->raw_init(call); if (ret < 0 && ret != -ENOSYS) pr_warn("Could not initialize trace events/%s\n", name); } return ret; } static int __register_event(struct trace_event_call *call, struct module *mod) { int ret; ret = event_init(call); if (ret < 0) return ret; list_add(&call->list, &ftrace_events); if (call->flags & TRACE_EVENT_FL_DYNAMIC) atomic_set(&call->refcnt, 0); else call->module = mod; return 0; } static char *eval_replace(char *ptr, struct trace_eval_map *map, int len) { int rlen; int elen; /* Find the length of the eval value as a string */ elen = snprintf(ptr, 0, "%ld", map->eval_value); /* Make sure there's enough room to replace the string with the value */ if (len < elen) return NULL; snprintf(ptr, elen + 1, "%ld", map->eval_value); /* Get the rest of the string of ptr */ rlen = strlen(ptr + len); memmove(ptr + elen, ptr + len, rlen); /* Make sure we end the new string */ ptr[elen + rlen] = 0; return ptr + elen; } static void update_event_printk(struct trace_event_call *call, struct trace_eval_map *map) { char *ptr; int quote = 0; int len = strlen(map->eval_string); for (ptr = call->print_fmt; *ptr; ptr++) { if (*ptr == '\\') { ptr++; /* paranoid */ if (!*ptr) break; continue; } if (*ptr == '"') { quote ^= 1; continue; } if (quote) continue; if (isdigit(*ptr)) { /* skip numbers */ do { ptr++; /* Check for alpha chars like ULL */ } while (isalnum(*ptr)); if (!*ptr) break; /* * A number must have some kind of delimiter after * it, and we can ignore that too. */ continue; } if (isalpha(*ptr) || *ptr == '_') { if (strncmp(map->eval_string, ptr, len) == 0 && !isalnum(ptr[len]) && ptr[len] != '_') { ptr = eval_replace(ptr, map, len); /* enum/sizeof string smaller than value */ if (WARN_ON_ONCE(!ptr)) return; /* * No need to decrement here, as eval_replace() * returns the pointer to the character passed * the eval, and two evals can not be placed * back to back without something in between. * We can skip that something in between. */ continue; } skip_more: do { ptr++; } while (isalnum(*ptr) || *ptr == '_'); if (!*ptr) break; /* * If what comes after this variable is a '.' or * '->' then we can continue to ignore that string. */ if (*ptr == '.' || (ptr[0] == '-' && ptr[1] == '>')) { ptr += *ptr == '.' ? 1 : 2; if (!*ptr) break; goto skip_more; } /* * Once again, we can skip the delimiter that came * after the string. */ continue; } } } static void add_str_to_module(struct module *module, char *str) { struct module_string *modstr; modstr = kmalloc(sizeof(*modstr), GFP_KERNEL); /* * If we failed to allocate memory here, then we'll just * let the str memory leak when the module is removed. * If this fails to allocate, there's worse problems than * a leaked string on module removal. */ if (WARN_ON_ONCE(!modstr)) return; modstr->module = module; modstr->str = str; list_add(&modstr->next, &module_strings); } static void update_event_fields(struct trace_event_call *call, struct trace_eval_map *map) { struct ftrace_event_field *field; struct list_head *head; char *ptr; char *str; int len = strlen(map->eval_string); /* Dynamic events should never have field maps */ if (WARN_ON_ONCE(call->flags & TRACE_EVENT_FL_DYNAMIC)) return; head = trace_get_fields(call); list_for_each_entry(field, head, link) { ptr = strchr(field->type, '['); if (!ptr) continue; ptr++; if (!isalpha(*ptr) && *ptr != '_') continue; if (strncmp(map->eval_string, ptr, len) != 0) continue; str = kstrdup(field->type, GFP_KERNEL); if (WARN_ON_ONCE(!str)) return; ptr = str + (ptr - field->type); ptr = eval_replace(ptr, map, len); /* enum/sizeof string smaller than value */ if (WARN_ON_ONCE(!ptr)) { kfree(str); continue; } /* * If the event is part of a module, then we need to free the string * when the module is removed. Otherwise, it will stay allocated * until a reboot. */ if (call->module) add_str_to_module(call->module, str); field->type = str; } } void trace_event_eval_update(struct trace_eval_map **map, int len) { struct trace_event_call *call, *p; const char *last_system = NULL; bool first = false; int last_i; int i; down_write(&trace_event_sem); list_for_each_entry_safe(call, p, &ftrace_events, list) { /* events are usually grouped together with systems */ if (!last_system || call->class->system != last_system) { first = true; last_i = 0; last_system = call->class->system; } /* * Since calls are grouped by systems, the likelihood that the * next call in the iteration belongs to the same system as the * previous call is high. As an optimization, we skip searching * for a map[] that matches the call's system if the last call * was from the same system. That's what last_i is for. If the * call has the same system as the previous call, then last_i * will be the index of the first map[] that has a matching * system. */ for (i = last_i; i < len; i++) { if (call->class->system == map[i]->system) { /* Save the first system if need be */ if (first) { last_i = i; first = false; } update_event_printk(call, map[i]); update_event_fields(call, map[i]); } } cond_resched(); } up_write(&trace_event_sem); } static struct trace_event_file * trace_create_new_event(struct trace_event_call *call, struct trace_array *tr) { struct trace_pid_list *no_pid_list; struct trace_pid_list *pid_list; struct trace_event_file *file; unsigned int first; file = kmem_cache_alloc(file_cachep, GFP_TRACE); if (!file) return NULL; pid_list = rcu_dereference_protected(tr->filtered_pids, lockdep_is_held(&event_mutex)); no_pid_list = rcu_dereference_protected(tr->filtered_no_pids, lockdep_is_held(&event_mutex)); if (!trace_pid_list_first(pid_list, &first) || !trace_pid_list_first(no_pid_list, &first)) file->flags |= EVENT_FILE_FL_PID_FILTER; file->event_call = call; file->tr = tr; atomic_set(&file->sm_ref, 0); atomic_set(&file->tm_ref, 0); INIT_LIST_HEAD(&file->triggers); list_add(&file->list, &tr->events); return file; } /* Add an event to a trace directory */ static int __trace_add_new_event(struct trace_event_call *call, struct trace_array *tr) { struct trace_event_file *file; file = trace_create_new_event(call, tr); if (!file) return -ENOMEM; if (eventdir_initialized) return event_create_dir(tr->event_dir, file); else return event_define_fields(call); } /* * Just create a descriptor for early init. A descriptor is required * for enabling events at boot. We want to enable events before * the filesystem is initialized. */ static int __trace_early_add_new_event(struct trace_event_call *call, struct trace_array *tr) { struct trace_event_file *file; file = trace_create_new_event(call, tr); if (!file) return -ENOMEM; return event_define_fields(call); } struct ftrace_module_file_ops; static void __add_event_to_tracers(struct trace_event_call *call); /* Add an additional event_call dynamically */ int trace_add_event_call(struct trace_event_call *call) { int ret; lockdep_assert_held(&event_mutex); mutex_lock(&trace_types_lock); ret = __register_event(call, NULL); if (ret >= 0) __add_event_to_tracers(call); mutex_unlock(&trace_types_lock); return ret; } EXPORT_SYMBOL_GPL(trace_add_event_call); /* * Must be called under locking of trace_types_lock, event_mutex and * trace_event_sem. */ static void __trace_remove_event_call(struct trace_event_call *call) { event_remove(call); trace_destroy_fields(call); free_event_filter(call->filter); call->filter = NULL; } static int probe_remove_event_call(struct trace_event_call *call) { struct trace_array *tr; struct trace_event_file *file; #ifdef CONFIG_PERF_EVENTS if (call->perf_refcount) return -EBUSY; #endif do_for_each_event_file(tr, file) { if (file->event_call != call) continue; /* * We can't rely on ftrace_event_enable_disable(enable => 0) * we are going to do, EVENT_FILE_FL_SOFT_MODE can suppress * TRACE_REG_UNREGISTER. */ if (file->flags & EVENT_FILE_FL_ENABLED) goto busy; if (file->flags & EVENT_FILE_FL_WAS_ENABLED) tr->clear_trace = true; /* * The do_for_each_event_file_safe() is * a double loop. After finding the call for this * trace_array, we use break to jump to the next * trace_array. */ break; } while_for_each_event_file(); __trace_remove_event_call(call); return 0; busy: /* No need to clear the trace now */ list_for_each_entry(tr, &ftrace_trace_arrays, list) { tr->clear_trace = false; } return -EBUSY; } /* Remove an event_call */ int trace_remove_event_call(struct trace_event_call *call) { int ret; lockdep_assert_held(&event_mutex); mutex_lock(&trace_types_lock); down_write(&trace_event_sem); ret = probe_remove_event_call(call); up_write(&trace_event_sem); mutex_unlock(&trace_types_lock); return ret; } EXPORT_SYMBOL_GPL(trace_remove_event_call); #define for_each_event(event, start, end) \ for (event = start; \ (unsigned long)event < (unsigned long)end; \ event++) #ifdef CONFIG_MODULES static void trace_module_add_events(struct module *mod) { struct trace_event_call **call, **start, **end; if (!mod->num_trace_events) return; /* Don't add infrastructure for mods without tracepoints */ if (trace_module_has_bad_taint(mod)) { pr_err("%s: module has bad taint, not creating trace events\n", mod->name); return; } start = mod->trace_events; end = mod->trace_events + mod->num_trace_events; for_each_event(call, start, end) { __register_event(*call, mod); __add_event_to_tracers(*call); } } static void trace_module_remove_events(struct module *mod) { struct trace_event_call *call, *p; struct module_string *modstr, *m; down_write(&trace_event_sem); list_for_each_entry_safe(call, p, &ftrace_events, list) { if ((call->flags & TRACE_EVENT_FL_DYNAMIC) || !call->module) continue; if (call->module == mod) __trace_remove_event_call(call); } /* Check for any strings allocade for this module */ list_for_each_entry_safe(modstr, m, &module_strings, next) { if (modstr->module != mod) continue; list_del(&modstr->next); kfree(modstr->str); kfree(modstr); } up_write(&trace_event_sem); /* * It is safest to reset the ring buffer if the module being unloaded * registered any events that were used. The only worry is if * a new module gets loaded, and takes on the same id as the events * of this module. When printing out the buffer, traced events left * over from this module may be passed to the new module events and * unexpected results may occur. */ tracing_reset_all_online_cpus_unlocked(); } static int trace_module_notify(struct notifier_block *self, unsigned long val, void *data) { struct module *mod = data; mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); switch (val) { case MODULE_STATE_COMING: trace_module_add_events(mod); break; case MODULE_STATE_GOING: trace_module_remove_events(mod); break; } mutex_unlock(&trace_types_lock); mutex_unlock(&event_mutex); return NOTIFY_OK; } static struct notifier_block trace_module_nb = { .notifier_call = trace_module_notify, .priority = 1, /* higher than trace.c module notify */ }; #endif /* CONFIG_MODULES */ /* Create a new event directory structure for a trace directory. */ static void __trace_add_event_dirs(struct trace_array *tr) { struct trace_event_call *call; int ret; list_for_each_entry(call, &ftrace_events, list) { ret = __trace_add_new_event(call, tr); if (ret < 0) pr_warn("Could not create directory for event %s\n", trace_event_name(call)); } } /* Returns any file that matches the system and event */ struct trace_event_file * __find_event_file(struct trace_array *tr, const char *system, const char *event) { struct trace_event_file *file; struct trace_event_call *call; const char *name; list_for_each_entry(file, &tr->events, list) { call = file->event_call; name = trace_event_name(call); if (!name || !call->class) continue; if (strcmp(event, name) == 0 && strcmp(system, call->class->system) == 0) return file; } return NULL; } /* Returns valid trace event files that match system and event */ struct trace_event_file * find_event_file(struct trace_array *tr, const char *system, const char *event) { struct trace_event_file *file; file = __find_event_file(tr, system, event); if (!file || !file->event_call->class->reg || file->event_call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) return NULL; return file; } /** * trace_get_event_file - Find and return a trace event file * @instance: The name of the trace instance containing the event * @system: The name of the system containing the event * @event: The name of the event * * Return a trace event file given the trace instance name, trace * system, and trace event name. If the instance name is NULL, it * refers to the top-level trace array. * * This function will look it up and return it if found, after calling * trace_array_get() to prevent the instance from going away, and * increment the event's module refcount to prevent it from being * removed. * * To release the file, call trace_put_event_file(), which will call * trace_array_put() and decrement the event's module refcount. * * Return: The trace event on success, ERR_PTR otherwise. */ struct trace_event_file *trace_get_event_file(const char *instance, const char *system, const char *event) { struct trace_array *tr = top_trace_array(); struct trace_event_file *file = NULL; int ret = -EINVAL; if (instance) { tr = trace_array_find_get(instance); if (!tr) return ERR_PTR(-ENOENT); } else { ret = trace_array_get(tr); if (ret) return ERR_PTR(ret); } mutex_lock(&event_mutex); file = find_event_file(tr, system, event); if (!file) { trace_array_put(tr); ret = -EINVAL; goto out; } /* Don't let event modules unload while in use */ ret = trace_event_try_get_ref(file->event_call); if (!ret) { trace_array_put(tr); ret = -EBUSY; goto out; } ret = 0; out: mutex_unlock(&event_mutex); if (ret) file = ERR_PTR(ret); return file; } EXPORT_SYMBOL_GPL(trace_get_event_file); /** * trace_put_event_file - Release a file from trace_get_event_file() * @file: The trace event file * * If a file was retrieved using trace_get_event_file(), this should * be called when it's no longer needed. It will cancel the previous * trace_array_get() called by that function, and decrement the * event's module refcount. */ void trace_put_event_file(struct trace_event_file *file) { mutex_lock(&event_mutex); trace_event_put_ref(file->event_call); mutex_unlock(&event_mutex); trace_array_put(file->tr); } EXPORT_SYMBOL_GPL(trace_put_event_file); #ifdef CONFIG_DYNAMIC_FTRACE /* Avoid typos */ #define ENABLE_EVENT_STR "enable_event" #define DISABLE_EVENT_STR "disable_event" struct event_probe_data { struct trace_event_file *file; unsigned long count; int ref; bool enable; }; static void update_event_probe(struct event_probe_data *data) { if (data->enable) clear_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &data->file->flags); else set_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &data->file->flags); } static void event_enable_probe(unsigned long ip, unsigned long parent_ip, struct trace_array *tr, struct ftrace_probe_ops *ops, void *data) { struct ftrace_func_mapper *mapper = data; struct event_probe_data *edata; void **pdata; pdata = ftrace_func_mapper_find_ip(mapper, ip); if (!pdata || !*pdata) return; edata = *pdata; update_event_probe(edata); } static void event_enable_count_probe(unsigned long ip, unsigned long parent_ip, struct trace_array *tr, struct ftrace_probe_ops *ops, void *data) { struct ftrace_func_mapper *mapper = data; struct event_probe_data *edata; void **pdata; pdata = ftrace_func_mapper_find_ip(mapper, ip); if (!pdata || !*pdata) return; edata = *pdata; if (!edata->count) return; /* Skip if the event is in a state we want to switch to */ if (edata->enable == !(edata->file->flags & EVENT_FILE_FL_SOFT_DISABLED)) return; if (edata->count != -1) (edata->count)--; update_event_probe(edata); } static int event_enable_print(struct seq_file *m, unsigned long ip, struct ftrace_probe_ops *ops, void *data) { struct ftrace_func_mapper *mapper = data; struct event_probe_data *edata; void **pdata; pdata = ftrace_func_mapper_find_ip(mapper, ip); if (WARN_ON_ONCE(!pdata || !*pdata)) return 0; edata = *pdata; seq_printf(m, "%ps:", (void *)ip); seq_printf(m, "%s:%s:%s", edata->enable ? ENABLE_EVENT_STR : DISABLE_EVENT_STR, edata->file->event_call->class->system, trace_event_name(edata->file->event_call)); if (edata->count == -1) seq_puts(m, ":unlimited\n"); else seq_printf(m, ":count=%ld\n", edata->count); return 0; } static int event_enable_init(struct ftrace_probe_ops *ops, struct trace_array *tr, unsigned long ip, void *init_data, void **data) { struct ftrace_func_mapper *mapper = *data; struct event_probe_data *edata = init_data; int ret; if (!mapper) { mapper = allocate_ftrace_func_mapper(); if (!mapper) return -ENODEV; *data = mapper; } ret = ftrace_func_mapper_add_ip(mapper, ip, edata); if (ret < 0) return ret; edata->ref++; return 0; } static int free_probe_data(void *data) { struct event_probe_data *edata = data; edata->ref--; if (!edata->ref) { /* Remove the SOFT_MODE flag */ __ftrace_event_enable_disable(edata->file, 0, 1); trace_event_put_ref(edata->file->event_call); kfree(edata); } return 0; } static void event_enable_free(struct ftrace_probe_ops *ops, struct trace_array *tr, unsigned long ip, void *data) { struct ftrace_func_mapper *mapper = data; struct event_probe_data *edata; if (!ip) { if (!mapper) return; free_ftrace_func_mapper(mapper, free_probe_data); return; } edata = ftrace_func_mapper_remove_ip(mapper, ip); if (WARN_ON_ONCE(!edata)) return; if (WARN_ON_ONCE(edata->ref <= 0)) return; free_probe_data(edata); } static struct ftrace_probe_ops event_enable_probe_ops = { .func = event_enable_probe, .print = event_enable_print, .init = event_enable_init, .free = event_enable_free, }; static struct ftrace_probe_ops event_enable_count_probe_ops = { .func = event_enable_count_probe, .print = event_enable_print, .init = event_enable_init, .free = event_enable_free, }; static struct ftrace_probe_ops event_disable_probe_ops = { .func = event_enable_probe, .print = event_enable_print, .init = event_enable_init, .free = event_enable_free, }; static struct ftrace_probe_ops event_disable_count_probe_ops = { .func = event_enable_count_probe, .print = event_enable_print, .init = event_enable_init, .free = event_enable_free, }; static int event_enable_func(struct trace_array *tr, struct ftrace_hash *hash, char *glob, char *cmd, char *param, int enabled) { struct trace_event_file *file; struct ftrace_probe_ops *ops; struct event_probe_data *data; const char *system; const char *event; char *number; bool enable; int ret; if (!tr) return -ENODEV; /* hash funcs only work with set_ftrace_filter */ if (!enabled || !param) return -EINVAL; system = strsep(¶m, ":"); if (!param) return -EINVAL; event = strsep(¶m, ":"); mutex_lock(&event_mutex); ret = -EINVAL; file = find_event_file(tr, system, event); if (!file) goto out; enable = strcmp(cmd, ENABLE_EVENT_STR) == 0; if (enable) ops = param ? &event_enable_count_probe_ops : &event_enable_probe_ops; else ops = param ? &event_disable_count_probe_ops : &event_disable_probe_ops; if (glob[0] == '!') { ret = unregister_ftrace_function_probe_func(glob+1, tr, ops); goto out; } ret = -ENOMEM; data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) goto out; data->enable = enable; data->count = -1; data->file = file; if (!param) goto out_reg; number = strsep(¶m, ":"); ret = -EINVAL; if (!strlen(number)) goto out_free; /* * We use the callback data field (which is a pointer) * as our counter. */ ret = kstrtoul(number, 0, &data->count); if (ret) goto out_free; out_reg: /* Don't let event modules unload while probe registered */ ret = trace_event_try_get_ref(file->event_call); if (!ret) { ret = -EBUSY; goto out_free; } ret = __ftrace_event_enable_disable(file, 1, 1); if (ret < 0) goto out_put; ret = register_ftrace_function_probe(glob, tr, ops, data); /* * The above returns on success the # of functions enabled, * but if it didn't find any functions it returns zero. * Consider no functions a failure too. */ if (!ret) { ret = -ENOENT; goto out_disable; } else if (ret < 0) goto out_disable; /* Just return zero, not the number of enabled functions */ ret = 0; out: mutex_unlock(&event_mutex); return ret; out_disable: __ftrace_event_enable_disable(file, 0, 1); out_put: trace_event_put_ref(file->event_call); out_free: kfree(data); goto out; } static struct ftrace_func_command event_enable_cmd = { .name = ENABLE_EVENT_STR, .func = event_enable_func, }; static struct ftrace_func_command event_disable_cmd = { .name = DISABLE_EVENT_STR, .func = event_enable_func, }; static __init int register_event_cmds(void) { int ret; ret = register_ftrace_command(&event_enable_cmd); if (WARN_ON(ret < 0)) return ret; ret = register_ftrace_command(&event_disable_cmd); if (WARN_ON(ret < 0)) unregister_ftrace_command(&event_enable_cmd); return ret; } #else static inline int register_event_cmds(void) { return 0; } #endif /* CONFIG_DYNAMIC_FTRACE */ /* * The top level array and trace arrays created by boot-time tracing * have already had its trace_event_file descriptors created in order * to allow for early events to be recorded. * This function is called after the tracefs has been initialized, * and we now have to create the files associated to the events. */ static void __trace_early_add_event_dirs(struct trace_array *tr) { struct trace_event_file *file; int ret; list_for_each_entry(file, &tr->events, list) { ret = event_create_dir(tr->event_dir, file); if (ret < 0) pr_warn("Could not create directory for event %s\n", trace_event_name(file->event_call)); } } /* * For early boot up, the top trace array and the trace arrays created * by boot-time tracing require to have a list of events that can be * enabled. This must be done before the filesystem is set up in order * to allow events to be traced early. */ void __trace_early_add_events(struct trace_array *tr) { struct trace_event_call *call; int ret; list_for_each_entry(call, &ftrace_events, list) { /* Early boot up should not have any modules loaded */ if (!(call->flags & TRACE_EVENT_FL_DYNAMIC) && WARN_ON_ONCE(call->module)) continue; ret = __trace_early_add_new_event(call, tr); if (ret < 0) pr_warn("Could not create early event %s\n", trace_event_name(call)); } } /* Remove the event directory structure for a trace directory. */ static void __trace_remove_event_dirs(struct trace_array *tr) { struct trace_event_file *file, *next; list_for_each_entry_safe(file, next, &tr->events, list) remove_event_file_dir(file); } static void __add_event_to_tracers(struct trace_event_call *call) { struct trace_array *tr; list_for_each_entry(tr, &ftrace_trace_arrays, list) __trace_add_new_event(call, tr); } extern struct trace_event_call *__start_ftrace_events[]; extern struct trace_event_call *__stop_ftrace_events[]; static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata; static __init int setup_trace_event(char *str) { strlcpy(bootup_event_buf, str, COMMAND_LINE_SIZE); ring_buffer_expanded = true; disable_tracing_selftest("running event tracing"); return 1; } __setup("trace_event=", setup_trace_event); /* Expects to have event_mutex held when called */ static int create_event_toplevel_files(struct dentry *parent, struct trace_array *tr) { struct dentry *d_events; struct dentry *entry; entry = trace_create_file("set_event", TRACE_MODE_WRITE, parent, tr, &ftrace_set_event_fops); if (!entry) return -ENOMEM; d_events = tracefs_create_dir("events", parent); if (!d_events) { pr_warn("Could not create tracefs 'events' directory\n"); return -ENOMEM; } entry = trace_create_file("enable", TRACE_MODE_WRITE, d_events, tr, &ftrace_tr_enable_fops); if (!entry) return -ENOMEM; /* There are not as crucial, just warn if they are not created */ trace_create_file("set_event_pid", TRACE_MODE_WRITE, parent, tr, &ftrace_set_event_pid_fops); trace_create_file("set_event_notrace_pid", TRACE_MODE_WRITE, parent, tr, &ftrace_set_event_notrace_pid_fops); /* ring buffer internal formats */ trace_create_file("header_page", TRACE_MODE_READ, d_events, ring_buffer_print_page_header, &ftrace_show_header_fops); trace_create_file("header_event", TRACE_MODE_READ, d_events, ring_buffer_print_entry_header, &ftrace_show_header_fops); tr->event_dir = d_events; return 0; } /** * event_trace_add_tracer - add a instance of a trace_array to events * @parent: The parent dentry to place the files/directories for events in * @tr: The trace array associated with these events * * When a new instance is created, it needs to set up its events * directory, as well as other files associated with events. It also * creates the event hierarchy in the @parent/events directory. * * Returns 0 on success. * * Must be called with event_mutex held. */ int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr) { int ret; lockdep_assert_held(&event_mutex); ret = create_event_toplevel_files(parent, tr); if (ret) goto out; down_write(&trace_event_sem); /* If tr already has the event list, it is initialized in early boot. */ if (unlikely(!list_empty(&tr->events))) __trace_early_add_event_dirs(tr); else __trace_add_event_dirs(tr); up_write(&trace_event_sem); out: return ret; } /* * The top trace array already had its file descriptors created. * Now the files themselves need to be created. */ static __init int early_event_add_tracer(struct dentry *parent, struct trace_array *tr) { int ret; mutex_lock(&event_mutex); ret = create_event_toplevel_files(parent, tr); if (ret) goto out_unlock; down_write(&trace_event_sem); __trace_early_add_event_dirs(tr); up_write(&trace_event_sem); out_unlock: mutex_unlock(&event_mutex); return ret; } /* Must be called with event_mutex held */ int event_trace_del_tracer(struct trace_array *tr) { lockdep_assert_held(&event_mutex); /* Disable any event triggers and associated soft-disabled events */ clear_event_triggers(tr); /* Clear the pid list */ __ftrace_clear_event_pids(tr, TRACE_PIDS | TRACE_NO_PIDS); /* Disable any running events */ __ftrace_set_clr_event_nolock(tr, NULL, NULL, NULL, 0); /* Make sure no more events are being executed */ tracepoint_synchronize_unregister(); down_write(&trace_event_sem); __trace_remove_event_dirs(tr); tracefs_remove(tr->event_dir); up_write(&trace_event_sem); tr->event_dir = NULL; return 0; } static __init int event_trace_memsetup(void) { field_cachep = KMEM_CACHE(ftrace_event_field, SLAB_PANIC); file_cachep = KMEM_CACHE(trace_event_file, SLAB_PANIC); return 0; } static __init void early_enable_events(struct trace_array *tr, bool disable_first) { char *buf = bootup_event_buf; char *token; int ret; while (true) { token = strsep(&buf, ","); if (!token) break; if (*token) { /* Restarting syscalls requires that we stop them first */ if (disable_first) ftrace_set_clr_event(tr, token, 0); ret = ftrace_set_clr_event(tr, token, 1); if (ret) pr_warn("Failed to enable trace event: %s\n", token); } /* Put back the comma to allow this to be called again */ if (buf) *(buf - 1) = ','; } } static __init int event_trace_enable(void) { struct trace_array *tr = top_trace_array(); struct trace_event_call **iter, *call; int ret; if (!tr) return -ENODEV; for_each_event(iter, __start_ftrace_events, __stop_ftrace_events) { call = *iter; ret = event_init(call); if (!ret) list_add(&call->list, &ftrace_events); } /* * We need the top trace array to have a working set of trace * points at early init, before the debug files and directories * are created. Create the file entries now, and attach them * to the actual file dentries later. */ __trace_early_add_events(tr); early_enable_events(tr, false); trace_printk_start_comm(); register_event_cmds(); register_trigger_cmds(); return 0; } /* * event_trace_enable() is called from trace_event_init() first to * initialize events and perhaps start any events that are on the * command line. Unfortunately, there are some events that will not * start this early, like the system call tracepoints that need * to set the %SYSCALL_WORK_SYSCALL_TRACEPOINT flag of pid 1. But * event_trace_enable() is called before pid 1 starts, and this flag * is never set, making the syscall tracepoint never get reached, but * the event is enabled regardless (and not doing anything). */ static __init int event_trace_enable_again(void) { struct trace_array *tr; tr = top_trace_array(); if (!tr) return -ENODEV; early_enable_events(tr, true); return 0; } early_initcall(event_trace_enable_again); /* Init fields which doesn't related to the tracefs */ static __init int event_trace_init_fields(void) { if (trace_define_generic_fields()) pr_warn("tracing: Failed to allocated generic fields"); if (trace_define_common_fields()) pr_warn("tracing: Failed to allocate common fields"); return 0; } __init int event_trace_init(void) { struct trace_array *tr; int ret; tr = top_trace_array(); if (!tr) return -ENODEV; trace_create_file("available_events", TRACE_MODE_READ, NULL, tr, &ftrace_avail_fops); ret = early_event_add_tracer(NULL, tr); if (ret) return ret; #ifdef CONFIG_MODULES ret = register_module_notifier(&trace_module_nb); if (ret) pr_warn("Failed to register trace events module notifier\n"); #endif eventdir_initialized = true; return 0; } void __init trace_event_init(void) { event_trace_memsetup(); init_ftrace_syscalls(); event_trace_enable(); event_trace_init_fields(); } #ifdef CONFIG_EVENT_TRACE_STARTUP_TEST static DEFINE_SPINLOCK(test_spinlock); static DEFINE_SPINLOCK(test_spinlock_irq); static DEFINE_MUTEX(test_mutex); static __init void test_work(struct work_struct *dummy) { spin_lock(&test_spinlock); spin_lock_irq(&test_spinlock_irq); udelay(1); spin_unlock_irq(&test_spinlock_irq); spin_unlock(&test_spinlock); mutex_lock(&test_mutex); msleep(1); mutex_unlock(&test_mutex); } static __init int event_test_thread(void *unused) { void *test_malloc; test_malloc = kmalloc(1234, GFP_KERNEL); if (!test_malloc) pr_info("failed to kmalloc\n"); schedule_on_each_cpu(test_work); kfree(test_malloc); set_current_state(TASK_INTERRUPTIBLE); while (!kthread_should_stop()) { schedule(); set_current_state(TASK_INTERRUPTIBLE); } __set_current_state(TASK_RUNNING); return 0; } /* * Do various things that may trigger events. */ static __init void event_test_stuff(void) { struct task_struct *test_thread; test_thread = kthread_run(event_test_thread, NULL, "test-events"); msleep(1); kthread_stop(test_thread); } /* * For every trace event defined, we will test each trace point separately, * and then by groups, and finally all trace points. */ static __init void event_trace_self_tests(void) { struct trace_subsystem_dir *dir; struct trace_event_file *file; struct trace_event_call *call; struct event_subsystem *system; struct trace_array *tr; int ret; tr = top_trace_array(); if (!tr) return; pr_info("Running tests on trace events:\n"); list_for_each_entry(file, &tr->events, list) { call = file->event_call; /* Only test those that have a probe */ if (!call->class || !call->class->probe) continue; /* * Testing syscall events here is pretty useless, but * we still do it if configured. But this is time consuming. * What we really need is a user thread to perform the * syscalls as we test. */ #ifndef CONFIG_EVENT_TRACE_TEST_SYSCALLS if (call->class->system && strcmp(call->class->system, "syscalls") == 0) continue; #endif pr_info("Testing event %s: ", trace_event_name(call)); /* * If an event is already enabled, someone is using * it and the self test should not be on. */ if (file->flags & EVENT_FILE_FL_ENABLED) { pr_warn("Enabled event during self test!\n"); WARN_ON_ONCE(1); continue; } ftrace_event_enable_disable(file, 1); event_test_stuff(); ftrace_event_enable_disable(file, 0); pr_cont("OK\n"); } /* Now test at the sub system level */ pr_info("Running tests on trace event systems:\n"); list_for_each_entry(dir, &tr->systems, list) { system = dir->subsystem; /* the ftrace system is special, skip it */ if (strcmp(system->name, "ftrace") == 0) continue; pr_info("Testing event system %s: ", system->name); ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 1); if (WARN_ON_ONCE(ret)) { pr_warn("error enabling system %s\n", system->name); continue; } event_test_stuff(); ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 0); if (WARN_ON_ONCE(ret)) { pr_warn("error disabling system %s\n", system->name); continue; } pr_cont("OK\n"); } /* Test with all events enabled */ pr_info("Running tests on all trace events:\n"); pr_info("Testing all events: "); ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 1); if (WARN_ON_ONCE(ret)) { pr_warn("error enabling all events\n"); return; } event_test_stuff(); /* reset sysname */ ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 0); if (WARN_ON_ONCE(ret)) { pr_warn("error disabling all events\n"); return; } pr_cont("OK\n"); } #ifdef CONFIG_FUNCTION_TRACER static DEFINE_PER_CPU(atomic_t, ftrace_test_event_disable); static struct trace_event_file event_trace_file __initdata; static void __init function_test_events_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *regs) { struct trace_buffer *buffer; struct ring_buffer_event *event; struct ftrace_entry *entry; unsigned int trace_ctx; long disabled; int cpu; trace_ctx = tracing_gen_ctx(); preempt_disable_notrace(); cpu = raw_smp_processor_id(); disabled = atomic_inc_return(&per_cpu(ftrace_test_event_disable, cpu)); if (disabled != 1) goto out; event = trace_event_buffer_lock_reserve(&buffer, &event_trace_file, TRACE_FN, sizeof(*entry), trace_ctx); if (!event) goto out; entry = ring_buffer_event_data(event); entry->ip = ip; entry->parent_ip = parent_ip; event_trigger_unlock_commit(&event_trace_file, buffer, event, entry, trace_ctx); out: atomic_dec(&per_cpu(ftrace_test_event_disable, cpu)); preempt_enable_notrace(); } static struct ftrace_ops trace_ops __initdata = { .func = function_test_events_call, }; static __init void event_trace_self_test_with_function(void) { int ret; event_trace_file.tr = top_trace_array(); if (WARN_ON(!event_trace_file.tr)) return; ret = register_ftrace_function(&trace_ops); if (WARN_ON(ret < 0)) { pr_info("Failed to enable function tracer for event tests\n"); return; } pr_info("Running tests again, along with the function tracer\n"); event_trace_self_tests(); unregister_ftrace_function(&trace_ops); } #else static __init void event_trace_self_test_with_function(void) { } #endif static __init int event_trace_self_tests_init(void) { if (!tracing_selftest_disabled) { event_trace_self_tests(); event_trace_self_test_with_function(); } return 0; } late_initcall(event_trace_self_tests_init); #endif |
| 272 272 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_GRE_H #define __LINUX_GRE_H #include <linux/skbuff.h> #include <net/ip_tunnels.h> struct gre_base_hdr { __be16 flags; __be16 protocol; } __packed; struct gre_full_hdr { struct gre_base_hdr fixed_header; __be16 csum; __be16 reserved1; __be32 key; __be32 seq; } __packed; #define GRE_HEADER_SECTION 4 #define GREPROTO_CISCO 0 #define GREPROTO_PPTP 1 #define GREPROTO_MAX 2 #define GRE_IP_PROTO_MAX 2 struct gre_protocol { int (*handler)(struct sk_buff *skb); void (*err_handler)(struct sk_buff *skb, u32 info); }; int gre_add_protocol(const struct gre_protocol *proto, u8 version); int gre_del_protocol(const struct gre_protocol *proto, u8 version); struct net_device *gretap_fb_dev_create(struct net *net, const char *name, u8 name_assign_type); int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, bool *csum_err, __be16 proto, int nhs); static inline bool netif_is_gretap(const struct net_device *dev) { return dev->rtnl_link_ops && !strcmp(dev->rtnl_link_ops->kind, "gretap"); } static inline bool netif_is_ip6gretap(const struct net_device *dev) { return dev->rtnl_link_ops && !strcmp(dev->rtnl_link_ops->kind, "ip6gretap"); } static inline int gre_calc_hlen(__be16 o_flags) { int addend = 4; if (o_flags & TUNNEL_CSUM) addend += 4; if (o_flags & TUNNEL_KEY) addend += 4; if (o_flags & TUNNEL_SEQ) addend += 4; return addend; } static inline __be16 gre_flags_to_tnl_flags(__be16 flags) { __be16 tflags = 0; if (flags & GRE_CSUM) tflags |= TUNNEL_CSUM; if (flags & GRE_ROUTING) tflags |= TUNNEL_ROUTING; if (flags & GRE_KEY) tflags |= TUNNEL_KEY; if (flags & GRE_SEQ) tflags |= TUNNEL_SEQ; if (flags & GRE_STRICT) tflags |= TUNNEL_STRICT; if (flags & GRE_REC) tflags |= TUNNEL_REC; if (flags & GRE_VERSION) tflags |= TUNNEL_VERSION; return tflags; } static inline __be16 gre_tnl_flags_to_gre_flags(__be16 tflags) { __be16 flags = 0; if (tflags & TUNNEL_CSUM) flags |= GRE_CSUM; if (tflags & TUNNEL_ROUTING) flags |= GRE_ROUTING; if (tflags & TUNNEL_KEY) flags |= GRE_KEY; if (tflags & TUNNEL_SEQ) flags |= GRE_SEQ; if (tflags & TUNNEL_STRICT) flags |= GRE_STRICT; if (tflags & TUNNEL_REC) flags |= GRE_REC; if (tflags & TUNNEL_VERSION) flags |= GRE_VERSION; return flags; } static inline void gre_build_header(struct sk_buff *skb, int hdr_len, __be16 flags, __be16 proto, __be32 key, __be32 seq) { struct gre_base_hdr *greh; skb_push(skb, hdr_len); skb_set_inner_protocol(skb, proto); skb_reset_transport_header(skb); greh = (struct gre_base_hdr *)skb->data; greh->flags = gre_tnl_flags_to_gre_flags(flags); greh->protocol = proto; if (flags & (TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_SEQ)) { __be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4); if (flags & TUNNEL_SEQ) { *ptr = seq; ptr--; } if (flags & TUNNEL_KEY) { *ptr = key; ptr--; } if (flags & TUNNEL_CSUM && !(skb_shinfo(skb)->gso_type & (SKB_GSO_GRE | SKB_GSO_GRE_CSUM))) { *ptr = 0; if (skb->ip_summed == CHECKSUM_PARTIAL) { *(__sum16 *)ptr = csum_fold(lco_csum(skb)); } else { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = sizeof(*greh); } } } } #endif |
| 1675 1581 1562 839 344 1000 146 28 1777 1775 1777 636 636 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/interval_tree.c - interval tree for mapping->i_mmap * * Copyright (C) 2012, Michel Lespinasse <walken@google.com> */ #include <linux/mm.h> #include <linux/fs.h> #include <linux/rmap.h> #include <linux/interval_tree_generic.h> static inline unsigned long vma_start_pgoff(struct vm_area_struct *v) { return v->vm_pgoff; } static inline unsigned long vma_last_pgoff(struct vm_area_struct *v) { return v->vm_pgoff + vma_pages(v) - 1; } INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.rb, unsigned long, shared.rb_subtree_last, vma_start_pgoff, vma_last_pgoff, /* empty */, vma_interval_tree) /* Insert node immediately after prev in the interval tree */ void vma_interval_tree_insert_after(struct vm_area_struct *node, struct vm_area_struct *prev, struct rb_root_cached *root) { struct rb_node **link; struct vm_area_struct *parent; unsigned long last = vma_last_pgoff(node); VM_BUG_ON_VMA(vma_start_pgoff(node) != vma_start_pgoff(prev), node); if (!prev->shared.rb.rb_right) { parent = prev; link = &prev->shared.rb.rb_right; } else { parent = rb_entry(prev->shared.rb.rb_right, struct vm_area_struct, shared.rb); if (parent->shared.rb_subtree_last < last) parent->shared.rb_subtree_last = last; while (parent->shared.rb.rb_left) { parent = rb_entry(parent->shared.rb.rb_left, struct vm_area_struct, shared.rb); if (parent->shared.rb_subtree_last < last) parent->shared.rb_subtree_last = last; } link = &parent->shared.rb.rb_left; } node->shared.rb_subtree_last = last; rb_link_node(&node->shared.rb, &parent->shared.rb, link); rb_insert_augmented(&node->shared.rb, &root->rb_root, &vma_interval_tree_augment); } static inline unsigned long avc_start_pgoff(struct anon_vma_chain *avc) { return vma_start_pgoff(avc->vma); } static inline unsigned long avc_last_pgoff(struct anon_vma_chain *avc) { return vma_last_pgoff(avc->vma); } INTERVAL_TREE_DEFINE(struct anon_vma_chain, rb, unsigned long, rb_subtree_last, avc_start_pgoff, avc_last_pgoff, static inline, __anon_vma_interval_tree) void anon_vma_interval_tree_insert(struct anon_vma_chain *node, struct rb_root_cached *root) { #ifdef CONFIG_DEBUG_VM_RB node->cached_vma_start = avc_start_pgoff(node); node->cached_vma_last = avc_last_pgoff(node); #endif __anon_vma_interval_tree_insert(node, root); } void anon_vma_interval_tree_remove(struct anon_vma_chain *node, struct rb_root_cached *root) { __anon_vma_interval_tree_remove(node, root); } struct anon_vma_chain * anon_vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long first, unsigned long last) { return __anon_vma_interval_tree_iter_first(root, first, last); } struct anon_vma_chain * anon_vma_interval_tree_iter_next(struct anon_vma_chain *node, unsigned long first, unsigned long last) { return __anon_vma_interval_tree_iter_next(node, first, last); } #ifdef CONFIG_DEBUG_VM_RB void anon_vma_interval_tree_verify(struct anon_vma_chain *node) { WARN_ON_ONCE(node->cached_vma_start != avc_start_pgoff(node)); WARN_ON_ONCE(node->cached_vma_last != avc_last_pgoff(node)); } #endif |
| 4465 1092 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PKRU_H #define _ASM_X86_PKRU_H #include <asm/cpufeature.h> #define PKRU_AD_BIT 0x1u #define PKRU_WD_BIT 0x2u #define PKRU_BITS_PER_PKEY 2 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS extern u32 init_pkru_value; #define pkru_get_init_value() READ_ONCE(init_pkru_value) #else #define init_pkru_value 0 #define pkru_get_init_value() 0 #endif static inline bool __pkru_allows_read(u32 pkru, u16 pkey) { int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY; return !(pkru & (PKRU_AD_BIT << pkru_pkey_bits)); } static inline bool __pkru_allows_write(u32 pkru, u16 pkey) { int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY; /* * Access-disable disables writes too so we need to check * both bits here. */ return !(pkru & ((PKRU_AD_BIT|PKRU_WD_BIT) << pkru_pkey_bits)); } static inline u32 read_pkru(void) { if (cpu_feature_enabled(X86_FEATURE_OSPKE)) return rdpkru(); return 0; } static inline void write_pkru(u32 pkru) { if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return; /* * WRPKRU is relatively expensive compared to RDPKRU. * Avoid WRPKRU when it would not change the value. */ if (pkru != rdpkru()) wrpkru(pkru); } static inline void pkru_write_default(void) { if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return; wrpkru(pkru_get_init_value()); } #endif |
| 3325 3323 999 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 | // SPDX-License-Identifier: GPL-2.0-or-later /* * "TEE" target extension for Xtables * Copyright © Sebastian Claßen, 2007 * Jan Engelhardt, 2007-2010 * * based on ipt_ROUTE.c from Cédric de Launois * <delaunois@info.ucl.be> */ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/route.h> #include <linux/netfilter/x_tables.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/route.h> #include <net/netfilter/ipv4/nf_dup_ipv4.h> #include <net/netfilter/ipv6/nf_dup_ipv6.h> #include <linux/netfilter/xt_TEE.h> struct xt_tee_priv { struct list_head list; struct xt_tee_tginfo *tginfo; int oif; }; static unsigned int tee_net_id __read_mostly; static const union nf_inet_addr tee_zero_address; struct tee_net { struct list_head priv_list; /* lock protects the priv_list */ struct mutex lock; }; static unsigned int tee_tg4(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tee_tginfo *info = par->targinfo; int oif = info->priv ? info->priv->oif : 0; nf_dup_ipv4(xt_net(par), skb, xt_hooknum(par), &info->gw.in, oif); return XT_CONTINUE; } #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) static unsigned int tee_tg6(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tee_tginfo *info = par->targinfo; int oif = info->priv ? info->priv->oif : 0; nf_dup_ipv6(xt_net(par), skb, xt_hooknum(par), &info->gw.in6, oif); return XT_CONTINUE; } #endif static int tee_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct tee_net *tn = net_generic(net, tee_net_id); struct xt_tee_priv *priv; mutex_lock(&tn->lock); list_for_each_entry(priv, &tn->priv_list, list) { switch (event) { case NETDEV_REGISTER: if (!strcmp(dev->name, priv->tginfo->oif)) priv->oif = dev->ifindex; break; case NETDEV_UNREGISTER: if (dev->ifindex == priv->oif) priv->oif = -1; break; case NETDEV_CHANGENAME: if (!strcmp(dev->name, priv->tginfo->oif)) priv->oif = dev->ifindex; else if (dev->ifindex == priv->oif) priv->oif = -1; break; } } mutex_unlock(&tn->lock); return NOTIFY_DONE; } static int tee_tg_check(const struct xt_tgchk_param *par) { struct tee_net *tn = net_generic(par->net, tee_net_id); struct xt_tee_tginfo *info = par->targinfo; struct xt_tee_priv *priv; /* 0.0.0.0 and :: not allowed */ if (memcmp(&info->gw, &tee_zero_address, sizeof(tee_zero_address)) == 0) return -EINVAL; if (info->oif[0]) { struct net_device *dev; if (info->oif[sizeof(info->oif)-1] != '\0') return -EINVAL; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (priv == NULL) return -ENOMEM; priv->tginfo = info; priv->oif = -1; info->priv = priv; dev = dev_get_by_name(par->net, info->oif); if (dev) { priv->oif = dev->ifindex; dev_put(dev); } mutex_lock(&tn->lock); list_add(&priv->list, &tn->priv_list); mutex_unlock(&tn->lock); } else info->priv = NULL; static_key_slow_inc(&xt_tee_enabled); return 0; } static void tee_tg_destroy(const struct xt_tgdtor_param *par) { struct tee_net *tn = net_generic(par->net, tee_net_id); struct xt_tee_tginfo *info = par->targinfo; if (info->priv) { mutex_lock(&tn->lock); list_del(&info->priv->list); mutex_unlock(&tn->lock); kfree(info->priv); } static_key_slow_dec(&xt_tee_enabled); } static struct xt_target tee_tg_reg[] __read_mostly = { { .name = "TEE", .revision = 1, .family = NFPROTO_IPV4, .target = tee_tg4, .targetsize = sizeof(struct xt_tee_tginfo), .usersize = offsetof(struct xt_tee_tginfo, priv), .checkentry = tee_tg_check, .destroy = tee_tg_destroy, .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "TEE", .revision = 1, .family = NFPROTO_IPV6, .target = tee_tg6, .targetsize = sizeof(struct xt_tee_tginfo), .usersize = offsetof(struct xt_tee_tginfo, priv), .checkentry = tee_tg_check, .destroy = tee_tg_destroy, .me = THIS_MODULE, }, #endif }; static int __net_init tee_net_init(struct net *net) { struct tee_net *tn = net_generic(net, tee_net_id); INIT_LIST_HEAD(&tn->priv_list); mutex_init(&tn->lock); return 0; } static struct pernet_operations tee_net_ops = { .init = tee_net_init, .id = &tee_net_id, .size = sizeof(struct tee_net), }; static struct notifier_block tee_netdev_notifier = { .notifier_call = tee_netdev_event, }; static int __init tee_tg_init(void) { int ret; ret = register_pernet_subsys(&tee_net_ops); if (ret < 0) return ret; ret = xt_register_targets(tee_tg_reg, ARRAY_SIZE(tee_tg_reg)); if (ret < 0) goto cleanup_subsys; ret = register_netdevice_notifier(&tee_netdev_notifier); if (ret < 0) goto unregister_targets; return 0; unregister_targets: xt_unregister_targets(tee_tg_reg, ARRAY_SIZE(tee_tg_reg)); cleanup_subsys: unregister_pernet_subsys(&tee_net_ops); return ret; } static void __exit tee_tg_exit(void) { unregister_netdevice_notifier(&tee_netdev_notifier); xt_unregister_targets(tee_tg_reg, ARRAY_SIZE(tee_tg_reg)); unregister_pernet_subsys(&tee_net_ops); } module_init(tee_tg_init); module_exit(tee_tg_exit); MODULE_AUTHOR("Sebastian Claßen <sebastian.classen@freenet.ag>"); MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>"); MODULE_DESCRIPTION("Xtables: Reroute packet copy"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ipt_TEE"); MODULE_ALIAS("ip6t_TEE"); |
| 999 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 | // SPDX-License-Identifier: GPL-2.0-only /* * Connection tracking protocol helper module for SCTP. * * Copyright (c) 2004 Kiran Kumar Immidi <immidi_kiran@yahoo.com> * Copyright (c) 2004-2012 Patrick McHardy <kaber@trash.net> * * SCTP is defined in RFC 2960. References to various sections in this code * are to this RFC. */ #include <linux/types.h> #include <linux/timer.h> #include <linux/netfilter.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/sctp.h> #include <linux/string.h> #include <linux/seq_file.h> #include <linux/spinlock.h> #include <linux/interrupt.h> #include <net/sctp/checksum.h> #include <net/netfilter/nf_log.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_timeout.h> static const char *const sctp_conntrack_names[] = { [SCTP_CONNTRACK_NONE] = "NONE", [SCTP_CONNTRACK_CLOSED] = "CLOSED", [SCTP_CONNTRACK_COOKIE_WAIT] = "COOKIE_WAIT", [SCTP_CONNTRACK_COOKIE_ECHOED] = "COOKIE_ECHOED", [SCTP_CONNTRACK_ESTABLISHED] = "ESTABLISHED", [SCTP_CONNTRACK_SHUTDOWN_SENT] = "SHUTDOWN_SENT", [SCTP_CONNTRACK_SHUTDOWN_RECD] = "SHUTDOWN_RECD", [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = "SHUTDOWN_ACK_SENT", [SCTP_CONNTRACK_HEARTBEAT_SENT] = "HEARTBEAT_SENT", }; #define SECS * HZ #define MINS * 60 SECS #define HOURS * 60 MINS #define DAYS * 24 HOURS static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { [SCTP_CONNTRACK_CLOSED] = 10 SECS, [SCTP_CONNTRACK_COOKIE_WAIT] = 3 SECS, [SCTP_CONNTRACK_COOKIE_ECHOED] = 3 SECS, [SCTP_CONNTRACK_ESTABLISHED] = 210 SECS, [SCTP_CONNTRACK_SHUTDOWN_SENT] = 3 SECS, [SCTP_CONNTRACK_SHUTDOWN_RECD] = 3 SECS, [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS, [SCTP_CONNTRACK_HEARTBEAT_SENT] = 30 SECS, }; #define SCTP_FLAG_HEARTBEAT_VTAG_FAILED 1 #define sNO SCTP_CONNTRACK_NONE #define sCL SCTP_CONNTRACK_CLOSED #define sCW SCTP_CONNTRACK_COOKIE_WAIT #define sCE SCTP_CONNTRACK_COOKIE_ECHOED #define sES SCTP_CONNTRACK_ESTABLISHED #define sSS SCTP_CONNTRACK_SHUTDOWN_SENT #define sSR SCTP_CONNTRACK_SHUTDOWN_RECD #define sSA SCTP_CONNTRACK_SHUTDOWN_ACK_SENT #define sHS SCTP_CONNTRACK_HEARTBEAT_SENT #define sIV SCTP_CONNTRACK_MAX /* These are the descriptions of the states: NOTE: These state names are tantalizingly similar to the states of an SCTP endpoint. But the interpretation of the states is a little different, considering that these are the states of the connection and not of an end point. Please note the subtleties. -Kiran NONE - Nothing so far. COOKIE WAIT - We have seen an INIT chunk in the original direction, or also an INIT_ACK chunk in the reply direction. COOKIE ECHOED - We have seen a COOKIE_ECHO chunk in the original direction. ESTABLISHED - We have seen a COOKIE_ACK in the reply direction. SHUTDOWN_SENT - We have seen a SHUTDOWN chunk in the original direction. SHUTDOWN_RECD - We have seen a SHUTDOWN chunk in the reply directoin. SHUTDOWN_ACK_SENT - We have seen a SHUTDOWN_ACK chunk in the direction opposite to that of the SHUTDOWN chunk. CLOSED - We have seen a SHUTDOWN_COMPLETE chunk in the direction of the SHUTDOWN chunk. Connection is closed. HEARTBEAT_SENT - We have seen a HEARTBEAT in a new flow. */ /* TODO - I have assumed that the first INIT is in the original direction. This messes things when an INIT comes in the reply direction in CLOSED state. - Check the error type in the reply dir before transitioning from cookie echoed to closed. - Sec 5.2.4 of RFC 2960 - Full Multi Homing support. */ /* SCTP conntrack state transitions */ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { { /* ORIGINAL */ /* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */ /* init */ {sCL, sCL, sCW, sCE, sES, sCL, sCL, sSA, sCW}, /* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL}, /* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, /* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL}, /* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA}, /* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't have Stale cookie*/ /* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL},/* 5.2.4 - Big TODO */ /* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */ /* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL}, /* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, /* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, }, { /* REPLY */ /* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */ /* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* INIT in sCL Big TODO */ /* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV}, /* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV}, /* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV}, /* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV}, /* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV}, /* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */ /* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV}, /* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV}, /* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, /* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sES}, } }; #ifdef CONFIG_NF_CONNTRACK_PROCFS /* Print out the private part of the conntrack. */ static void sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct) { seq_printf(s, "%s ", sctp_conntrack_names[ct->proto.sctp.state]); } #endif #define for_each_sctp_chunk(skb, sch, _sch, offset, dataoff, count) \ for ((offset) = (dataoff) + sizeof(struct sctphdr), (count) = 0; \ (offset) < (skb)->len && \ ((sch) = skb_header_pointer((skb), (offset), sizeof(_sch), &(_sch))); \ (offset) += (ntohs((sch)->length) + 3) & ~3, (count)++) /* Some validity checks to make sure the chunks are fine */ static int do_basic_checks(struct nf_conn *ct, const struct sk_buff *skb, unsigned int dataoff, unsigned long *map) { u_int32_t offset, count; struct sctp_chunkhdr _sch, *sch; int flag; flag = 0; for_each_sctp_chunk (skb, sch, _sch, offset, dataoff, count) { pr_debug("Chunk Num: %d Type: %d\n", count, sch->type); if (sch->type == SCTP_CID_INIT || sch->type == SCTP_CID_INIT_ACK || sch->type == SCTP_CID_SHUTDOWN_COMPLETE) flag = 1; /* * Cookie Ack/Echo chunks not the first OR * Init / Init Ack / Shutdown compl chunks not the only chunks * OR zero-length. */ if (((sch->type == SCTP_CID_COOKIE_ACK || sch->type == SCTP_CID_COOKIE_ECHO || flag) && count != 0) || !sch->length) { pr_debug("Basic checks failed\n"); return 1; } if (map) set_bit(sch->type, map); } pr_debug("Basic checks passed\n"); return count == 0; } static int sctp_new_state(enum ip_conntrack_dir dir, enum sctp_conntrack cur_state, int chunk_type) { int i; pr_debug("Chunk type: %d\n", chunk_type); switch (chunk_type) { case SCTP_CID_INIT: pr_debug("SCTP_CID_INIT\n"); i = 0; break; case SCTP_CID_INIT_ACK: pr_debug("SCTP_CID_INIT_ACK\n"); i = 1; break; case SCTP_CID_ABORT: pr_debug("SCTP_CID_ABORT\n"); i = 2; break; case SCTP_CID_SHUTDOWN: pr_debug("SCTP_CID_SHUTDOWN\n"); i = 3; break; case SCTP_CID_SHUTDOWN_ACK: pr_debug("SCTP_CID_SHUTDOWN_ACK\n"); i = 4; break; case SCTP_CID_ERROR: pr_debug("SCTP_CID_ERROR\n"); i = 5; break; case SCTP_CID_COOKIE_ECHO: pr_debug("SCTP_CID_COOKIE_ECHO\n"); i = 6; break; case SCTP_CID_COOKIE_ACK: pr_debug("SCTP_CID_COOKIE_ACK\n"); i = 7; break; case SCTP_CID_SHUTDOWN_COMPLETE: pr_debug("SCTP_CID_SHUTDOWN_COMPLETE\n"); i = 8; break; case SCTP_CID_HEARTBEAT: pr_debug("SCTP_CID_HEARTBEAT"); i = 9; break; case SCTP_CID_HEARTBEAT_ACK: pr_debug("SCTP_CID_HEARTBEAT_ACK"); i = 10; break; default: /* Other chunks like DATA or SACK do not change the state */ pr_debug("Unknown chunk type, Will stay in %s\n", sctp_conntrack_names[cur_state]); return cur_state; } pr_debug("dir: %d cur_state: %s chunk_type: %d new_state: %s\n", dir, sctp_conntrack_names[cur_state], chunk_type, sctp_conntrack_names[sctp_conntracks[dir][i][cur_state]]); return sctp_conntracks[dir][i][cur_state]; } /* Don't need lock here: this conntrack not in circulation yet */ static noinline bool sctp_new(struct nf_conn *ct, const struct sk_buff *skb, const struct sctphdr *sh, unsigned int dataoff) { enum sctp_conntrack new_state; const struct sctp_chunkhdr *sch; struct sctp_chunkhdr _sch; u32 offset, count; memset(&ct->proto.sctp, 0, sizeof(ct->proto.sctp)); new_state = SCTP_CONNTRACK_MAX; for_each_sctp_chunk(skb, sch, _sch, offset, dataoff, count) { new_state = sctp_new_state(IP_CT_DIR_ORIGINAL, SCTP_CONNTRACK_NONE, sch->type); /* Invalid: delete conntrack */ if (new_state == SCTP_CONNTRACK_NONE || new_state == SCTP_CONNTRACK_MAX) { pr_debug("nf_conntrack_sctp: invalid new deleting.\n"); return false; } /* Copy the vtag into the state info */ if (sch->type == SCTP_CID_INIT) { struct sctp_inithdr _inithdr, *ih; /* Sec 8.5.1 (A) */ if (sh->vtag) return false; ih = skb_header_pointer(skb, offset + sizeof(_sch), sizeof(_inithdr), &_inithdr); if (!ih) return false; pr_debug("Setting vtag %x for new conn\n", ih->init_tag); ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = ih->init_tag; } else if (sch->type == SCTP_CID_HEARTBEAT) { pr_debug("Setting vtag %x for secondary conntrack\n", sh->vtag); ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = sh->vtag; } else if (sch->type == SCTP_CID_SHUTDOWN_ACK) { /* If it is a shutdown ack OOTB packet, we expect a return shutdown complete, otherwise an ABORT Sec 8.4 (5) and (8) */ pr_debug("Setting vtag %x for new conn OOTB\n", sh->vtag); ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = sh->vtag; } ct->proto.sctp.state = SCTP_CONNTRACK_NONE; } return true; } static bool sctp_error(struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state) { const struct sctphdr *sh; const char *logmsg; if (skb->len < dataoff + sizeof(struct sctphdr)) { logmsg = "nf_ct_sctp: short packet "; goto out_invalid; } if (state->hook == NF_INET_PRE_ROUTING && state->net->ct.sysctl_checksum && skb->ip_summed == CHECKSUM_NONE) { if (skb_ensure_writable(skb, dataoff + sizeof(*sh))) { logmsg = "nf_ct_sctp: failed to read header "; goto out_invalid; } sh = (const struct sctphdr *)(skb->data + dataoff); if (sh->checksum != sctp_compute_cksum(skb, dataoff)) { logmsg = "nf_ct_sctp: bad CRC "; goto out_invalid; } skb->ip_summed = CHECKSUM_UNNECESSARY; } return false; out_invalid: nf_l4proto_log_invalid(skb, state, IPPROTO_SCTP, "%s", logmsg); return true; } /* Returns verdict for packet, or -NF_ACCEPT for invalid. */ int nf_conntrack_sctp_packet(struct nf_conn *ct, struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state) { enum sctp_conntrack new_state, old_state; enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); const struct sctphdr *sh; struct sctphdr _sctph; const struct sctp_chunkhdr *sch; struct sctp_chunkhdr _sch; u_int32_t offset, count; unsigned int *timeouts; unsigned long map[256 / sizeof(unsigned long)] = { 0 }; bool ignore = false; if (sctp_error(skb, dataoff, state)) return -NF_ACCEPT; sh = skb_header_pointer(skb, dataoff, sizeof(_sctph), &_sctph); if (sh == NULL) goto out; if (do_basic_checks(ct, skb, dataoff, map) != 0) goto out; if (!nf_ct_is_confirmed(ct)) { /* If an OOTB packet has any of these chunks discard (Sec 8.4) */ if (test_bit(SCTP_CID_ABORT, map) || test_bit(SCTP_CID_SHUTDOWN_COMPLETE, map) || test_bit(SCTP_CID_COOKIE_ACK, map)) return -NF_ACCEPT; if (!sctp_new(ct, skb, sh, dataoff)) return -NF_ACCEPT; } /* Check the verification tag (Sec 8.5) */ if (!test_bit(SCTP_CID_INIT, map) && !test_bit(SCTP_CID_SHUTDOWN_COMPLETE, map) && !test_bit(SCTP_CID_COOKIE_ECHO, map) && !test_bit(SCTP_CID_ABORT, map) && !test_bit(SCTP_CID_SHUTDOWN_ACK, map) && !test_bit(SCTP_CID_HEARTBEAT, map) && !test_bit(SCTP_CID_HEARTBEAT_ACK, map) && sh->vtag != ct->proto.sctp.vtag[dir]) { pr_debug("Verification tag check failed\n"); goto out; } old_state = new_state = SCTP_CONNTRACK_NONE; spin_lock_bh(&ct->lock); for_each_sctp_chunk (skb, sch, _sch, offset, dataoff, count) { /* Special cases of Verification tag check (Sec 8.5.1) */ if (sch->type == SCTP_CID_INIT) { /* (A) vtag MUST be zero */ if (sh->vtag != 0) goto out_unlock; } else if (sch->type == SCTP_CID_ABORT) { /* (B) vtag MUST match own vtag if T flag is unset OR * MUST match peer's vtag if T flag is set */ if ((!(sch->flags & SCTP_CHUNK_FLAG_T) && sh->vtag != ct->proto.sctp.vtag[dir]) || ((sch->flags & SCTP_CHUNK_FLAG_T) && sh->vtag != ct->proto.sctp.vtag[!dir])) goto out_unlock; } else if (sch->type == SCTP_CID_SHUTDOWN_COMPLETE) { /* (C) vtag MUST match own vtag if T flag is unset OR * MUST match peer's vtag if T flag is set */ if ((!(sch->flags & SCTP_CHUNK_FLAG_T) && sh->vtag != ct->proto.sctp.vtag[dir]) || ((sch->flags & SCTP_CHUNK_FLAG_T) && sh->vtag != ct->proto.sctp.vtag[!dir])) goto out_unlock; } else if (sch->type == SCTP_CID_COOKIE_ECHO) { /* (D) vtag must be same as init_vtag as found in INIT_ACK */ if (sh->vtag != ct->proto.sctp.vtag[dir]) goto out_unlock; } else if (sch->type == SCTP_CID_HEARTBEAT) { if (ct->proto.sctp.vtag[dir] == 0) { pr_debug("Setting %d vtag %x for dir %d\n", sch->type, sh->vtag, dir); ct->proto.sctp.vtag[dir] = sh->vtag; } else if (sh->vtag != ct->proto.sctp.vtag[dir]) { if (test_bit(SCTP_CID_DATA, map) || ignore) goto out_unlock; ct->proto.sctp.flags |= SCTP_FLAG_HEARTBEAT_VTAG_FAILED; ct->proto.sctp.last_dir = dir; ignore = true; continue; } else if (ct->proto.sctp.flags & SCTP_FLAG_HEARTBEAT_VTAG_FAILED) { ct->proto.sctp.flags &= ~SCTP_FLAG_HEARTBEAT_VTAG_FAILED; } } else if (sch->type == SCTP_CID_HEARTBEAT_ACK) { if (ct->proto.sctp.vtag[dir] == 0) { pr_debug("Setting vtag %x for dir %d\n", sh->vtag, dir); ct->proto.sctp.vtag[dir] = sh->vtag; } else if (sh->vtag != ct->proto.sctp.vtag[dir]) { if (test_bit(SCTP_CID_DATA, map) || ignore) goto out_unlock; if ((ct->proto.sctp.flags & SCTP_FLAG_HEARTBEAT_VTAG_FAILED) == 0 || ct->proto.sctp.last_dir == dir) goto out_unlock; ct->proto.sctp.flags &= ~SCTP_FLAG_HEARTBEAT_VTAG_FAILED; ct->proto.sctp.vtag[dir] = sh->vtag; ct->proto.sctp.vtag[!dir] = 0; } else if (ct->proto.sctp.flags & SCTP_FLAG_HEARTBEAT_VTAG_FAILED) { ct->proto.sctp.flags &= ~SCTP_FLAG_HEARTBEAT_VTAG_FAILED; } } old_state = ct->proto.sctp.state; new_state = sctp_new_state(dir, old_state, sch->type); /* Invalid */ if (new_state == SCTP_CONNTRACK_MAX) { pr_debug("nf_conntrack_sctp: Invalid dir=%i ctype=%u " "conntrack=%u\n", dir, sch->type, old_state); goto out_unlock; } /* If it is an INIT or an INIT ACK note down the vtag */ if (sch->type == SCTP_CID_INIT || sch->type == SCTP_CID_INIT_ACK) { struct sctp_inithdr _inithdr, *ih; ih = skb_header_pointer(skb, offset + sizeof(_sch), sizeof(_inithdr), &_inithdr); if (ih == NULL) goto out_unlock; pr_debug("Setting vtag %x for dir %d\n", ih->init_tag, !dir); ct->proto.sctp.vtag[!dir] = ih->init_tag; /* don't renew timeout on init retransmit so * port reuse by client or NAT middlebox cannot * keep entry alive indefinitely (incl. nat info). */ if (new_state == SCTP_CONNTRACK_CLOSED && old_state == SCTP_CONNTRACK_CLOSED && nf_ct_is_confirmed(ct)) ignore = true; } ct->proto.sctp.state = new_state; if (old_state != new_state) { nf_conntrack_event_cache(IPCT_PROTOINFO, ct); if (new_state == SCTP_CONNTRACK_ESTABLISHED && !test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); } } spin_unlock_bh(&ct->lock); /* allow but do not refresh timeout */ if (ignore) return NF_ACCEPT; timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) timeouts = nf_sctp_pernet(nf_ct_net(ct))->timeouts; nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); return NF_ACCEPT; out_unlock: spin_unlock_bh(&ct->lock); out: return -NF_ACCEPT; } static bool sctp_can_early_drop(const struct nf_conn *ct) { switch (ct->proto.sctp.state) { case SCTP_CONNTRACK_SHUTDOWN_SENT: case SCTP_CONNTRACK_SHUTDOWN_RECD: case SCTP_CONNTRACK_SHUTDOWN_ACK_SENT: return true; default: break; } return false; } #if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> static int sctp_to_nlattr(struct sk_buff *skb, struct nlattr *nla, struct nf_conn *ct, bool destroy) { struct nlattr *nest_parms; spin_lock_bh(&ct->lock); nest_parms = nla_nest_start(skb, CTA_PROTOINFO_SCTP); if (!nest_parms) goto nla_put_failure; if (nla_put_u8(skb, CTA_PROTOINFO_SCTP_STATE, ct->proto.sctp.state)) goto nla_put_failure; if (destroy) goto skip_state; if (nla_put_be32(skb, CTA_PROTOINFO_SCTP_VTAG_ORIGINAL, ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL]) || nla_put_be32(skb, CTA_PROTOINFO_SCTP_VTAG_REPLY, ct->proto.sctp.vtag[IP_CT_DIR_REPLY])) goto nla_put_failure; skip_state: spin_unlock_bh(&ct->lock); nla_nest_end(skb, nest_parms); return 0; nla_put_failure: spin_unlock_bh(&ct->lock); return -1; } static const struct nla_policy sctp_nla_policy[CTA_PROTOINFO_SCTP_MAX+1] = { [CTA_PROTOINFO_SCTP_STATE] = { .type = NLA_U8 }, [CTA_PROTOINFO_SCTP_VTAG_ORIGINAL] = { .type = NLA_U32 }, [CTA_PROTOINFO_SCTP_VTAG_REPLY] = { .type = NLA_U32 }, }; #define SCTP_NLATTR_SIZE ( \ NLA_ALIGN(NLA_HDRLEN + 1) + \ NLA_ALIGN(NLA_HDRLEN + 4) + \ NLA_ALIGN(NLA_HDRLEN + 4)) static int nlattr_to_sctp(struct nlattr *cda[], struct nf_conn *ct) { struct nlattr *attr = cda[CTA_PROTOINFO_SCTP]; struct nlattr *tb[CTA_PROTOINFO_SCTP_MAX+1]; int err; /* updates may not contain the internal protocol info, skip parsing */ if (!attr) return 0; err = nla_parse_nested_deprecated(tb, CTA_PROTOINFO_SCTP_MAX, attr, sctp_nla_policy, NULL); if (err < 0) return err; if (!tb[CTA_PROTOINFO_SCTP_STATE] || !tb[CTA_PROTOINFO_SCTP_VTAG_ORIGINAL] || !tb[CTA_PROTOINFO_SCTP_VTAG_REPLY]) return -EINVAL; spin_lock_bh(&ct->lock); ct->proto.sctp.state = nla_get_u8(tb[CTA_PROTOINFO_SCTP_STATE]); ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = nla_get_be32(tb[CTA_PROTOINFO_SCTP_VTAG_ORIGINAL]); ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = nla_get_be32(tb[CTA_PROTOINFO_SCTP_VTAG_REPLY]); spin_unlock_bh(&ct->lock); return 0; } #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> static int sctp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeouts = data; struct nf_sctp_net *sn = nf_sctp_pernet(net); int i; if (!timeouts) timeouts = sn->timeouts; /* set default SCTP timeouts. */ for (i=0; i<SCTP_CONNTRACK_MAX; i++) timeouts[i] = sn->timeouts[i]; /* there's a 1:1 mapping between attributes and protocol states. */ for (i=CTA_TIMEOUT_SCTP_UNSPEC+1; i<CTA_TIMEOUT_SCTP_MAX+1; i++) { if (tb[i]) { timeouts[i] = ntohl(nla_get_be32(tb[i])) * HZ; } } timeouts[CTA_TIMEOUT_SCTP_UNSPEC] = timeouts[CTA_TIMEOUT_SCTP_CLOSED]; return 0; } static int sctp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) { const unsigned int *timeouts = data; int i; for (i=CTA_TIMEOUT_SCTP_UNSPEC+1; i<CTA_TIMEOUT_SCTP_MAX+1; i++) { if (nla_put_be32(skb, i, htonl(timeouts[i] / HZ))) goto nla_put_failure; } return 0; nla_put_failure: return -ENOSPC; } static const struct nla_policy sctp_timeout_nla_policy[CTA_TIMEOUT_SCTP_MAX+1] = { [CTA_TIMEOUT_SCTP_CLOSED] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_COOKIE_WAIT] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_COOKIE_ECHOED] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_ESTABLISHED] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_SHUTDOWN_SENT] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_SHUTDOWN_RECD] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_HEARTBEAT_SENT] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED] = { .type = NLA_U32 }, }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ void nf_conntrack_sctp_init_net(struct net *net) { struct nf_sctp_net *sn = nf_sctp_pernet(net); int i; for (i = 0; i < SCTP_CONNTRACK_MAX; i++) sn->timeouts[i] = sctp_timeouts[i]; /* timeouts[0] is unused, init it so ->timeouts[0] contains * 'new' timeout, like udp or icmp. */ sn->timeouts[0] = sctp_timeouts[SCTP_CONNTRACK_CLOSED]; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp = { .l4proto = IPPROTO_SCTP, #ifdef CONFIG_NF_CONNTRACK_PROCFS .print_conntrack = sctp_print_conntrack, #endif .can_early_drop = sctp_can_early_drop, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .nlattr_size = SCTP_NLATTR_SIZE, .to_nlattr = sctp_to_nlattr, .from_nlattr = nlattr_to_sctp, .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = sctp_timeout_nlattr_to_obj, .obj_to_nlattr = sctp_timeout_obj_to_nlattr, .nlattr_max = CTA_TIMEOUT_SCTP_MAX, .obj_size = sizeof(unsigned int) * SCTP_CONNTRACK_MAX, .nla_policy = sctp_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ }; |
| 999 999 998 999 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 | // SPDX-License-Identifier: GPL-2.0-or-later /* 6LoWPAN fragment reassembly * * Authors: * Alexander Aring <aar@pengutronix.de> * * Based on: net/ipv6/reassembly.c */ #define pr_fmt(fmt) "6LoWPAN: " fmt #include <linux/net.h> #include <linux/list.h> #include <linux/netdevice.h> #include <linux/random.h> #include <linux/jhash.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/export.h> #include <net/ieee802154_netdev.h> #include <net/6lowpan.h> #include <net/ipv6_frag.h> #include <net/inet_frag.h> #include <net/ip.h> #include "6lowpan_i.h" static const char lowpan_frags_cache_name[] = "lowpan-frags"; static struct inet_frags lowpan_frags; static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *skb, struct sk_buff *prev, struct net_device *ldev); static void lowpan_frag_init(struct inet_frag_queue *q, const void *a) { const struct frag_lowpan_compare_key *key = a; BUILD_BUG_ON(sizeof(*key) > sizeof(q->key)); memcpy(&q->key, key, sizeof(*key)); } static void lowpan_frag_expire(struct timer_list *t) { struct inet_frag_queue *frag = from_timer(frag, t, timer); struct frag_queue *fq; fq = container_of(frag, struct frag_queue, q); spin_lock(&fq->q.lock); if (fq->q.flags & INET_FRAG_COMPLETE) goto out; inet_frag_kill(&fq->q); out: spin_unlock(&fq->q.lock); inet_frag_put(&fq->q); } static inline struct lowpan_frag_queue * fq_find(struct net *net, const struct lowpan_802154_cb *cb, const struct ieee802154_addr *src, const struct ieee802154_addr *dst) { struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); struct frag_lowpan_compare_key key = {}; struct inet_frag_queue *q; key.tag = cb->d_tag; key.d_size = cb->d_size; key.src = *src; key.dst = *dst; q = inet_frag_find(ieee802154_lowpan->fqdir, &key); if (!q) return NULL; return container_of(q, struct lowpan_frag_queue, q); } static int lowpan_frag_queue(struct lowpan_frag_queue *fq, struct sk_buff *skb, u8 frag_type) { struct sk_buff *prev_tail; struct net_device *ldev; int end, offset, err; /* inet_frag_queue_* functions use skb->cb; see struct ipfrag_skb_cb * in inet_fragment.c */ BUILD_BUG_ON(sizeof(struct lowpan_802154_cb) > sizeof(struct inet_skb_parm)); BUILD_BUG_ON(sizeof(struct lowpan_802154_cb) > sizeof(struct inet6_skb_parm)); if (fq->q.flags & INET_FRAG_COMPLETE) goto err; offset = lowpan_802154_cb(skb)->d_offset << 3; end = lowpan_802154_cb(skb)->d_size; /* Is this the final fragment? */ if (offset + skb->len == end) { /* If we already have some bits beyond end * or have different end, the segment is corrupted. */ if (end < fq->q.len || ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len)) goto err; fq->q.flags |= INET_FRAG_LAST_IN; fq->q.len = end; } else { if (end > fq->q.len) { /* Some bits beyond end -> corruption. */ if (fq->q.flags & INET_FRAG_LAST_IN) goto err; fq->q.len = end; } } ldev = skb->dev; if (ldev) skb->dev = NULL; barrier(); prev_tail = fq->q.fragments_tail; err = inet_frag_queue_insert(&fq->q, skb, offset, end); if (err) goto err; fq->q.stamp = skb->tstamp; fq->q.mono_delivery_time = skb->mono_delivery_time; if (frag_type == LOWPAN_DISPATCH_FRAG1) fq->q.flags |= INET_FRAG_FIRST_IN; fq->q.meat += skb->len; add_frag_mem_limit(fq->q.fqdir, skb->truesize); if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { int res; unsigned long orefdst = skb->_skb_refdst; skb->_skb_refdst = 0UL; res = lowpan_frag_reasm(fq, skb, prev_tail, ldev); skb->_skb_refdst = orefdst; return res; } skb_dst_drop(skb); return -1; err: kfree_skb(skb); return -1; } /* Check if this packet is complete. * * It is called with locked fq, and caller must check that * queue is eligible for reassembly i.e. it is not COMPLETE, * the last and the first frames arrived and all the bits are here. */ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *skb, struct sk_buff *prev_tail, struct net_device *ldev) { void *reasm_data; inet_frag_kill(&fq->q); reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail); if (!reasm_data) goto out_oom; inet_frag_reasm_finish(&fq->q, skb, reasm_data, false); skb->dev = ldev; skb->tstamp = fq->q.stamp; fq->q.rb_fragments = RB_ROOT; fq->q.fragments_tail = NULL; fq->q.last_run_head = NULL; return 1; out_oom: net_dbg_ratelimited("lowpan_frag_reasm: no memory for reassembly\n"); return -1; } static int lowpan_frag_rx_handlers_result(struct sk_buff *skb, lowpan_rx_result res) { switch (res) { case RX_QUEUED: return NET_RX_SUCCESS; case RX_CONTINUE: /* nobody cared about this packet */ net_warn_ratelimited("%s: received unknown dispatch\n", __func__); fallthrough; default: /* all others failure */ return NET_RX_DROP; } } static lowpan_rx_result lowpan_frag_rx_h_iphc(struct sk_buff *skb) { int ret; if (!lowpan_is_iphc(*skb_network_header(skb))) return RX_CONTINUE; ret = lowpan_iphc_decompress(skb); if (ret < 0) return RX_DROP; return RX_QUEUED; } static int lowpan_invoke_frag_rx_handlers(struct sk_buff *skb) { lowpan_rx_result res; #define CALL_RXH(rxh) \ do { \ res = rxh(skb); \ if (res != RX_CONTINUE) \ goto rxh_next; \ } while (0) /* likely at first */ CALL_RXH(lowpan_frag_rx_h_iphc); CALL_RXH(lowpan_rx_h_ipv6); rxh_next: return lowpan_frag_rx_handlers_result(skb, res); #undef CALL_RXH } #define LOWPAN_FRAG_DGRAM_SIZE_HIGH_MASK 0x07 #define LOWPAN_FRAG_DGRAM_SIZE_HIGH_SHIFT 8 static int lowpan_get_cb(struct sk_buff *skb, u8 frag_type, struct lowpan_802154_cb *cb) { bool fail; u8 high = 0, low = 0; __be16 d_tag = 0; fail = lowpan_fetch_skb(skb, &high, 1); fail |= lowpan_fetch_skb(skb, &low, 1); /* remove the dispatch value and use first three bits as high value * for the datagram size */ cb->d_size = (high & LOWPAN_FRAG_DGRAM_SIZE_HIGH_MASK) << LOWPAN_FRAG_DGRAM_SIZE_HIGH_SHIFT | low; fail |= lowpan_fetch_skb(skb, &d_tag, 2); cb->d_tag = ntohs(d_tag); if (frag_type == LOWPAN_DISPATCH_FRAGN) { fail |= lowpan_fetch_skb(skb, &cb->d_offset, 1); } else { skb_reset_network_header(skb); cb->d_offset = 0; /* check if datagram_size has ipv6hdr on FRAG1 */ fail |= cb->d_size < sizeof(struct ipv6hdr); /* check if we can dereference the dispatch value */ fail |= !skb->len; } if (unlikely(fail)) return -EIO; return 0; } int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type) { struct lowpan_frag_queue *fq; struct net *net = dev_net(skb->dev); struct lowpan_802154_cb *cb = lowpan_802154_cb(skb); struct ieee802154_hdr hdr = {}; int err; if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) goto err; err = lowpan_get_cb(skb, frag_type, cb); if (err < 0) goto err; if (frag_type == LOWPAN_DISPATCH_FRAG1) { err = lowpan_invoke_frag_rx_handlers(skb); if (err == NET_RX_DROP) goto err; } if (cb->d_size > IPV6_MIN_MTU) { net_warn_ratelimited("lowpan_frag_rcv: datagram size exceeds MTU\n"); goto err; } fq = fq_find(net, cb, &hdr.source, &hdr.dest); if (fq != NULL) { int ret; spin_lock(&fq->q.lock); ret = lowpan_frag_queue(fq, skb, frag_type); spin_unlock(&fq->q.lock); inet_frag_put(&fq->q); return ret; } err: kfree_skb(skb); return -1; } #ifdef CONFIG_SYSCTL static struct ctl_table lowpan_frags_ns_ctl_table[] = { { .procname = "6lowpanfrag_high_thresh", .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "6lowpanfrag_low_thresh", .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "6lowpanfrag_time", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { } }; /* secret interval has been deprecated */ static int lowpan_frags_secret_interval_unused; static struct ctl_table lowpan_frags_ctl_table[] = { { .procname = "6lowpanfrag_secret_interval", .data = &lowpan_frags_secret_interval_unused, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { } }; static int __net_init lowpan_frags_ns_sysctl_register(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); table = lowpan_frags_ns_ctl_table; if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(lowpan_frags_ns_ctl_table), GFP_KERNEL); if (table == NULL) goto err_alloc; /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) table[0].procname = NULL; } table[0].data = &ieee802154_lowpan->fqdir->high_thresh; table[0].extra1 = &ieee802154_lowpan->fqdir->low_thresh; table[1].data = &ieee802154_lowpan->fqdir->low_thresh; table[1].extra2 = &ieee802154_lowpan->fqdir->high_thresh; table[2].data = &ieee802154_lowpan->fqdir->timeout; hdr = register_net_sysctl(net, "net/ieee802154/6lowpan", table); if (hdr == NULL) goto err_reg; ieee802154_lowpan->sysctl.frags_hdr = hdr; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; } static void __net_exit lowpan_frags_ns_sysctl_unregister(struct net *net) { struct ctl_table *table; struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); table = ieee802154_lowpan->sysctl.frags_hdr->ctl_table_arg; unregister_net_sysctl_table(ieee802154_lowpan->sysctl.frags_hdr); if (!net_eq(net, &init_net)) kfree(table); } static struct ctl_table_header *lowpan_ctl_header; static int __init lowpan_frags_sysctl_register(void) { lowpan_ctl_header = register_net_sysctl(&init_net, "net/ieee802154/6lowpan", lowpan_frags_ctl_table); return lowpan_ctl_header == NULL ? -ENOMEM : 0; } static void lowpan_frags_sysctl_unregister(void) { unregister_net_sysctl_table(lowpan_ctl_header); } #else static inline int lowpan_frags_ns_sysctl_register(struct net *net) { return 0; } static inline void lowpan_frags_ns_sysctl_unregister(struct net *net) { } static inline int __init lowpan_frags_sysctl_register(void) { return 0; } static inline void lowpan_frags_sysctl_unregister(void) { } #endif static int __net_init lowpan_frags_init_net(struct net *net) { struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); int res; res = fqdir_init(&ieee802154_lowpan->fqdir, &lowpan_frags, net); if (res < 0) return res; ieee802154_lowpan->fqdir->high_thresh = IPV6_FRAG_HIGH_THRESH; ieee802154_lowpan->fqdir->low_thresh = IPV6_FRAG_LOW_THRESH; ieee802154_lowpan->fqdir->timeout = IPV6_FRAG_TIMEOUT; res = lowpan_frags_ns_sysctl_register(net); if (res < 0) fqdir_exit(ieee802154_lowpan->fqdir); return res; } static void __net_exit lowpan_frags_pre_exit_net(struct net *net) { struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); fqdir_pre_exit(ieee802154_lowpan->fqdir); } static void __net_exit lowpan_frags_exit_net(struct net *net) { struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); lowpan_frags_ns_sysctl_unregister(net); fqdir_exit(ieee802154_lowpan->fqdir); } static struct pernet_operations lowpan_frags_ops = { .init = lowpan_frags_init_net, .pre_exit = lowpan_frags_pre_exit_net, .exit = lowpan_frags_exit_net, }; static u32 lowpan_key_hashfn(const void *data, u32 len, u32 seed) { return jhash2(data, sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed); } static u32 lowpan_obj_hashfn(const void *data, u32 len, u32 seed) { const struct inet_frag_queue *fq = data; return jhash2((const u32 *)&fq->key, sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed); } static int lowpan_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr) { const struct frag_lowpan_compare_key *key = arg->key; const struct inet_frag_queue *fq = ptr; return !!memcmp(&fq->key, key, sizeof(*key)); } static const struct rhashtable_params lowpan_rhash_params = { .head_offset = offsetof(struct inet_frag_queue, node), .hashfn = lowpan_key_hashfn, .obj_hashfn = lowpan_obj_hashfn, .obj_cmpfn = lowpan_obj_cmpfn, .automatic_shrinking = true, }; int __init lowpan_net_frag_init(void) { int ret; lowpan_frags.constructor = lowpan_frag_init; lowpan_frags.destructor = NULL; lowpan_frags.qsize = sizeof(struct frag_queue); lowpan_frags.frag_expire = lowpan_frag_expire; lowpan_frags.frags_cache_name = lowpan_frags_cache_name; lowpan_frags.rhash_params = lowpan_rhash_params; ret = inet_frags_init(&lowpan_frags); if (ret) goto out; ret = lowpan_frags_sysctl_register(); if (ret) goto err_sysctl; ret = register_pernet_subsys(&lowpan_frags_ops); if (ret) goto err_pernet; out: return ret; err_pernet: lowpan_frags_sysctl_unregister(); err_sysctl: inet_frags_fini(&lowpan_frags); return ret; } void lowpan_net_frag_exit(void) { lowpan_frags_sysctl_unregister(); unregister_pernet_subsys(&lowpan_frags_ops); inet_frags_fini(&lowpan_frags); } |
| 2361 9833 8642 3427 3427 59 2261 3419 10 10 1249 1249 374 374 52 52 52 51 2 52 8572 8566 8573 8584 81 6454 6452 6453 6449 6456 40 105 105 105 105 105 2115 2113 2320 2319 2320 19 2319 45 45 45 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 | // SPDX-License-Identifier: GPL-2.0 /* * Kernel timekeeping code and accessor functions. Based on code from * timer.c, moved in commit 8524070b7982. */ #include <linux/timekeeper_internal.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/nmi.h> #include <linux/sched.h> #include <linux/sched/loadavg.h> #include <linux/sched/clock.h> #include <linux/syscore_ops.h> #include <linux/clocksource.h> #include <linux/jiffies.h> #include <linux/time.h> #include <linux/timex.h> #include <linux/tick.h> #include <linux/stop_machine.h> #include <linux/pvclock_gtod.h> #include <linux/compiler.h> #include <linux/audit.h> #include <linux/random.h> #include "tick-internal.h" #include "ntp_internal.h" #include "timekeeping_internal.h" #define TK_CLEAR_NTP (1 << 0) #define TK_MIRROR (1 << 1) #define TK_CLOCK_WAS_SET (1 << 2) enum timekeeping_adv_mode { /* Update timekeeper when a tick has passed */ TK_ADV_TICK, /* Update timekeeper on a direct frequency change */ TK_ADV_FREQ }; DEFINE_RAW_SPINLOCK(timekeeper_lock); /* * The most important data for readout fits into a single 64 byte * cache line. */ static struct { seqcount_raw_spinlock_t seq; struct timekeeper timekeeper; } tk_core ____cacheline_aligned = { .seq = SEQCNT_RAW_SPINLOCK_ZERO(tk_core.seq, &timekeeper_lock), }; static struct timekeeper shadow_timekeeper; /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; /** * struct tk_fast - NMI safe timekeeper * @seq: Sequence counter for protecting updates. The lowest bit * is the index for the tk_read_base array * @base: tk_read_base array. Access is indexed by the lowest bit of * @seq. * * See @update_fast_timekeeper() below. */ struct tk_fast { seqcount_latch_t seq; struct tk_read_base base[2]; }; /* Suspend-time cycles value for halted fast timekeeper. */ static u64 cycles_at_suspend; static u64 dummy_clock_read(struct clocksource *cs) { if (timekeeping_suspended) return cycles_at_suspend; return local_clock(); } static struct clocksource dummy_clock = { .read = dummy_clock_read, }; /* * Boot time initialization which allows local_clock() to be utilized * during early boot when clocksources are not available. local_clock() * returns nanoseconds already so no conversion is required, hence mult=1 * and shift=0. When the first proper clocksource is installed then * the fast time keepers are updated with the correct values. */ #define FAST_TK_INIT \ { \ .clock = &dummy_clock, \ .mask = CLOCKSOURCE_MASK(64), \ .mult = 1, \ .shift = 0, \ } static struct tk_fast tk_fast_mono ____cacheline_aligned = { .seq = SEQCNT_LATCH_ZERO(tk_fast_mono.seq), .base[0] = FAST_TK_INIT, .base[1] = FAST_TK_INIT, }; static struct tk_fast tk_fast_raw ____cacheline_aligned = { .seq = SEQCNT_LATCH_ZERO(tk_fast_raw.seq), .base[0] = FAST_TK_INIT, .base[1] = FAST_TK_INIT, }; static inline void tk_normalize_xtime(struct timekeeper *tk) { while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) { tk->tkr_mono.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec++; } while (tk->tkr_raw.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_raw.shift)) { tk->tkr_raw.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_raw.shift; tk->raw_sec++; } } static inline struct timespec64 tk_xtime(const struct timekeeper *tk) { struct timespec64 ts; ts.tv_sec = tk->xtime_sec; ts.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); return ts; } static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec = ts->tv_sec; tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift; } static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec += ts->tv_sec; tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift; tk_normalize_xtime(tk); } static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) { struct timespec64 tmp; /* * Verify consistency of: offset_real = -wall_to_monotonic * before modifying anything */ set_normalized_timespec64(&tmp, -tk->wall_to_monotonic.tv_sec, -tk->wall_to_monotonic.tv_nsec); WARN_ON_ONCE(tk->offs_real != timespec64_to_ktime(tmp)); tk->wall_to_monotonic = wtm; set_normalized_timespec64(&tmp, -wtm.tv_sec, -wtm.tv_nsec); tk->offs_real = timespec64_to_ktime(tmp); tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0)); } static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) { tk->offs_boot = ktime_add(tk->offs_boot, delta); /* * Timespec representation for VDSO update to avoid 64bit division * on every update. */ tk->monotonic_to_boot = ktime_to_timespec64(tk->offs_boot); } /* * tk_clock_read - atomic clocksource read() helper * * This helper is necessary to use in the read paths because, while the * seqcount ensures we don't return a bad value while structures are updated, * it doesn't protect from potential crashes. There is the possibility that * the tkr's clocksource may change between the read reference, and the * clock reference passed to the read function. This can cause crashes if * the wrong clocksource is passed to the wrong read function. * This isn't necessary to use when holding the timekeeper_lock or doing * a read of the fast-timekeeper tkrs (which is protected by its own locking * and update logic). */ static inline u64 tk_clock_read(const struct tk_read_base *tkr) { struct clocksource *clock = READ_ONCE(tkr->clock); return clock->read(clock); } #ifdef CONFIG_DEBUG_TIMEKEEPING #define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */ static void timekeeping_check_update(struct timekeeper *tk, u64 offset) { u64 max_cycles = tk->tkr_mono.clock->max_cycles; const char *name = tk->tkr_mono.clock->name; if (offset > max_cycles) { printk_deferred("WARNING: timekeeping: Cycle offset (%lld) is larger than allowed by the '%s' clock's max_cycles value (%lld): time overflow danger\n", offset, name, max_cycles); printk_deferred(" timekeeping: Your kernel is sick, but tries to cope by capping time updates\n"); } else { if (offset > (max_cycles >> 1)) { printk_deferred("INFO: timekeeping: Cycle offset (%lld) is larger than the '%s' clock's 50%% safety margin (%lld)\n", offset, name, max_cycles >> 1); printk_deferred(" timekeeping: Your kernel is still fine, but is feeling a bit nervous\n"); } } if (tk->underflow_seen) { if (jiffies - tk->last_warning > WARNING_FREQ) { printk_deferred("WARNING: Underflow in clocksource '%s' observed, time update ignored.\n", name); printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); printk_deferred(" Your kernel is probably still fine.\n"); tk->last_warning = jiffies; } tk->underflow_seen = 0; } if (tk->overflow_seen) { if (jiffies - tk->last_warning > WARNING_FREQ) { printk_deferred("WARNING: Overflow in clocksource '%s' observed, time update capped.\n", name); printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); printk_deferred(" Your kernel is probably still fine.\n"); tk->last_warning = jiffies; } tk->overflow_seen = 0; } } static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr) { struct timekeeper *tk = &tk_core.timekeeper; u64 now, last, mask, max, delta; unsigned int seq; /* * Since we're called holding a seqcount, the data may shift * under us while we're doing the calculation. This can cause * false positives, since we'd note a problem but throw the * results away. So nest another seqcount here to atomically * grab the points we are checking with. */ do { seq = read_seqcount_begin(&tk_core.seq); now = tk_clock_read(tkr); last = tkr->cycle_last; mask = tkr->mask; max = tkr->clock->max_cycles; } while (read_seqcount_retry(&tk_core.seq, seq)); delta = clocksource_delta(now, last, mask); /* * Try to catch underflows by checking if we are seeing small * mask-relative negative values. */ if (unlikely((~delta & mask) < (mask >> 3))) { tk->underflow_seen = 1; delta = 0; } /* Cap delta value to the max_cycles values to avoid mult overflows */ if (unlikely(delta > max)) { tk->overflow_seen = 1; delta = tkr->clock->max_cycles; } return delta; } #else static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset) { } static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr) { u64 cycle_now, delta; /* read clocksource */ cycle_now = tk_clock_read(tkr); /* calculate the delta since the last update_wall_time */ delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask); return delta; } #endif /** * tk_setup_internals - Set up internals to use clocksource clock. * * @tk: The target timekeeper to setup. * @clock: Pointer to clocksource. * * Calculates a fixed cycle/nsec interval for a given clocksource/adjustment * pair and interval request. * * Unless you're the timekeeping code, you should not be using this! */ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) { u64 interval; u64 tmp, ntpinterval; struct clocksource *old_clock; ++tk->cs_was_changed_seq; old_clock = tk->tkr_mono.clock; tk->tkr_mono.clock = clock; tk->tkr_mono.mask = clock->mask; tk->tkr_mono.cycle_last = tk_clock_read(&tk->tkr_mono); tk->tkr_raw.clock = clock; tk->tkr_raw.mask = clock->mask; tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last; /* Do the ns -> cycle conversion first, using original mult */ tmp = NTP_INTERVAL_LENGTH; tmp <<= clock->shift; ntpinterval = tmp; tmp += clock->mult/2; do_div(tmp, clock->mult); if (tmp == 0) tmp = 1; interval = (u64) tmp; tk->cycle_interval = interval; /* Go back from cycles -> shifted ns */ tk->xtime_interval = interval * clock->mult; tk->xtime_remainder = ntpinterval - tk->xtime_interval; tk->raw_interval = interval * clock->mult; /* if changing clocks, convert xtime_nsec shift units */ if (old_clock) { int shift_change = clock->shift - old_clock->shift; if (shift_change < 0) { tk->tkr_mono.xtime_nsec >>= -shift_change; tk->tkr_raw.xtime_nsec >>= -shift_change; } else { tk->tkr_mono.xtime_nsec <<= shift_change; tk->tkr_raw.xtime_nsec <<= shift_change; } } tk->tkr_mono.shift = clock->shift; tk->tkr_raw.shift = clock->shift; tk->ntp_error = 0; tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; tk->ntp_tick = ntpinterval << tk->ntp_error_shift; /* * The timekeeper keeps its own mult values for the currently * active clocksource. These value will be adjusted via NTP * to counteract clock drifting. */ tk->tkr_mono.mult = clock->mult; tk->tkr_raw.mult = clock->mult; tk->ntp_err_mult = 0; tk->skip_second_overflow = 0; } /* Timekeeper helper functions. */ static inline u64 timekeeping_delta_to_ns(const struct tk_read_base *tkr, u64 delta) { u64 nsec; nsec = delta * tkr->mult + tkr->xtime_nsec; nsec >>= tkr->shift; return nsec; } static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) { u64 delta; delta = timekeeping_get_delta(tkr); return timekeeping_delta_to_ns(tkr, delta); } static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles) { u64 delta; /* calculate the delta since the last update_wall_time */ delta = clocksource_delta(cycles, tkr->cycle_last, tkr->mask); return timekeeping_delta_to_ns(tkr, delta); } /** * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper. * @tkr: Timekeeping readout base from which we take the update * @tkf: Pointer to NMI safe timekeeper * * We want to use this from any context including NMI and tracing / * instrumenting the timekeeping code itself. * * Employ the latch technique; see @raw_write_seqcount_latch. * * So if a NMI hits the update of base[0] then it will use base[1] * which is still consistent. In the worst case this can result is a * slightly wrong timestamp (a few nanoseconds). See * @ktime_get_mono_fast_ns. */ static void update_fast_timekeeper(const struct tk_read_base *tkr, struct tk_fast *tkf) { struct tk_read_base *base = tkf->base; /* Force readers off to base[1] */ raw_write_seqcount_latch(&tkf->seq); /* Update base[0] */ memcpy(base, tkr, sizeof(*base)); /* Force readers back to base[0] */ raw_write_seqcount_latch(&tkf->seq); /* Update base[1] */ memcpy(base + 1, base, sizeof(*base)); } static __always_inline u64 fast_tk_get_delta_ns(struct tk_read_base *tkr) { u64 delta, cycles = tk_clock_read(tkr); delta = clocksource_delta(cycles, tkr->cycle_last, tkr->mask); return timekeeping_delta_to_ns(tkr, delta); } static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) { struct tk_read_base *tkr; unsigned int seq; u64 now; do { seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); now = ktime_to_ns(tkr->base); now += fast_tk_get_delta_ns(tkr); } while (raw_read_seqcount_latch_retry(&tkf->seq, seq)); return now; } /** * ktime_get_mono_fast_ns - Fast NMI safe access to clock monotonic * * This timestamp is not guaranteed to be monotonic across an update. * The timestamp is calculated by: * * now = base_mono + clock_delta * slope * * So if the update lowers the slope, readers who are forced to the * not yet updated second array are still using the old steeper slope. * * tmono * ^ * | o n * | o n * | u * | o * |o * |12345678---> reader order * * o = old slope * u = update * n = new slope * * So reader 6 will observe time going backwards versus reader 5. * * While other CPUs are likely to be able to observe that, the only way * for a CPU local observation is when an NMI hits in the middle of * the update. Timestamps taken from that NMI context might be ahead * of the following timestamps. Callers need to be aware of that and * deal with it. */ u64 notrace ktime_get_mono_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_mono); } EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns); /** * ktime_get_raw_fast_ns - Fast NMI safe access to clock monotonic raw * * Contrary to ktime_get_mono_fast_ns() this is always correct because the * conversion factor is not affected by NTP/PTP correction. */ u64 notrace ktime_get_raw_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_raw); } EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns); /** * ktime_get_boot_fast_ns - NMI safe and fast access to boot clock. * * To keep it NMI safe since we're accessing from tracing, we're not using a * separate timekeeper with updates to monotonic clock and boot offset * protected with seqcounts. This has the following minor side effects: * * (1) Its possible that a timestamp be taken after the boot offset is updated * but before the timekeeper is updated. If this happens, the new boot offset * is added to the old timekeeping making the clock appear to update slightly * earlier: * CPU 0 CPU 1 * timekeeping_inject_sleeptime64() * __timekeeping_inject_sleeptime(tk, delta); * timestamp(); * timekeeping_update(tk, TK_CLEAR_NTP...); * * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be * partially updated. Since the tk->offs_boot update is a rare event, this * should be a rare occurrence which postprocessing should be able to handle. * * The caveats vs. timestamp ordering as documented for ktime_get_mono_fast_ns() * apply as well. */ u64 notrace ktime_get_boot_fast_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_boot))); } EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns); /** * ktime_get_tai_fast_ns - NMI safe and fast access to tai clock. * * The same limitations as described for ktime_get_boot_fast_ns() apply. The * mono time and the TAI offset are not read atomically which may yield wrong * readouts. However, an update of the TAI offset is an rare event e.g., caused * by settime or adjtimex with an offset. The user of this function has to deal * with the possibility of wrong timestamps in post processing. */ u64 notrace ktime_get_tai_fast_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_tai))); } EXPORT_SYMBOL_GPL(ktime_get_tai_fast_ns); static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono) { struct tk_read_base *tkr; u64 basem, baser, delta; unsigned int seq; do { seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); basem = ktime_to_ns(tkr->base); baser = ktime_to_ns(tkr->base_real); delta = fast_tk_get_delta_ns(tkr); } while (raw_read_seqcount_latch_retry(&tkf->seq, seq)); if (mono) *mono = basem + delta; return baser + delta; } /** * ktime_get_real_fast_ns: - NMI safe and fast access to clock realtime. * * See ktime_get_mono_fast_ns() for documentation of the time stamp ordering. */ u64 ktime_get_real_fast_ns(void) { return __ktime_get_real_fast(&tk_fast_mono, NULL); } EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns); /** * ktime_get_fast_timestamps: - NMI safe timestamps * @snapshot: Pointer to timestamp storage * * Stores clock monotonic, boottime and realtime timestamps. * * Boot time is a racy access on 32bit systems if the sleep time injection * happens late during resume and not in timekeeping_resume(). That could * be avoided by expanding struct tk_read_base with boot offset for 32bit * and adding more overhead to the update. As this is a hard to observe * once per resume event which can be filtered with reasonable effort using * the accurate mono/real timestamps, it's probably not worth the trouble. * * Aside of that it might be possible on 32 and 64 bit to observe the * following when the sleep time injection happens late: * * CPU 0 CPU 1 * timekeeping_resume() * ktime_get_fast_timestamps() * mono, real = __ktime_get_real_fast() * inject_sleep_time() * update boot offset * boot = mono + bootoffset; * * That means that boot time already has the sleep time adjustment, but * real time does not. On the next readout both are in sync again. * * Preventing this for 64bit is not really feasible without destroying the * careful cache layout of the timekeeper because the sequence count and * struct tk_read_base would then need two cache lines instead of one. * * Access to the time keeper clock source is disabled across the innermost * steps of suspend/resume. The accessors still work, but the timestamps * are frozen until time keeping is resumed which happens very early. * * For regular suspend/resume there is no observable difference vs. sched * clock, but it might affect some of the nasty low level debug printks. * * OTOH, access to sched clock is not guaranteed across suspend/resume on * all systems either so it depends on the hardware in use. * * If that turns out to be a real problem then this could be mitigated by * using sched clock in a similar way as during early boot. But it's not as * trivial as on early boot because it needs some careful protection * against the clock monotonic timestamp jumping backwards on resume. */ void ktime_get_fast_timestamps(struct ktime_timestamps *snapshot) { struct timekeeper *tk = &tk_core.timekeeper; snapshot->real = __ktime_get_real_fast(&tk_fast_mono, &snapshot->mono); snapshot->boot = snapshot->mono + ktime_to_ns(data_race(tk->offs_boot)); } /** * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource. * @tk: Timekeeper to snapshot. * * It generally is unsafe to access the clocksource after timekeeping has been * suspended, so take a snapshot of the readout base of @tk and use it as the * fast timekeeper's readout base while suspended. It will return the same * number of cycles every time until timekeeping is resumed at which time the * proper readout base for the fast timekeeper will be restored automatically. */ static void halt_fast_timekeeper(const struct timekeeper *tk) { static struct tk_read_base tkr_dummy; const struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); cycles_at_suspend = tk_clock_read(tkr); tkr_dummy.clock = &dummy_clock; tkr_dummy.base_real = tkr->base + tk->offs_real; update_fast_timekeeper(&tkr_dummy, &tk_fast_mono); tkr = &tk->tkr_raw; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); tkr_dummy.clock = &dummy_clock; update_fast_timekeeper(&tkr_dummy, &tk_fast_raw); } static RAW_NOTIFIER_HEAD(pvclock_gtod_chain); static void update_pvclock_gtod(struct timekeeper *tk, bool was_set) { raw_notifier_call_chain(&pvclock_gtod_chain, was_set, tk); } /** * pvclock_gtod_register_notifier - register a pvclock timedata update listener * @nb: Pointer to the notifier block to register */ int pvclock_gtod_register_notifier(struct notifier_block *nb) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; int ret; raw_spin_lock_irqsave(&timekeeper_lock, flags); ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb); update_pvclock_gtod(tk, true); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return ret; } EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier); /** * pvclock_gtod_unregister_notifier - unregister a pvclock * timedata update listener * @nb: Pointer to the notifier block to unregister */ int pvclock_gtod_unregister_notifier(struct notifier_block *nb) { unsigned long flags; int ret; raw_spin_lock_irqsave(&timekeeper_lock, flags); ret = raw_notifier_chain_unregister(&pvclock_gtod_chain, nb); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return ret; } EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier); /* * tk_update_leap_state - helper to update the next_leap_ktime */ static inline void tk_update_leap_state(struct timekeeper *tk) { tk->next_leap_ktime = ntp_get_next_leap(); if (tk->next_leap_ktime != KTIME_MAX) /* Convert to monotonic time */ tk->next_leap_ktime = ktime_sub(tk->next_leap_ktime, tk->offs_real); } /* * Update the ktime_t based scalar nsec members of the timekeeper */ static inline void tk_update_ktime_data(struct timekeeper *tk) { u64 seconds; u32 nsec; /* * The xtime based monotonic readout is: * nsec = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec + now(); * The ktime based monotonic readout is: * nsec = base_mono + now(); * ==> base_mono = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec */ seconds = (u64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec); nsec = (u32) tk->wall_to_monotonic.tv_nsec; tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); /* * The sum of the nanoseconds portions of xtime and * wall_to_monotonic can be greater/equal one second. Take * this into account before updating tk->ktime_sec. */ nsec += (u32)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); if (nsec >= NSEC_PER_SEC) seconds++; tk->ktime_sec = seconds; /* Update the monotonic raw base */ tk->tkr_raw.base = ns_to_ktime(tk->raw_sec * NSEC_PER_SEC); } /* must hold timekeeper_lock */ static void timekeeping_update(struct timekeeper *tk, unsigned int action) { if (action & TK_CLEAR_NTP) { tk->ntp_error = 0; ntp_clear(); } tk_update_leap_state(tk); tk_update_ktime_data(tk); update_vsyscall(tk); update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); tk->tkr_mono.base_real = tk->tkr_mono.base + tk->offs_real; update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono); update_fast_timekeeper(&tk->tkr_raw, &tk_fast_raw); if (action & TK_CLOCK_WAS_SET) tk->clock_was_set_seq++; /* * The mirroring of the data to the shadow-timekeeper needs * to happen last here to ensure we don't over-write the * timekeeper structure on the next update with stale data */ if (action & TK_MIRROR) memcpy(&shadow_timekeeper, &tk_core.timekeeper, sizeof(tk_core.timekeeper)); } /** * timekeeping_forward_now - update clock to the current time * @tk: Pointer to the timekeeper to update * * Forward the current clock to update its state since the last call to * update_wall_time(). This is useful before significant clock changes, * as it avoids having to deal with this time offset explicitly. */ static void timekeeping_forward_now(struct timekeeper *tk) { u64 cycle_now, delta; cycle_now = tk_clock_read(&tk->tkr_mono); delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask); tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; tk->tkr_mono.xtime_nsec += delta * tk->tkr_mono.mult; tk->tkr_raw.xtime_nsec += delta * tk->tkr_raw.mult; tk_normalize_xtime(tk); } /** * ktime_get_real_ts64 - Returns the time of day in a timespec64. * @ts: pointer to the timespec to be set * * Returns the time of day in a timespec64 (WARN if suspended). */ void ktime_get_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(ktime_get_real_ts64); ktime_t ktime_get(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get); u32 ktime_get_resolution_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u32 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); nsecs = tk->tkr_mono.mult >> tk->tkr_mono.shift; } while (read_seqcount_retry(&tk_core.seq, seq)); return nsecs; } EXPORT_SYMBOL_GPL(ktime_get_resolution_ns); static ktime_t *offsets[TK_OFFS_MAX] = { [TK_OFFS_REAL] = &tk_core.timekeeper.offs_real, [TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot, [TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai, }; ktime_t ktime_get_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base, *offset = offsets[offs]; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_with_offset); ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base, *offset = offsets[offs]; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset); /** * ktime_mono_to_any() - convert monotonic time to any other time * @tmono: time to convert. * @offs: which offset to use */ ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs) { ktime_t *offset = offsets[offs]; unsigned int seq; ktime_t tconv; do { seq = read_seqcount_begin(&tk_core.seq); tconv = ktime_add(tmono, *offset); } while (read_seqcount_retry(&tk_core.seq, seq)); return tconv; } EXPORT_SYMBOL_GPL(ktime_mono_to_any); /** * ktime_get_raw - Returns the raw monotonic time in ktime_t format */ ktime_t ktime_get_raw(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_raw.base; nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_raw); /** * ktime_get_ts64 - get the monotonic clock in timespec64 format * @ts: pointer to timespec variable * * The function calculates the monotonic clock from the realtime * clock and the wall_to_monotonic offset and stores the result * in normalized timespec64 format in the variable pointed to by @ts. */ void ktime_get_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 tomono; unsigned int seq; u64 nsec; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsec = timekeeping_get_ns(&tk->tkr_mono); tomono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_sec += tomono.tv_sec; ts->tv_nsec = 0; timespec64_add_ns(ts, nsec + tomono.tv_nsec); } EXPORT_SYMBOL_GPL(ktime_get_ts64); /** * ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC * * Returns the seconds portion of CLOCK_MONOTONIC with a single non * serialized read. tk->ktime_sec is of type 'unsigned long' so this * works on both 32 and 64 bit systems. On 32 bit systems the readout * covers ~136 years of uptime which should be enough to prevent * premature wrap arounds. */ time64_t ktime_get_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; WARN_ON(timekeeping_suspended); return tk->ktime_sec; } EXPORT_SYMBOL_GPL(ktime_get_seconds); /** * ktime_get_real_seconds - Get the seconds portion of CLOCK_REALTIME * * Returns the wall clock seconds since 1970. * * For 64bit systems the fast access to tk->xtime_sec is preserved. On * 32bit systems the access must be protected with the sequence * counter to provide "atomic" access to the 64bit tk->xtime_sec * value. */ time64_t ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; time64_t seconds; unsigned int seq; if (IS_ENABLED(CONFIG_64BIT)) return tk->xtime_sec; do { seq = read_seqcount_begin(&tk_core.seq); seconds = tk->xtime_sec; } while (read_seqcount_retry(&tk_core.seq, seq)); return seconds; } EXPORT_SYMBOL_GPL(ktime_get_real_seconds); /** * __ktime_get_real_seconds - The same as ktime_get_real_seconds * but without the sequence counter protect. This internal function * is called just when timekeeping lock is already held. */ noinstr time64_t __ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; return tk->xtime_sec; } /** * ktime_get_snapshot - snapshots the realtime/monotonic raw clocks with counter * @systime_snapshot: pointer to struct receiving the system time snapshot */ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) { struct timekeeper *tk = &tk_core.timekeeper; u32 mono_mult, mono_shift; unsigned int seq; ktime_t base_raw; ktime_t base_real; ktime_t base_boot; u64 nsec_raw; u64 nsec_real; u64 now; WARN_ON_ONCE(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); now = tk_clock_read(&tk->tkr_mono); systime_snapshot->cs_id = tk->tkr_mono.clock->id; systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq; systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq; base_real = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_real); base_boot = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_boot); base_raw = tk->tkr_raw.base; nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, now); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, now); mono_mult = tk->tkr_mono.mult; mono_shift = tk->tkr_mono.shift; } while (read_seqcount_retry(&tk_core.seq, seq)); systime_snapshot->cycles = now; systime_snapshot->real = ktime_add_ns(base_real, nsec_real); systime_snapshot->boot = ktime_add_ns(base_boot, nsec_real); systime_snapshot->raw = ktime_add_ns(base_raw, nsec_raw); systime_snapshot->mono_shift = mono_shift; systime_snapshot->mono_mult = mono_mult; } EXPORT_SYMBOL_GPL(ktime_get_snapshot); /* Scale base by mult/div checking for overflow */ static int scale64_check_overflow(u64 mult, u64 div, u64 *base) { u64 tmp, rem; tmp = div64_u64_rem(*base, div, &rem); if (((int)sizeof(u64)*8 - fls64(mult) < fls64(tmp)) || ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem))) return -EOVERFLOW; tmp *= mult; rem = div64_u64(rem * mult, div); *base = tmp + rem; return 0; } /** * adjust_historical_crosststamp - adjust crosstimestamp previous to current interval * @history: Snapshot representing start of history * @partial_history_cycles: Cycle offset into history (fractional part) * @total_history_cycles: Total history length in cycles * @discontinuity: True indicates clock was set on history period * @ts: Cross timestamp that should be adjusted using * partial/total ratio * * Helper function used by get_device_system_crosststamp() to correct the * crosstimestamp corresponding to the start of the current interval to the * system counter value (timestamp point) provided by the driver. The * total_history_* quantities are the total history starting at the provided * reference point and ending at the start of the current interval. The cycle * count between the driver timestamp point and the start of the current * interval is partial_history_cycles. */ static int adjust_historical_crosststamp(struct system_time_snapshot *history, u64 partial_history_cycles, u64 total_history_cycles, bool discontinuity, struct system_device_crosststamp *ts) { struct timekeeper *tk = &tk_core.timekeeper; u64 corr_raw, corr_real; bool interp_forward; int ret; if (total_history_cycles == 0 || partial_history_cycles == 0) return 0; /* Interpolate shortest distance from beginning or end of history */ interp_forward = partial_history_cycles > total_history_cycles / 2; partial_history_cycles = interp_forward ? total_history_cycles - partial_history_cycles : partial_history_cycles; /* * Scale the monotonic raw time delta by: * partial_history_cycles / total_history_cycles */ corr_raw = (u64)ktime_to_ns( ktime_sub(ts->sys_monoraw, history->raw)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_raw); if (ret) return ret; /* * If there is a discontinuity in the history, scale monotonic raw * correction by: * mult(real)/mult(raw) yielding the realtime correction * Otherwise, calculate the realtime correction similar to monotonic * raw calculation */ if (discontinuity) { corr_real = mul_u64_u32_div (corr_raw, tk->tkr_mono.mult, tk->tkr_raw.mult); } else { corr_real = (u64)ktime_to_ns( ktime_sub(ts->sys_realtime, history->real)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_real); if (ret) return ret; } /* Fixup monotonic raw and real time time values */ if (interp_forward) { ts->sys_monoraw = ktime_add_ns(history->raw, corr_raw); ts->sys_realtime = ktime_add_ns(history->real, corr_real); } else { ts->sys_monoraw = ktime_sub_ns(ts->sys_monoraw, corr_raw); ts->sys_realtime = ktime_sub_ns(ts->sys_realtime, corr_real); } return 0; } /* * timestamp_in_interval - true if ts is chronologically in [start, end] * * True if ts occurs chronologically at or after start, and before or at end. */ static bool timestamp_in_interval(u64 start, u64 end, u64 ts) { if (ts >= start && ts <= end) return true; if (start > end && (ts >= start || ts <= end)) return true; return false; } /** * get_device_system_crosststamp - Synchronously capture system/device timestamp * @get_time_fn: Callback to get simultaneous device time and * system counter from the device driver * @ctx: Context passed to get_time_fn() * @history_begin: Historical reference point used to interpolate system * time when counter provided by the driver is before the current interval * @xtstamp: Receives simultaneously captured system and device time * * Reads a timestamp from a device and correlates it to system time */ int get_device_system_crosststamp(int (*get_time_fn) (ktime_t *device_time, struct system_counterval_t *sys_counterval, void *ctx), void *ctx, struct system_time_snapshot *history_begin, struct system_device_crosststamp *xtstamp) { struct system_counterval_t system_counterval; struct timekeeper *tk = &tk_core.timekeeper; u64 cycles, now, interval_start; unsigned int clock_was_set_seq = 0; ktime_t base_real, base_raw; u64 nsec_real, nsec_raw; u8 cs_was_changed_seq; unsigned int seq; bool do_interp; int ret; do { seq = read_seqcount_begin(&tk_core.seq); /* * Try to synchronously capture device time and a system * counter value calling back into the device driver */ ret = get_time_fn(&xtstamp->device, &system_counterval, ctx); if (ret) return ret; /* * Verify that the clocksource associated with the captured * system counter value is the same as the currently installed * timekeeper clocksource */ if (tk->tkr_mono.clock != system_counterval.cs) return -ENODEV; cycles = system_counterval.cycles; /* * Check whether the system counter value provided by the * device driver is on the current timekeeping interval. */ now = tk_clock_read(&tk->tkr_mono); interval_start = tk->tkr_mono.cycle_last; if (!timestamp_in_interval(interval_start, now, cycles)) { clock_was_set_seq = tk->clock_was_set_seq; cs_was_changed_seq = tk->cs_was_changed_seq; cycles = interval_start; do_interp = true; } else { do_interp = false; } base_real = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_real); base_raw = tk->tkr_raw.base; nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, cycles); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, cycles); } while (read_seqcount_retry(&tk_core.seq, seq)); xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real); xtstamp->sys_monoraw = ktime_add_ns(base_raw, nsec_raw); /* * Interpolate if necessary, adjusting back from the start of the * current interval */ if (do_interp) { u64 partial_history_cycles, total_history_cycles; bool discontinuity; /* * Check that the counter value is not before the provided * history reference and that the history doesn't cross a * clocksource change */ if (!history_begin || !timestamp_in_interval(history_begin->cycles, cycles, system_counterval.cycles) || history_begin->cs_was_changed_seq != cs_was_changed_seq) return -EINVAL; partial_history_cycles = cycles - system_counterval.cycles; total_history_cycles = cycles - history_begin->cycles; discontinuity = history_begin->clock_was_set_seq != clock_was_set_seq; ret = adjust_historical_crosststamp(history_begin, partial_history_cycles, total_history_cycles, discontinuity, xtstamp); if (ret) return ret; } return 0; } EXPORT_SYMBOL_GPL(get_device_system_crosststamp); /** * do_settimeofday64 - Sets the time of day. * @ts: pointer to the timespec64 variable containing the new time * * Sets the time of day to the new time and update NTP and notify hrtimers */ int do_settimeofday64(const struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 ts_delta, xt; unsigned long flags; int ret = 0; if (!timespec64_valid_settod(ts)) return -EINVAL; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); xt = tk_xtime(tk); ts_delta = timespec64_sub(*ts, xt); if (timespec64_compare(&tk->wall_to_monotonic, &ts_delta) > 0) { ret = -EINVAL; goto out; } tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts_delta)); tk_set_xtime(tk, ts); out: timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL); if (!ret) { audit_tk_injoffset(ts_delta); add_device_randomness(ts, sizeof(*ts)); } return ret; } EXPORT_SYMBOL(do_settimeofday64); /** * timekeeping_inject_offset - Adds or subtracts from the current time. * @ts: Pointer to the timespec variable containing the offset * * Adds or subtracts an offset value from the current time. */ static int timekeeping_inject_offset(const struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; struct timespec64 tmp; int ret = 0; if (ts->tv_nsec < 0 || ts->tv_nsec >= NSEC_PER_SEC) return -EINVAL; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); /* Make sure the proposed value is valid */ tmp = timespec64_add(tk_xtime(tk), *ts); if (timespec64_compare(&tk->wall_to_monotonic, ts) > 0 || !timespec64_valid_settod(&tmp)) { ret = -EINVAL; goto error; } tk_xtime_add(tk, ts); tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *ts)); error: /* even if we error out, we forwarded the time, so call update */ timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL); return ret; } /* * Indicates if there is an offset between the system clock and the hardware * clock/persistent clock/rtc. */ int persistent_clock_is_local; /* * Adjust the time obtained from the CMOS to be UTC time instead of * local time. * * This is ugly, but preferable to the alternatives. Otherwise we * would either need to write a program to do it in /etc/rc (and risk * confusion if the program gets run more than once; it would also be * hard to make the program warp the clock precisely n hours) or * compile in the timezone information into the kernel. Bad, bad.... * * - TYT, 1992-01-01 * * The best thing to do is to keep the CMOS clock in universal time (UTC) * as real UNIX machines always do it. This avoids all headaches about * daylight saving times and warping kernel clocks. */ void timekeeping_warp_clock(void) { if (sys_tz.tz_minuteswest != 0) { struct timespec64 adjust; persistent_clock_is_local = 1; adjust.tv_sec = sys_tz.tz_minuteswest * 60; adjust.tv_nsec = 0; timekeeping_inject_offset(&adjust); } } /* * __timekeeping_set_tai_offset - Sets the TAI offset from UTC and monotonic */ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) { tk->tai_offset = tai_offset; tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0)); } /* * change_clocksource - Swaps clocksources if a new one is available * * Accumulates current time interval and initializes new clocksource */ static int change_clocksource(void *data) { struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *new, *old = NULL; unsigned long flags; bool change = false; new = (struct clocksource *) data; /* * If the cs is in module, get a module reference. Succeeds * for built-in code (owner == NULL) as well. */ if (try_module_get(new->owner)) { if (!new->enable || new->enable(new) == 0) change = true; else module_put(new->owner); } raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); if (change) { old = tk->tkr_mono.clock; tk_setup_internals(tk, new); } timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); if (old) { if (old->disable) old->disable(old); module_put(old->owner); } return 0; } /** * timekeeping_notify - Install a new clock source * @clock: pointer to the clock source * * This function is called from clocksource.c after a new, better clock * source has been registered. The caller holds the clocksource_mutex. */ int timekeeping_notify(struct clocksource *clock) { struct timekeeper *tk = &tk_core.timekeeper; if (tk->tkr_mono.clock == clock) return 0; stop_machine(change_clocksource, clock, NULL); tick_clock_notify(); return tk->tkr_mono.clock == clock ? 0 : -1; } /** * ktime_get_raw_ts64 - Returns the raw monotonic time in a timespec * @ts: pointer to the timespec64 to be set * * Returns the raw monotonic time (completely un-modified by ntp) */ void ktime_get_raw_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->raw_sec; nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(ktime_get_raw_ts64); /** * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres */ int timekeeping_valid_for_hres(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; int ret; do { seq = read_seqcount_begin(&tk_core.seq); ret = tk->tkr_mono.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } /** * timekeeping_max_deferment - Returns max time the clocksource can be deferred */ u64 timekeeping_max_deferment(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 ret; do { seq = read_seqcount_begin(&tk_core.seq); ret = tk->tkr_mono.clock->max_idle_ns; } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } /** * read_persistent_clock64 - Return time from the persistent clock. * @ts: Pointer to the storage for the readout value * * Weak dummy function for arches that do not yet support it. * Reads the time from the battery backed persistent clock. * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported. * * XXX - Do be sure to remove it once all arches implement it. */ void __weak read_persistent_clock64(struct timespec64 *ts) { ts->tv_sec = 0; ts->tv_nsec = 0; } /** * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset * from the boot. * * Weak dummy function for arches that do not yet support it. * @wall_time: - current time as returned by persistent clock * @boot_offset: - offset that is defined as wall_time - boot_time * * The default function calculates offset based on the current value of * local_clock(). This way architectures that support sched_clock() but don't * support dedicated boot time clock will provide the best estimate of the * boot time. */ void __weak __init read_persistent_wall_and_boot_offset(struct timespec64 *wall_time, struct timespec64 *boot_offset) { read_persistent_clock64(wall_time); *boot_offset = ns_to_timespec64(local_clock()); } /* * Flag reflecting whether timekeeping_resume() has injected sleeptime. * * The flag starts of false and is only set when a suspend reaches * timekeeping_suspend(), timekeeping_resume() sets it to false when the * timekeeper clocksource is not stopping across suspend and has been * used to update sleep time. If the timekeeper clocksource has stopped * then the flag stays true and is used by the RTC resume code to decide * whether sleeptime must be injected and if so the flag gets false then. * * If a suspend fails before reaching timekeeping_resume() then the flag * stays false and prevents erroneous sleeptime injection. */ static bool suspend_timing_needed; /* Flag for if there is a persistent clock on this platform */ static bool persistent_clock_exists; /* * timekeeping_init - Initializes the clocksource and common timekeeping values */ void __init timekeeping_init(void) { struct timespec64 wall_time, boot_offset, wall_to_mono; struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *clock; unsigned long flags; read_persistent_wall_and_boot_offset(&wall_time, &boot_offset); if (timespec64_valid_settod(&wall_time) && timespec64_to_ns(&wall_time) > 0) { persistent_clock_exists = true; } else if (timespec64_to_ns(&wall_time) != 0) { pr_warn("Persistent clock returned invalid value"); wall_time = (struct timespec64){0}; } if (timespec64_compare(&wall_time, &boot_offset) < 0) boot_offset = (struct timespec64){0}; /* * We want set wall_to_mono, so the following is true: * wall time + wall_to_mono = boot time */ wall_to_mono = timespec64_sub(boot_offset, wall_time); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); ntp_init(); clock = clocksource_default_clock(); if (clock->enable) clock->enable(clock); tk_setup_internals(tk, clock); tk_set_xtime(tk, &wall_time); tk->raw_sec = 0; tk_set_wall_to_mono(tk, wall_to_mono); timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); } /* time in seconds when suspend began for persistent clock */ static struct timespec64 timekeeping_suspend_time; /** * __timekeeping_inject_sleeptime - Internal function to add sleep interval * @tk: Pointer to the timekeeper to be updated * @delta: Pointer to the delta value in timespec64 format * * Takes a timespec offset measuring a suspend interval and properly * adds the sleep offset to the timekeeping variables. */ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, const struct timespec64 *delta) { if (!timespec64_valid_strict(delta)) { printk_deferred(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid " "sleep delta value!\n"); return; } tk_xtime_add(tk, delta); tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta)); tk_update_sleep_time(tk, timespec64_to_ktime(*delta)); tk_debug_account_sleep_time(delta); } #if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE) /** * We have three kinds of time sources to use for sleep time * injection, the preference order is: * 1) non-stop clocksource * 2) persistent clock (ie: RTC accessible when irqs are off) * 3) RTC * * 1) and 2) are used by timekeeping, 3) by RTC subsystem. * If system has neither 1) nor 2), 3) will be used finally. * * * If timekeeping has injected sleeptime via either 1) or 2), * 3) becomes needless, so in this case we don't need to call * rtc_resume(), and this is what timekeeping_rtc_skipresume() * means. */ bool timekeeping_rtc_skipresume(void) { return !suspend_timing_needed; } /** * 1) can be determined whether to use or not only when doing * timekeeping_resume() which is invoked after rtc_suspend(), * so we can't skip rtc_suspend() surely if system has 1). * * But if system has 2), 2) will definitely be used, so in this * case we don't need to call rtc_suspend(), and this is what * timekeeping_rtc_skipsuspend() means. */ bool timekeeping_rtc_skipsuspend(void) { return persistent_clock_exists; } /** * timekeeping_inject_sleeptime64 - Adds suspend interval to timeekeeping values * @delta: pointer to a timespec64 delta value * * This hook is for architectures that cannot support read_persistent_clock64 * because their RTC/persistent clock is only accessible when irqs are enabled. * and also don't have an effective nonstop clocksource. * * This function should only be called by rtc_resume(), and allows * a suspend offset to be injected into the timekeeping values. */ void timekeeping_inject_sleeptime64(const struct timespec64 *delta) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); suspend_timing_needed = false; timekeeping_forward_now(tk); __timekeeping_inject_sleeptime(tk, delta); timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL | CLOCK_SET_BOOT); } #endif /** * timekeeping_resume - Resumes the generic timekeeping subsystem. */ void timekeeping_resume(void) { struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *clock = tk->tkr_mono.clock; unsigned long flags; struct timespec64 ts_new, ts_delta; u64 cycle_now, nsec; bool inject_sleeptime = false; read_persistent_clock64(&ts_new); clockevents_resume(); clocksource_resume(); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); /* * After system resumes, we need to calculate the suspended time and * compensate it for the OS time. There are 3 sources that could be * used: Nonstop clocksource during suspend, persistent clock and rtc * device. * * One specific platform may have 1 or 2 or all of them, and the * preference will be: * suspend-nonstop clocksource -> persistent clock -> rtc * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ cycle_now = tk_clock_read(&tk->tkr_mono); nsec = clocksource_stop_suspend_timing(clock, cycle_now); if (nsec > 0) { ts_delta = ns_to_timespec64(nsec); inject_sleeptime = true; } else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) { ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time); inject_sleeptime = true; } if (inject_sleeptime) { suspend_timing_needed = false; __timekeeping_inject_sleeptime(tk, &ts_delta); } /* Re-base the last cycle value */ tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; tk->ntp_error = 0; timekeeping_suspended = 0; timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); touch_softlockup_watchdog(); /* Resume the clockevent device(s) and hrtimers */ tick_resume(); /* Notify timerfd as resume is equivalent to clock_was_set() */ timerfd_resume(); } int timekeeping_suspend(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; struct timespec64 delta, delta_delta; static struct timespec64 old_delta; struct clocksource *curr_clock; u64 cycle_now; read_persistent_clock64(&timekeeping_suspend_time); /* * On some systems the persistent_clock can not be detected at * timekeeping_init by its return value, so if we see a valid * value returned, update the persistent_clock_exists flag. */ if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec) persistent_clock_exists = true; suspend_timing_needed = true; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); timekeeping_suspended = 1; /* * Since we've called forward_now, cycle_last stores the value * just read from the current clocksource. Save this to potentially * use in suspend timing. */ curr_clock = tk->tkr_mono.clock; cycle_now = tk->tkr_mono.cycle_last; clocksource_start_suspend_timing(curr_clock, cycle_now); if (persistent_clock_exists) { /* * To avoid drift caused by repeated suspend/resumes, * which each can add ~1 second drift error, * try to compensate so the difference in system time * and persistent_clock time stays close to constant. */ delta = timespec64_sub(tk_xtime(tk), timekeeping_suspend_time); delta_delta = timespec64_sub(delta, old_delta); if (abs(delta_delta.tv_sec) >= 2) { /* * if delta_delta is too large, assume time correction * has occurred and set old_delta to the current delta. */ old_delta = delta; } else { /* Otherwise try to adjust old_system to compensate */ timekeeping_suspend_time = timespec64_add(timekeeping_suspend_time, delta_delta); } } timekeeping_update(tk, TK_MIRROR); halt_fast_timekeeper(tk); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); tick_suspend(); clocksource_suspend(); clockevents_suspend(); return 0; } /* sysfs resume/suspend bits for timekeeping */ static struct syscore_ops timekeeping_syscore_ops = { .resume = timekeeping_resume, .suspend = timekeeping_suspend, }; static int __init timekeeping_init_ops(void) { register_syscore_ops(&timekeeping_syscore_ops); return 0; } device_initcall(timekeeping_init_ops); /* * Apply a multiplier adjustment to the timekeeper */ static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk, s64 offset, s32 mult_adj) { s64 interval = tk->cycle_interval; if (mult_adj == 0) { return; } else if (mult_adj == -1) { interval = -interval; offset = -offset; } else if (mult_adj != 1) { interval *= mult_adj; offset *= mult_adj; } /* * So the following can be confusing. * * To keep things simple, lets assume mult_adj == 1 for now. * * When mult_adj != 1, remember that the interval and offset values * have been appropriately scaled so the math is the same. * * The basic idea here is that we're increasing the multiplier * by one, this causes the xtime_interval to be incremented by * one cycle_interval. This is because: * xtime_interval = cycle_interval * mult * So if mult is being incremented by one: * xtime_interval = cycle_interval * (mult + 1) * Its the same as: * xtime_interval = (cycle_interval * mult) + cycle_interval * Which can be shortened to: * xtime_interval += cycle_interval * * So offset stores the non-accumulated cycles. Thus the current * time (in shifted nanoseconds) is: * now = (offset * adj) + xtime_nsec * Now, even though we're adjusting the clock frequency, we have * to keep time consistent. In other words, we can't jump back * in time, and we also want to avoid jumping forward in time. * * So given the same offset value, we need the time to be the same * both before and after the freq adjustment. * now = (offset * adj_1) + xtime_nsec_1 * now = (offset * adj_2) + xtime_nsec_2 * So: * (offset * adj_1) + xtime_nsec_1 = * (offset * adj_2) + xtime_nsec_2 * And we know: * adj_2 = adj_1 + 1 * So: * (offset * adj_1) + xtime_nsec_1 = * (offset * (adj_1+1)) + xtime_nsec_2 * (offset * adj_1) + xtime_nsec_1 = * (offset * adj_1) + offset + xtime_nsec_2 * Canceling the sides: * xtime_nsec_1 = offset + xtime_nsec_2 * Which gives us: * xtime_nsec_2 = xtime_nsec_1 - offset * Which simplifies to: * xtime_nsec -= offset */ if ((mult_adj > 0) && (tk->tkr_mono.mult + mult_adj < mult_adj)) { /* NTP adjustment caused clocksource mult overflow */ WARN_ON_ONCE(1); return; } tk->tkr_mono.mult += mult_adj; tk->xtime_interval += interval; tk->tkr_mono.xtime_nsec -= offset; } /* * Adjust the timekeeper's multiplier to the correct frequency * and also to reduce the accumulated error value. */ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) { u32 mult; /* * Determine the multiplier from the current NTP tick length. * Avoid expensive division when the tick length doesn't change. */ if (likely(tk->ntp_tick == ntp_tick_length())) { mult = tk->tkr_mono.mult - tk->ntp_err_mult; } else { tk->ntp_tick = ntp_tick_length(); mult = div64_u64((tk->ntp_tick >> tk->ntp_error_shift) - tk->xtime_remainder, tk->cycle_interval); } /* * If the clock is behind the NTP time, increase the multiplier by 1 * to catch up with it. If it's ahead and there was a remainder in the * tick division, the clock will slow down. Otherwise it will stay * ahead until the tick length changes to a non-divisible value. */ tk->ntp_err_mult = tk->ntp_error > 0 ? 1 : 0; mult += tk->ntp_err_mult; timekeeping_apply_adjustment(tk, offset, mult - tk->tkr_mono.mult); if (unlikely(tk->tkr_mono.clock->maxadj && (abs(tk->tkr_mono.mult - tk->tkr_mono.clock->mult) > tk->tkr_mono.clock->maxadj))) { printk_once(KERN_WARNING "Adjusting %s more than 11%% (%ld vs %ld)\n", tk->tkr_mono.clock->name, (long)tk->tkr_mono.mult, (long)tk->tkr_mono.clock->mult + tk->tkr_mono.clock->maxadj); } /* * It may be possible that when we entered this function, xtime_nsec * was very small. Further, if we're slightly speeding the clocksource * in the code above, its possible the required corrective factor to * xtime_nsec could cause it to underflow. * * Now, since we have already accumulated the second and the NTP * subsystem has been notified via second_overflow(), we need to skip * the next update. */ if (unlikely((s64)tk->tkr_mono.xtime_nsec < 0)) { tk->tkr_mono.xtime_nsec += (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec--; tk->skip_second_overflow = 1; } } /* * accumulate_nsecs_to_secs - Accumulates nsecs into secs * * Helper function that accumulates the nsecs greater than a second * from the xtime_nsec field to the xtime_secs field. * It also calls into the NTP code to handle leapsecond processing. */ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk) { u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr_mono.shift; unsigned int clock_set = 0; while (tk->tkr_mono.xtime_nsec >= nsecps) { int leap; tk->tkr_mono.xtime_nsec -= nsecps; tk->xtime_sec++; /* * Skip NTP update if this second was accumulated before, * i.e. xtime_nsec underflowed in timekeeping_adjust() */ if (unlikely(tk->skip_second_overflow)) { tk->skip_second_overflow = 0; continue; } /* Figure out if its a leap sec and apply if needed */ leap = second_overflow(tk->xtime_sec); if (unlikely(leap)) { struct timespec64 ts; tk->xtime_sec += leap; ts.tv_sec = leap; ts.tv_nsec = 0; tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts)); __timekeeping_set_tai_offset(tk, tk->tai_offset - leap); clock_set = TK_CLOCK_WAS_SET; } } return clock_set; } /* * logarithmic_accumulation - shifted accumulation of cycles * * This functions accumulates a shifted interval of cycles into * a shifted interval nanoseconds. Allows for O(log) accumulation * loop. * * Returns the unconsumed cycles. */ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, u32 shift, unsigned int *clock_set) { u64 interval = tk->cycle_interval << shift; u64 snsec_per_sec; /* If the offset is smaller than a shifted interval, do nothing */ if (offset < interval) return offset; /* Accumulate one shifted interval */ offset -= interval; tk->tkr_mono.cycle_last += interval; tk->tkr_raw.cycle_last += interval; tk->tkr_mono.xtime_nsec += tk->xtime_interval << shift; *clock_set |= accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ tk->tkr_raw.xtime_nsec += tk->raw_interval << shift; snsec_per_sec = (u64)NSEC_PER_SEC << tk->tkr_raw.shift; while (tk->tkr_raw.xtime_nsec >= snsec_per_sec) { tk->tkr_raw.xtime_nsec -= snsec_per_sec; tk->raw_sec++; } /* Accumulate error between NTP and clock interval */ tk->ntp_error += tk->ntp_tick << shift; tk->ntp_error -= (tk->xtime_interval + tk->xtime_remainder) << (tk->ntp_error_shift + shift); return offset; } /* * timekeeping_advance - Updates the timekeeper to the current time and * current NTP tick length */ static bool timekeeping_advance(enum timekeeping_adv_mode mode) { struct timekeeper *real_tk = &tk_core.timekeeper; struct timekeeper *tk = &shadow_timekeeper; u64 offset; int shift = 0, maxshift; unsigned int clock_set = 0; unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); /* Make sure we're fully resumed: */ if (unlikely(timekeeping_suspended)) goto out; offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), tk->tkr_mono.cycle_last, tk->tkr_mono.mask); /* Check if there's really nothing to do */ if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) goto out; /* Do some additional sanity checking */ timekeeping_check_update(tk, offset); /* * With NO_HZ we may have to accumulate many cycle_intervals * (think "ticks") worth of time at once. To do this efficiently, * we calculate the largest doubling multiple of cycle_intervals * that is smaller than the offset. We then accumulate that * chunk in one go, and then try to consume the next smaller * doubled multiple. */ shift = ilog2(offset) - ilog2(tk->cycle_interval); shift = max(0, shift); /* Bound shift to one less than what overflows tick_length */ maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1; shift = min(shift, maxshift); while (offset >= tk->cycle_interval) { offset = logarithmic_accumulation(tk, offset, shift, &clock_set); if (offset < tk->cycle_interval<<shift) shift--; } /* Adjust the multiplier to correct NTP error */ timekeeping_adjust(tk, offset); /* * Finally, make sure that after the rounding * xtime_nsec isn't larger than NSEC_PER_SEC */ clock_set |= accumulate_nsecs_to_secs(tk); write_seqcount_begin(&tk_core.seq); /* * Update the real timekeeper. * * We could avoid this memcpy by switching pointers, but that * requires changes to all other timekeeper usage sites as * well, i.e. move the timekeeper pointer getter into the * spinlocked/seqcount protected sections. And we trade this * memcpy under the tk_core.seq against one before we start * updating. */ timekeeping_update(tk, clock_set); memcpy(real_tk, tk, sizeof(*tk)); /* The memcpy must come last. Do not put anything here! */ write_seqcount_end(&tk_core.seq); out: raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return !!clock_set; } /** * update_wall_time - Uses the current clocksource to increment the wall time * */ void update_wall_time(void) { if (timekeeping_advance(TK_ADV_TICK)) clock_was_set_delayed(); } /** * getboottime64 - Return the real time of system boot. * @ts: pointer to the timespec64 to be set * * Returns the wall-time of boot in a timespec64. * * This is based on the wall_to_monotonic offset and the total suspend * time. Calls to settimeofday will affect the value returned (which * basically means that however wrong your real time clock is at boot time, * you get the right time here). */ void getboottime64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot); *ts = ktime_to_timespec64(t); } EXPORT_SYMBOL_GPL(getboottime64); void ktime_get_coarse_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); *ts = tk_xtime(tk); } while (read_seqcount_retry(&tk_core.seq, seq)); } EXPORT_SYMBOL(ktime_get_coarse_real_ts64); void ktime_get_coarse_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 now, mono; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); now = tk_xtime(tk); mono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); set_normalized_timespec64(ts, now.tv_sec + mono.tv_sec, now.tv_nsec + mono.tv_nsec); } EXPORT_SYMBOL(ktime_get_coarse_ts64); /* * Must hold jiffies_lock */ void do_timer(unsigned long ticks) { jiffies_64 += ticks; calc_global_load(); } /** * ktime_get_update_offsets_now - hrtimer helper * @cwsseq: pointer to check and store the clock was set sequence number * @offs_real: pointer to storage for monotonic -> realtime offset * @offs_boot: pointer to storage for monotonic -> boottime offset * @offs_tai: pointer to storage for monotonic -> clock tai offset * * Returns current monotonic time and updates the offsets if the * sequence number in @cwsseq and timekeeper.clock_was_set_seq are * different. * * Called from hrtimer_interrupt() or retrigger_next_event() */ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, ktime_t *offs_boot, ktime_t *offs_tai) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); base = ktime_add_ns(base, nsecs); if (*cwsseq != tk->clock_was_set_seq) { *cwsseq = tk->clock_was_set_seq; *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; *offs_tai = tk->offs_tai; } /* Handle leapsecond insertion adjustments */ if (unlikely(base >= tk->next_leap_ktime)) *offs_real = ktime_sub(tk->offs_real, ktime_set(1, 0)); } while (read_seqcount_retry(&tk_core.seq, seq)); return base; } /* * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex */ static int timekeeping_validate_timex(const struct __kernel_timex *txc) { if (txc->modes & ADJ_ADJTIME) { /* singleshot must not be used with any other mode bits */ if (!(txc->modes & ADJ_OFFSET_SINGLESHOT)) return -EINVAL; if (!(txc->modes & ADJ_OFFSET_READONLY) && !capable(CAP_SYS_TIME)) return -EPERM; } else { /* In order to modify anything, you gotta be super-user! */ if (txc->modes && !capable(CAP_SYS_TIME)) return -EPERM; /* * if the quartz is off by more than 10% then * something is VERY wrong! */ if (txc->modes & ADJ_TICK && (txc->tick < 900000/USER_HZ || txc->tick > 1100000/USER_HZ)) return -EINVAL; } if (txc->modes & ADJ_SETOFFSET) { /* In order to inject time, you gotta be super-user! */ if (!capable(CAP_SYS_TIME)) return -EPERM; /* * Validate if a timespec/timeval used to inject a time * offset is valid. Offsets can be positive or negative, so * we don't check tv_sec. The value of the timeval/timespec * is the sum of its fields,but *NOTE*: * The field tv_usec/tv_nsec must always be non-negative and * we can't have more nanoseconds/microseconds than a second. */ if (txc->time.tv_usec < 0) return -EINVAL; if (txc->modes & ADJ_NANO) { if (txc->time.tv_usec >= NSEC_PER_SEC) return -EINVAL; } else { if (txc->time.tv_usec >= USEC_PER_SEC) return -EINVAL; } } /* * Check for potential multiplication overflows that can * only happen on 64-bit systems: */ if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) { if (LLONG_MIN / PPM_SCALE > txc->freq) return -EINVAL; if (LLONG_MAX / PPM_SCALE < txc->freq) return -EINVAL; } return 0; } /** * random_get_entropy_fallback - Returns the raw clock source value, * used by random.c for platforms with no valid random_get_entropy(). */ unsigned long random_get_entropy_fallback(void) { struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono; struct clocksource *clock = READ_ONCE(tkr->clock); if (unlikely(timekeeping_suspended || !clock)) return 0; return clock->read(clock); } EXPORT_SYMBOL_GPL(random_get_entropy_fallback); /** * do_adjtimex() - Accessor function to NTP __do_adjtimex function */ int do_adjtimex(struct __kernel_timex *txc) { struct timekeeper *tk = &tk_core.timekeeper; struct audit_ntp_data ad; bool clock_set = false; struct timespec64 ts; unsigned long flags; s32 orig_tai, tai; int ret; /* Validate the data before disabling interrupts */ ret = timekeeping_validate_timex(txc); if (ret) return ret; add_device_randomness(txc, sizeof(*txc)); if (txc->modes & ADJ_SETOFFSET) { struct timespec64 delta; delta.tv_sec = txc->time.tv_sec; delta.tv_nsec = txc->time.tv_usec; if (!(txc->modes & ADJ_NANO)) delta.tv_nsec *= 1000; ret = timekeeping_inject_offset(&delta); if (ret) return ret; audit_tk_injoffset(delta); } audit_ntp_init(&ad); ktime_get_real_ts64(&ts); add_device_randomness(&ts, sizeof(ts)); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); orig_tai = tai = tk->tai_offset; ret = __do_adjtimex(txc, &ts, &tai, &ad); if (tai != orig_tai) { __timekeeping_set_tai_offset(tk, tai); timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); clock_set = true; } tk_update_leap_state(tk); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); audit_ntp_log(&ad); /* Update the multiplier immediately if frequency was set directly */ if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK)) clock_set |= timekeeping_advance(TK_ADV_FREQ); if (clock_set) clock_was_set(CLOCK_SET_WALL); ntp_notify_cmos_timer(); return ret; } #ifdef CONFIG_NTP_PPS /** * hardpps() - Accessor function to NTP __hardpps function */ void hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts) { unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); __hardpps(phase_ts, raw_ts); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); } EXPORT_SYMBOL(hardpps); #endif /* CONFIG_NTP_PPS */ |
| 999 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* Connection tracking via netlink socket. Allows for user space * protocol helpers and general trouble making from userspace. * * (C) 2001 by Jay Schulist <jschlst@samba.org> * (C) 2002-2006 by Harald Welte <laforge@gnumonks.org> * (C) 2003 by Patrick Mchardy <kaber@trash.net> * (C) 2005-2012 by Pablo Neira Ayuso <pablo@netfilter.org> * * Initial connection tracking via netlink development funded and * generally made possible by Network Robots, Inc. (www.networkrobots.com) * * Further development of this code funded by Astaro AG (http://www.astaro.com) * * This software may be used and distributed according to the terms * of the GNU General Public License, incorporated herein by reference. */ #include <linux/init.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/rculist.h> #include <linux/rculist_nulls.h> #include <linux/types.h> #include <linux/timer.h> #include <linux/security.h> #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/netlink.h> #include <linux/spinlock.h> #include <linux/interrupt.h> #include <linux/slab.h> #include <linux/siphash.h> #include <linux/netfilter.h> #include <net/netlink.h> #include <net/sock.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_expect.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_tuple.h> #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_timestamp.h> #include <net/netfilter/nf_conntrack_labels.h> #include <net/netfilter/nf_conntrack_synproxy.h> #if IS_ENABLED(CONFIG_NF_NAT) #include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_helper.h> #endif #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> #include "nf_internals.h" MODULE_LICENSE("GPL"); struct ctnetlink_list_dump_ctx { struct nf_conn *last; unsigned int cpu; bool done; }; static int ctnetlink_dump_tuples_proto(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l4proto *l4proto) { int ret = 0; struct nlattr *nest_parms; nest_parms = nla_nest_start(skb, CTA_TUPLE_PROTO); if (!nest_parms) goto nla_put_failure; if (nla_put_u8(skb, CTA_PROTO_NUM, tuple->dst.protonum)) goto nla_put_failure; if (likely(l4proto->tuple_to_nlattr)) ret = l4proto->tuple_to_nlattr(skb, tuple); nla_nest_end(skb, nest_parms); return ret; nla_put_failure: return -1; } static int ipv4_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { if (nla_put_in_addr(skb, CTA_IP_V4_SRC, tuple->src.u3.ip) || nla_put_in_addr(skb, CTA_IP_V4_DST, tuple->dst.u3.ip)) return -EMSGSIZE; return 0; } static int ipv6_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { if (nla_put_in6_addr(skb, CTA_IP_V6_SRC, &tuple->src.u3.in6) || nla_put_in6_addr(skb, CTA_IP_V6_DST, &tuple->dst.u3.in6)) return -EMSGSIZE; return 0; } static int ctnetlink_dump_tuples_ip(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { int ret = 0; struct nlattr *nest_parms; nest_parms = nla_nest_start(skb, CTA_TUPLE_IP); if (!nest_parms) goto nla_put_failure; switch (tuple->src.l3num) { case NFPROTO_IPV4: ret = ipv4_tuple_to_nlattr(skb, tuple); break; case NFPROTO_IPV6: ret = ipv6_tuple_to_nlattr(skb, tuple); break; } nla_nest_end(skb, nest_parms); return ret; nla_put_failure: return -1; } static int ctnetlink_dump_tuples(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { const struct nf_conntrack_l4proto *l4proto; int ret; rcu_read_lock(); ret = ctnetlink_dump_tuples_ip(skb, tuple); if (ret >= 0) { l4proto = nf_ct_l4proto_find(tuple->dst.protonum); ret = ctnetlink_dump_tuples_proto(skb, tuple, l4proto); } rcu_read_unlock(); return ret; } static int ctnetlink_dump_zone_id(struct sk_buff *skb, int attrtype, const struct nf_conntrack_zone *zone, int dir) { if (zone->id == NF_CT_DEFAULT_ZONE_ID || zone->dir != dir) return 0; if (nla_put_be16(skb, attrtype, htons(zone->id))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int ctnetlink_dump_status(struct sk_buff *skb, const struct nf_conn *ct) { if (nla_put_be32(skb, CTA_STATUS, htonl(ct->status))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int ctnetlink_dump_timeout(struct sk_buff *skb, const struct nf_conn *ct, bool skip_zero) { long timeout; if (nf_ct_is_confirmed(ct)) timeout = nf_ct_expires(ct) / HZ; else timeout = ct->timeout / HZ; if (skip_zero && timeout == 0) return 0; if (nla_put_be32(skb, CTA_TIMEOUT, htonl(timeout))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int ctnetlink_dump_protoinfo(struct sk_buff *skb, struct nf_conn *ct, bool destroy) { const struct nf_conntrack_l4proto *l4proto; struct nlattr *nest_proto; int ret; l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); if (!l4proto->to_nlattr) return 0; nest_proto = nla_nest_start(skb, CTA_PROTOINFO); if (!nest_proto) goto nla_put_failure; ret = l4proto->to_nlattr(skb, nest_proto, ct, destroy); nla_nest_end(skb, nest_proto); return ret; nla_put_failure: return -1; } static int ctnetlink_dump_helpinfo(struct sk_buff *skb, const struct nf_conn *ct) { struct nlattr *nest_helper; const struct nf_conn_help *help = nfct_help(ct); struct nf_conntrack_helper *helper; if (!help) return 0; rcu_read_lock(); helper = rcu_dereference(help->helper); if (!helper) goto out; nest_helper = nla_nest_start(skb, CTA_HELP); if (!nest_helper) goto nla_put_failure; if (nla_put_string(skb, CTA_HELP_NAME, helper->name)) goto nla_put_failure; if (helper->to_nlattr) helper->to_nlattr(skb, ct); nla_nest_end(skb, nest_helper); out: rcu_read_unlock(); return 0; nla_put_failure: rcu_read_unlock(); return -1; } static int dump_counters(struct sk_buff *skb, struct nf_conn_acct *acct, enum ip_conntrack_dir dir, int type) { enum ctattr_type attr = dir ? CTA_COUNTERS_REPLY: CTA_COUNTERS_ORIG; struct nf_conn_counter *counter = acct->counter; struct nlattr *nest_count; u64 pkts, bytes; if (type == IPCTNL_MSG_CT_GET_CTRZERO) { pkts = atomic64_xchg(&counter[dir].packets, 0); bytes = atomic64_xchg(&counter[dir].bytes, 0); } else { pkts = atomic64_read(&counter[dir].packets); bytes = atomic64_read(&counter[dir].bytes); } nest_count = nla_nest_start(skb, attr); if (!nest_count) goto nla_put_failure; if (nla_put_be64(skb, CTA_COUNTERS_PACKETS, cpu_to_be64(pkts), CTA_COUNTERS_PAD) || nla_put_be64(skb, CTA_COUNTERS_BYTES, cpu_to_be64(bytes), CTA_COUNTERS_PAD)) goto nla_put_failure; nla_nest_end(skb, nest_count); return 0; nla_put_failure: return -1; } static int ctnetlink_dump_acct(struct sk_buff *skb, const struct nf_conn *ct, int type) { struct nf_conn_acct *acct = nf_conn_acct_find(ct); if (!acct) return 0; if (dump_counters(skb, acct, IP_CT_DIR_ORIGINAL, type) < 0) return -1; if (dump_counters(skb, acct, IP_CT_DIR_REPLY, type) < 0) return -1; return 0; } static int ctnetlink_dump_timestamp(struct sk_buff *skb, const struct nf_conn *ct) { struct nlattr *nest_count; const struct nf_conn_tstamp *tstamp; tstamp = nf_conn_tstamp_find(ct); if (!tstamp) return 0; nest_count = nla_nest_start(skb, CTA_TIMESTAMP); if (!nest_count) goto nla_put_failure; if (nla_put_be64(skb, CTA_TIMESTAMP_START, cpu_to_be64(tstamp->start), CTA_TIMESTAMP_PAD) || (tstamp->stop != 0 && nla_put_be64(skb, CTA_TIMESTAMP_STOP, cpu_to_be64(tstamp->stop), CTA_TIMESTAMP_PAD))) goto nla_put_failure; nla_nest_end(skb, nest_count); return 0; nla_put_failure: return -1; } #ifdef CONFIG_NF_CONNTRACK_MARK static int ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct, bool dump) { u32 mark = READ_ONCE(ct->mark); if (!mark && !dump) return 0; if (nla_put_be32(skb, CTA_MARK, htonl(mark))) goto nla_put_failure; return 0; nla_put_failure: return -1; } #else #define ctnetlink_dump_mark(a, b, c) (0) #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK static int ctnetlink_dump_secctx(struct sk_buff *skb, const struct nf_conn *ct) { struct nlattr *nest_secctx; int len, ret; char *secctx; ret = security_secid_to_secctx(ct->secmark, &secctx, &len); if (ret) return 0; ret = -1; nest_secctx = nla_nest_start(skb, CTA_SECCTX); if (!nest_secctx) goto nla_put_failure; if (nla_put_string(skb, CTA_SECCTX_NAME, secctx)) goto nla_put_failure; nla_nest_end(skb, nest_secctx); ret = 0; nla_put_failure: security_release_secctx(secctx, len); return ret; } #else #define ctnetlink_dump_secctx(a, b) (0) #endif #ifdef CONFIG_NF_CONNTRACK_EVENTS static inline int ctnetlink_label_size(const struct nf_conn *ct) { struct nf_conn_labels *labels = nf_ct_labels_find(ct); if (!labels) return 0; return nla_total_size(sizeof(labels->bits)); } #endif static int ctnetlink_dump_labels(struct sk_buff *skb, const struct nf_conn *ct) { struct nf_conn_labels *labels = nf_ct_labels_find(ct); unsigned int i; if (!labels) return 0; i = 0; do { if (labels->bits[i] != 0) return nla_put(skb, CTA_LABELS, sizeof(labels->bits), labels->bits); i++; } while (i < ARRAY_SIZE(labels->bits)); return 0; } #define master_tuple(ct) &(ct->master->tuplehash[IP_CT_DIR_ORIGINAL].tuple) static int ctnetlink_dump_master(struct sk_buff *skb, const struct nf_conn *ct) { struct nlattr *nest_parms; if (!(ct->status & IPS_EXPECTED)) return 0; nest_parms = nla_nest_start(skb, CTA_TUPLE_MASTER); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, master_tuple(ct)) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); return 0; nla_put_failure: return -1; } static int dump_ct_seq_adj(struct sk_buff *skb, const struct nf_ct_seqadj *seq, int type) { struct nlattr *nest_parms; nest_parms = nla_nest_start(skb, type); if (!nest_parms) goto nla_put_failure; if (nla_put_be32(skb, CTA_SEQADJ_CORRECTION_POS, htonl(seq->correction_pos)) || nla_put_be32(skb, CTA_SEQADJ_OFFSET_BEFORE, htonl(seq->offset_before)) || nla_put_be32(skb, CTA_SEQADJ_OFFSET_AFTER, htonl(seq->offset_after))) goto nla_put_failure; nla_nest_end(skb, nest_parms); return 0; nla_put_failure: return -1; } static int ctnetlink_dump_ct_seq_adj(struct sk_buff *skb, struct nf_conn *ct) { struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); struct nf_ct_seqadj *seq; if (!(ct->status & IPS_SEQ_ADJUST) || !seqadj) return 0; spin_lock_bh(&ct->lock); seq = &seqadj->seq[IP_CT_DIR_ORIGINAL]; if (dump_ct_seq_adj(skb, seq, CTA_SEQ_ADJ_ORIG) == -1) goto err; seq = &seqadj->seq[IP_CT_DIR_REPLY]; if (dump_ct_seq_adj(skb, seq, CTA_SEQ_ADJ_REPLY) == -1) goto err; spin_unlock_bh(&ct->lock); return 0; err: spin_unlock_bh(&ct->lock); return -1; } static int ctnetlink_dump_ct_synproxy(struct sk_buff *skb, struct nf_conn *ct) { struct nf_conn_synproxy *synproxy = nfct_synproxy(ct); struct nlattr *nest_parms; if (!synproxy) return 0; nest_parms = nla_nest_start(skb, CTA_SYNPROXY); if (!nest_parms) goto nla_put_failure; if (nla_put_be32(skb, CTA_SYNPROXY_ISN, htonl(synproxy->isn)) || nla_put_be32(skb, CTA_SYNPROXY_ITS, htonl(synproxy->its)) || nla_put_be32(skb, CTA_SYNPROXY_TSOFF, htonl(synproxy->tsoff))) goto nla_put_failure; nla_nest_end(skb, nest_parms); return 0; nla_put_failure: return -1; } static int ctnetlink_dump_id(struct sk_buff *skb, const struct nf_conn *ct) { __be32 id = (__force __be32)nf_ct_get_id(ct); if (nla_put_be32(skb, CTA_ID, id)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int ctnetlink_dump_use(struct sk_buff *skb, const struct nf_conn *ct) { if (nla_put_be32(skb, CTA_USE, htonl(refcount_read(&ct->ct_general.use)))) goto nla_put_failure; return 0; nla_put_failure: return -1; } /* all these functions access ct->ext. Caller must either hold a reference * on ct or prevent its deletion by holding either the bucket spinlock or * pcpu dying list lock. */ static int ctnetlink_dump_extinfo(struct sk_buff *skb, struct nf_conn *ct, u32 type) { if (ctnetlink_dump_acct(skb, ct, type) < 0 || ctnetlink_dump_timestamp(skb, ct) < 0 || ctnetlink_dump_helpinfo(skb, ct) < 0 || ctnetlink_dump_labels(skb, ct) < 0 || ctnetlink_dump_ct_seq_adj(skb, ct) < 0 || ctnetlink_dump_ct_synproxy(skb, ct) < 0) return -1; return 0; } static int ctnetlink_dump_info(struct sk_buff *skb, struct nf_conn *ct) { if (ctnetlink_dump_status(skb, ct) < 0 || ctnetlink_dump_mark(skb, ct, true) < 0 || ctnetlink_dump_secctx(skb, ct) < 0 || ctnetlink_dump_id(skb, ct) < 0 || ctnetlink_dump_use(skb, ct) < 0 || ctnetlink_dump_master(skb, ct) < 0) return -1; if (!test_bit(IPS_OFFLOAD_BIT, &ct->status) && (ctnetlink_dump_timeout(skb, ct, false) < 0 || ctnetlink_dump_protoinfo(skb, ct, false) < 0)) return -1; return 0; } static int ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, struct nf_conn *ct, bool extinfo, unsigned int flags) { const struct nf_conntrack_zone *zone; struct nlmsghdr *nlh; struct nlattr *nest_parms; unsigned int event; if (portid) flags |= NLM_F_MULTI; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_NEW); nlh = nfnl_msg_put(skb, portid, seq, event, flags, nf_ct_l3num(ct), NFNETLINK_V0, 0); if (!nlh) goto nlmsg_failure; zone = nf_ct_zone(ct); nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_ORIG) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_REPL) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); if (ctnetlink_dump_zone_id(skb, CTA_ZONE, zone, NF_CT_DEFAULT_ZONE_DIR) < 0) goto nla_put_failure; if (ctnetlink_dump_info(skb, ct) < 0) goto nla_put_failure; if (extinfo && ctnetlink_dump_extinfo(skb, ct, type) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); return skb->len; nlmsg_failure: nla_put_failure: nlmsg_cancel(skb, nlh); return -1; } static const struct nla_policy cta_ip_nla_policy[CTA_IP_MAX + 1] = { [CTA_IP_V4_SRC] = { .type = NLA_U32 }, [CTA_IP_V4_DST] = { .type = NLA_U32 }, [CTA_IP_V6_SRC] = { .len = sizeof(__be32) * 4 }, [CTA_IP_V6_DST] = { .len = sizeof(__be32) * 4 }, }; #if defined(CONFIG_NETFILTER_NETLINK_GLUE_CT) || defined(CONFIG_NF_CONNTRACK_EVENTS) static size_t ctnetlink_proto_size(const struct nf_conn *ct) { const struct nf_conntrack_l4proto *l4proto; size_t len, len4 = 0; len = nla_policy_len(cta_ip_nla_policy, CTA_IP_MAX + 1); len *= 3u; /* ORIG, REPLY, MASTER */ l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); len += l4proto->nlattr_size; if (l4proto->nlattr_tuple_size) { len4 = l4proto->nlattr_tuple_size(); len4 *= 3u; /* ORIG, REPLY, MASTER */ } return len + len4; } #endif static inline size_t ctnetlink_acct_size(const struct nf_conn *ct) { if (!nf_ct_ext_exist(ct, NF_CT_EXT_ACCT)) return 0; return 2 * nla_total_size(0) /* CTA_COUNTERS_ORIG|REPL */ + 2 * nla_total_size_64bit(sizeof(uint64_t)) /* CTA_COUNTERS_PACKETS */ + 2 * nla_total_size_64bit(sizeof(uint64_t)) /* CTA_COUNTERS_BYTES */ ; } static inline int ctnetlink_secctx_size(const struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_SECMARK int len, ret; ret = security_secid_to_secctx(ct->secmark, NULL, &len); if (ret) return 0; return nla_total_size(0) /* CTA_SECCTX */ + nla_total_size(sizeof(char) * len); /* CTA_SECCTX_NAME */ #else return 0; #endif } static inline size_t ctnetlink_timestamp_size(const struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP if (!nf_ct_ext_exist(ct, NF_CT_EXT_TSTAMP)) return 0; return nla_total_size(0) + 2 * nla_total_size_64bit(sizeof(uint64_t)); #else return 0; #endif } #ifdef CONFIG_NF_CONNTRACK_EVENTS static size_t ctnetlink_nlmsg_size(const struct nf_conn *ct) { return NLMSG_ALIGN(sizeof(struct nfgenmsg)) + 3 * nla_total_size(0) /* CTA_TUPLE_ORIG|REPL|MASTER */ + 3 * nla_total_size(0) /* CTA_TUPLE_IP */ + 3 * nla_total_size(0) /* CTA_TUPLE_PROTO */ + 3 * nla_total_size(sizeof(u_int8_t)) /* CTA_PROTO_NUM */ + nla_total_size(sizeof(u_int32_t)) /* CTA_ID */ + nla_total_size(sizeof(u_int32_t)) /* CTA_STATUS */ + ctnetlink_acct_size(ct) + ctnetlink_timestamp_size(ct) + nla_total_size(sizeof(u_int32_t)) /* CTA_TIMEOUT */ + nla_total_size(0) /* CTA_PROTOINFO */ + nla_total_size(0) /* CTA_HELP */ + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */ + ctnetlink_secctx_size(ct) #if IS_ENABLED(CONFIG_NF_NAT) + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */ + 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */ #endif #ifdef CONFIG_NF_CONNTRACK_MARK + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */ #endif #ifdef CONFIG_NF_CONNTRACK_ZONES + nla_total_size(sizeof(u_int16_t)) /* CTA_ZONE|CTA_TUPLE_ZONE */ #endif + ctnetlink_proto_size(ct) + ctnetlink_label_size(ct) ; } static int ctnetlink_conntrack_event(unsigned int events, const struct nf_ct_event *item) { const struct nf_conntrack_zone *zone; struct net *net; struct nlmsghdr *nlh; struct nlattr *nest_parms; struct nf_conn *ct = item->ct; struct sk_buff *skb; unsigned int type; unsigned int flags = 0, group; int err; if (events & (1 << IPCT_DESTROY)) { type = IPCTNL_MSG_CT_DELETE; group = NFNLGRP_CONNTRACK_DESTROY; } else if (events & ((1 << IPCT_NEW) | (1 << IPCT_RELATED))) { type = IPCTNL_MSG_CT_NEW; flags = NLM_F_CREATE|NLM_F_EXCL; group = NFNLGRP_CONNTRACK_NEW; } else if (events) { type = IPCTNL_MSG_CT_NEW; group = NFNLGRP_CONNTRACK_UPDATE; } else return 0; net = nf_ct_net(ct); if (!item->report && !nfnetlink_has_listeners(net, group)) return 0; skb = nlmsg_new(ctnetlink_nlmsg_size(ct), GFP_ATOMIC); if (skb == NULL) goto errout; type = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, type); nlh = nfnl_msg_put(skb, item->portid, 0, type, flags, nf_ct_l3num(ct), NFNETLINK_V0, 0); if (!nlh) goto nlmsg_failure; zone = nf_ct_zone(ct); nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_ORIG) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_REPL) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); if (ctnetlink_dump_zone_id(skb, CTA_ZONE, zone, NF_CT_DEFAULT_ZONE_DIR) < 0) goto nla_put_failure; if (ctnetlink_dump_id(skb, ct) < 0) goto nla_put_failure; if (ctnetlink_dump_status(skb, ct) < 0) goto nla_put_failure; if (events & (1 << IPCT_DESTROY)) { if (ctnetlink_dump_timeout(skb, ct, true) < 0) goto nla_put_failure; if (ctnetlink_dump_acct(skb, ct, type) < 0 || ctnetlink_dump_timestamp(skb, ct) < 0 || ctnetlink_dump_protoinfo(skb, ct, true) < 0) goto nla_put_failure; } else { if (ctnetlink_dump_timeout(skb, ct, false) < 0) goto nla_put_failure; if (events & (1 << IPCT_PROTOINFO) && ctnetlink_dump_protoinfo(skb, ct, false) < 0) goto nla_put_failure; if ((events & (1 << IPCT_HELPER) || nfct_help(ct)) && ctnetlink_dump_helpinfo(skb, ct) < 0) goto nla_put_failure; #ifdef CONFIG_NF_CONNTRACK_SECMARK if ((events & (1 << IPCT_SECMARK) || ct->secmark) && ctnetlink_dump_secctx(skb, ct) < 0) goto nla_put_failure; #endif if (events & (1 << IPCT_LABEL) && ctnetlink_dump_labels(skb, ct) < 0) goto nla_put_failure; if (events & (1 << IPCT_RELATED) && ctnetlink_dump_master(skb, ct) < 0) goto nla_put_failure; if (events & (1 << IPCT_SEQADJ) && ctnetlink_dump_ct_seq_adj(skb, ct) < 0) goto nla_put_failure; if (events & (1 << IPCT_SYNPROXY) && ctnetlink_dump_ct_synproxy(skb, ct) < 0) goto nla_put_failure; } #ifdef CONFIG_NF_CONNTRACK_MARK if (ctnetlink_dump_mark(skb, ct, events & (1 << IPCT_MARK))) goto nla_put_failure; #endif nlmsg_end(skb, nlh); err = nfnetlink_send(skb, net, item->portid, group, item->report, GFP_ATOMIC); if (err == -ENOBUFS || err == -EAGAIN) return -ENOBUFS; return 0; nla_put_failure: nlmsg_cancel(skb, nlh); nlmsg_failure: kfree_skb(skb); errout: if (nfnetlink_set_err(net, 0, group, -ENOBUFS) > 0) return -ENOBUFS; return 0; } #endif /* CONFIG_NF_CONNTRACK_EVENTS */ static int ctnetlink_done(struct netlink_callback *cb) { if (cb->args[1]) nf_ct_put((struct nf_conn *)cb->args[1]); kfree(cb->data); return 0; } struct ctnetlink_filter_u32 { u32 val; u32 mask; }; struct ctnetlink_filter { u8 family; u_int32_t orig_flags; u_int32_t reply_flags; struct nf_conntrack_tuple orig; struct nf_conntrack_tuple reply; struct nf_conntrack_zone zone; struct ctnetlink_filter_u32 mark; struct ctnetlink_filter_u32 status; }; static const struct nla_policy cta_filter_nla_policy[CTA_FILTER_MAX + 1] = { [CTA_FILTER_ORIG_FLAGS] = { .type = NLA_U32 }, [CTA_FILTER_REPLY_FLAGS] = { .type = NLA_U32 }, }; static int ctnetlink_parse_filter(const struct nlattr *attr, struct ctnetlink_filter *filter) { struct nlattr *tb[CTA_FILTER_MAX + 1]; int ret = 0; ret = nla_parse_nested(tb, CTA_FILTER_MAX, attr, cta_filter_nla_policy, NULL); if (ret) return ret; if (tb[CTA_FILTER_ORIG_FLAGS]) { filter->orig_flags = nla_get_u32(tb[CTA_FILTER_ORIG_FLAGS]); if (filter->orig_flags & ~CTA_FILTER_F_ALL) return -EOPNOTSUPP; } if (tb[CTA_FILTER_REPLY_FLAGS]) { filter->reply_flags = nla_get_u32(tb[CTA_FILTER_REPLY_FLAGS]); if (filter->reply_flags & ~CTA_FILTER_F_ALL) return -EOPNOTSUPP; } return 0; } static int ctnetlink_parse_zone(const struct nlattr *attr, struct nf_conntrack_zone *zone); static int ctnetlink_parse_tuple_filter(const struct nlattr * const cda[], struct nf_conntrack_tuple *tuple, u32 type, u_int8_t l3num, struct nf_conntrack_zone *zone, u_int32_t flags); static int ctnetlink_filter_parse_mark(struct ctnetlink_filter_u32 *mark, const struct nlattr * const cda[]) { #ifdef CONFIG_NF_CONNTRACK_MARK if (cda[CTA_MARK]) { mark->val = ntohl(nla_get_be32(cda[CTA_MARK])); if (cda[CTA_MARK_MASK]) mark->mask = ntohl(nla_get_be32(cda[CTA_MARK_MASK])); else mark->mask = 0xffffffff; } else if (cda[CTA_MARK_MASK]) { return -EINVAL; } #endif return 0; } static int ctnetlink_filter_parse_status(struct ctnetlink_filter_u32 *status, const struct nlattr * const cda[]) { if (cda[CTA_STATUS]) { status->val = ntohl(nla_get_be32(cda[CTA_STATUS])); if (cda[CTA_STATUS_MASK]) status->mask = ntohl(nla_get_be32(cda[CTA_STATUS_MASK])); else status->mask = status->val; /* status->val == 0? always true, else always false. */ if (status->mask == 0) return -EINVAL; } else if (cda[CTA_STATUS_MASK]) { return -EINVAL; } /* CTA_STATUS is NLA_U32, if this fires UAPI needs to be extended */ BUILD_BUG_ON(__IPS_MAX_BIT >= 32); return 0; } static struct ctnetlink_filter * ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) { struct ctnetlink_filter *filter; int err; #ifndef CONFIG_NF_CONNTRACK_MARK if (cda[CTA_MARK] || cda[CTA_MARK_MASK]) return ERR_PTR(-EOPNOTSUPP); #endif filter = kzalloc(sizeof(*filter), GFP_KERNEL); if (filter == NULL) return ERR_PTR(-ENOMEM); filter->family = family; err = ctnetlink_filter_parse_mark(&filter->mark, cda); if (err) goto err_filter; err = ctnetlink_filter_parse_status(&filter->status, cda); if (err) goto err_filter; if (!cda[CTA_FILTER]) return filter; err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone); if (err < 0) goto err_filter; err = ctnetlink_parse_filter(cda[CTA_FILTER], filter); if (err < 0) goto err_filter; if (filter->orig_flags) { if (!cda[CTA_TUPLE_ORIG]) { err = -EINVAL; goto err_filter; } err = ctnetlink_parse_tuple_filter(cda, &filter->orig, CTA_TUPLE_ORIG, filter->family, &filter->zone, filter->orig_flags); if (err < 0) goto err_filter; } if (filter->reply_flags) { if (!cda[CTA_TUPLE_REPLY]) { err = -EINVAL; goto err_filter; } err = ctnetlink_parse_tuple_filter(cda, &filter->reply, CTA_TUPLE_REPLY, filter->family, &filter->zone, filter->reply_flags); if (err < 0) goto err_filter; } return filter; err_filter: kfree(filter); return ERR_PTR(err); } static bool ctnetlink_needs_filter(u8 family, const struct nlattr * const *cda) { return family || cda[CTA_MARK] || cda[CTA_FILTER] || cda[CTA_STATUS]; } static int ctnetlink_start(struct netlink_callback *cb) { const struct nlattr * const *cda = cb->data; struct ctnetlink_filter *filter = NULL; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u8 family = nfmsg->nfgen_family; if (ctnetlink_needs_filter(family, cda)) { filter = ctnetlink_alloc_filter(cda, family); if (IS_ERR(filter)) return PTR_ERR(filter); } cb->data = filter; return 0; } static int ctnetlink_filter_match_tuple(struct nf_conntrack_tuple *filter_tuple, struct nf_conntrack_tuple *ct_tuple, u_int32_t flags, int family) { switch (family) { case NFPROTO_IPV4: if ((flags & CTA_FILTER_FLAG(CTA_IP_SRC)) && filter_tuple->src.u3.ip != ct_tuple->src.u3.ip) return 0; if ((flags & CTA_FILTER_FLAG(CTA_IP_DST)) && filter_tuple->dst.u3.ip != ct_tuple->dst.u3.ip) return 0; break; case NFPROTO_IPV6: if ((flags & CTA_FILTER_FLAG(CTA_IP_SRC)) && !ipv6_addr_cmp(&filter_tuple->src.u3.in6, &ct_tuple->src.u3.in6)) return 0; if ((flags & CTA_FILTER_FLAG(CTA_IP_DST)) && !ipv6_addr_cmp(&filter_tuple->dst.u3.in6, &ct_tuple->dst.u3.in6)) return 0; break; } if ((flags & CTA_FILTER_FLAG(CTA_PROTO_NUM)) && filter_tuple->dst.protonum != ct_tuple->dst.protonum) return 0; switch (ct_tuple->dst.protonum) { case IPPROTO_TCP: case IPPROTO_UDP: if ((flags & CTA_FILTER_FLAG(CTA_PROTO_SRC_PORT)) && filter_tuple->src.u.tcp.port != ct_tuple->src.u.tcp.port) return 0; if ((flags & CTA_FILTER_FLAG(CTA_PROTO_DST_PORT)) && filter_tuple->dst.u.tcp.port != ct_tuple->dst.u.tcp.port) return 0; break; case IPPROTO_ICMP: if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_TYPE)) && filter_tuple->dst.u.icmp.type != ct_tuple->dst.u.icmp.type) return 0; if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_CODE)) && filter_tuple->dst.u.icmp.code != ct_tuple->dst.u.icmp.code) return 0; if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_ID)) && filter_tuple->src.u.icmp.id != ct_tuple->src.u.icmp.id) return 0; break; case IPPROTO_ICMPV6: if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_TYPE)) && filter_tuple->dst.u.icmp.type != ct_tuple->dst.u.icmp.type) return 0; if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_CODE)) && filter_tuple->dst.u.icmp.code != ct_tuple->dst.u.icmp.code) return 0; if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_ID)) && filter_tuple->src.u.icmp.id != ct_tuple->src.u.icmp.id) return 0; break; } return 1; } static int ctnetlink_filter_match(struct nf_conn *ct, void *data) { struct ctnetlink_filter *filter = data; struct nf_conntrack_tuple *tuple; u32 status; if (filter == NULL) goto out; /* Match entries of a given L3 protocol number. * If it is not specified, ie. l3proto == 0, * then match everything. */ if (filter->family && nf_ct_l3num(ct) != filter->family) goto ignore_entry; if (filter->orig_flags) { tuple = nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL); if (!ctnetlink_filter_match_tuple(&filter->orig, tuple, filter->orig_flags, filter->family)) goto ignore_entry; } if (filter->reply_flags) { tuple = nf_ct_tuple(ct, IP_CT_DIR_REPLY); if (!ctnetlink_filter_match_tuple(&filter->reply, tuple, filter->reply_flags, filter->family)) goto ignore_entry; } #ifdef CONFIG_NF_CONNTRACK_MARK if ((READ_ONCE(ct->mark) & filter->mark.mask) != filter->mark.val) goto ignore_entry; #endif status = (u32)READ_ONCE(ct->status); if ((status & filter->status.mask) != filter->status.val) goto ignore_entry; out: return 1; ignore_entry: return 0; } static int ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { unsigned int flags = cb->data ? NLM_F_DUMP_FILTERED : 0; struct net *net = sock_net(skb->sk); struct nf_conn *ct, *last; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; struct nf_conn *nf_ct_evict[8]; int res, i; spinlock_t *lockp; last = (struct nf_conn *)cb->args[1]; i = 0; local_bh_disable(); for (; cb->args[0] < nf_conntrack_htable_size; cb->args[0]++) { restart: while (i) { i--; if (nf_ct_should_gc(nf_ct_evict[i])) nf_ct_kill(nf_ct_evict[i]); nf_ct_put(nf_ct_evict[i]); } lockp = &nf_conntrack_locks[cb->args[0] % CONNTRACK_LOCKS]; nf_conntrack_lock(lockp); if (cb->args[0] >= nf_conntrack_htable_size) { spin_unlock(lockp); goto out; } hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[cb->args[0]], hnnode) { ct = nf_ct_tuplehash_to_ctrack(h); if (nf_ct_is_expired(ct)) { /* need to defer nf_ct_kill() until lock is released */ if (i < ARRAY_SIZE(nf_ct_evict) && refcount_inc_not_zero(&ct->ct_general.use)) nf_ct_evict[i++] = ct; continue; } if (!net_eq(net, nf_ct_net(ct))) continue; if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) continue; if (cb->args[1]) { if (ct != last) continue; cb->args[1] = 0; } if (!ctnetlink_filter_match(ct, cb->data)) continue; res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), ct, true, flags); if (res < 0) { nf_conntrack_get(&ct->ct_general); cb->args[1] = (unsigned long)ct; spin_unlock(lockp); goto out; } } spin_unlock(lockp); if (cb->args[1]) { cb->args[1] = 0; goto restart; } } out: local_bh_enable(); if (last) { /* nf ct hash resize happened, now clear the leftover. */ if ((struct nf_conn *)cb->args[1] == last) cb->args[1] = 0; nf_ct_put(last); } while (i) { i--; if (nf_ct_should_gc(nf_ct_evict[i])) nf_ct_kill(nf_ct_evict[i]); nf_ct_put(nf_ct_evict[i]); } return skb->len; } static int ipv4_nlattr_to_tuple(struct nlattr *tb[], struct nf_conntrack_tuple *t, u_int32_t flags) { if (flags & CTA_FILTER_FLAG(CTA_IP_SRC)) { if (!tb[CTA_IP_V4_SRC]) return -EINVAL; t->src.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_SRC]); } if (flags & CTA_FILTER_FLAG(CTA_IP_DST)) { if (!tb[CTA_IP_V4_DST]) return -EINVAL; t->dst.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_DST]); } return 0; } static int ipv6_nlattr_to_tuple(struct nlattr *tb[], struct nf_conntrack_tuple *t, u_int32_t flags) { if (flags & CTA_FILTER_FLAG(CTA_IP_SRC)) { if (!tb[CTA_IP_V6_SRC]) return -EINVAL; t->src.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_SRC]); } if (flags & CTA_FILTER_FLAG(CTA_IP_DST)) { if (!tb[CTA_IP_V6_DST]) return -EINVAL; t->dst.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_DST]); } return 0; } static int ctnetlink_parse_tuple_ip(struct nlattr *attr, struct nf_conntrack_tuple *tuple, u_int32_t flags) { struct nlattr *tb[CTA_IP_MAX+1]; int ret = 0; ret = nla_parse_nested_deprecated(tb, CTA_IP_MAX, attr, NULL, NULL); if (ret < 0) return ret; ret = nla_validate_nested_deprecated(attr, CTA_IP_MAX, cta_ip_nla_policy, NULL); if (ret) return ret; switch (tuple->src.l3num) { case NFPROTO_IPV4: ret = ipv4_nlattr_to_tuple(tb, tuple, flags); break; case NFPROTO_IPV6: ret = ipv6_nlattr_to_tuple(tb, tuple, flags); break; } return ret; } static const struct nla_policy proto_nla_policy[CTA_PROTO_MAX+1] = { [CTA_PROTO_NUM] = { .type = NLA_U8 }, }; static int ctnetlink_parse_tuple_proto(struct nlattr *attr, struct nf_conntrack_tuple *tuple, u_int32_t flags) { const struct nf_conntrack_l4proto *l4proto; struct nlattr *tb[CTA_PROTO_MAX+1]; int ret = 0; ret = nla_parse_nested_deprecated(tb, CTA_PROTO_MAX, attr, proto_nla_policy, NULL); if (ret < 0) return ret; if (!(flags & CTA_FILTER_FLAG(CTA_PROTO_NUM))) return 0; if (!tb[CTA_PROTO_NUM]) return -EINVAL; tuple->dst.protonum = nla_get_u8(tb[CTA_PROTO_NUM]); rcu_read_lock(); l4proto = nf_ct_l4proto_find(tuple->dst.protonum); if (likely(l4proto->nlattr_to_tuple)) { ret = nla_validate_nested_deprecated(attr, CTA_PROTO_MAX, l4proto->nla_policy, NULL); if (ret == 0) ret = l4proto->nlattr_to_tuple(tb, tuple, flags); } rcu_read_unlock(); return ret; } static int ctnetlink_parse_zone(const struct nlattr *attr, struct nf_conntrack_zone *zone) { nf_ct_zone_init(zone, NF_CT_DEFAULT_ZONE_ID, NF_CT_DEFAULT_ZONE_DIR, 0); #ifdef CONFIG_NF_CONNTRACK_ZONES if (attr) zone->id = ntohs(nla_get_be16(attr)); #else if (attr) return -EOPNOTSUPP; #endif return 0; } static int ctnetlink_parse_tuple_zone(struct nlattr *attr, enum ctattr_type type, struct nf_conntrack_zone *zone) { int ret; if (zone->id != NF_CT_DEFAULT_ZONE_ID) return -EINVAL; ret = ctnetlink_parse_zone(attr, zone); if (ret < 0) return ret; if (type == CTA_TUPLE_REPLY) zone->dir = NF_CT_ZONE_DIR_REPL; else zone->dir = NF_CT_ZONE_DIR_ORIG; return 0; } static const struct nla_policy tuple_nla_policy[CTA_TUPLE_MAX+1] = { [CTA_TUPLE_IP] = { .type = NLA_NESTED }, [CTA_TUPLE_PROTO] = { .type = NLA_NESTED }, [CTA_TUPLE_ZONE] = { .type = NLA_U16 }, }; #define CTA_FILTER_F_ALL_CTA_PROTO \ (CTA_FILTER_F_CTA_PROTO_SRC_PORT | \ CTA_FILTER_F_CTA_PROTO_DST_PORT | \ CTA_FILTER_F_CTA_PROTO_ICMP_TYPE | \ CTA_FILTER_F_CTA_PROTO_ICMP_CODE | \ CTA_FILTER_F_CTA_PROTO_ICMP_ID | \ CTA_FILTER_F_CTA_PROTO_ICMPV6_TYPE | \ CTA_FILTER_F_CTA_PROTO_ICMPV6_CODE | \ CTA_FILTER_F_CTA_PROTO_ICMPV6_ID) static int ctnetlink_parse_tuple_filter(const struct nlattr * const cda[], struct nf_conntrack_tuple *tuple, u32 type, u_int8_t l3num, struct nf_conntrack_zone *zone, u_int32_t flags) { struct nlattr *tb[CTA_TUPLE_MAX+1]; int err; memset(tuple, 0, sizeof(*tuple)); err = nla_parse_nested_deprecated(tb, CTA_TUPLE_MAX, cda[type], tuple_nla_policy, NULL); if (err < 0) return err; if (l3num != NFPROTO_IPV4 && l3num != NFPROTO_IPV6) return -EOPNOTSUPP; tuple->src.l3num = l3num; if (flags & CTA_FILTER_FLAG(CTA_IP_DST) || flags & CTA_FILTER_FLAG(CTA_IP_SRC)) { if (!tb[CTA_TUPLE_IP]) return -EINVAL; err = ctnetlink_parse_tuple_ip(tb[CTA_TUPLE_IP], tuple, flags); if (err < 0) return err; } if (flags & CTA_FILTER_FLAG(CTA_PROTO_NUM)) { if (!tb[CTA_TUPLE_PROTO]) return -EINVAL; err = ctnetlink_parse_tuple_proto(tb[CTA_TUPLE_PROTO], tuple, flags); if (err < 0) return err; } else if (flags & CTA_FILTER_FLAG(ALL_CTA_PROTO)) { /* Can't manage proto flags without a protonum */ return -EINVAL; } if ((flags & CTA_FILTER_FLAG(CTA_TUPLE_ZONE)) && tb[CTA_TUPLE_ZONE]) { if (!zone) return -EINVAL; err = ctnetlink_parse_tuple_zone(tb[CTA_TUPLE_ZONE], type, zone); if (err < 0) return err; } /* orig and expect tuples get DIR_ORIGINAL */ if (type == CTA_TUPLE_REPLY) tuple->dst.dir = IP_CT_DIR_REPLY; else tuple->dst.dir = IP_CT_DIR_ORIGINAL; return 0; } static int ctnetlink_parse_tuple(const struct nlattr * const cda[], struct nf_conntrack_tuple *tuple, u32 type, u_int8_t l3num, struct nf_conntrack_zone *zone) { return ctnetlink_parse_tuple_filter(cda, tuple, type, l3num, zone, CTA_FILTER_FLAG(ALL)); } static const struct nla_policy help_nla_policy[CTA_HELP_MAX+1] = { [CTA_HELP_NAME] = { .type = NLA_NUL_STRING, .len = NF_CT_HELPER_NAME_LEN - 1 }, }; static int ctnetlink_parse_help(const struct nlattr *attr, char **helper_name, struct nlattr **helpinfo) { int err; struct nlattr *tb[CTA_HELP_MAX+1]; err = nla_parse_nested_deprecated(tb, CTA_HELP_MAX, attr, help_nla_policy, NULL); if (err < 0) return err; if (!tb[CTA_HELP_NAME]) return -EINVAL; *helper_name = nla_data(tb[CTA_HELP_NAME]); if (tb[CTA_HELP_INFO]) *helpinfo = tb[CTA_HELP_INFO]; return 0; } static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { [CTA_TUPLE_ORIG] = { .type = NLA_NESTED }, [CTA_TUPLE_REPLY] = { .type = NLA_NESTED }, [CTA_STATUS] = { .type = NLA_U32 }, [CTA_PROTOINFO] = { .type = NLA_NESTED }, [CTA_HELP] = { .type = NLA_NESTED }, [CTA_NAT_SRC] = { .type = NLA_NESTED }, [CTA_TIMEOUT] = { .type = NLA_U32 }, [CTA_MARK] = { .type = NLA_U32 }, [CTA_ID] = { .type = NLA_U32 }, [CTA_NAT_DST] = { .type = NLA_NESTED }, [CTA_TUPLE_MASTER] = { .type = NLA_NESTED }, [CTA_NAT_SEQ_ADJ_ORIG] = { .type = NLA_NESTED }, [CTA_NAT_SEQ_ADJ_REPLY] = { .type = NLA_NESTED }, [CTA_ZONE] = { .type = NLA_U16 }, [CTA_MARK_MASK] = { .type = NLA_U32 }, [CTA_LABELS] = { .type = NLA_BINARY, .len = NF_CT_LABELS_MAX_SIZE }, [CTA_LABELS_MASK] = { .type = NLA_BINARY, .len = NF_CT_LABELS_MAX_SIZE }, [CTA_FILTER] = { .type = NLA_NESTED }, [CTA_STATUS_MASK] = { .type = NLA_U32 }, }; static int ctnetlink_flush_iterate(struct nf_conn *ct, void *data) { return ctnetlink_filter_match(ct, data); } static int ctnetlink_flush_conntrack(struct net *net, const struct nlattr * const cda[], u32 portid, int report, u8 family) { struct ctnetlink_filter *filter = NULL; struct nf_ct_iter_data iter = { .net = net, .portid = portid, .report = report, }; if (ctnetlink_needs_filter(family, cda)) { if (cda[CTA_FILTER]) return -EOPNOTSUPP; filter = ctnetlink_alloc_filter(cda, family); if (IS_ERR(filter)) return PTR_ERR(filter); iter.data = filter; } nf_ct_iterate_cleanup_net(ctnetlink_flush_iterate, &iter); kfree(filter); return 0; } static int ctnetlink_del_conntrack(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { u8 family = info->nfmsg->nfgen_family; struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; struct nf_conn *ct; int err; err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); if (err < 0) return err; if (cda[CTA_TUPLE_ORIG]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, family, &zone); else if (cda[CTA_TUPLE_REPLY]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, family, &zone); else { u_int8_t u3 = info->nfmsg->version ? family : AF_UNSPEC; return ctnetlink_flush_conntrack(info->net, cda, NETLINK_CB(skb).portid, nlmsg_report(info->nlh), u3); } if (err < 0) return err; h = nf_conntrack_find_get(info->net, &zone, &tuple); if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); if (cda[CTA_ID]) { __be32 id = nla_get_be32(cda[CTA_ID]); if (id != (__force __be32)nf_ct_get_id(ct)) { nf_ct_put(ct); return -ENOENT; } } nf_ct_delete(ct, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); nf_ct_put(ct); return 0; } static int ctnetlink_get_conntrack(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; struct sk_buff *skb2; struct nf_conn *ct; int err; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = ctnetlink_start, .dump = ctnetlink_dump_table, .done = ctnetlink_done, .data = (void *)cda, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); if (err < 0) return err; if (cda[CTA_TUPLE_ORIG]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, u3, &zone); else if (cda[CTA_TUPLE_REPLY]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, u3, &zone); else return -EINVAL; if (err < 0) return err; h = nf_conntrack_find_get(info->net, &zone, &tuple); if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb2) { nf_ct_put(ct); return -ENOMEM; } err = ctnetlink_fill_info(skb2, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFNL_MSG_TYPE(info->nlh->nlmsg_type), ct, true, 0); nf_ct_put(ct); if (err <= 0) { kfree_skb(skb2); return -ENOMEM; } return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); } static int ctnetlink_done_list(struct netlink_callback *cb) { struct ctnetlink_list_dump_ctx *ctx = (void *)cb->ctx; if (ctx->last) nf_ct_put(ctx->last); return 0; } #ifdef CONFIG_NF_CONNTRACK_EVENTS static int ctnetlink_dump_one_entry(struct sk_buff *skb, struct netlink_callback *cb, struct nf_conn *ct, bool dying) { struct ctnetlink_list_dump_ctx *ctx = (void *)cb->ctx; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u8 l3proto = nfmsg->nfgen_family; int res; if (l3proto && nf_ct_l3num(ct) != l3proto) return 0; if (ctx->last) { if (ct != ctx->last) return 0; ctx->last = NULL; } /* We can't dump extension info for the unconfirmed * list because unconfirmed conntracks can have * ct->ext reallocated (and thus freed). * * In the dying list case ct->ext can't be free'd * until after we drop pcpu->lock. */ res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), ct, dying, 0); if (res < 0) { if (!refcount_inc_not_zero(&ct->ct_general.use)) return 0; ctx->last = ct; } return res; } #endif static int ctnetlink_dump_unconfirmed(struct sk_buff *skb, struct netlink_callback *cb) { return 0; } static int ctnetlink_dump_dying(struct sk_buff *skb, struct netlink_callback *cb) { struct ctnetlink_list_dump_ctx *ctx = (void *)cb->ctx; struct nf_conn *last = ctx->last; #ifdef CONFIG_NF_CONNTRACK_EVENTS const struct net *net = sock_net(skb->sk); struct nf_conntrack_net_ecache *ecache_net; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; #endif if (ctx->done) return 0; ctx->last = NULL; #ifdef CONFIG_NF_CONNTRACK_EVENTS ecache_net = nf_conn_pernet_ecache(net); spin_lock_bh(&ecache_net->dying_lock); hlist_nulls_for_each_entry(h, n, &ecache_net->dying_list, hnnode) { struct nf_conn *ct; int res; ct = nf_ct_tuplehash_to_ctrack(h); if (last && last != ct) continue; res = ctnetlink_dump_one_entry(skb, cb, ct, true); if (res < 0) { spin_unlock_bh(&ecache_net->dying_lock); nf_ct_put(last); return skb->len; } nf_ct_put(last); last = NULL; } spin_unlock_bh(&ecache_net->dying_lock); #endif ctx->done = true; nf_ct_put(last); return skb->len; } static int ctnetlink_get_ct_dying(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ctnetlink_dump_dying, .done = ctnetlink_done_list, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } return -EOPNOTSUPP; } static int ctnetlink_get_ct_unconfirmed(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ctnetlink_dump_unconfirmed, .done = ctnetlink_done_list, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } return -EOPNOTSUPP; } #if IS_ENABLED(CONFIG_NF_NAT) static int ctnetlink_parse_nat_setup(struct nf_conn *ct, enum nf_nat_manip_type manip, const struct nlattr *attr) __must_hold(RCU) { const struct nf_nat_hook *nat_hook; int err; nat_hook = rcu_dereference(nf_nat_hook); if (!nat_hook) { #ifdef CONFIG_MODULES rcu_read_unlock(); nfnl_unlock(NFNL_SUBSYS_CTNETLINK); if (request_module("nf-nat") < 0) { nfnl_lock(NFNL_SUBSYS_CTNETLINK); rcu_read_lock(); return -EOPNOTSUPP; } nfnl_lock(NFNL_SUBSYS_CTNETLINK); rcu_read_lock(); nat_hook = rcu_dereference(nf_nat_hook); if (nat_hook) return -EAGAIN; #endif return -EOPNOTSUPP; } err = nat_hook->parse_nat_setup(ct, manip, attr); if (err == -EAGAIN) { #ifdef CONFIG_MODULES rcu_read_unlock(); nfnl_unlock(NFNL_SUBSYS_CTNETLINK); if (request_module("nf-nat-%u", nf_ct_l3num(ct)) < 0) { nfnl_lock(NFNL_SUBSYS_CTNETLINK); rcu_read_lock(); return -EOPNOTSUPP; } nfnl_lock(NFNL_SUBSYS_CTNETLINK); rcu_read_lock(); #else err = -EOPNOTSUPP; #endif } return err; } #endif static int ctnetlink_change_status(struct nf_conn *ct, const struct nlattr * const cda[]) { return nf_ct_change_status_common(ct, ntohl(nla_get_be32(cda[CTA_STATUS]))); } static int ctnetlink_setup_nat(struct nf_conn *ct, const struct nlattr * const cda[]) { #if IS_ENABLED(CONFIG_NF_NAT) int ret; if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC]) return 0; ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_DST, cda[CTA_NAT_DST]); if (ret < 0) return ret; return ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_SRC, cda[CTA_NAT_SRC]); #else if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC]) return 0; return -EOPNOTSUPP; #endif } static int ctnetlink_change_helper(struct nf_conn *ct, const struct nlattr * const cda[]) { struct nf_conntrack_helper *helper; struct nf_conn_help *help = nfct_help(ct); char *helpname = NULL; struct nlattr *helpinfo = NULL; int err; err = ctnetlink_parse_help(cda[CTA_HELP], &helpname, &helpinfo); if (err < 0) return err; /* don't change helper of sibling connections */ if (ct->master) { /* If we try to change the helper to the same thing twice, * treat the second attempt as a no-op instead of returning * an error. */ err = -EBUSY; if (help) { rcu_read_lock(); helper = rcu_dereference(help->helper); if (helper && !strcmp(helper->name, helpname)) err = 0; rcu_read_unlock(); } return err; } if (!strcmp(helpname, "")) { if (help && help->helper) { /* we had a helper before ... */ nf_ct_remove_expectations(ct); RCU_INIT_POINTER(help->helper, NULL); } return 0; } rcu_read_lock(); helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), nf_ct_protonum(ct)); if (helper == NULL) { rcu_read_unlock(); return -EOPNOTSUPP; } if (help) { if (rcu_access_pointer(help->helper) == helper) { /* update private helper data if allowed. */ if (helper->from_nlattr) helper->from_nlattr(helpinfo, ct); err = 0; } else err = -EBUSY; } else { /* we cannot set a helper for an existing conntrack */ err = -EOPNOTSUPP; } rcu_read_unlock(); return err; } static int ctnetlink_change_timeout(struct nf_conn *ct, const struct nlattr * const cda[]) { return __nf_ct_change_timeout(ct, (u64)ntohl(nla_get_be32(cda[CTA_TIMEOUT])) * HZ); } #if defined(CONFIG_NF_CONNTRACK_MARK) static void ctnetlink_change_mark(struct nf_conn *ct, const struct nlattr * const cda[]) { u32 mark, newmark, mask = 0; if (cda[CTA_MARK_MASK]) mask = ~ntohl(nla_get_be32(cda[CTA_MARK_MASK])); mark = ntohl(nla_get_be32(cda[CTA_MARK])); newmark = (READ_ONCE(ct->mark) & mask) ^ mark; if (newmark != READ_ONCE(ct->mark)) WRITE_ONCE(ct->mark, newmark); } #endif static const struct nla_policy protoinfo_policy[CTA_PROTOINFO_MAX+1] = { [CTA_PROTOINFO_TCP] = { .type = NLA_NESTED }, [CTA_PROTOINFO_DCCP] = { .type = NLA_NESTED }, [CTA_PROTOINFO_SCTP] = { .type = NLA_NESTED }, }; static int ctnetlink_change_protoinfo(struct nf_conn *ct, const struct nlattr * const cda[]) { const struct nlattr *attr = cda[CTA_PROTOINFO]; const struct nf_conntrack_l4proto *l4proto; struct nlattr *tb[CTA_PROTOINFO_MAX+1]; int err = 0; err = nla_parse_nested_deprecated(tb, CTA_PROTOINFO_MAX, attr, protoinfo_policy, NULL); if (err < 0) return err; l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); if (l4proto->from_nlattr) err = l4proto->from_nlattr(tb, ct); return err; } static const struct nla_policy seqadj_policy[CTA_SEQADJ_MAX+1] = { [CTA_SEQADJ_CORRECTION_POS] = { .type = NLA_U32 }, [CTA_SEQADJ_OFFSET_BEFORE] = { .type = NLA_U32 }, [CTA_SEQADJ_OFFSET_AFTER] = { .type = NLA_U32 }, }; static int change_seq_adj(struct nf_ct_seqadj *seq, const struct nlattr * const attr) { int err; struct nlattr *cda[CTA_SEQADJ_MAX+1]; err = nla_parse_nested_deprecated(cda, CTA_SEQADJ_MAX, attr, seqadj_policy, NULL); if (err < 0) return err; if (!cda[CTA_SEQADJ_CORRECTION_POS]) return -EINVAL; seq->correction_pos = ntohl(nla_get_be32(cda[CTA_SEQADJ_CORRECTION_POS])); if (!cda[CTA_SEQADJ_OFFSET_BEFORE]) return -EINVAL; seq->offset_before = ntohl(nla_get_be32(cda[CTA_SEQADJ_OFFSET_BEFORE])); if (!cda[CTA_SEQADJ_OFFSET_AFTER]) return -EINVAL; seq->offset_after = ntohl(nla_get_be32(cda[CTA_SEQADJ_OFFSET_AFTER])); return 0; } static int ctnetlink_change_seq_adj(struct nf_conn *ct, const struct nlattr * const cda[]) { struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); int ret = 0; if (!seqadj) return 0; spin_lock_bh(&ct->lock); if (cda[CTA_SEQ_ADJ_ORIG]) { ret = change_seq_adj(&seqadj->seq[IP_CT_DIR_ORIGINAL], cda[CTA_SEQ_ADJ_ORIG]); if (ret < 0) goto err; set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); } if (cda[CTA_SEQ_ADJ_REPLY]) { ret = change_seq_adj(&seqadj->seq[IP_CT_DIR_REPLY], cda[CTA_SEQ_ADJ_REPLY]); if (ret < 0) goto err; set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); } spin_unlock_bh(&ct->lock); return 0; err: spin_unlock_bh(&ct->lock); return ret; } static const struct nla_policy synproxy_policy[CTA_SYNPROXY_MAX + 1] = { [CTA_SYNPROXY_ISN] = { .type = NLA_U32 }, [CTA_SYNPROXY_ITS] = { .type = NLA_U32 }, [CTA_SYNPROXY_TSOFF] = { .type = NLA_U32 }, }; static int ctnetlink_change_synproxy(struct nf_conn *ct, const struct nlattr * const cda[]) { struct nf_conn_synproxy *synproxy = nfct_synproxy(ct); struct nlattr *tb[CTA_SYNPROXY_MAX + 1]; int err; if (!synproxy) return 0; err = nla_parse_nested_deprecated(tb, CTA_SYNPROXY_MAX, cda[CTA_SYNPROXY], synproxy_policy, NULL); if (err < 0) return err; if (!tb[CTA_SYNPROXY_ISN] || !tb[CTA_SYNPROXY_ITS] || !tb[CTA_SYNPROXY_TSOFF]) return -EINVAL; synproxy->isn = ntohl(nla_get_be32(tb[CTA_SYNPROXY_ISN])); synproxy->its = ntohl(nla_get_be32(tb[CTA_SYNPROXY_ITS])); synproxy->tsoff = ntohl(nla_get_be32(tb[CTA_SYNPROXY_TSOFF])); return 0; } static int ctnetlink_attach_labels(struct nf_conn *ct, const struct nlattr * const cda[]) { #ifdef CONFIG_NF_CONNTRACK_LABELS size_t len = nla_len(cda[CTA_LABELS]); const void *mask = cda[CTA_LABELS_MASK]; if (len & (sizeof(u32)-1)) /* must be multiple of u32 */ return -EINVAL; if (mask) { if (nla_len(cda[CTA_LABELS_MASK]) == 0 || nla_len(cda[CTA_LABELS_MASK]) != len) return -EINVAL; mask = nla_data(cda[CTA_LABELS_MASK]); } len /= sizeof(u32); return nf_connlabels_replace(ct, nla_data(cda[CTA_LABELS]), mask, len); #else return -EOPNOTSUPP; #endif } static int ctnetlink_change_conntrack(struct nf_conn *ct, const struct nlattr * const cda[]) { int err; /* only allow NAT changes and master assignation for new conntracks */ if (cda[CTA_NAT_SRC] || cda[CTA_NAT_DST] || cda[CTA_TUPLE_MASTER]) return -EOPNOTSUPP; if (cda[CTA_HELP]) { err = ctnetlink_change_helper(ct, cda); if (err < 0) return err; } if (cda[CTA_TIMEOUT]) { err = ctnetlink_change_timeout(ct, cda); if (err < 0) return err; } if (cda[CTA_STATUS]) { err = ctnetlink_change_status(ct, cda); if (err < 0) return err; } if (cda[CTA_PROTOINFO]) { err = ctnetlink_change_protoinfo(ct, cda); if (err < 0) return err; } #if defined(CONFIG_NF_CONNTRACK_MARK) if (cda[CTA_MARK]) ctnetlink_change_mark(ct, cda); #endif if (cda[CTA_SEQ_ADJ_ORIG] || cda[CTA_SEQ_ADJ_REPLY]) { err = ctnetlink_change_seq_adj(ct, cda); if (err < 0) return err; } if (cda[CTA_SYNPROXY]) { err = ctnetlink_change_synproxy(ct, cda); if (err < 0) return err; } if (cda[CTA_LABELS]) { err = ctnetlink_attach_labels(ct, cda); if (err < 0) return err; } return 0; } static struct nf_conn * ctnetlink_create_conntrack(struct net *net, const struct nf_conntrack_zone *zone, const struct nlattr * const cda[], struct nf_conntrack_tuple *otuple, struct nf_conntrack_tuple *rtuple, u8 u3) { struct nf_conn *ct; int err = -EINVAL; struct nf_conntrack_helper *helper; struct nf_conn_tstamp *tstamp; u64 timeout; ct = nf_conntrack_alloc(net, zone, otuple, rtuple, GFP_ATOMIC); if (IS_ERR(ct)) return ERR_PTR(-ENOMEM); if (!cda[CTA_TIMEOUT]) goto err1; rcu_read_lock(); if (cda[CTA_HELP]) { char *helpname = NULL; struct nlattr *helpinfo = NULL; err = ctnetlink_parse_help(cda[CTA_HELP], &helpname, &helpinfo); if (err < 0) goto err2; helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), nf_ct_protonum(ct)); if (helper == NULL) { rcu_read_unlock(); #ifdef CONFIG_MODULES if (request_module("nfct-helper-%s", helpname) < 0) { err = -EOPNOTSUPP; goto err1; } rcu_read_lock(); helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), nf_ct_protonum(ct)); if (helper) { err = -EAGAIN; goto err2; } rcu_read_unlock(); #endif err = -EOPNOTSUPP; goto err1; } else { struct nf_conn_help *help; help = nf_ct_helper_ext_add(ct, GFP_ATOMIC); if (help == NULL) { err = -ENOMEM; goto err2; } /* set private helper data if allowed. */ if (helper->from_nlattr) helper->from_nlattr(helpinfo, ct); /* disable helper auto-assignment for this entry */ ct->status |= IPS_HELPER; RCU_INIT_POINTER(help->helper, helper); } } err = ctnetlink_setup_nat(ct, cda); if (err < 0) goto err2; nf_ct_acct_ext_add(ct, GFP_ATOMIC); nf_ct_tstamp_ext_add(ct, GFP_ATOMIC); nf_ct_ecache_ext_add(ct, 0, 0, GFP_ATOMIC); nf_ct_labels_ext_add(ct); nfct_seqadj_ext_add(ct); nfct_synproxy_ext_add(ct); /* we must add conntrack extensions before confirmation. */ ct->status |= IPS_CONFIRMED; timeout = (u64)ntohl(nla_get_be32(cda[CTA_TIMEOUT])) * HZ; __nf_ct_set_timeout(ct, timeout); if (cda[CTA_STATUS]) { err = ctnetlink_change_status(ct, cda); if (err < 0) goto err2; } if (cda[CTA_SEQ_ADJ_ORIG] || cda[CTA_SEQ_ADJ_REPLY]) { err = ctnetlink_change_seq_adj(ct, cda); if (err < 0) goto err2; } memset(&ct->proto, 0, sizeof(ct->proto)); if (cda[CTA_PROTOINFO]) { err = ctnetlink_change_protoinfo(ct, cda); if (err < 0) goto err2; } if (cda[CTA_SYNPROXY]) { err = ctnetlink_change_synproxy(ct, cda); if (err < 0) goto err2; } #if defined(CONFIG_NF_CONNTRACK_MARK) if (cda[CTA_MARK]) ctnetlink_change_mark(ct, cda); #endif /* setup master conntrack: this is a confirmed expectation */ if (cda[CTA_TUPLE_MASTER]) { struct nf_conntrack_tuple master; struct nf_conntrack_tuple_hash *master_h; struct nf_conn *master_ct; err = ctnetlink_parse_tuple(cda, &master, CTA_TUPLE_MASTER, u3, NULL); if (err < 0) goto err2; master_h = nf_conntrack_find_get(net, zone, &master); if (master_h == NULL) { err = -ENOENT; goto err2; } master_ct = nf_ct_tuplehash_to_ctrack(master_h); __set_bit(IPS_EXPECTED_BIT, &ct->status); ct->master = master_ct; } tstamp = nf_conn_tstamp_find(ct); if (tstamp) tstamp->start = ktime_get_real_ns(); err = nf_conntrack_hash_check_insert(ct); if (err < 0) goto err3; rcu_read_unlock(); return ct; err3: if (ct->master) nf_ct_put(ct->master); err2: rcu_read_unlock(); err1: nf_conntrack_free(ct); return ERR_PTR(err); } static int ctnetlink_new_conntrack(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { struct nf_conntrack_tuple otuple, rtuple; struct nf_conntrack_tuple_hash *h = NULL; u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_zone zone; struct nf_conn *ct; int err; err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); if (err < 0) return err; if (cda[CTA_TUPLE_ORIG]) { err = ctnetlink_parse_tuple(cda, &otuple, CTA_TUPLE_ORIG, u3, &zone); if (err < 0) return err; } if (cda[CTA_TUPLE_REPLY]) { err = ctnetlink_parse_tuple(cda, &rtuple, CTA_TUPLE_REPLY, u3, &zone); if (err < 0) return err; } if (cda[CTA_TUPLE_ORIG]) h = nf_conntrack_find_get(info->net, &zone, &otuple); else if (cda[CTA_TUPLE_REPLY]) h = nf_conntrack_find_get(info->net, &zone, &rtuple); if (h == NULL) { err = -ENOENT; if (info->nlh->nlmsg_flags & NLM_F_CREATE) { enum ip_conntrack_events events; if (!cda[CTA_TUPLE_ORIG] || !cda[CTA_TUPLE_REPLY]) return -EINVAL; if (otuple.dst.protonum != rtuple.dst.protonum) return -EINVAL; ct = ctnetlink_create_conntrack(info->net, &zone, cda, &otuple, &rtuple, u3); if (IS_ERR(ct)) return PTR_ERR(ct); err = 0; if (test_bit(IPS_EXPECTED_BIT, &ct->status)) events = 1 << IPCT_RELATED; else events = 1 << IPCT_NEW; if (cda[CTA_LABELS] && ctnetlink_attach_labels(ct, cda) == 0) events |= (1 << IPCT_LABEL); nf_conntrack_eventmask_report((1 << IPCT_REPLY) | (1 << IPCT_ASSURED) | (1 << IPCT_HELPER) | (1 << IPCT_PROTOINFO) | (1 << IPCT_SEQADJ) | (1 << IPCT_MARK) | (1 << IPCT_SYNPROXY) | events, ct, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); nf_ct_put(ct); } return err; } /* implicit 'else' */ err = -EEXIST; ct = nf_ct_tuplehash_to_ctrack(h); if (!(info->nlh->nlmsg_flags & NLM_F_EXCL)) { err = ctnetlink_change_conntrack(ct, cda); if (err == 0) { nf_conntrack_eventmask_report((1 << IPCT_REPLY) | (1 << IPCT_ASSURED) | (1 << IPCT_HELPER) | (1 << IPCT_LABEL) | (1 << IPCT_PROTOINFO) | (1 << IPCT_SEQADJ) | (1 << IPCT_MARK) | (1 << IPCT_SYNPROXY), ct, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); } } nf_ct_put(ct); return err; } static int ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq, __u16 cpu, const struct ip_conntrack_stat *st) { struct nlmsghdr *nlh; unsigned int flags = portid ? NLM_F_MULTI : 0, event; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_GET_STATS_CPU); nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, NFNETLINK_V0, htons(cpu)); if (!nlh) goto nlmsg_failure; if (nla_put_be32(skb, CTA_STATS_FOUND, htonl(st->found)) || nla_put_be32(skb, CTA_STATS_INVALID, htonl(st->invalid)) || nla_put_be32(skb, CTA_STATS_INSERT, htonl(st->insert)) || nla_put_be32(skb, CTA_STATS_INSERT_FAILED, htonl(st->insert_failed)) || nla_put_be32(skb, CTA_STATS_DROP, htonl(st->drop)) || nla_put_be32(skb, CTA_STATS_EARLY_DROP, htonl(st->early_drop)) || nla_put_be32(skb, CTA_STATS_ERROR, htonl(st->error)) || nla_put_be32(skb, CTA_STATS_SEARCH_RESTART, htonl(st->search_restart)) || nla_put_be32(skb, CTA_STATS_CLASH_RESOLVE, htonl(st->clash_resolve)) || nla_put_be32(skb, CTA_STATS_CHAIN_TOOLONG, htonl(st->chaintoolong))) goto nla_put_failure; nlmsg_end(skb, nlh); return skb->len; nla_put_failure: nlmsg_failure: nlmsg_cancel(skb, nlh); return -1; } static int ctnetlink_ct_stat_cpu_dump(struct sk_buff *skb, struct netlink_callback *cb) { int cpu; struct net *net = sock_net(skb->sk); if (cb->args[0] == nr_cpu_ids) return 0; for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) { const struct ip_conntrack_stat *st; if (!cpu_possible(cpu)) continue; st = per_cpu_ptr(net->ct.stat, cpu); if (ctnetlink_ct_stat_cpu_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cpu, st) < 0) break; } cb->args[0] = cpu; return skb->len; } static int ctnetlink_stat_ct_cpu(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ctnetlink_ct_stat_cpu_dump, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } return 0; } static int ctnetlink_stat_ct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, struct net *net) { unsigned int flags = portid ? NLM_F_MULTI : 0, event; unsigned int nr_conntracks; struct nlmsghdr *nlh; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_GET_STATS); nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, NFNETLINK_V0, 0); if (!nlh) goto nlmsg_failure; nr_conntracks = nf_conntrack_count(net); if (nla_put_be32(skb, CTA_STATS_GLOBAL_ENTRIES, htonl(nr_conntracks))) goto nla_put_failure; if (nla_put_be32(skb, CTA_STATS_GLOBAL_MAX_ENTRIES, htonl(nf_conntrack_max))) goto nla_put_failure; nlmsg_end(skb, nlh); return skb->len; nla_put_failure: nlmsg_failure: nlmsg_cancel(skb, nlh); return -1; } static int ctnetlink_stat_ct(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { struct sk_buff *skb2; int err; skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb2 == NULL) return -ENOMEM; err = ctnetlink_stat_ct_fill_info(skb2, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFNL_MSG_TYPE(info->nlh->nlmsg_type), sock_net(skb->sk)); if (err <= 0) { kfree_skb(skb2); return -ENOMEM; } return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); } static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = { [CTA_EXPECT_MASTER] = { .type = NLA_NESTED }, [CTA_EXPECT_TUPLE] = { .type = NLA_NESTED }, [CTA_EXPECT_MASK] = { .type = NLA_NESTED }, [CTA_EXPECT_TIMEOUT] = { .type = NLA_U32 }, [CTA_EXPECT_ID] = { .type = NLA_U32 }, [CTA_EXPECT_HELP_NAME] = { .type = NLA_NUL_STRING, .len = NF_CT_HELPER_NAME_LEN - 1 }, [CTA_EXPECT_ZONE] = { .type = NLA_U16 }, [CTA_EXPECT_FLAGS] = { .type = NLA_U32 }, [CTA_EXPECT_CLASS] = { .type = NLA_U32 }, [CTA_EXPECT_NAT] = { .type = NLA_NESTED }, [CTA_EXPECT_FN] = { .type = NLA_NUL_STRING }, }; static struct nf_conntrack_expect * ctnetlink_alloc_expect(const struct nlattr *const cda[], struct nf_conn *ct, struct nf_conntrack_helper *helper, struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *mask); #ifdef CONFIG_NETFILTER_NETLINK_GLUE_CT static size_t ctnetlink_glue_build_size(const struct nf_conn *ct) { return 3 * nla_total_size(0) /* CTA_TUPLE_ORIG|REPL|MASTER */ + 3 * nla_total_size(0) /* CTA_TUPLE_IP */ + 3 * nla_total_size(0) /* CTA_TUPLE_PROTO */ + 3 * nla_total_size(sizeof(u_int8_t)) /* CTA_PROTO_NUM */ + nla_total_size(sizeof(u_int32_t)) /* CTA_ID */ + nla_total_size(sizeof(u_int32_t)) /* CTA_STATUS */ + nla_total_size(sizeof(u_int32_t)) /* CTA_TIMEOUT */ + nla_total_size(0) /* CTA_PROTOINFO */ + nla_total_size(0) /* CTA_HELP */ + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */ + ctnetlink_secctx_size(ct) + ctnetlink_acct_size(ct) + ctnetlink_timestamp_size(ct) #if IS_ENABLED(CONFIG_NF_NAT) + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */ + 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */ #endif #ifdef CONFIG_NF_CONNTRACK_MARK + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */ #endif #ifdef CONFIG_NF_CONNTRACK_ZONES + nla_total_size(sizeof(u_int16_t)) /* CTA_ZONE|CTA_TUPLE_ZONE */ #endif + ctnetlink_proto_size(ct) ; } static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) { const struct nf_conntrack_zone *zone; struct nlattr *nest_parms; zone = nf_ct_zone(ct); nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_ORIG) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_REPL) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); if (ctnetlink_dump_zone_id(skb, CTA_ZONE, zone, NF_CT_DEFAULT_ZONE_DIR) < 0) goto nla_put_failure; if (ctnetlink_dump_id(skb, ct) < 0) goto nla_put_failure; if (ctnetlink_dump_status(skb, ct) < 0) goto nla_put_failure; if (ctnetlink_dump_timeout(skb, ct, false) < 0) goto nla_put_failure; if (ctnetlink_dump_protoinfo(skb, ct, false) < 0) goto nla_put_failure; if (ctnetlink_dump_acct(skb, ct, IPCTNL_MSG_CT_GET) < 0 || ctnetlink_dump_timestamp(skb, ct) < 0) goto nla_put_failure; if (ctnetlink_dump_helpinfo(skb, ct) < 0) goto nla_put_failure; #ifdef CONFIG_NF_CONNTRACK_SECMARK if (ct->secmark && ctnetlink_dump_secctx(skb, ct) < 0) goto nla_put_failure; #endif if (ct->master && ctnetlink_dump_master(skb, ct) < 0) goto nla_put_failure; if ((ct->status & IPS_SEQ_ADJUST) && ctnetlink_dump_ct_seq_adj(skb, ct) < 0) goto nla_put_failure; if (ctnetlink_dump_ct_synproxy(skb, ct) < 0) goto nla_put_failure; #ifdef CONFIG_NF_CONNTRACK_MARK if (ctnetlink_dump_mark(skb, ct, true) < 0) goto nla_put_failure; #endif if (ctnetlink_dump_labels(skb, ct) < 0) goto nla_put_failure; return 0; nla_put_failure: return -ENOSPC; } static int ctnetlink_glue_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) { struct nlattr *nest_parms; nest_parms = nla_nest_start(skb, ct_attr); if (!nest_parms) goto nla_put_failure; if (__ctnetlink_glue_build(skb, ct) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); if (nla_put_be32(skb, ct_info_attr, htonl(ctinfo))) goto nla_put_failure; return 0; nla_put_failure: return -ENOSPC; } static int ctnetlink_update_status(struct nf_conn *ct, const struct nlattr * const cda[]) { unsigned int status = ntohl(nla_get_be32(cda[CTA_STATUS])); unsigned long d = ct->status ^ status; if (d & IPS_SEEN_REPLY && !(status & IPS_SEEN_REPLY)) /* SEEN_REPLY bit can only be set */ return -EBUSY; if (d & IPS_ASSURED && !(status & IPS_ASSURED)) /* ASSURED bit can only be set */ return -EBUSY; /* This check is less strict than ctnetlink_change_status() * because callers often flip IPS_EXPECTED bits when sending * an NFQA_CT attribute to the kernel. So ignore the * unchangeable bits but do not error out. Also user programs * are allowed to clear the bits that they are allowed to change. */ __nf_ct_change_status(ct, status, ~status); return 0; } static int ctnetlink_glue_parse_ct(const struct nlattr *cda[], struct nf_conn *ct) { int err; if (cda[CTA_TIMEOUT]) { err = ctnetlink_change_timeout(ct, cda); if (err < 0) return err; } if (cda[CTA_STATUS]) { err = ctnetlink_update_status(ct, cda); if (err < 0) return err; } if (cda[CTA_HELP]) { err = ctnetlink_change_helper(ct, cda); if (err < 0) return err; } if (cda[CTA_LABELS]) { err = ctnetlink_attach_labels(ct, cda); if (err < 0) return err; } #if defined(CONFIG_NF_CONNTRACK_MARK) if (cda[CTA_MARK]) { ctnetlink_change_mark(ct, cda); } #endif return 0; } static int ctnetlink_glue_parse(const struct nlattr *attr, struct nf_conn *ct) { struct nlattr *cda[CTA_MAX+1]; int ret; ret = nla_parse_nested_deprecated(cda, CTA_MAX, attr, ct_nla_policy, NULL); if (ret < 0) return ret; return ctnetlink_glue_parse_ct((const struct nlattr **)cda, ct); } static int ctnetlink_glue_exp_parse(const struct nlattr * const *cda, const struct nf_conn *ct, struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *mask) { int err; err = ctnetlink_parse_tuple(cda, tuple, CTA_EXPECT_TUPLE, nf_ct_l3num(ct), NULL); if (err < 0) return err; return ctnetlink_parse_tuple(cda, mask, CTA_EXPECT_MASK, nf_ct_l3num(ct), NULL); } static int ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, u32 portid, u32 report) { struct nlattr *cda[CTA_EXPECT_MAX+1]; struct nf_conntrack_tuple tuple, mask; struct nf_conntrack_helper *helper = NULL; struct nf_conntrack_expect *exp; int err; err = nla_parse_nested_deprecated(cda, CTA_EXPECT_MAX, attr, exp_nla_policy, NULL); if (err < 0) return err; err = ctnetlink_glue_exp_parse((const struct nlattr * const *)cda, ct, &tuple, &mask); if (err < 0) return err; if (cda[CTA_EXPECT_HELP_NAME]) { const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]); helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), nf_ct_protonum(ct)); if (helper == NULL) return -EOPNOTSUPP; } exp = ctnetlink_alloc_expect((const struct nlattr * const *)cda, ct, helper, &tuple, &mask); if (IS_ERR(exp)) return PTR_ERR(exp); err = nf_ct_expect_related_report(exp, portid, report, 0); nf_ct_expect_put(exp); return err; } static void ctnetlink_glue_seqadj(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, int diff) { if (!(ct->status & IPS_NAT_MASK)) return; nf_ct_tcp_seqadj_set(skb, ct, ctinfo, diff); } static const struct nfnl_ct_hook ctnetlink_glue_hook = { .build_size = ctnetlink_glue_build_size, .build = ctnetlink_glue_build, .parse = ctnetlink_glue_parse, .attach_expect = ctnetlink_glue_attach_expect, .seq_adjust = ctnetlink_glue_seqadj, }; #endif /* CONFIG_NETFILTER_NETLINK_GLUE_CT */ /*********************************************************************** * EXPECT ***********************************************************************/ static int ctnetlink_exp_dump_tuple(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple, u32 type) { struct nlattr *nest_parms; nest_parms = nla_nest_start(skb, type); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, tuple) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); return 0; nla_put_failure: return -1; } static int ctnetlink_exp_dump_mask(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple_mask *mask) { const struct nf_conntrack_l4proto *l4proto; struct nf_conntrack_tuple m; struct nlattr *nest_parms; int ret; memset(&m, 0xFF, sizeof(m)); memcpy(&m.src.u3, &mask->src.u3, sizeof(m.src.u3)); m.src.u.all = mask->src.u.all; m.src.l3num = tuple->src.l3num; m.dst.protonum = tuple->dst.protonum; nest_parms = nla_nest_start(skb, CTA_EXPECT_MASK); if (!nest_parms) goto nla_put_failure; rcu_read_lock(); ret = ctnetlink_dump_tuples_ip(skb, &m); if (ret >= 0) { l4proto = nf_ct_l4proto_find(tuple->dst.protonum); ret = ctnetlink_dump_tuples_proto(skb, &m, l4proto); } rcu_read_unlock(); if (unlikely(ret < 0)) goto nla_put_failure; nla_nest_end(skb, nest_parms); return 0; nla_put_failure: return -1; } #if IS_ENABLED(CONFIG_NF_NAT) static const union nf_inet_addr any_addr; #endif static __be32 nf_expect_get_id(const struct nf_conntrack_expect *exp) { static siphash_aligned_key_t exp_id_seed; unsigned long a, b, c, d; net_get_random_once(&exp_id_seed, sizeof(exp_id_seed)); a = (unsigned long)exp; b = (unsigned long)exp->helper; c = (unsigned long)exp->master; d = (unsigned long)siphash(&exp->tuple, sizeof(exp->tuple), &exp_id_seed); #ifdef CONFIG_64BIT return (__force __be32)siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &exp_id_seed); #else return (__force __be32)siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &exp_id_seed); #endif } static int ctnetlink_exp_dump_expect(struct sk_buff *skb, const struct nf_conntrack_expect *exp) { struct nf_conn *master = exp->master; long timeout = ((long)exp->timeout.expires - (long)jiffies) / HZ; struct nf_conn_help *help; #if IS_ENABLED(CONFIG_NF_NAT) struct nlattr *nest_parms; struct nf_conntrack_tuple nat_tuple = {}; #endif struct nf_ct_helper_expectfn *expfn; if (timeout < 0) timeout = 0; if (ctnetlink_exp_dump_tuple(skb, &exp->tuple, CTA_EXPECT_TUPLE) < 0) goto nla_put_failure; if (ctnetlink_exp_dump_mask(skb, &exp->tuple, &exp->mask) < 0) goto nla_put_failure; if (ctnetlink_exp_dump_tuple(skb, &master->tuplehash[IP_CT_DIR_ORIGINAL].tuple, CTA_EXPECT_MASTER) < 0) goto nla_put_failure; #if IS_ENABLED(CONFIG_NF_NAT) if (!nf_inet_addr_cmp(&exp->saved_addr, &any_addr) || exp->saved_proto.all) { nest_parms = nla_nest_start(skb, CTA_EXPECT_NAT); if (!nest_parms) goto nla_put_failure; if (nla_put_be32(skb, CTA_EXPECT_NAT_DIR, htonl(exp->dir))) goto nla_put_failure; nat_tuple.src.l3num = nf_ct_l3num(master); nat_tuple.src.u3 = exp->saved_addr; nat_tuple.dst.protonum = nf_ct_protonum(master); nat_tuple.src.u = exp->saved_proto; if (ctnetlink_exp_dump_tuple(skb, &nat_tuple, CTA_EXPECT_NAT_TUPLE) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); } #endif if (nla_put_be32(skb, CTA_EXPECT_TIMEOUT, htonl(timeout)) || nla_put_be32(skb, CTA_EXPECT_ID, nf_expect_get_id(exp)) || nla_put_be32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags)) || nla_put_be32(skb, CTA_EXPECT_CLASS, htonl(exp->class))) goto nla_put_failure; help = nfct_help(master); if (help) { struct nf_conntrack_helper *helper; helper = rcu_dereference(help->helper); if (helper && nla_put_string(skb, CTA_EXPECT_HELP_NAME, helper->name)) goto nla_put_failure; } expfn = nf_ct_helper_expectfn_find_by_symbol(exp->expectfn); if (expfn != NULL && nla_put_string(skb, CTA_EXPECT_FN, expfn->name)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int ctnetlink_exp_fill_info(struct sk_buff *skb, u32 portid, u32 seq, int event, const struct nf_conntrack_expect *exp) { struct nlmsghdr *nlh; unsigned int flags = portid ? NLM_F_MULTI : 0; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_EXP, event); nlh = nfnl_msg_put(skb, portid, seq, event, flags, exp->tuple.src.l3num, NFNETLINK_V0, 0); if (!nlh) goto nlmsg_failure; if (ctnetlink_exp_dump_expect(skb, exp) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); return skb->len; nlmsg_failure: nla_put_failure: nlmsg_cancel(skb, nlh); return -1; } #ifdef CONFIG_NF_CONNTRACK_EVENTS static int ctnetlink_expect_event(unsigned int events, const struct nf_exp_event *item) { struct nf_conntrack_expect *exp = item->exp; struct net *net = nf_ct_exp_net(exp); struct nlmsghdr *nlh; struct sk_buff *skb; unsigned int type, group; int flags = 0; if (events & (1 << IPEXP_DESTROY)) { type = IPCTNL_MSG_EXP_DELETE; group = NFNLGRP_CONNTRACK_EXP_DESTROY; } else if (events & (1 << IPEXP_NEW)) { type = IPCTNL_MSG_EXP_NEW; flags = NLM_F_CREATE|NLM_F_EXCL; group = NFNLGRP_CONNTRACK_EXP_NEW; } else return 0; if (!item->report && !nfnetlink_has_listeners(net, group)) return 0; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (skb == NULL) goto errout; type = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_EXP, type); nlh = nfnl_msg_put(skb, item->portid, 0, type, flags, exp->tuple.src.l3num, NFNETLINK_V0, 0); if (!nlh) goto nlmsg_failure; if (ctnetlink_exp_dump_expect(skb, exp) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); nfnetlink_send(skb, net, item->portid, group, item->report, GFP_ATOMIC); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); nlmsg_failure: kfree_skb(skb); errout: nfnetlink_set_err(net, 0, 0, -ENOBUFS); return 0; } #endif static int ctnetlink_exp_done(struct netlink_callback *cb) { if (cb->args[1]) nf_ct_expect_put((struct nf_conntrack_expect *)cb->args[1]); return 0; } static int ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct nf_conntrack_expect *exp, *last; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; rcu_read_lock(); last = (struct nf_conntrack_expect *)cb->args[1]; for (; cb->args[0] < nf_ct_expect_hsize; cb->args[0]++) { restart: hlist_for_each_entry_rcu(exp, &nf_ct_expect_hash[cb->args[0]], hnode) { if (l3proto && exp->tuple.src.l3num != l3proto) continue; if (!net_eq(nf_ct_net(exp->master), net)) continue; if (cb->args[1]) { if (exp != last) continue; cb->args[1] = 0; } if (ctnetlink_exp_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp) < 0) { if (!refcount_inc_not_zero(&exp->use)) continue; cb->args[1] = (unsigned long)exp; goto out; } } if (cb->args[1]) { cb->args[1] = 0; goto restart; } } out: rcu_read_unlock(); if (last) nf_ct_expect_put(last); return skb->len; } static int ctnetlink_exp_ct_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { struct nf_conntrack_expect *exp, *last; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); struct nf_conn *ct = cb->data; struct nf_conn_help *help = nfct_help(ct); u_int8_t l3proto = nfmsg->nfgen_family; if (cb->args[0]) return 0; rcu_read_lock(); last = (struct nf_conntrack_expect *)cb->args[1]; restart: hlist_for_each_entry_rcu(exp, &help->expectations, lnode) { if (l3proto && exp->tuple.src.l3num != l3proto) continue; if (cb->args[1]) { if (exp != last) continue; cb->args[1] = 0; } if (ctnetlink_exp_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp) < 0) { if (!refcount_inc_not_zero(&exp->use)) continue; cb->args[1] = (unsigned long)exp; goto out; } } if (cb->args[1]) { cb->args[1] = 0; goto restart; } cb->args[0] = 1; out: rcu_read_unlock(); if (last) nf_ct_expect_put(last); return skb->len; } static int ctnetlink_dump_exp_ct(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[], struct netlink_ext_ack *extack) { int err; struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int8_t u3 = nfmsg->nfgen_family; struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct nf_conntrack_zone zone; struct netlink_dump_control c = { .dump = ctnetlink_exp_ct_dump_table, .done = ctnetlink_exp_done, }; err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER, u3, NULL); if (err < 0) return err; err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); if (err < 0) return err; h = nf_conntrack_find_get(net, &zone, &tuple); if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); /* No expectation linked to this connection tracking. */ if (!nfct_help(ct)) { nf_ct_put(ct); return 0; } c.data = ct; err = netlink_dump_start(ctnl, skb, nlh, &c); nf_ct_put(ct); return err; } static int ctnetlink_get_expect(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; struct nf_conntrack_zone zone; struct sk_buff *skb2; int err; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { if (cda[CTA_EXPECT_MASTER]) return ctnetlink_dump_exp_ct(info->net, info->sk, skb, info->nlh, cda, info->extack); else { struct netlink_dump_control c = { .dump = ctnetlink_exp_dump_table, .done = ctnetlink_exp_done, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } } err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); if (err < 0) return err; if (cda[CTA_EXPECT_TUPLE]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3, NULL); else if (cda[CTA_EXPECT_MASTER]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER, u3, NULL); else return -EINVAL; if (err < 0) return err; exp = nf_ct_expect_find_get(info->net, &zone, &tuple); if (!exp) return -ENOENT; if (cda[CTA_EXPECT_ID]) { __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]); if (id != nf_expect_get_id(exp)) { nf_ct_expect_put(exp); return -ENOENT; } } skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb2) { nf_ct_expect_put(exp); return -ENOMEM; } rcu_read_lock(); err = ctnetlink_exp_fill_info(skb2, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp); rcu_read_unlock(); nf_ct_expect_put(exp); if (err <= 0) { kfree_skb(skb2); return -ENOMEM; } return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); } static bool expect_iter_name(struct nf_conntrack_expect *exp, void *data) { struct nf_conntrack_helper *helper; const struct nf_conn_help *m_help; const char *name = data; m_help = nfct_help(exp->master); helper = rcu_dereference(m_help->helper); if (!helper) return false; return strcmp(helper->name, name) == 0; } static bool expect_iter_all(struct nf_conntrack_expect *exp, void *data) { return true; } static int ctnetlink_del_expect(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_expect *exp; struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; int err; if (cda[CTA_EXPECT_TUPLE]) { /* delete a single expect by tuple */ err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); if (err < 0) return err; err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3, NULL); if (err < 0) return err; /* bump usage count to 2 */ exp = nf_ct_expect_find_get(info->net, &zone, &tuple); if (!exp) return -ENOENT; if (cda[CTA_EXPECT_ID]) { __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]); if (id != nf_expect_get_id(exp)) { nf_ct_expect_put(exp); return -ENOENT; } } /* after list removal, usage count == 1 */ spin_lock_bh(&nf_conntrack_expect_lock); if (del_timer(&exp->timeout)) { nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); nf_ct_expect_put(exp); } spin_unlock_bh(&nf_conntrack_expect_lock); /* have to put what we 'get' above. * after this line usage count == 0 */ nf_ct_expect_put(exp); } else if (cda[CTA_EXPECT_HELP_NAME]) { char *name = nla_data(cda[CTA_EXPECT_HELP_NAME]); nf_ct_expect_iterate_net(info->net, expect_iter_name, name, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); } else { /* This basically means we have to flush everything*/ nf_ct_expect_iterate_net(info->net, expect_iter_all, NULL, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); } return 0; } static int ctnetlink_change_expect(struct nf_conntrack_expect *x, const struct nlattr * const cda[]) { if (cda[CTA_EXPECT_TIMEOUT]) { if (!del_timer(&x->timeout)) return -ETIME; x->timeout.expires = jiffies + ntohl(nla_get_be32(cda[CTA_EXPECT_TIMEOUT])) * HZ; add_timer(&x->timeout); } return 0; } #if IS_ENABLED(CONFIG_NF_NAT) static const struct nla_policy exp_nat_nla_policy[CTA_EXPECT_NAT_MAX+1] = { [CTA_EXPECT_NAT_DIR] = { .type = NLA_U32 }, [CTA_EXPECT_NAT_TUPLE] = { .type = NLA_NESTED }, }; #endif static int ctnetlink_parse_expect_nat(const struct nlattr *attr, struct nf_conntrack_expect *exp, u_int8_t u3) { #if IS_ENABLED(CONFIG_NF_NAT) struct nlattr *tb[CTA_EXPECT_NAT_MAX+1]; struct nf_conntrack_tuple nat_tuple = {}; int err; err = nla_parse_nested_deprecated(tb, CTA_EXPECT_NAT_MAX, attr, exp_nat_nla_policy, NULL); if (err < 0) return err; if (!tb[CTA_EXPECT_NAT_DIR] || !tb[CTA_EXPECT_NAT_TUPLE]) return -EINVAL; err = ctnetlink_parse_tuple((const struct nlattr * const *)tb, &nat_tuple, CTA_EXPECT_NAT_TUPLE, u3, NULL); if (err < 0) return err; exp->saved_addr = nat_tuple.src.u3; exp->saved_proto = nat_tuple.src.u; exp->dir = ntohl(nla_get_be32(tb[CTA_EXPECT_NAT_DIR])); return 0; #else return -EOPNOTSUPP; #endif } static struct nf_conntrack_expect * ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct, struct nf_conntrack_helper *helper, struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *mask) { u_int32_t class = 0; struct nf_conntrack_expect *exp; struct nf_conn_help *help; int err; help = nfct_help(ct); if (!help) return ERR_PTR(-EOPNOTSUPP); if (cda[CTA_EXPECT_CLASS] && helper) { class = ntohl(nla_get_be32(cda[CTA_EXPECT_CLASS])); if (class > helper->expect_class_max) return ERR_PTR(-EINVAL); } exp = nf_ct_expect_alloc(ct); if (!exp) return ERR_PTR(-ENOMEM); if (cda[CTA_EXPECT_FLAGS]) { exp->flags = ntohl(nla_get_be32(cda[CTA_EXPECT_FLAGS])); exp->flags &= ~NF_CT_EXPECT_USERSPACE; } else { exp->flags = 0; } if (cda[CTA_EXPECT_FN]) { const char *name = nla_data(cda[CTA_EXPECT_FN]); struct nf_ct_helper_expectfn *expfn; expfn = nf_ct_helper_expectfn_find_by_name(name); if (expfn == NULL) { err = -EINVAL; goto err_out; } exp->expectfn = expfn->expectfn; } else exp->expectfn = NULL; exp->class = class; exp->master = ct; exp->helper = helper; exp->tuple = *tuple; exp->mask.src.u3 = mask->src.u3; exp->mask.src.u.all = mask->src.u.all; if (cda[CTA_EXPECT_NAT]) { err = ctnetlink_parse_expect_nat(cda[CTA_EXPECT_NAT], exp, nf_ct_l3num(ct)); if (err < 0) goto err_out; } return exp; err_out: nf_ct_expect_put(exp); return ERR_PTR(err); } static int ctnetlink_create_expect(struct net *net, const struct nf_conntrack_zone *zone, const struct nlattr * const cda[], u_int8_t u3, u32 portid, int report) { struct nf_conntrack_tuple tuple, mask, master_tuple; struct nf_conntrack_tuple_hash *h = NULL; struct nf_conntrack_helper *helper = NULL; struct nf_conntrack_expect *exp; struct nf_conn *ct; int err; /* caller guarantees that those three CTA_EXPECT_* exist */ err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3, NULL); if (err < 0) return err; err = ctnetlink_parse_tuple(cda, &mask, CTA_EXPECT_MASK, u3, NULL); if (err < 0) return err; err = ctnetlink_parse_tuple(cda, &master_tuple, CTA_EXPECT_MASTER, u3, NULL); if (err < 0) return err; /* Look for master conntrack of this expectation */ h = nf_conntrack_find_get(net, zone, &master_tuple); if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); rcu_read_lock(); if (cda[CTA_EXPECT_HELP_NAME]) { const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]); helper = __nf_conntrack_helper_find(helpname, u3, nf_ct_protonum(ct)); if (helper == NULL) { rcu_read_unlock(); #ifdef CONFIG_MODULES if (request_module("nfct-helper-%s", helpname) < 0) { err = -EOPNOTSUPP; goto err_ct; } rcu_read_lock(); helper = __nf_conntrack_helper_find(helpname, u3, nf_ct_protonum(ct)); if (helper) { err = -EAGAIN; goto err_rcu; } rcu_read_unlock(); #endif err = -EOPNOTSUPP; goto err_ct; } } exp = ctnetlink_alloc_expect(cda, ct, helper, &tuple, &mask); if (IS_ERR(exp)) { err = PTR_ERR(exp); goto err_rcu; } err = nf_ct_expect_related_report(exp, portid, report, 0); nf_ct_expect_put(exp); err_rcu: rcu_read_unlock(); err_ct: nf_ct_put(ct); return err; } static int ctnetlink_new_expect(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; struct nf_conntrack_zone zone; int err; if (!cda[CTA_EXPECT_TUPLE] || !cda[CTA_EXPECT_MASK] || !cda[CTA_EXPECT_MASTER]) return -EINVAL; err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); if (err < 0) return err; err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3, NULL); if (err < 0) return err; spin_lock_bh(&nf_conntrack_expect_lock); exp = __nf_ct_expect_find(info->net, &zone, &tuple); if (!exp) { spin_unlock_bh(&nf_conntrack_expect_lock); err = -ENOENT; if (info->nlh->nlmsg_flags & NLM_F_CREATE) { err = ctnetlink_create_expect(info->net, &zone, cda, u3, NETLINK_CB(skb).portid, nlmsg_report(info->nlh)); } return err; } err = -EEXIST; if (!(info->nlh->nlmsg_flags & NLM_F_EXCL)) err = ctnetlink_change_expect(exp, cda); spin_unlock_bh(&nf_conntrack_expect_lock); return err; } static int ctnetlink_exp_stat_fill_info(struct sk_buff *skb, u32 portid, u32 seq, int cpu, const struct ip_conntrack_stat *st) { struct nlmsghdr *nlh; unsigned int flags = portid ? NLM_F_MULTI : 0, event; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_EXP_GET_STATS_CPU); nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, NFNETLINK_V0, htons(cpu)); if (!nlh) goto nlmsg_failure; if (nla_put_be32(skb, CTA_STATS_EXP_NEW, htonl(st->expect_new)) || nla_put_be32(skb, CTA_STATS_EXP_CREATE, htonl(st->expect_create)) || nla_put_be32(skb, CTA_STATS_EXP_DELETE, htonl(st->expect_delete))) goto nla_put_failure; nlmsg_end(skb, nlh); return skb->len; nla_put_failure: nlmsg_failure: nlmsg_cancel(skb, nlh); return -1; } static int ctnetlink_exp_stat_cpu_dump(struct sk_buff *skb, struct netlink_callback *cb) { int cpu; struct net *net = sock_net(skb->sk); if (cb->args[0] == nr_cpu_ids) return 0; for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) { const struct ip_conntrack_stat *st; if (!cpu_possible(cpu)) continue; st = per_cpu_ptr(net->ct.stat, cpu); if (ctnetlink_exp_stat_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cpu, st) < 0) break; } cb->args[0] = cpu; return skb->len; } static int ctnetlink_stat_exp_cpu(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ctnetlink_exp_stat_cpu_dump, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } return 0; } #ifdef CONFIG_NF_CONNTRACK_EVENTS static struct nf_ct_event_notifier ctnl_notifier = { .ct_event = ctnetlink_conntrack_event, .exp_event = ctnetlink_expect_event, }; #endif static const struct nfnl_callback ctnl_cb[IPCTNL_MSG_MAX] = { [IPCTNL_MSG_CT_NEW] = { .call = ctnetlink_new_conntrack, .type = NFNL_CB_MUTEX, .attr_count = CTA_MAX, .policy = ct_nla_policy }, [IPCTNL_MSG_CT_GET] = { .call = ctnetlink_get_conntrack, .type = NFNL_CB_MUTEX, .attr_count = CTA_MAX, .policy = ct_nla_policy }, [IPCTNL_MSG_CT_DELETE] = { .call = ctnetlink_del_conntrack, .type = NFNL_CB_MUTEX, .attr_count = CTA_MAX, .policy = ct_nla_policy }, [IPCTNL_MSG_CT_GET_CTRZERO] = { .call = ctnetlink_get_conntrack, .type = NFNL_CB_MUTEX, .attr_count = CTA_MAX, .policy = ct_nla_policy }, [IPCTNL_MSG_CT_GET_STATS_CPU] = { .call = ctnetlink_stat_ct_cpu, .type = NFNL_CB_MUTEX, }, [IPCTNL_MSG_CT_GET_STATS] = { .call = ctnetlink_stat_ct, .type = NFNL_CB_MUTEX, }, [IPCTNL_MSG_CT_GET_DYING] = { .call = ctnetlink_get_ct_dying, .type = NFNL_CB_MUTEX, }, [IPCTNL_MSG_CT_GET_UNCONFIRMED] = { .call = ctnetlink_get_ct_unconfirmed, .type = NFNL_CB_MUTEX, }, }; static const struct nfnl_callback ctnl_exp_cb[IPCTNL_MSG_EXP_MAX] = { [IPCTNL_MSG_EXP_GET] = { .call = ctnetlink_get_expect, .type = NFNL_CB_MUTEX, .attr_count = CTA_EXPECT_MAX, .policy = exp_nla_policy }, [IPCTNL_MSG_EXP_NEW] = { .call = ctnetlink_new_expect, .type = NFNL_CB_MUTEX, .attr_count = CTA_EXPECT_MAX, .policy = exp_nla_policy }, [IPCTNL_MSG_EXP_DELETE] = { .call = ctnetlink_del_expect, .type = NFNL_CB_MUTEX, .attr_count = CTA_EXPECT_MAX, .policy = exp_nla_policy }, [IPCTNL_MSG_EXP_GET_STATS_CPU] = { .call = ctnetlink_stat_exp_cpu, .type = NFNL_CB_MUTEX, }, }; static const struct nfnetlink_subsystem ctnl_subsys = { .name = "conntrack", .subsys_id = NFNL_SUBSYS_CTNETLINK, .cb_count = IPCTNL_MSG_MAX, .cb = ctnl_cb, }; static const struct nfnetlink_subsystem ctnl_exp_subsys = { .name = "conntrack_expect", .subsys_id = NFNL_SUBSYS_CTNETLINK_EXP, .cb_count = IPCTNL_MSG_EXP_MAX, .cb = ctnl_exp_cb, }; MODULE_ALIAS("ip_conntrack_netlink"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_EXP); static int __net_init ctnetlink_net_init(struct net *net) { #ifdef CONFIG_NF_CONNTRACK_EVENTS nf_conntrack_register_notifier(net, &ctnl_notifier); #endif return 0; } static void ctnetlink_net_pre_exit(struct net *net) { #ifdef CONFIG_NF_CONNTRACK_EVENTS nf_conntrack_unregister_notifier(net); #endif } static struct pernet_operations ctnetlink_net_ops = { .init = ctnetlink_net_init, .pre_exit = ctnetlink_net_pre_exit, }; static int __init ctnetlink_init(void) { int ret; BUILD_BUG_ON(sizeof(struct ctnetlink_list_dump_ctx) > sizeof_field(struct netlink_callback, ctx)); ret = nfnetlink_subsys_register(&ctnl_subsys); if (ret < 0) { pr_err("ctnetlink_init: cannot register with nfnetlink.\n"); goto err_out; } ret = nfnetlink_subsys_register(&ctnl_exp_subsys); if (ret < 0) { pr_err("ctnetlink_init: cannot register exp with nfnetlink.\n"); goto err_unreg_subsys; } ret = register_pernet_subsys(&ctnetlink_net_ops); if (ret < 0) { pr_err("ctnetlink_init: cannot register pernet operations\n"); goto err_unreg_exp_subsys; } #ifdef CONFIG_NETFILTER_NETLINK_GLUE_CT /* setup interaction between nf_queue and nf_conntrack_netlink. */ RCU_INIT_POINTER(nfnl_ct_hook, &ctnetlink_glue_hook); #endif return 0; err_unreg_exp_subsys: nfnetlink_subsys_unregister(&ctnl_exp_subsys); err_unreg_subsys: nfnetlink_subsys_unregister(&ctnl_subsys); err_out: return ret; } static void __exit ctnetlink_exit(void) { unregister_pernet_subsys(&ctnetlink_net_ops); nfnetlink_subsys_unregister(&ctnl_exp_subsys); nfnetlink_subsys_unregister(&ctnl_subsys); #ifdef CONFIG_NETFILTER_NETLINK_GLUE_CT RCU_INIT_POINTER(nfnl_ct_hook, NULL); #endif synchronize_rcu(); } module_init(ctnetlink_init); module_exit(ctnetlink_exit); |
| 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // 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. * * Implementation of the Transmission Control Protocol(TCP). * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * Corey Minyard <wf-rch!minyard@relay.EU.net> * Florian La Roche, <flla@stud.uni-sb.de> * Charles Hedrick, <hedrick@klinzhai.rutgers.edu> * Linus Torvalds, <torvalds@cs.helsinki.fi> * Alan Cox, <gw4pts@gw4pts.ampr.org> * Matthew Dillon, <dillon@apollo.west.oic.com> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Jorge Cwik, <jorge@laser.satlink.net> * * Fixes: * Alan Cox : Numerous verify_area() calls * Alan Cox : Set the ACK bit on a reset * Alan Cox : Stopped it crashing if it closed while * sk->inuse=1 and was trying to connect * (tcp_err()). * Alan Cox : All icmp error handling was broken * pointers passed where wrong and the * socket was looked up backwards. Nobody * tested any icmp error code obviously. * Alan Cox : tcp_err() now handled properly. It * wakes people on errors. poll * behaves and the icmp error race * has gone by moving it into sock.c * Alan Cox : tcp_send_reset() fixed to work for * everything not just packets for * unknown sockets. * Alan Cox : tcp option processing. * Alan Cox : Reset tweaked (still not 100%) [Had * syn rule wrong] * Herp Rosmanith : More reset fixes * Alan Cox : No longer acks invalid rst frames. * Acking any kind of RST is right out. * Alan Cox : Sets an ignore me flag on an rst * receive otherwise odd bits of prattle * escape still * Alan Cox : Fixed another acking RST frame bug. * Should stop LAN workplace lockups. * Alan Cox : Some tidyups using the new skb list * facilities * Alan Cox : sk->keepopen now seems to work * Alan Cox : Pulls options out correctly on accepts * Alan Cox : Fixed assorted sk->rqueue->next errors * Alan Cox : PSH doesn't end a TCP read. Switched a * bit to skb ops. * Alan Cox : Tidied tcp_data to avoid a potential * nasty. * Alan Cox : Added some better commenting, as the * tcp is hard to follow * Alan Cox : Removed incorrect check for 20 * psh * Michael O'Reilly : ack < copied bug fix. * Johannes Stille : Misc tcp fixes (not all in yet). * Alan Cox : FIN with no memory -> CRASH * Alan Cox : Added socket option proto entries. * Also added awareness of them to accept. * Alan Cox : Added TCP options (SOL_TCP) * Alan Cox : Switched wakeup calls to callbacks, * so the kernel can layer network * sockets. * Alan Cox : Use ip_tos/ip_ttl settings. * Alan Cox : Handle FIN (more) properly (we hope). * Alan Cox : RST frames sent on unsynchronised * state ack error. * Alan Cox : Put in missing check for SYN bit. * Alan Cox : Added tcp_select_window() aka NET2E * window non shrink trick. * Alan Cox : Added a couple of small NET2E timer * fixes * Charles Hedrick : TCP fixes * Toomas Tamm : TCP window fixes * Alan Cox : Small URG fix to rlogin ^C ack fight * Charles Hedrick : Rewrote most of it to actually work * Linus : Rewrote tcp_read() and URG handling * completely * Gerhard Koerting: Fixed some missing timer handling * Matthew Dillon : Reworked TCP machine states as per RFC * Gerhard Koerting: PC/TCP workarounds * Adam Caldwell : Assorted timer/timing errors * Matthew Dillon : Fixed another RST bug * Alan Cox : Move to kernel side addressing changes. * Alan Cox : Beginning work on TCP fastpathing * (not yet usable) * Arnt Gulbrandsen: Turbocharged tcp_check() routine. * Alan Cox : TCP fast path debugging * Alan Cox : Window clamping * Michael Riepe : Bug in tcp_check() * Matt Dillon : More TCP improvements and RST bug fixes * Matt Dillon : Yet more small nasties remove from the * TCP code (Be very nice to this man if * tcp finally works 100%) 8) * Alan Cox : BSD accept semantics. * Alan Cox : Reset on closedown bug. * Peter De Schrijver : ENOTCONN check missing in tcp_sendto(). * Michael Pall : Handle poll() after URG properly in * all cases. * Michael Pall : Undo the last fix in tcp_read_urg() * (multi URG PUSH broke rlogin). * Michael Pall : Fix the multi URG PUSH problem in * tcp_readable(), poll() after URG * works now. * Michael Pall : recv(...,MSG_OOB) never blocks in the * BSD api. * Alan Cox : Changed the semantics of sk->socket to * fix a race and a signal problem with * accept() and async I/O. * Alan Cox : Relaxed the rules on tcp_sendto(). * Yury Shevchuk : Really fixed accept() blocking problem. * Craig I. Hagan : Allow for BSD compatible TIME_WAIT for * clients/servers which listen in on * fixed ports. * Alan Cox : Cleaned the above up and shrank it to * a sensible code size. * Alan Cox : Self connect lockup fix. * Alan Cox : No connect to multicast. * Ross Biro : Close unaccepted children on master * socket close. * Alan Cox : Reset tracing code. * Alan Cox : Spurious resets on shutdown. * Alan Cox : Giant 15 minute/60 second timer error * Alan Cox : Small whoops in polling before an * accept. * Alan Cox : Kept the state trace facility since * it's handy for debugging. * Alan Cox : More reset handler fixes. * Alan Cox : Started rewriting the code based on * the RFC's for other useful protocol * references see: Comer, KA9Q NOS, and * for a reference on the difference * between specifications and how BSD * works see the 4.4lite source. * A.N.Kuznetsov : Don't time wait on completion of tidy * close. * Linus Torvalds : Fin/Shutdown & copied_seq changes. * Linus Torvalds : Fixed BSD port reuse to work first syn * Alan Cox : Reimplemented timers as per the RFC * and using multiple timers for sanity. * Alan Cox : Small bug fixes, and a lot of new * comments. * Alan Cox : Fixed dual reader crash by locking * the buffers (much like datagram.c) * Alan Cox : Fixed stuck sockets in probe. A probe * now gets fed up of retrying without * (even a no space) answer. * Alan Cox : Extracted closing code better * Alan Cox : Fixed the closing state machine to * resemble the RFC. * Alan Cox : More 'per spec' fixes. * Jorge Cwik : Even faster checksumming. * Alan Cox : tcp_data() doesn't ack illegal PSH * only frames. At least one pc tcp stack * generates them. * Alan Cox : Cache last socket. * Alan Cox : Per route irtt. * Matt Day : poll()->select() match BSD precisely on error * Alan Cox : New buffers * Marc Tamsky : Various sk->prot->retransmits and * sk->retransmits misupdating fixed. * Fixed tcp_write_timeout: stuck close, * and TCP syn retries gets used now. * Mark Yarvis : In tcp_read_wakeup(), don't send an * ack if state is TCP_CLOSED. * Alan Cox : Look up device on a retransmit - routes may * change. Doesn't yet cope with MSS shrink right * but it's a start! * Marc Tamsky : Closing in closing fixes. * Mike Shaver : RFC1122 verifications. * Alan Cox : rcv_saddr errors. * Alan Cox : Block double connect(). * Alan Cox : Small hooks for enSKIP. * Alexey Kuznetsov: Path MTU discovery. * Alan Cox : Support soft errors. * Alan Cox : Fix MTU discovery pathological case * when the remote claims no mtu! * Marc Tamsky : TCP_CLOSE fix. * Colin (G3TNE) : Send a reset on syn ack replies in * window but wrong (fixes NT lpd problems) * Pedro Roque : Better TCP window handling, delayed ack. * Joerg Reuter : No modification of locked buffers in * tcp_do_retransmit() * Eric Schenk : Changed receiver side silly window * avoidance algorithm to BSD style * algorithm. This doubles throughput * against machines running Solaris, * and seems to result in general * improvement. * Stefan Magdalinski : adjusted tcp_readable() to fix FIONREAD * Willy Konynenberg : Transparent proxying support. * Mike McLagan : Routing by source * Keith Owens : Do proper merging with partial SKB's in * tcp_do_sendmsg to avoid burstiness. * Eric Schenk : Fix fast close down bug with * shutdown() followed by close(). * Andi Kleen : Make poll agree with SIGIO * Salvatore Sanfilippo : Support SO_LINGER with linger == 1 and * lingertime == 0 (RFC 793 ABORT Call) * Hirokazu Takahashi : Use copy_from_user() instead of * csum_and_copy_from_user() if possible. * * Description of States: * * TCP_SYN_SENT sent a connection request, waiting for ack * * TCP_SYN_RECV received a connection request, sent ack, * waiting for final ack in three-way handshake. * * TCP_ESTABLISHED connection established * * TCP_FIN_WAIT1 our side has shutdown, waiting to complete * transmission of remaining buffered data * * TCP_FIN_WAIT2 all buffered data sent, waiting for remote * to shutdown * * TCP_CLOSING both sides have shutdown but we still have * data we have to finish sending * * TCP_TIME_WAIT timeout to catch resent junk before entering * closed, can only be entered from FIN_WAIT2 * or CLOSING. Required because the other end * may not have gotten our last ACK causing it * to retransmit the data packet (which we ignore) * * TCP_CLOSE_WAIT remote side has shutdown and is waiting for * us to finish writing our data and to shutdown * (we have to close() to move on to LAST_ACK) * * TCP_LAST_ACK out side has shutdown after remote has * shutdown. There may still be data in our * buffer that we have to finish sending * * TCP_CLOSE socket is finished */ #define pr_fmt(fmt) "TCP: " fmt #include <crypto/hash.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/poll.h> #include <linux/inet_diag.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/skbuff.h> #include <linux/scatterlist.h> #include <linux/splice.h> #include <linux/net.h> #include <linux/socket.h> #include <linux/random.h> #include <linux/memblock.h> #include <linux/highmem.h> #include <linux/cache.h> #include <linux/err.h> #include <linux/time.h> #include <linux/slab.h> #include <linux/errqueue.h> #include <linux/static_key.h> #include <linux/btf.h> #include <net/icmp.h> #include <net/inet_common.h> #include <net/tcp.h> #include <net/mptcp.h> #include <net/xfrm.h> #include <net/ip.h> #include <net/sock.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <net/busy_poll.h> /* Track pending CMSGs. */ enum { TCP_CMSG_INQ = 1, TCP_CMSG_TS = 2 }; DEFINE_PER_CPU(unsigned int, tcp_orphan_count); EXPORT_PER_CPU_SYMBOL_GPL(tcp_orphan_count); long sysctl_tcp_mem[3] __read_mostly; EXPORT_SYMBOL(sysctl_tcp_mem); atomic_long_t tcp_memory_allocated ____cacheline_aligned_in_smp; /* Current allocated memory. */ EXPORT_SYMBOL(tcp_memory_allocated); DEFINE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc); EXPORT_PER_CPU_SYMBOL_GPL(tcp_memory_per_cpu_fw_alloc); #if IS_ENABLED(CONFIG_SMC) DEFINE_STATIC_KEY_FALSE(tcp_have_smc); EXPORT_SYMBOL(tcp_have_smc); #endif /* * Current number of TCP sockets. */ struct percpu_counter tcp_sockets_allocated ____cacheline_aligned_in_smp; EXPORT_SYMBOL(tcp_sockets_allocated); /* * TCP splice context */ struct tcp_splice_state { struct pipe_inode_info *pipe; size_t len; unsigned int flags; }; /* * Pressure flag: try to collapse. * Technical note: it is used by multiple contexts non atomically. * All the __sk_mem_schedule() is of this nature: accounting * is strict, actions are advisory and have some latency. */ unsigned long tcp_memory_pressure __read_mostly; EXPORT_SYMBOL_GPL(tcp_memory_pressure); void tcp_enter_memory_pressure(struct sock *sk) { unsigned long val; if (READ_ONCE(tcp_memory_pressure)) return; val = jiffies; if (!val) val--; if (!cmpxchg(&tcp_memory_pressure, 0, val)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURES); } EXPORT_SYMBOL_GPL(tcp_enter_memory_pressure); void tcp_leave_memory_pressure(struct sock *sk) { unsigned long val; if (!READ_ONCE(tcp_memory_pressure)) return; val = xchg(&tcp_memory_pressure, 0); if (val) NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURESCHRONO, jiffies_to_msecs(jiffies - val)); } EXPORT_SYMBOL_GPL(tcp_leave_memory_pressure); /* Convert seconds to retransmits based on initial and max timeout */ static u8 secs_to_retrans(int seconds, int timeout, int rto_max) { u8 res = 0; if (seconds > 0) { int period = timeout; res = 1; while (seconds > period && res < 255) { res++; timeout <<= 1; if (timeout > rto_max) timeout = rto_max; period += timeout; } } return res; } /* Convert retransmits to seconds based on initial and max timeout */ static int retrans_to_secs(u8 retrans, int timeout, int rto_max) { int period = 0; if (retrans > 0) { period = timeout; while (--retrans) { timeout <<= 1; if (timeout > rto_max) timeout = rto_max; period += timeout; } } return period; } static u64 tcp_compute_delivery_rate(const struct tcp_sock *tp) { u32 rate = READ_ONCE(tp->rate_delivered); u32 intv = READ_ONCE(tp->rate_interval_us); u64 rate64 = 0; if (rate && intv) { rate64 = (u64)rate * tp->mss_cache * USEC_PER_SEC; do_div(rate64, intv); } return rate64; } /* Address-family independent initialization for a tcp_sock. * * NOTE: A lot of things set to zero explicitly by call to * sk_alloc() so need not be done here. */ void tcp_init_sock(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); tp->out_of_order_queue = RB_ROOT; sk->tcp_rtx_queue = RB_ROOT; tcp_init_xmit_timers(sk); INIT_LIST_HEAD(&tp->tsq_node); INIT_LIST_HEAD(&tp->tsorted_sent_queue); icsk->icsk_rto = TCP_TIMEOUT_INIT; icsk->icsk_rto_min = TCP_RTO_MIN; icsk->icsk_delack_max = TCP_DELACK_MAX; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U); /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control * algorithms that we must have the following bandaid to talk * efficiently to them. -DaveM */ tcp_snd_cwnd_set(tp, TCP_INIT_CWND); /* There's a bubble in the pipe until at least the first ACK. */ tp->app_limited = ~0U; tp->rate_app_limited = 1; /* See draft-stevens-tcpca-spec-01 for discussion of the * initialization of these values. */ tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_clamp = ~0; tp->mss_cache = TCP_MSS_DEFAULT; tp->reordering = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering); tcp_assign_congestion_control(sk); tp->tsoffset = 0; tp->rack.reo_wnd_steps = 1; sk->sk_write_space = sk_stream_write_space; sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); icsk->icsk_sync_mss = tcp_sync_mss; WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1])); WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1])); set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); sk_sockets_allocated_inc(sk); } EXPORT_SYMBOL(tcp_init_sock); static void tcp_tx_timestamp(struct sock *sk, u16 tsflags) { struct sk_buff *skb = tcp_write_queue_tail(sk); if (tsflags && skb) { struct skb_shared_info *shinfo = skb_shinfo(skb); struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); sock_tx_timestamp(sk, tsflags, &shinfo->tx_flags); if (tsflags & SOF_TIMESTAMPING_TX_ACK) tcb->txstamp_ack = 1; if (tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) shinfo->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1; } } static bool tcp_stream_is_readable(struct sock *sk, int target) { if (tcp_epollin_ready(sk, target)) return true; return sk_is_readable(sk); } /* * Wait for a TCP event. * * Note that we don't need to lock the socket, as the upper poll layers * take care of normal races (between the test and the event) and we don't * go look at any of the socket buffers directly. */ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) { __poll_t mask; struct sock *sk = sock->sk; const struct tcp_sock *tp = tcp_sk(sk); u8 shutdown; int state; sock_poll_wait(file, sock, wait); state = inet_sk_state_load(sk); if (state == TCP_LISTEN) return inet_csk_listen_poll(sk); /* Socket is not locked. We are protected from async events * by poll logic and correct handling of state changes * made by other threads is impossible in any case. */ mask = 0; /* * EPOLLHUP is certainly not done right. But poll() doesn't * have a notion of HUP in just one direction, and for a * socket the read side is more interesting. * * Some poll() documentation says that EPOLLHUP is incompatible * with the EPOLLOUT/POLLWR flags, so somebody should check this * all. But careful, it tends to be safer to return too many * bits than too few, and you can easily break real applications * if you don't tell them that something has hung up! * * Check-me. * * Check number 1. EPOLLHUP is _UNMASKABLE_ event (see UNIX98 and * our fs/select.c). It means that after we received EOF, * poll always returns immediately, making impossible poll() on write() * in state CLOSE_WAIT. One solution is evident --- to set EPOLLHUP * if and only if shutdown has been made in both directions. * Actually, it is interesting to look how Solaris and DUX * solve this dilemma. I would prefer, if EPOLLHUP were maskable, * then we could set it on SND_SHUTDOWN. BTW examples given * in Stevens' books assume exactly this behaviour, it explains * why EPOLLHUP is incompatible with EPOLLOUT. --ANK * * NOTE. Check for TCP_CLOSE is added. The goal is to prevent * blocking on fresh not-connected or disconnected socket. --ANK */ shutdown = READ_ONCE(sk->sk_shutdown); if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) mask |= EPOLLHUP; if (shutdown & RCV_SHUTDOWN) mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; /* Connected or passive Fast Open socket? */ if (state != TCP_SYN_SENT && (state != TCP_SYN_RECV || rcu_access_pointer(tp->fastopen_rsk))) { int target = sock_rcvlowat(sk, 0, INT_MAX); u16 urg_data = READ_ONCE(tp->urg_data); if (unlikely(urg_data) && READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq) && !sock_flag(sk, SOCK_URGINLINE)) target++; if (tcp_stream_is_readable(sk, target)) mask |= EPOLLIN | EPOLLRDNORM; if (!(shutdown & SEND_SHUTDOWN)) { if (__sk_stream_is_writeable(sk, 1)) { mask |= EPOLLOUT | EPOLLWRNORM; } else { /* send SIGIO later */ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); /* Race breaker. If space is freed after * wspace test but before the flags are set, * IO signal will be lost. Memory barrier * pairs with the input side. */ smp_mb__after_atomic(); if (__sk_stream_is_writeable(sk, 1)) mask |= EPOLLOUT | EPOLLWRNORM; } } else mask |= EPOLLOUT | EPOLLWRNORM; if (urg_data & TCP_URG_VALID) mask |= EPOLLPRI; } else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) { /* Active TCP fastopen socket with defer_connect * Return EPOLLOUT so application can call write() * in order for kernel to generate SYN+data */ mask |= EPOLLOUT | EPOLLWRNORM; } /* This barrier is coupled with smp_wmb() in tcp_done_with_error() */ smp_rmb(); if (READ_ONCE(sk->sk_err) || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR; return mask; } EXPORT_SYMBOL(tcp_poll); int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) { struct tcp_sock *tp = tcp_sk(sk); int answ; bool slow; switch (cmd) { case SIOCINQ: if (sk->sk_state == TCP_LISTEN) return -EINVAL; slow = lock_sock_fast(sk); answ = tcp_inq(sk); unlock_sock_fast(sk, slow); break; case SIOCATMARK: answ = READ_ONCE(tp->urg_data) && READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq); break; case SIOCOUTQ: if (sk->sk_state == TCP_LISTEN) return -EINVAL; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else answ = READ_ONCE(tp->write_seq) - tp->snd_una; break; case SIOCOUTQNSD: if (sk->sk_state == TCP_LISTEN) return -EINVAL; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else answ = READ_ONCE(tp->write_seq) - READ_ONCE(tp->snd_nxt); break; default: return -ENOIOCTLCMD; } return put_user(answ, (int __user *)arg); } EXPORT_SYMBOL(tcp_ioctl); void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb) { TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; tp->pushed_seq = tp->write_seq; } static inline bool forced_push(const struct tcp_sock *tp) { return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1)); } void tcp_skb_entail(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); tcb->seq = tcb->end_seq = tp->write_seq; tcb->tcp_flags = TCPHDR_ACK; __skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); if (tp->nonagle & TCP_NAGLE_PUSH) tp->nonagle &= ~TCP_NAGLE_PUSH; tcp_slow_start_after_idle_check(sk); } static inline void tcp_mark_urg(struct tcp_sock *tp, int flags) { if (flags & MSG_OOB) tp->snd_up = tp->write_seq; } /* If a not yet filled skb is pushed, do not send it if * we have data packets in Qdisc or NIC queues : * Because TX completion will happen shortly, it gives a chance * to coalesce future sendmsg() payload into this skb, without * need for a timer, and with no latency trade off. * As packets containing data payload have a bigger truesize * than pure acks (dataless) packets, the last checks prevent * autocorking if we only have an ACK in Qdisc/NIC queues, * or if TX completion was delayed after we processed ACK packet. */ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb, int size_goal) { return skb->len < size_goal && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_autocorking) && !tcp_rtx_queue_empty(sk) && refcount_read(&sk->sk_wmem_alloc) > skb->truesize && tcp_skb_can_collapse_to(skb); } void tcp_push(struct sock *sk, int flags, int mss_now, int nonagle, int size_goal) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; skb = tcp_write_queue_tail(sk); if (!skb) return; if (!(flags & MSG_MORE) || forced_push(tp)) tcp_mark_push(tp, skb); tcp_mark_urg(tp, flags); if (tcp_should_autocork(sk, skb, size_goal)) { /* avoid atomic op if TSQ_THROTTLED bit is already set */ if (!test_bit(TSQ_THROTTLED, &sk->sk_tsq_flags)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING); set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); smp_mb__after_atomic(); } /* It is possible TX completion already happened * before we set TSQ_THROTTLED. */ if (refcount_read(&sk->sk_wmem_alloc) > skb->truesize) return; } if (flags & MSG_MORE) nonagle = TCP_NAGLE_CORK; __tcp_push_pending_frames(sk, mss_now, nonagle); } static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, unsigned int offset, size_t len) { struct tcp_splice_state *tss = rd_desc->arg.data; int ret; ret = skb_splice_bits(skb, skb->sk, offset, tss->pipe, min(rd_desc->count, len), tss->flags); if (ret > 0) rd_desc->count -= ret; return ret; } static int __tcp_splice_read(struct sock *sk, struct tcp_splice_state *tss) { /* Store TCP splice context information in read_descriptor_t. */ read_descriptor_t rd_desc = { .arg.data = tss, .count = tss->len, }; return tcp_read_sock(sk, &rd_desc, tcp_splice_data_recv); } /** * tcp_splice_read - splice data from TCP socket to a pipe * @sock: socket to splice from * @ppos: position (not valid) * @pipe: pipe to splice to * @len: number of bytes to splice * @flags: splice modifier flags * * Description: * Will read pages from given socket and fill them into a pipe. * **/ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct sock *sk = sock->sk; struct tcp_splice_state tss = { .pipe = pipe, .len = len, .flags = flags, }; long timeo; ssize_t spliced; int ret; sock_rps_record_flow(sk); /* * We can't seek on a socket input */ if (unlikely(*ppos)) return -ESPIPE; ret = spliced = 0; lock_sock(sk); timeo = sock_rcvtimeo(sk, sock->file->f_flags & O_NONBLOCK); while (tss.len) { ret = __tcp_splice_read(sk, &tss); if (ret < 0) break; else if (!ret) { if (spliced) break; if (sock_flag(sk, SOCK_DONE)) break; if (sk->sk_err) { ret = sock_error(sk); break; } if (sk->sk_shutdown & RCV_SHUTDOWN) break; if (sk->sk_state == TCP_CLOSE) { /* * This occurs when user tries to read * from never connected socket. */ ret = -ENOTCONN; break; } if (!timeo) { ret = -EAGAIN; break; } /* if __tcp_splice_read() got nothing while we have * an skb in receive queue, we do not want to loop. * This might happen with URG data. */ if (!skb_queue_empty(&sk->sk_receive_queue)) break; sk_wait_data(sk, &timeo, NULL); if (signal_pending(current)) { ret = sock_intr_errno(timeo); break; } continue; } tss.len -= ret; spliced += ret; if (!timeo) break; release_sock(sk); lock_sock(sk); if (sk->sk_err || sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN) || signal_pending(current)) break; } release_sock(sk); if (spliced) return spliced; return ret; } EXPORT_SYMBOL(tcp_splice_read); struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, bool force_schedule) { struct sk_buff *skb; skb = alloc_skb_fclone(size + MAX_TCP_HEADER, gfp); if (likely(skb)) { bool mem_scheduled; skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); if (force_schedule) { mem_scheduled = true; sk_forced_mem_schedule(sk, skb->truesize); } else { mem_scheduled = sk_wmem_schedule(sk, skb->truesize); } if (likely(mem_scheduled)) { skb_reserve(skb, MAX_TCP_HEADER); skb->ip_summed = CHECKSUM_PARTIAL; INIT_LIST_HEAD(&skb->tcp_tsorted_anchor); return skb; } __kfree_skb(skb); } else { sk->sk_prot->enter_memory_pressure(sk); sk_stream_moderate_sndbuf(sk); } return NULL; } static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, int large_allowed) { struct tcp_sock *tp = tcp_sk(sk); u32 new_size_goal, size_goal; if (!large_allowed) return mss_now; /* Note : tcp_tso_autosize() will eventually split this later */ new_size_goal = tcp_bound_to_half_wnd(tp, sk->sk_gso_max_size); /* We try hard to avoid divides here */ size_goal = tp->gso_segs * mss_now; if (unlikely(new_size_goal < size_goal || new_size_goal >= size_goal + mss_now)) { tp->gso_segs = min_t(u16, new_size_goal / mss_now, sk->sk_gso_max_segs); size_goal = tp->gso_segs * mss_now; } return max(size_goal, mss_now); } int tcp_send_mss(struct sock *sk, int *size_goal, int flags) { int mss_now; mss_now = tcp_current_mss(sk); *size_goal = tcp_xmit_size_goal(sk, mss_now, !(flags & MSG_OOB)); return mss_now; } /* In some cases, both sendpage() and sendmsg() could have added * an skb to the write queue, but failed adding payload on it. * We need to remove it to consume less memory, but more * importantly be able to generate EPOLLOUT for Edge Trigger epoll() * users. */ void tcp_remove_empty_skb(struct sock *sk) { struct sk_buff *skb = tcp_write_queue_tail(sk); if (skb && TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { tcp_unlink_write_queue(skb, sk); if (tcp_write_queue_empty(sk)) tcp_chrono_stop(sk, TCP_CHRONO_BUSY); tcp_wmem_free_skb(sk, skb); } } /* skb changing from pure zc to mixed, must charge zc */ static int tcp_downgrade_zcopy_pure(struct sock *sk, struct sk_buff *skb) { if (unlikely(skb_zcopy_pure(skb))) { u32 extra = skb->truesize - SKB_TRUESIZE(skb_end_offset(skb)); if (!sk_wmem_schedule(sk, extra)) return -ENOMEM; sk_mem_charge(sk, extra); skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY; } return 0; } static int tcp_wmem_schedule(struct sock *sk, int copy) { int left; if (likely(sk_wmem_schedule(sk, copy))) return copy; /* We could be in trouble if we have nothing queued. * Use whatever is left in sk->sk_forward_alloc and tcp_wmem[0] * to guarantee some progress. */ left = sock_net(sk)->ipv4.sysctl_tcp_wmem[0] - sk->sk_wmem_queued; if (left > 0) sk_forced_mem_schedule(sk, min(left, copy)); return min(copy, sk->sk_forward_alloc); } static struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags, struct page *page, int offset, size_t *size) { struct sk_buff *skb = tcp_write_queue_tail(sk); struct tcp_sock *tp = tcp_sk(sk); bool can_coalesce; int copy, i; if (!skb || (copy = size_goal - skb->len) <= 0 || !tcp_skb_can_collapse_to(skb)) { new_segment: if (!sk_stream_memory_free(sk)) return NULL; skb = tcp_stream_alloc_skb(sk, 0, sk->sk_allocation, tcp_rtx_and_write_queues_empty(sk)); if (!skb) return NULL; #ifdef CONFIG_TLS_DEVICE skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED); #endif tcp_skb_entail(sk, skb); copy = size_goal; } if (copy > *size) copy = *size; i = skb_shinfo(skb)->nr_frags; can_coalesce = skb_can_coalesce(skb, i, page, offset); if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) { tcp_mark_push(tp, skb); goto new_segment; } if (tcp_downgrade_zcopy_pure(sk, skb)) return NULL; copy = tcp_wmem_schedule(sk, copy); if (!copy) return NULL; if (can_coalesce) { skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); } else { get_page(page); skb_fill_page_desc_noacc(skb, i, page, offset, copy); } if (!(flags & MSG_NO_SHARED_FRAGS)) skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG; skb->len += copy; skb->data_len += copy; skb->truesize += copy; sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); WRITE_ONCE(tp->write_seq, tp->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0); *size = copy; return skb; } ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, size_t size, int flags) { struct tcp_sock *tp = tcp_sk(sk); int mss_now, size_goal; int err; ssize_t copied; long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); if (IS_ENABLED(CONFIG_DEBUG_VM) && WARN_ONCE(!sendpage_ok(page), "page must not be a Slab one and have page_count > 0")) return -EINVAL; /* Wait for a connection to finish. One exception is TCP Fast Open * (passive side) where data is allowed to be sent before a connection * is fully established. */ if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) && !tcp_passive_fastopen(sk)) { err = sk_stream_wait_connect(sk, &timeo); if (err != 0) goto out_err; } sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); mss_now = tcp_send_mss(sk, &size_goal, flags); copied = 0; err = -EPIPE; if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto out_err; while (size > 0) { struct sk_buff *skb; size_t copy = size; skb = tcp_build_frag(sk, size_goal, flags, page, offset, ©); if (!skb) goto wait_for_space; if (!copied) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; copied += copy; offset += copy; size -= copy; if (!size) goto out; if (skb->len < size_goal || (flags & MSG_OOB)) continue; if (forced_push(tp)) { tcp_mark_push(tp, skb); __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH); } else if (skb == tcp_send_head(sk)) tcp_push_one(sk, mss_now); continue; wait_for_space: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH, size_goal); err = sk_stream_wait_memory(sk, &timeo); if (err != 0) goto do_error; mss_now = tcp_send_mss(sk, &size_goal, flags); } out: if (copied) { tcp_tx_timestamp(sk, sk->sk_tsflags); if (!(flags & MSG_SENDPAGE_NOTLAST)) tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); } return copied; do_error: tcp_remove_empty_skb(sk); if (copied) goto out; out_err: /* make sure we wake any epoll edge trigger waiter */ if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } return sk_stream_error(sk, flags, err); } EXPORT_SYMBOL_GPL(do_tcp_sendpages); int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags) { if (!(sk->sk_route_caps & NETIF_F_SG)) return sock_no_sendpage_locked(sk, page, offset, size, flags); tcp_rate_check_app_limited(sk); /* is sending application-limited? */ return do_tcp_sendpages(sk, page, offset, size, flags); } EXPORT_SYMBOL_GPL(tcp_sendpage_locked); int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { int ret; lock_sock(sk); ret = tcp_sendpage_locked(sk, page, offset, size, flags); release_sock(sk); return ret; } EXPORT_SYMBOL(tcp_sendpage); void tcp_free_fastopen_req(struct tcp_sock *tp) { if (tp->fastopen_req) { kfree(tp->fastopen_req); tp->fastopen_req = NULL; } } int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, size_t size, struct ubuf_info *uarg) { struct tcp_sock *tp = tcp_sk(sk); struct inet_sock *inet = inet_sk(sk); struct sockaddr *uaddr = msg->msg_name; int err, flags; if (!(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) & TFO_CLIENT_ENABLE) || (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) && uaddr->sa_family == AF_UNSPEC)) return -EOPNOTSUPP; if (tp->fastopen_req) return -EALREADY; /* Another Fast Open is in progress */ tp->fastopen_req = kzalloc(sizeof(struct tcp_fastopen_request), sk->sk_allocation); if (unlikely(!tp->fastopen_req)) return -ENOBUFS; tp->fastopen_req->data = msg; tp->fastopen_req->size = size; tp->fastopen_req->uarg = uarg; if (inet->defer_connect) { err = tcp_connect(sk); /* Same failure procedure as in tcp_v4/6_connect */ if (err) { tcp_set_state(sk, TCP_CLOSE); inet->inet_dport = 0; sk->sk_route_caps = 0; } } flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0; err = __inet_stream_connect(sk->sk_socket, uaddr, msg->msg_namelen, flags, 1); /* fastopen_req could already be freed in __inet_stream_connect * if the connection times out or gets rst */ if (tp->fastopen_req) { *copied = tp->fastopen_req->copied; tcp_free_fastopen_req(tp); inet->defer_connect = 0; } return err; } int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) { struct tcp_sock *tp = tcp_sk(sk); struct ubuf_info *uarg = NULL; struct sk_buff *skb; struct sockcm_cookie sockc; int flags, err, copied = 0; int mss_now = 0, size_goal, copied_syn = 0; int process_backlog = 0; bool zc = false; long timeo; flags = msg->msg_flags; if ((flags & MSG_ZEROCOPY) && size) { skb = tcp_write_queue_tail(sk); if (msg->msg_ubuf) { uarg = msg->msg_ubuf; net_zcopy_get(uarg); zc = sk->sk_route_caps & NETIF_F_SG; } else if (sock_flag(sk, SOCK_ZEROCOPY)) { uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb)); if (!uarg) { err = -ENOBUFS; goto out_err; } zc = sk->sk_route_caps & NETIF_F_SG; if (!zc) uarg_to_msgzc(uarg)->zerocopy = 0; } } if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) && !tp->repair) { err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size, uarg); if (err == -EINPROGRESS && copied_syn > 0) goto out; else if (err) goto out_err; } timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); tcp_rate_check_app_limited(sk); /* is sending application-limited? */ /* Wait for a connection to finish. One exception is TCP Fast Open * (passive side) where data is allowed to be sent before a connection * is fully established. */ if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) && !tcp_passive_fastopen(sk)) { err = sk_stream_wait_connect(sk, &timeo); if (err != 0) goto do_error; } if (unlikely(tp->repair)) { if (tp->repair_queue == TCP_RECV_QUEUE) { copied = tcp_send_rcvq(sk, msg, size); goto out_nopush; } err = -EINVAL; if (tp->repair_queue == TCP_NO_QUEUE) goto out_err; /* 'common' sending to sendq */ } sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) { err = -EINVAL; goto out_err; } } /* This should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); /* Ok commence sending. */ copied = 0; restart: mss_now = tcp_send_mss(sk, &size_goal, flags); err = -EPIPE; if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto do_error; while (msg_data_left(msg)) { int copy = 0; skb = tcp_write_queue_tail(sk); if (skb) copy = size_goal - skb->len; if (copy <= 0 || !tcp_skb_can_collapse_to(skb)) { bool first_skb; new_segment: if (!sk_stream_memory_free(sk)) goto wait_for_space; if (unlikely(process_backlog >= 16)) { process_backlog = 0; if (sk_flush_backlog(sk)) goto restart; } first_skb = tcp_rtx_and_write_queues_empty(sk); skb = tcp_stream_alloc_skb(sk, 0, sk->sk_allocation, first_skb); if (!skb) goto wait_for_space; process_backlog++; tcp_skb_entail(sk, skb); copy = size_goal; /* All packets are restored as if they have * already been sent. skb_mstamp_ns isn't set to * avoid wrong rtt estimation. */ if (tp->repair) TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED; } /* Try to append data to the end of skb. */ if (copy > msg_data_left(msg)) copy = msg_data_left(msg); if (!zc) { bool merge = true; int i = skb_shinfo(skb)->nr_frags; struct page_frag *pfrag = sk_page_frag(sk); if (!sk_page_frag_refill(sk, pfrag)) goto wait_for_space; if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { if (i >= READ_ONCE(sysctl_max_skb_frags)) { tcp_mark_push(tp, skb); goto new_segment; } merge = false; } copy = min_t(int, copy, pfrag->size - pfrag->offset); if (unlikely(skb_zcopy_pure(skb) || skb_zcopy_managed(skb))) { if (tcp_downgrade_zcopy_pure(sk, skb)) goto wait_for_space; skb_zcopy_downgrade_managed(skb); } copy = tcp_wmem_schedule(sk, copy); if (!copy) goto wait_for_space; err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb, pfrag->page, pfrag->offset, copy); if (err) goto do_error; /* Update the skb. */ if (merge) { skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); } else { skb_fill_page_desc(skb, i, pfrag->page, pfrag->offset, copy); page_ref_inc(pfrag->page); } pfrag->offset += copy; } else { /* First append to a fragless skb builds initial * pure zerocopy skb */ if (!skb->len) skb_shinfo(skb)->flags |= SKBFL_PURE_ZEROCOPY; if (!skb_zcopy_pure(skb)) { copy = tcp_wmem_schedule(sk, copy); if (!copy) goto wait_for_space; } err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg); if (err == -EMSGSIZE || err == -EEXIST) { tcp_mark_push(tp, skb); goto new_segment; } if (err < 0) goto do_error; copy = err; } if (!copied) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; WRITE_ONCE(tp->write_seq, tp->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0); copied += copy; if (!msg_data_left(msg)) { if (unlikely(flags & MSG_EOR)) TCP_SKB_CB(skb)->eor = 1; goto out; } if (skb->len < size_goal || (flags & MSG_OOB) || unlikely(tp->repair)) continue; if (forced_push(tp)) { tcp_mark_push(tp, skb); __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH); } else if (skb == tcp_send_head(sk)) tcp_push_one(sk, mss_now); continue; wait_for_space: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); if (copied) tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH, size_goal); err = sk_stream_wait_memory(sk, &timeo); if (err != 0) goto do_error; mss_now = tcp_send_mss(sk, &size_goal, flags); } out: if (copied) { tcp_tx_timestamp(sk, sockc.tsflags); tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); } out_nopush: net_zcopy_put(uarg); return copied + copied_syn; do_error: tcp_remove_empty_skb(sk); if (copied + copied_syn) goto out; out_err: net_zcopy_put_abort(uarg, true); err = sk_stream_error(sk, flags, err); /* make sure we wake any epoll edge trigger waiter */ if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } return err; } EXPORT_SYMBOL_GPL(tcp_sendmsg_locked); int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { int ret; lock_sock(sk); ret = tcp_sendmsg_locked(sk, msg, size); release_sock(sk); return ret; } EXPORT_SYMBOL(tcp_sendmsg); /* * Handle reading urgent data. BSD has very simple semantics for * this, no blocking and very strange errors 8) */ static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags) { struct tcp_sock *tp = tcp_sk(sk); /* No URG data to read. */ if (sock_flag(sk, SOCK_URGINLINE) || !tp->urg_data || tp->urg_data == TCP_URG_READ) return -EINVAL; /* Yes this is right ! */ if (sk->sk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DONE)) return -ENOTCONN; if (tp->urg_data & TCP_URG_VALID) { int err = 0; char c = tp->urg_data; if (!(flags & MSG_PEEK)) WRITE_ONCE(tp->urg_data, TCP_URG_READ); /* Read urgent data. */ msg->msg_flags |= MSG_OOB; if (len > 0) { if (!(flags & MSG_TRUNC)) err = memcpy_to_msg(msg, &c, 1); len = 1; } else msg->msg_flags |= MSG_TRUNC; return err ? -EFAULT : len; } if (sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN)) return 0; /* Fixed the recv(..., MSG_OOB) behaviour. BSD docs and * the available implementations agree in this case: * this call should never block, independent of the * blocking state of the socket. * Mike <pall@rz.uni-karlsruhe.de> */ return -EAGAIN; } static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len) { struct sk_buff *skb; int copied = 0, err = 0; /* XXX -- need to support SO_PEEK_OFF */ skb_rbtree_walk(skb, &sk->tcp_rtx_queue) { err = skb_copy_datagram_msg(skb, 0, msg, skb->len); if (err) return err; copied += skb->len; } skb_queue_walk(&sk->sk_write_queue, skb) { err = skb_copy_datagram_msg(skb, 0, msg, skb->len); if (err) break; copied += skb->len; } return err ?: copied; } /* Clean up the receive buffer for full frames taken by the user, * then send an ACK if necessary. COPIED is the number of bytes * tcp_recvmsg has given to the user so far, it speeds up the * calculation of whether or not we must ACK for the sake of * a window update. */ void __tcp_cleanup_rbuf(struct sock *sk, int copied) { struct tcp_sock *tp = tcp_sk(sk); bool time_to_ack = false; if (inet_csk_ack_scheduled(sk)) { const struct inet_connection_sock *icsk = inet_csk(sk); if (/* Once-per-two-segments ACK was not sent by tcp_input.c */ tp->rcv_nxt - tp->rcv_wup > icsk->icsk_ack.rcv_mss || /* * If this read emptied read buffer, we send ACK, if * connection is not bidirectional, user drained * receive buffer and there was a small segment * in queue. */ (copied > 0 && ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED2) || ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED) && !inet_csk_in_pingpong_mode(sk))) && !atomic_read(&sk->sk_rmem_alloc))) time_to_ack = true; } /* We send an ACK if we can now advertise a non-zero window * which has been raised "significantly". * * Even if window raised up to infinity, do not send window open ACK * in states, where we will not receive more. It is useless. */ if (copied > 0 && !time_to_ack && !(sk->sk_shutdown & RCV_SHUTDOWN)) { __u32 rcv_window_now = tcp_receive_window(tp); /* Optimize, __tcp_select_window() is not cheap. */ if (2*rcv_window_now <= tp->window_clamp) { __u32 new_window = __tcp_select_window(sk); /* Send ACK now, if this read freed lots of space * in our buffer. Certainly, new_window is new window. * We can advertise it now, if it is not less than current one. * "Lots" means "at least twice" here. */ if (new_window && new_window >= 2 * rcv_window_now) time_to_ack = true; } } if (time_to_ack) tcp_send_ack(sk); } void tcp_cleanup_rbuf(struct sock *sk, int copied) { struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); struct tcp_sock *tp = tcp_sk(sk); WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq), "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n", tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt); __tcp_cleanup_rbuf(sk, copied); } static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb) { __skb_unlink(skb, &sk->sk_receive_queue); if (likely(skb->destructor == sock_rfree)) { sock_rfree(skb); skb->destructor = NULL; skb->sk = NULL; return skb_attempt_defer_free(skb); } __kfree_skb(skb); } struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) { struct sk_buff *skb; u32 offset; while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { offset = seq - TCP_SKB_CB(skb)->seq; if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { pr_err_once("%s: found a SYN, please report !\n", __func__); offset--; } if (offset < skb->len || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) { *off = offset; return skb; } /* This looks weird, but this can happen if TCP collapsing * splitted a fat GRO packet, while we released socket lock * in skb_splice_bits() */ tcp_eat_recv_skb(sk, skb); } return NULL; } EXPORT_SYMBOL(tcp_recv_skb); /* * This routine provides an alternative to tcp_recvmsg() for routines * that would like to handle copying from skbuffs directly in 'sendfile' * fashion. * Note: * - It is assumed that the socket was locked by the caller. * - The routine does not block. * - At present, there is no support for reading OOB data * or for 'peeking' the socket using this routine * (although both would be easy to implement). */ static int __tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor, bool noack, u32 *copied_seq) { struct sk_buff *skb; struct tcp_sock *tp = tcp_sk(sk); u32 seq = *copied_seq; u32 offset; int copied = 0; if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) { if (offset < skb->len) { int used; size_t len; len = skb->len - offset; /* Stop reading if we hit a patch of urgent data */ if (unlikely(tp->urg_data)) { u32 urg_offset = tp->urg_seq - seq; if (urg_offset < len) len = urg_offset; if (!len) break; } used = recv_actor(desc, skb, offset, len); if (used <= 0) { if (!copied) copied = used; break; } if (WARN_ON_ONCE(used > len)) used = len; seq += used; copied += used; offset += used; /* If recv_actor drops the lock (e.g. TCP splice * receive) the skb pointer might be invalid when * getting here: tcp_collapse might have deleted it * while aggregating skbs from the socket queue. */ skb = tcp_recv_skb(sk, seq - 1, &offset); if (!skb) break; /* TCP coalescing might have appended data to the skb. * Try to splice more frags */ if (offset + 1 != skb->len) continue; } if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) { tcp_eat_recv_skb(sk, skb); ++seq; break; } tcp_eat_recv_skb(sk, skb); if (!desc->count) break; WRITE_ONCE(*copied_seq, seq); } WRITE_ONCE(*copied_seq, seq); if (noack) goto out; tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ if (copied > 0) { tcp_recv_skb(sk, seq, &offset); tcp_cleanup_rbuf(sk, copied); } out: return copied; } int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor) { return __tcp_read_sock(sk, desc, recv_actor, false, &tcp_sk(sk)->copied_seq); } EXPORT_SYMBOL(tcp_read_sock); int tcp_read_sock_noack(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor, bool noack, u32 *copied_seq) { return __tcp_read_sock(sk, desc, recv_actor, noack, copied_seq); } int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { struct sk_buff *skb; int copied = 0; if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { u8 tcp_flags; int used; __skb_unlink(skb, &sk->sk_receive_queue); WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); tcp_flags = TCP_SKB_CB(skb)->tcp_flags; used = recv_actor(sk, skb); if (used < 0) { if (!copied) copied = used; break; } copied += used; if (tcp_flags & TCPHDR_FIN) break; } return copied; } EXPORT_SYMBOL(tcp_read_skb); void tcp_read_done(struct sock *sk, size_t len) { struct tcp_sock *tp = tcp_sk(sk); u32 seq = tp->copied_seq; struct sk_buff *skb; size_t left; u32 offset; if (sk->sk_state == TCP_LISTEN) return; left = len; while (left && (skb = tcp_recv_skb(sk, seq, &offset)) != NULL) { int used; used = min_t(size_t, skb->len - offset, left); seq += used; left -= used; if (skb->len > offset + used) break; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) { tcp_eat_recv_skb(sk, skb); ++seq; break; } tcp_eat_recv_skb(sk, skb); } WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ if (left != len) tcp_cleanup_rbuf(sk, len - left); } EXPORT_SYMBOL(tcp_read_done); int tcp_peek_len(struct socket *sock) { return tcp_inq(sock->sk); } EXPORT_SYMBOL(tcp_peek_len); /* Make sure sk_rcvbuf is big enough to satisfy SO_RCVLOWAT hint */ int tcp_set_rcvlowat(struct sock *sk, int val) { int cap; if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) cap = sk->sk_rcvbuf >> 1; else cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1; val = min(val, cap); WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); /* Check if we need to signal EPOLLIN right now */ tcp_data_ready(sk); if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) return 0; val <<= 1; if (val > sk->sk_rcvbuf) { WRITE_ONCE(sk->sk_rcvbuf, val); tcp_sk(sk)->window_clamp = tcp_win_from_space(sk, val); } return 0; } EXPORT_SYMBOL(tcp_set_rcvlowat); void tcp_update_recv_tstamps(struct sk_buff *skb, struct scm_timestamping_internal *tss) { if (skb->tstamp) tss->ts[0] = ktime_to_timespec64(skb->tstamp); else tss->ts[0] = (struct timespec64) {0}; if (skb_hwtstamps(skb)->hwtstamp) tss->ts[2] = ktime_to_timespec64(skb_hwtstamps(skb)->hwtstamp); else tss->ts[2] = (struct timespec64) {0}; } #ifdef CONFIG_MMU static const struct vm_operations_struct tcp_vm_ops = { }; int tcp_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { if (vma->vm_flags & (VM_WRITE | VM_EXEC)) return -EPERM; vm_flags_clear(vma, VM_MAYWRITE | VM_MAYEXEC); /* Instruct vm_insert_page() to not mmap_read_lock(mm) */ vm_flags_set(vma, VM_MIXEDMAP); vma->vm_ops = &tcp_vm_ops; return 0; } EXPORT_SYMBOL(tcp_mmap); static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb, u32 *offset_frag) { skb_frag_t *frag; if (unlikely(offset_skb >= skb->len)) return NULL; offset_skb -= skb_headlen(skb); if ((int)offset_skb < 0 || skb_has_frag_list(skb)) return NULL; frag = skb_shinfo(skb)->frags; while (offset_skb) { if (skb_frag_size(frag) > offset_skb) { *offset_frag = offset_skb; return frag; } offset_skb -= skb_frag_size(frag); ++frag; } *offset_frag = 0; return frag; } static bool can_map_frag(const skb_frag_t *frag) { struct page *page; if (skb_frag_size(frag) != PAGE_SIZE || skb_frag_off(frag)) return false; page = skb_frag_page(frag); if (PageCompound(page) || page->mapping) return false; return true; } static int find_next_mappable_frag(const skb_frag_t *frag, int remaining_in_skb) { int offset = 0; if (likely(can_map_frag(frag))) return 0; while (offset < remaining_in_skb && !can_map_frag(frag)) { offset += skb_frag_size(frag); ++frag; } return offset; } static void tcp_zerocopy_set_hint_for_skb(struct sock *sk, struct tcp_zerocopy_receive *zc, struct sk_buff *skb, u32 offset) { u32 frag_offset, partial_frag_remainder = 0; int mappable_offset; skb_frag_t *frag; /* worst case: skip to next skb. try to improve on this case below */ zc->recv_skip_hint = skb->len - offset; /* Find the frag containing this offset (and how far into that frag) */ frag = skb_advance_to_frag(skb, offset, &frag_offset); if (!frag) return; if (frag_offset) { struct skb_shared_info *info = skb_shinfo(skb); /* We read part of the last frag, must recvmsg() rest of skb. */ if (frag == &info->frags[info->nr_frags - 1]) return; /* Else, we must at least read the remainder in this frag. */ partial_frag_remainder = skb_frag_size(frag) - frag_offset; zc->recv_skip_hint -= partial_frag_remainder; ++frag; } /* partial_frag_remainder: If part way through a frag, must read rest. * mappable_offset: Bytes till next mappable frag, *not* counting bytes * in partial_frag_remainder. */ mappable_offset = find_next_mappable_frag(frag, zc->recv_skip_hint); zc->recv_skip_hint = mappable_offset + partial_frag_remainder; } static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, int flags, struct scm_timestamping_internal *tss, int *cmsg_flags); static int receive_fallback_to_copy(struct sock *sk, struct tcp_zerocopy_receive *zc, int inq, struct scm_timestamping_internal *tss) { unsigned long copy_address = (unsigned long)zc->copybuf_address; struct msghdr msg = {}; struct iovec iov; int err; zc->length = 0; zc->recv_skip_hint = 0; if (copy_address != zc->copybuf_address) return -EINVAL; err = import_single_range(ITER_DEST, (void __user *)copy_address, inq, &iov, &msg.msg_iter); if (err) return err; err = tcp_recvmsg_locked(sk, &msg, inq, MSG_DONTWAIT, tss, &zc->msg_flags); if (err < 0) return err; zc->copybuf_len = err; if (likely(zc->copybuf_len)) { struct sk_buff *skb; u32 offset; skb = tcp_recv_skb(sk, tcp_sk(sk)->copied_seq, &offset); if (skb) tcp_zerocopy_set_hint_for_skb(sk, zc, skb, offset); } return 0; } static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc, struct sk_buff *skb, u32 copylen, u32 *offset, u32 *seq) { unsigned long copy_address = (unsigned long)zc->copybuf_address; struct msghdr msg = {}; struct iovec iov; int err; if (copy_address != zc->copybuf_address) return -EINVAL; err = import_single_range(ITER_DEST, (void __user *)copy_address, copylen, &iov, &msg.msg_iter); if (err) return err; err = skb_copy_datagram_msg(skb, *offset, &msg, copylen); if (err) return err; zc->recv_skip_hint -= copylen; *offset += copylen; *seq += copylen; return (__s32)copylen; } static int tcp_zc_handle_leftover(struct tcp_zerocopy_receive *zc, struct sock *sk, struct sk_buff *skb, u32 *seq, s32 copybuf_len, struct scm_timestamping_internal *tss) { u32 offset, copylen = min_t(u32, copybuf_len, zc->recv_skip_hint); if (!copylen) return 0; /* skb is null if inq < PAGE_SIZE. */ if (skb) { offset = *seq - TCP_SKB_CB(skb)->seq; } else { skb = tcp_recv_skb(sk, *seq, &offset); if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); zc->msg_flags |= TCP_CMSG_TS; } } zc->copybuf_len = tcp_copy_straggler_data(zc, skb, copylen, &offset, seq); return zc->copybuf_len < 0 ? 0 : copylen; } static int tcp_zerocopy_vm_insert_batch_error(struct vm_area_struct *vma, struct page **pending_pages, unsigned long pages_remaining, unsigned long *address, u32 *length, u32 *seq, struct tcp_zerocopy_receive *zc, u32 total_bytes_to_map, int err) { /* At least one page did not map. Try zapping if we skipped earlier. */ if (err == -EBUSY && zc->flags & TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT) { u32 maybe_zap_len; maybe_zap_len = total_bytes_to_map - /* All bytes to map */ *length + /* Mapped or pending */ (pages_remaining * PAGE_SIZE); /* Failed map. */ zap_page_range(vma, *address, maybe_zap_len); err = 0; } if (!err) { unsigned long leftover_pages = pages_remaining; int bytes_mapped; /* We called zap_page_range, try to reinsert. */ err = vm_insert_pages(vma, *address, pending_pages, &pages_remaining); bytes_mapped = PAGE_SIZE * (leftover_pages - pages_remaining); *seq += bytes_mapped; *address += bytes_mapped; } if (err) { /* Either we were unable to zap, OR we zapped, retried an * insert, and still had an issue. Either ways, pages_remaining * is the number of pages we were unable to map, and we unroll * some state we speculatively touched before. */ const int bytes_not_mapped = PAGE_SIZE * pages_remaining; *length -= bytes_not_mapped; zc->recv_skip_hint += bytes_not_mapped; } return err; } static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma, struct page **pages, unsigned int pages_to_map, unsigned long *address, u32 *length, u32 *seq, struct tcp_zerocopy_receive *zc, u32 total_bytes_to_map) { unsigned long pages_remaining = pages_to_map; unsigned int pages_mapped; unsigned int bytes_mapped; int err; err = vm_insert_pages(vma, *address, pages, &pages_remaining); pages_mapped = pages_to_map - (unsigned int)pages_remaining; bytes_mapped = PAGE_SIZE * pages_mapped; /* Even if vm_insert_pages fails, it may have partially succeeded in * mapping (some but not all of the pages). */ *seq += bytes_mapped; *address += bytes_mapped; if (likely(!err)) return 0; /* Error: maybe zap and retry + rollback state for failed inserts. */ return tcp_zerocopy_vm_insert_batch_error(vma, pages + pages_mapped, pages_remaining, address, length, seq, zc, total_bytes_to_map, err); } #define TCP_VALID_ZC_MSG_FLAGS (TCP_CMSG_TS) static void tcp_zc_finalize_rx_tstamp(struct sock *sk, struct tcp_zerocopy_receive *zc, struct scm_timestamping_internal *tss) { unsigned long msg_control_addr; struct msghdr cmsg_dummy; msg_control_addr = (unsigned long)zc->msg_control; cmsg_dummy.msg_control = (void *)msg_control_addr; cmsg_dummy.msg_controllen = (__kernel_size_t)zc->msg_controllen; cmsg_dummy.msg_flags = in_compat_syscall() ? MSG_CMSG_COMPAT : 0; cmsg_dummy.msg_control_is_user = true; zc->msg_flags = 0; if (zc->msg_control == msg_control_addr && zc->msg_controllen == cmsg_dummy.msg_controllen) { tcp_recv_timestamp(&cmsg_dummy, sk, tss); zc->msg_control = (__u64) ((uintptr_t)cmsg_dummy.msg_control); zc->msg_controllen = (__u64)cmsg_dummy.msg_controllen; zc->msg_flags = (__u32)cmsg_dummy.msg_flags; } } #define TCP_ZEROCOPY_PAGE_BATCH_SIZE 32 static int tcp_zerocopy_receive(struct sock *sk, struct tcp_zerocopy_receive *zc, struct scm_timestamping_internal *tss) { u32 length = 0, offset, vma_len, avail_len, copylen = 0; unsigned long address = (unsigned long)zc->address; struct page *pages[TCP_ZEROCOPY_PAGE_BATCH_SIZE]; s32 copybuf_len = zc->copybuf_len; struct tcp_sock *tp = tcp_sk(sk); const skb_frag_t *frags = NULL; unsigned int pages_to_map = 0; struct vm_area_struct *vma; struct sk_buff *skb = NULL; u32 seq = tp->copied_seq; u32 total_bytes_to_map; int inq = tcp_inq(sk); int ret; zc->copybuf_len = 0; zc->msg_flags = 0; if (address & (PAGE_SIZE - 1) || address != zc->address) return -EINVAL; if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; sock_rps_record_flow(sk); if (inq && inq <= copybuf_len) return receive_fallback_to_copy(sk, zc, inq, tss); if (inq < PAGE_SIZE) { zc->length = 0; zc->recv_skip_hint = inq; if (!inq && sock_flag(sk, SOCK_DONE)) return -EIO; return 0; } mmap_read_lock(current->mm); vma = vma_lookup(current->mm, address); if (!vma || vma->vm_ops != &tcp_vm_ops) { mmap_read_unlock(current->mm); return -EINVAL; } vma_len = min_t(unsigned long, zc->length, vma->vm_end - address); avail_len = min_t(u32, vma_len, inq); total_bytes_to_map = avail_len & ~(PAGE_SIZE - 1); if (total_bytes_to_map) { if (!(zc->flags & TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT)) zap_page_range(vma, address, total_bytes_to_map); zc->length = total_bytes_to_map; zc->recv_skip_hint = 0; } else { zc->length = avail_len; zc->recv_skip_hint = avail_len; } ret = 0; while (length + PAGE_SIZE <= zc->length) { int mappable_offset; struct page *page; if (zc->recv_skip_hint < PAGE_SIZE) { u32 offset_frag; if (skb) { if (zc->recv_skip_hint > 0) break; skb = skb->next; offset = seq - TCP_SKB_CB(skb)->seq; } else { skb = tcp_recv_skb(sk, seq, &offset); } if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); zc->msg_flags |= TCP_CMSG_TS; } zc->recv_skip_hint = skb->len - offset; frags = skb_advance_to_frag(skb, offset, &offset_frag); if (!frags || offset_frag) break; } mappable_offset = find_next_mappable_frag(frags, zc->recv_skip_hint); if (mappable_offset) { zc->recv_skip_hint = mappable_offset; break; } page = skb_frag_page(frags); prefetchw(page); pages[pages_to_map++] = page; length += PAGE_SIZE; zc->recv_skip_hint -= PAGE_SIZE; frags++; if (pages_to_map == TCP_ZEROCOPY_PAGE_BATCH_SIZE || zc->recv_skip_hint < PAGE_SIZE) { /* Either full batch, or we're about to go to next skb * (and we cannot unroll failed ops across skbs). */ ret = tcp_zerocopy_vm_insert_batch(vma, pages, pages_to_map, &address, &length, &seq, zc, total_bytes_to_map); if (ret) goto out; pages_to_map = 0; } } if (pages_to_map) { ret = tcp_zerocopy_vm_insert_batch(vma, pages, pages_to_map, &address, &length, &seq, zc, total_bytes_to_map); } out: mmap_read_unlock(current->mm); /* Try to copy straggler data. */ if (!ret) copylen = tcp_zc_handle_leftover(zc, sk, skb, &seq, copybuf_len, tss); if (length + copylen) { WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ tcp_recv_skb(sk, seq, &offset); tcp_cleanup_rbuf(sk, length + copylen); ret = 0; if (length == zc->length) zc->recv_skip_hint = 0; } else { if (!zc->recv_skip_hint && sock_flag(sk, SOCK_DONE)) ret = -EIO; } zc->length = length; return ret; } #endif /* Similar to __sock_recv_timestamp, but does not require an skb */ void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, struct scm_timestamping_internal *tss) { int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); bool has_timestamping = false; if (tss->ts[0].tv_sec || tss->ts[0].tv_nsec) { if (sock_flag(sk, SOCK_RCVTSTAMP)) { if (sock_flag(sk, SOCK_RCVTSTAMPNS)) { if (new_tstamp) { struct __kernel_timespec kts = { .tv_sec = tss->ts[0].tv_sec, .tv_nsec = tss->ts[0].tv_nsec, }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW, sizeof(kts), &kts); } else { struct __kernel_old_timespec ts_old = { .tv_sec = tss->ts[0].tv_sec, .tv_nsec = tss->ts[0].tv_nsec, }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, sizeof(ts_old), &ts_old); } } else { if (new_tstamp) { struct __kernel_sock_timeval stv = { .tv_sec = tss->ts[0].tv_sec, .tv_usec = tss->ts[0].tv_nsec / 1000, }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW, sizeof(stv), &stv); } else { struct __kernel_old_timeval tv = { .tv_sec = tss->ts[0].tv_sec, .tv_usec = tss->ts[0].tv_nsec / 1000, }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, sizeof(tv), &tv); } } } if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_SOFTWARE) has_timestamping = true; else tss->ts[0] = (struct timespec64) {0}; } if (tss->ts[2].tv_sec || tss->ts[2].tv_nsec) { if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_RAW_HARDWARE) has_timestamping = true; else tss->ts[2] = (struct timespec64) {0}; } if (has_timestamping) { tss->ts[1] = (struct timespec64) {0}; if (sock_flag(sk, SOCK_TSTAMP_NEW)) put_cmsg_scm_timestamping64(msg, tss); else put_cmsg_scm_timestamping(msg, tss); } } static int tcp_inq_hint(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); u32 copied_seq = READ_ONCE(tp->copied_seq); u32 rcv_nxt = READ_ONCE(tp->rcv_nxt); int inq; inq = rcv_nxt - copied_seq; if (unlikely(inq < 0 || copied_seq != READ_ONCE(tp->copied_seq))) { lock_sock(sk); inq = tp->rcv_nxt - tp->copied_seq; release_sock(sk); } /* After receiving a FIN, tell the user-space to continue reading * by returning a non-zero inq. */ if (inq == 0 && sock_flag(sk, SOCK_DONE)) inq = 1; return inq; } /* * This routine copies from a sock struct into the user buffer. * * Technical note: in 2.3 we work on _locked_ socket, so that * tricks with *seq access order and skb->users are not required. * Probably, code can be easily improved even more. */ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, int flags, struct scm_timestamping_internal *tss, int *cmsg_flags) { struct tcp_sock *tp = tcp_sk(sk); int copied = 0; u32 peek_seq; u32 *seq; unsigned long used; int err; int target; /* Read at least this many bytes */ long timeo; struct sk_buff *skb, *last; u32 urg_hole = 0; err = -ENOTCONN; if (sk->sk_state == TCP_LISTEN) goto out; if (tp->recvmsg_inq) { *cmsg_flags = TCP_CMSG_INQ; msg->msg_get_inq = 1; } timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); /* Urgent data needs to be handled specially. */ if (flags & MSG_OOB) goto recv_urg; if (unlikely(tp->repair)) { err = -EPERM; if (!(flags & MSG_PEEK)) goto out; if (tp->repair_queue == TCP_SEND_QUEUE) goto recv_sndq; err = -EINVAL; if (tp->repair_queue == TCP_NO_QUEUE) goto out; /* 'common' recv queue MSG_PEEK-ing */ } seq = &tp->copied_seq; if (flags & MSG_PEEK) { peek_seq = tp->copied_seq; seq = &peek_seq; } target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); do { u32 offset; /* Are we at urgent data? Stop if we have read anything or have SIGURG pending. */ if (unlikely(tp->urg_data) && tp->urg_seq == *seq) { if (copied) break; if (signal_pending(current)) { copied = timeo ? sock_intr_errno(timeo) : -EAGAIN; break; } } /* Next get a buffer. */ last = skb_peek_tail(&sk->sk_receive_queue); skb_queue_walk(&sk->sk_receive_queue, skb) { last = skb; /* Now that we have two receive queues this * shouldn't happen. */ if (WARN(before(*seq, TCP_SKB_CB(skb)->seq), "TCP recvmsg seq # bug: copied %X, seq %X, rcvnxt %X, fl %X\n", *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags)) break; offset = *seq - TCP_SKB_CB(skb)->seq; if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { pr_err_once("%s: found a SYN, please report !\n", __func__); offset--; } if (offset < skb->len) goto found_ok_skb; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; WARN(!(flags & MSG_PEEK), "TCP recvmsg seq # bug 2: copied %X, seq %X, rcvnxt %X, fl %X\n", *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags); } /* Well, if we have backlog, try to process it now yet. */ if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) break; if (copied) { if (!timeo || sk->sk_err || sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN) || signal_pending(current)) break; } else { if (sock_flag(sk, SOCK_DONE)) break; if (sk->sk_err) { copied = sock_error(sk); break; } if (sk->sk_shutdown & RCV_SHUTDOWN) break; if (sk->sk_state == TCP_CLOSE) { /* This occurs when user tries to read * from never connected socket. */ copied = -ENOTCONN; break; } if (!timeo) { copied = -EAGAIN; break; } if (signal_pending(current)) { copied = sock_intr_errno(timeo); break; } } if (copied >= target) { /* Do not sleep, just process backlog. */ __sk_flush_backlog(sk); } else { tcp_cleanup_rbuf(sk, copied); sk_wait_data(sk, &timeo, last); } if ((flags & MSG_PEEK) && (peek_seq - copied - urg_hole != tp->copied_seq)) { net_dbg_ratelimited("TCP(%s:%d): Application bug, race in MSG_PEEK\n", current->comm, task_pid_nr(current)); peek_seq = tp->copied_seq; } continue; found_ok_skb: /* Ok so how much can we use? */ used = skb->len - offset; if (len < used) used = len; /* Do we have urgent data here? */ if (unlikely(tp->urg_data)) { u32 urg_offset = tp->urg_seq - *seq; if (urg_offset < used) { if (!urg_offset) { if (!sock_flag(sk, SOCK_URGINLINE)) { WRITE_ONCE(*seq, *seq + 1); urg_hole++; offset++; used--; if (!used) goto skip_copy; } } else used = urg_offset; } } if (!(flags & MSG_TRUNC)) { err = skb_copy_datagram_msg(skb, offset, msg, used); if (err) { /* Exception. Bailout! */ if (!copied) copied = -EFAULT; break; } } WRITE_ONCE(*seq, *seq + used); copied += used; len -= used; tcp_rcv_space_adjust(sk); skip_copy: if (unlikely(tp->urg_data) && after(tp->copied_seq, tp->urg_seq)) { WRITE_ONCE(tp->urg_data, 0); tcp_fast_path_check(sk); } if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); *cmsg_flags |= TCP_CMSG_TS; } if (used + offset < skb->len) continue; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; if (!(flags & MSG_PEEK)) tcp_eat_recv_skb(sk, skb); continue; found_fin_ok: /* Process the FIN. */ WRITE_ONCE(*seq, *seq + 1); if (!(flags & MSG_PEEK)) tcp_eat_recv_skb(sk, skb); break; } while (len > 0); /* According to UNIX98, msg_name/msg_namelen are ignored * on connected socket. I was just happy when found this 8) --ANK */ /* Clean up data we have read: This will do ACK frames. */ tcp_cleanup_rbuf(sk, copied); return copied; out: return err; recv_urg: err = tcp_recv_urg(sk, msg, len, flags); goto out; recv_sndq: err = tcp_peek_sndq(sk, msg, len); goto out; } int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { int cmsg_flags = 0, ret; struct scm_timestamping_internal tss; if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue) && sk->sk_state == TCP_ESTABLISHED) sk_busy_loop(sk, flags & MSG_DONTWAIT); lock_sock(sk); ret = tcp_recvmsg_locked(sk, msg, len, flags, &tss, &cmsg_flags); release_sock(sk); if ((cmsg_flags || msg->msg_get_inq) && ret >= 0) { if (cmsg_flags & TCP_CMSG_TS) tcp_recv_timestamp(msg, sk, &tss); if (msg->msg_get_inq) { msg->msg_inq = tcp_inq_hint(sk); if (cmsg_flags & TCP_CMSG_INQ) put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(msg->msg_inq), &msg->msg_inq); } } return ret; } EXPORT_SYMBOL(tcp_recvmsg); void tcp_set_state(struct sock *sk, int state) { int oldstate = sk->sk_state; /* We defined a new enum for TCP states that are exported in BPF * so as not force the internal TCP states to be frozen. The * following checks will detect if an internal state value ever * differs from the BPF value. If this ever happens, then we will * need to remap the internal value to the BPF value before calling * tcp_call_bpf_2arg. */ BUILD_BUG_ON((int)BPF_TCP_ESTABLISHED != (int)TCP_ESTABLISHED); BUILD_BUG_ON((int)BPF_TCP_SYN_SENT != (int)TCP_SYN_SENT); BUILD_BUG_ON((int)BPF_TCP_SYN_RECV != (int)TCP_SYN_RECV); BUILD_BUG_ON((int)BPF_TCP_FIN_WAIT1 != (int)TCP_FIN_WAIT1); BUILD_BUG_ON((int)BPF_TCP_FIN_WAIT2 != (int)TCP_FIN_WAIT2); BUILD_BUG_ON((int)BPF_TCP_TIME_WAIT != (int)TCP_TIME_WAIT); BUILD_BUG_ON((int)BPF_TCP_CLOSE != (int)TCP_CLOSE); BUILD_BUG_ON((int)BPF_TCP_CLOSE_WAIT != (int)TCP_CLOSE_WAIT); BUILD_BUG_ON((int)BPF_TCP_LAST_ACK != (int)TCP_LAST_ACK); BUILD_BUG_ON((int)BPF_TCP_LISTEN != (int)TCP_LISTEN); BUILD_BUG_ON((int)BPF_TCP_CLOSING != (int)TCP_CLOSING); BUILD_BUG_ON((int)BPF_TCP_NEW_SYN_RECV != (int)TCP_NEW_SYN_RECV); BUILD_BUG_ON((int)BPF_TCP_MAX_STATES != (int)TCP_MAX_STATES); /* bpf uapi header bpf.h defines an anonymous enum with values * BPF_TCP_* used by bpf programs. Currently gcc built vmlinux * is able to emit this enum in DWARF due to the above BUILD_BUG_ON. * But clang built vmlinux does not have this enum in DWARF * since clang removes the above code before generating IR/debuginfo. * Let us explicitly emit the type debuginfo to ensure the * above-mentioned anonymous enum in the vmlinux DWARF and hence BTF * regardless of which compiler is used. */ BTF_TYPE_EMIT_ENUM(BPF_TCP_ESTABLISHED); if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_STATE_CB_FLAG)) tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_STATE_CB, oldstate, state); switch (state) { case TCP_ESTABLISHED: if (oldstate != TCP_ESTABLISHED) TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); break; case TCP_CLOSE_WAIT: if (oldstate == TCP_SYN_RECV) TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); break; case TCP_CLOSE: if (oldstate == TCP_CLOSE_WAIT || oldstate == TCP_ESTABLISHED) TCP_INC_STATS(sock_net(sk), TCP_MIB_ESTABRESETS); sk->sk_prot->unhash(sk); if (inet_csk(sk)->icsk_bind_hash && !(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) inet_put_port(sk); fallthrough; default: if (oldstate == TCP_ESTABLISHED || oldstate == TCP_CLOSE_WAIT) TCP_DEC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); } /* Change state AFTER socket is unhashed to avoid closed * socket sitting in hash tables. */ inet_sk_state_store(sk, state); } EXPORT_SYMBOL_GPL(tcp_set_state); /* * State processing on a close. This implements the state shift for * sending our FIN frame. Note that we only send a FIN for some * states. A shutdown() may have already sent the FIN, or we may be * closed. */ static const unsigned char new_state[16] = { /* current state: new state: action: */ [0 /* (Invalid) */] = TCP_CLOSE, [TCP_ESTABLISHED] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, [TCP_SYN_SENT] = TCP_CLOSE, [TCP_SYN_RECV] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, [TCP_FIN_WAIT1] = TCP_FIN_WAIT1, [TCP_FIN_WAIT2] = TCP_FIN_WAIT2, [TCP_TIME_WAIT] = TCP_CLOSE, [TCP_CLOSE] = TCP_CLOSE, [TCP_CLOSE_WAIT] = TCP_LAST_ACK | TCP_ACTION_FIN, [TCP_LAST_ACK] = TCP_LAST_ACK, [TCP_LISTEN] = TCP_CLOSE, [TCP_CLOSING] = TCP_CLOSING, [TCP_NEW_SYN_RECV] = TCP_CLOSE, /* should not happen ! */ }; static int tcp_close_state(struct sock *sk) { int next = (int)new_state[sk->sk_state]; int ns = next & TCP_STATE_MASK; tcp_set_state(sk, ns); return next & TCP_ACTION_FIN; } /* * Shutdown the sending side of a connection. Much like close except * that we don't receive shut down or sock_set_flag(sk, SOCK_DEAD). */ void tcp_shutdown(struct sock *sk, int how) { /* We need to grab some memory, and put together a FIN, * and then put it into the queue to be sent. * Tim MacKenzie(tym@dibbler.cs.monash.edu.au) 4 Dec '92. */ if (!(how & SEND_SHUTDOWN)) return; /* If we've already sent a FIN, or it's a closed state, skip this. */ if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_SYN_SENT | TCPF_CLOSE_WAIT)) { /* Clear out any half completed packets. FIN if needed. */ if (tcp_close_state(sk)) tcp_send_fin(sk); } } EXPORT_SYMBOL(tcp_shutdown); int tcp_orphan_count_sum(void) { int i, total = 0; for_each_possible_cpu(i) total += per_cpu(tcp_orphan_count, i); return max(total, 0); } static int tcp_orphan_cache; static struct timer_list tcp_orphan_timer; #define TCP_ORPHAN_TIMER_PERIOD msecs_to_jiffies(100) static void tcp_orphan_update(struct timer_list *unused) { WRITE_ONCE(tcp_orphan_cache, tcp_orphan_count_sum()); mod_timer(&tcp_orphan_timer, jiffies + TCP_ORPHAN_TIMER_PERIOD); } static bool tcp_too_many_orphans(int shift) { return READ_ONCE(tcp_orphan_cache) << shift > READ_ONCE(sysctl_tcp_max_orphans); } bool tcp_check_oom(struct sock *sk, int shift) { bool too_many_orphans, out_of_socket_memory; too_many_orphans = tcp_too_many_orphans(shift); out_of_socket_memory = tcp_out_of_memory(sk); if (too_many_orphans) net_info_ratelimited("too many orphaned sockets\n"); if (out_of_socket_memory) net_info_ratelimited("out of memory -- consider tuning tcp_mem\n"); return too_many_orphans || out_of_socket_memory; } void __tcp_close(struct sock *sk, long timeout) { struct sk_buff *skb; int data_was_unread = 0; int state; WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if (sk->sk_state == TCP_LISTEN) { tcp_set_state(sk, TCP_CLOSE); /* Special case. */ inet_csk_listen_stop(sk); goto adjudge_to_death; } /* We need to flush the recv. buffs. We do this only on the * descriptor close, not protocol-sourced closes, because the * reader process may not have drained the data yet! */ while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) { u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) len--; data_was_unread += len; __kfree_skb(skb); } /* If socket has been already reset (e.g. in tcp_reset()) - kill it. */ if (sk->sk_state == TCP_CLOSE) goto adjudge_to_death; /* As outlined in RFC 2525, section 2.17, we send a RST here because * data was lost. To witness the awful effects of the old behavior of * always doing a FIN, run an older 2.1.x kernel or 2.0.x, start a bulk * GET in an FTP client, suspend the process, wait for the client to * advertise a zero window, then kill -9 the FTP client, wheee... * Note: timeout is always zero in such a case. */ if (unlikely(tcp_sk(sk)->repair)) { sk->sk_prot->disconnect(sk, 0); } else if (data_was_unread) { /* Unread data was tossed, zap the connection. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE); tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, sk->sk_allocation); } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { /* Check zero linger _after_ checking for unread data. */ sk->sk_prot->disconnect(sk, 0); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA); } else if (tcp_close_state(sk)) { /* We FIN if the application ate all the data before * zapping the connection. */ /* RED-PEN. Formally speaking, we have broken TCP state * machine. State transitions: * * TCP_ESTABLISHED -> TCP_FIN_WAIT1 * TCP_SYN_RECV -> TCP_FIN_WAIT1 (it is difficult) * TCP_CLOSE_WAIT -> TCP_LAST_ACK * * are legal only when FIN has been sent (i.e. in window), * rather than queued out of window. Purists blame. * * F.e. "RFC state" is ESTABLISHED, * if Linux state is FIN-WAIT-1, but FIN is still not sent. * * The visible declinations are that sometimes * we enter time-wait state, when it is not required really * (harmless), do not send active resets, when they are * required by specs (TCP_ESTABLISHED, TCP_CLOSE_WAIT, when * they look as CLOSING or LAST_ACK for Linux) * Probably, I missed some more holelets. * --ANK * XXX (TFO) - To start off we don't support SYN+ACK+FIN * in a single packet! (May consider it later but will * probably need API support or TCP_CORK SYN-ACK until * data is written and socket is closed.) */ tcp_send_fin(sk); } sk_stream_wait_close(sk, timeout); adjudge_to_death: state = sk->sk_state; sock_hold(sk); sock_orphan(sk); local_bh_disable(); bh_lock_sock(sk); /* remove backlog if any, without releasing ownership. */ __release_sock(sk); this_cpu_inc(tcp_orphan_count); /* Have we already been destroyed by a softirq or backlog? */ if (state != TCP_CLOSE && sk->sk_state == TCP_CLOSE) goto out; /* This is a (useful) BSD violating of the RFC. There is a * problem with TCP as specified in that the other end could * keep a socket open forever with no application left this end. * We use a 1 minute timeout (about the same as BSD) then kill * our end. If they send after that then tough - BUT: long enough * that we won't make the old 4*rto = almost no time - whoops * reset mistake. * * Nope, it was not mistake. It is really desired behaviour * f.e. on http servers, when such sockets are useless, but * consume significant resources. Let's do it with special * linger2 option. --ANK */ if (sk->sk_state == TCP_FIN_WAIT2) { struct tcp_sock *tp = tcp_sk(sk); if (tp->linger2 < 0) { tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, GFP_ATOMIC); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONLINGER); } else { const int tmo = tcp_fin_time(sk); if (tmo > TCP_TIMEWAIT_LEN) { inet_csk_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN); } else { tcp_time_wait(sk, TCP_FIN_WAIT2, tmo); goto out; } } } if (sk->sk_state != TCP_CLOSE) { if (tcp_check_oom(sk, 0)) { tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, GFP_ATOMIC); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); } else if (!check_net(sock_net(sk))) { /* Not possible to send reset; just close */ tcp_set_state(sk, TCP_CLOSE); } } if (sk->sk_state == TCP_CLOSE) { struct request_sock *req; req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, lockdep_sock_is_held(sk)); /* We could get here with a non-NULL req if the socket is * aborted (e.g., closed with unread data) before 3WHS * finishes. */ if (req) reqsk_fastopen_remove(sk, req, false); inet_csk_destroy_sock(sk); } /* Otherwise, socket is reprieved until protocol close. */ out: bh_unlock_sock(sk); local_bh_enable(); } void tcp_close(struct sock *sk, long timeout) { lock_sock(sk); __tcp_close(sk, timeout); release_sock(sk); if (!sk->sk_net_refcnt) inet_csk_clear_xmit_timers_sync(sk); sock_put(sk); } EXPORT_SYMBOL(tcp_close); /* These states need RST on ABORT according to RFC793 */ static inline bool tcp_need_reset(int state) { return (1 << state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_SYN_RECV); } static void tcp_rtx_queue_purge(struct sock *sk) { struct rb_node *p = rb_first(&sk->tcp_rtx_queue); tcp_sk(sk)->highest_sack = NULL; while (p) { struct sk_buff *skb = rb_to_skb(p); p = rb_next(p); /* Since we are deleting whole queue, no need to * list_del(&skb->tcp_tsorted_anchor) */ tcp_rtx_queue_unlink(skb, sk); tcp_wmem_free_skb(sk, skb); } } void tcp_write_queue_purge(struct sock *sk) { struct sk_buff *skb; tcp_chrono_stop(sk, TCP_CHRONO_BUSY); while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) { tcp_skb_tsorted_anchor_cleanup(skb); tcp_wmem_free_skb(sk, skb); } tcp_rtx_queue_purge(sk); INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue); tcp_clear_all_retrans_hints(tcp_sk(sk)); tcp_sk(sk)->packets_out = 0; inet_csk(sk)->icsk_backoff = 0; } int tcp_disconnect(struct sock *sk, int flags) { struct inet_sock *inet = inet_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int old_state = sk->sk_state; u32 seq; /* Deny disconnect if other threads are blocked in sk_wait_event() * or inet_wait_for_connect(). */ if (sk->sk_wait_pending) return -EBUSY; if (old_state != TCP_CLOSE) tcp_set_state(sk, TCP_CLOSE); /* ABORT function of RFC793 */ if (old_state == TCP_LISTEN) { inet_csk_listen_stop(sk); } else if (unlikely(tp->repair)) { WRITE_ONCE(sk->sk_err, ECONNABORTED); } else if (tcp_need_reset(old_state) || (tp->snd_nxt != tp->write_seq && (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK))) { /* The last check adjusts for discrepancy of Linux wrt. RFC * states */ tcp_send_active_reset(sk, gfp_any()); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (old_state == TCP_SYN_SENT) WRITE_ONCE(sk->sk_err, ECONNRESET); tcp_clear_xmit_timers(sk); __skb_queue_purge(&sk->sk_receive_queue); WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); WRITE_ONCE(tp->urg_data, 0); tcp_write_queue_purge(sk); tcp_fastopen_active_disable_ofo_check(sk); skb_rbtree_purge(&tp->out_of_order_queue); inet->inet_dport = 0; inet_bhash2_reset_saddr(sk); WRITE_ONCE(sk->sk_shutdown, 0); sock_reset_flag(sk, SOCK_DONE); tp->srtt_us = 0; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); tp->rcv_rtt_last_tsecr = 0; seq = tp->write_seq + tp->max_window + 2; if (!seq) seq = 1; WRITE_ONCE(tp->write_seq, seq); icsk->icsk_backoff = 0; icsk->icsk_probes_out = 0; icsk->icsk_probes_tstamp = 0; icsk->icsk_rto = TCP_TIMEOUT_INIT; icsk->icsk_rto_min = TCP_RTO_MIN; icsk->icsk_delack_max = TCP_DELACK_MAX; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tcp_snd_cwnd_set(tp, TCP_INIT_CWND); tp->snd_cwnd_cnt = 0; tp->is_cwnd_limited = 0; tp->max_packets_out = 0; tp->window_clamp = 0; tp->delivered = 0; tp->delivered_ce = 0; if (icsk->icsk_ca_ops->release) icsk->icsk_ca_ops->release(sk); memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); icsk->icsk_ca_initialized = 0; tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; tcp_clear_retrans(tp); tp->total_retrans = 0; inet_csk_delack_init(sk); /* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0 * issue in __tcp_select_window() */ icsk->icsk_ack.rcv_mss = TCP_MIN_MSS; memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); dst_release(xchg((__force struct dst_entry **)&sk->sk_rx_dst, NULL)); tcp_saved_syn_free(tp); tp->compressed_ack = 0; tp->segs_in = 0; tp->segs_out = 0; tp->bytes_sent = 0; tp->bytes_acked = 0; tp->bytes_received = 0; tp->bytes_retrans = 0; tp->data_segs_in = 0; tp->data_segs_out = 0; tp->duplicate_sack[0].start_seq = 0; tp->duplicate_sack[0].end_seq = 0; tp->dsack_dups = 0; tp->reord_seen = 0; tp->retrans_out = 0; tp->sacked_out = 0; tp->tlp_high_seq = 0; tp->last_oow_ack_time = 0; /* There's a bubble in the pipe until at least the first ACK. */ tp->app_limited = ~0U; tp->rate_app_limited = 1; tp->rack.mstamp = 0; tp->rack.advanced = 0; tp->rack.reo_wnd_steps = 1; tp->rack.last_delivered = 0; tp->rack.reo_wnd_persist = 0; tp->rack.dsack_seen = 0; tp->syn_data_acked = 0; tp->rx_opt.saw_tstamp = 0; tp->rx_opt.dsack = 0; tp->rx_opt.num_sacks = 0; tp->rcv_ooopack = 0; /* Clean up fastopen related fields */ tcp_free_fastopen_req(tp); inet->defer_connect = 0; tp->fastopen_client_fail = 0; WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); if (sk->sk_frag.page) { put_page(sk->sk_frag.page); sk->sk_frag.page = NULL; sk->sk_frag.offset = 0; } sk_error_report(sk); return 0; } EXPORT_SYMBOL(tcp_disconnect); static inline bool tcp_can_repair_sock(const struct sock *sk) { return sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN) && (sk->sk_state != TCP_LISTEN); } static int tcp_repair_set_window(struct tcp_sock *tp, sockptr_t optbuf, int len) { struct tcp_repair_window opt; if (!tp->repair) return -EPERM; if (len != sizeof(opt)) return -EINVAL; if (copy_from_sockptr(&opt, optbuf, sizeof(opt))) return -EFAULT; if (opt.max_window < opt.snd_wnd) return -EINVAL; if (after(opt.snd_wl1, tp->rcv_nxt + opt.rcv_wnd)) return -EINVAL; if (after(opt.rcv_wup, tp->rcv_nxt)) return -EINVAL; tp->snd_wl1 = opt.snd_wl1; tp->snd_wnd = opt.snd_wnd; tp->max_window = opt.max_window; tp->rcv_wnd = opt.rcv_wnd; tp->rcv_wup = opt.rcv_wup; return 0; } static int tcp_repair_options_est(struct sock *sk, sockptr_t optbuf, unsigned int len) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_repair_opt opt; size_t offset = 0; while (len >= sizeof(opt)) { if (copy_from_sockptr_offset(&opt, optbuf, offset, sizeof(opt))) return -EFAULT; offset += sizeof(opt); len -= sizeof(opt); switch (opt.opt_code) { case TCPOPT_MSS: tp->rx_opt.mss_clamp = opt.opt_val; tcp_mtup_init(sk); break; case TCPOPT_WINDOW: { u16 snd_wscale = opt.opt_val & 0xFFFF; u16 rcv_wscale = opt.opt_val >> 16; if (snd_wscale > TCP_MAX_WSCALE || rcv_wscale > TCP_MAX_WSCALE) return -EFBIG; tp->rx_opt.snd_wscale = snd_wscale; tp->rx_opt.rcv_wscale = rcv_wscale; tp->rx_opt.wscale_ok = 1; } break; case TCPOPT_SACK_PERM: if (opt.opt_val != 0) return -EINVAL; tp->rx_opt.sack_ok |= TCP_SACK_SEEN; break; case TCPOPT_TIMESTAMP: if (opt.opt_val != 0) return -EINVAL; tp->rx_opt.tstamp_ok = 1; break; } } return 0; } DEFINE_STATIC_KEY_FALSE(tcp_tx_delay_enabled); EXPORT_SYMBOL(tcp_tx_delay_enabled); static void tcp_enable_tx_delay(void) { if (!static_branch_unlikely(&tcp_tx_delay_enabled)) { static int __tcp_tx_delay_enabled = 0; if (cmpxchg(&__tcp_tx_delay_enabled, 0, 1) == 0) { static_branch_enable(&tcp_tx_delay_enabled); pr_info("TCP_TX_DELAY enabled\n"); } } } /* When set indicates to always queue non-full frames. Later the user clears * this option and we transmit any pending partial frames in the queue. This is * meant to be used alongside sendfile() to get properly filled frames when the * user (for example) must write out headers with a write() call first and then * use sendfile to send out the data parts. * * TCP_CORK can be set together with TCP_NODELAY and it is stronger than * TCP_NODELAY. */ void __tcp_sock_set_cork(struct sock *sk, bool on) { struct tcp_sock *tp = tcp_sk(sk); if (on) { tp->nonagle |= TCP_NAGLE_CORK; } else { tp->nonagle &= ~TCP_NAGLE_CORK; if (tp->nonagle & TCP_NAGLE_OFF) tp->nonagle |= TCP_NAGLE_PUSH; tcp_push_pending_frames(sk); } } void tcp_sock_set_cork(struct sock *sk, bool on) { lock_sock(sk); __tcp_sock_set_cork(sk, on); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_cork); /* TCP_NODELAY is weaker than TCP_CORK, so that this option on corked socket is * remembered, but it is not activated until cork is cleared. * * However, when TCP_NODELAY is set we make an explicit push, which overrides * even TCP_CORK for currently queued segments. */ void __tcp_sock_set_nodelay(struct sock *sk, bool on) { if (on) { tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF|TCP_NAGLE_PUSH; tcp_push_pending_frames(sk); } else { tcp_sk(sk)->nonagle &= ~TCP_NAGLE_OFF; } } void tcp_sock_set_nodelay(struct sock *sk) { lock_sock(sk); __tcp_sock_set_nodelay(sk, true); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_nodelay); static void __tcp_sock_set_quickack(struct sock *sk, int val) { if (!val) { inet_csk_enter_pingpong_mode(sk); return; } inet_csk_exit_pingpong_mode(sk); if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT) && inet_csk_ack_scheduled(sk)) { inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_PUSHED; tcp_cleanup_rbuf(sk, 1); if (!(val & 1)) inet_csk_enter_pingpong_mode(sk); } } void tcp_sock_set_quickack(struct sock *sk, int val) { lock_sock(sk); __tcp_sock_set_quickack(sk, val); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_quickack); int tcp_sock_set_syncnt(struct sock *sk, int val) { if (val < 1 || val > MAX_TCP_SYNCNT) return -EINVAL; lock_sock(sk); WRITE_ONCE(inet_csk(sk)->icsk_syn_retries, val); release_sock(sk); return 0; } EXPORT_SYMBOL(tcp_sock_set_syncnt); void tcp_sock_set_user_timeout(struct sock *sk, u32 val) { lock_sock(sk); WRITE_ONCE(inet_csk(sk)->icsk_user_timeout, val); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_user_timeout); int tcp_sock_set_keepidle_locked(struct sock *sk, int val) { struct tcp_sock *tp = tcp_sk(sk); if (val < 1 || val > MAX_TCP_KEEPIDLE) return -EINVAL; /* Paired with WRITE_ONCE() in keepalive_time_when() */ WRITE_ONCE(tp->keepalive_time, val * HZ); if (sock_flag(sk, SOCK_KEEPOPEN) && !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { u32 elapsed = keepalive_time_elapsed(tp); if (tp->keepalive_time > elapsed) elapsed = tp->keepalive_time - elapsed; else elapsed = 0; inet_csk_reset_keepalive_timer(sk, elapsed); } return 0; } int tcp_sock_set_keepidle(struct sock *sk, int val) { int err; lock_sock(sk); err = tcp_sock_set_keepidle_locked(sk, val); release_sock(sk); return err; } EXPORT_SYMBOL(tcp_sock_set_keepidle); int tcp_sock_set_keepintvl(struct sock *sk, int val) { if (val < 1 || val > MAX_TCP_KEEPINTVL) return -EINVAL; lock_sock(sk); WRITE_ONCE(tcp_sk(sk)->keepalive_intvl, val * HZ); release_sock(sk); return 0; } EXPORT_SYMBOL(tcp_sock_set_keepintvl); int tcp_sock_set_keepcnt(struct sock *sk, int val) { if (val < 1 || val > MAX_TCP_KEEPCNT) return -EINVAL; lock_sock(sk); /* Paired with READ_ONCE() in keepalive_probes() */ WRITE_ONCE(tcp_sk(sk)->keepalive_probes, val); release_sock(sk); return 0; } EXPORT_SYMBOL(tcp_sock_set_keepcnt); int tcp_set_window_clamp(struct sock *sk, int val) { struct tcp_sock *tp = tcp_sk(sk); if (!val) { if (sk->sk_state != TCP_CLOSE) return -EINVAL; tp->window_clamp = 0; } else { u32 new_rcv_ssthresh, old_window_clamp = tp->window_clamp; u32 new_window_clamp = val < SOCK_MIN_RCVBUF / 2 ? SOCK_MIN_RCVBUF / 2 : val; if (new_window_clamp == old_window_clamp) return 0; tp->window_clamp = new_window_clamp; if (new_window_clamp < old_window_clamp) { /* need to apply the reserved mem provisioning only * when shrinking the window clamp */ __tcp_adjust_rcv_ssthresh(sk, tp->window_clamp); } else { new_rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp); tp->rcv_ssthresh = max(new_rcv_ssthresh, tp->rcv_ssthresh); } } return 0; } /* * Socket option code for TCP. */ int do_tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); struct net *net = sock_net(sk); int val; int err = 0; /* These are data/string values, all the others are ints */ switch (optname) { case TCP_CONGESTION: { char name[TCP_CA_NAME_MAX]; if (optlen < 1) return -EINVAL; val = strncpy_from_sockptr(name, optval, min_t(long, TCP_CA_NAME_MAX-1, optlen)); if (val < 0) return -EFAULT; name[val] = 0; sockopt_lock_sock(sk); err = tcp_set_congestion_control(sk, name, !has_current_bpf_ctx(), sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)); sockopt_release_sock(sk); return err; } case TCP_ULP: { char name[TCP_ULP_NAME_MAX]; if (optlen < 1) return -EINVAL; val = strncpy_from_sockptr(name, optval, min_t(long, TCP_ULP_NAME_MAX - 1, optlen)); if (val < 0) return -EFAULT; name[val] = 0; sockopt_lock_sock(sk); err = tcp_set_ulp(sk, name); sockopt_release_sock(sk); return err; } case TCP_FASTOPEN_KEY: { __u8 key[TCP_FASTOPEN_KEY_BUF_LENGTH]; __u8 *backup_key = NULL; /* Allow a backup key as well to facilitate key rotation * First key is the active one. */ if (optlen != TCP_FASTOPEN_KEY_LENGTH && optlen != TCP_FASTOPEN_KEY_BUF_LENGTH) return -EINVAL; if (copy_from_sockptr(key, optval, optlen)) return -EFAULT; if (optlen == TCP_FASTOPEN_KEY_BUF_LENGTH) backup_key = key + TCP_FASTOPEN_KEY_LENGTH; return tcp_fastopen_reset_cipher(net, sk, key, backup_key); } default: /* fallthru */ break; } if (optlen < sizeof(int)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; sockopt_lock_sock(sk); switch (optname) { case TCP_MAXSEG: /* Values greater than interface MTU won't take effect. However * at the point when this call is done we typically don't yet * know which interface is going to be used */ if (val && (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW)) { err = -EINVAL; break; } tp->rx_opt.user_mss = val; break; case TCP_NODELAY: __tcp_sock_set_nodelay(sk, val); break; case TCP_THIN_LINEAR_TIMEOUTS: if (val < 0 || val > 1) err = -EINVAL; else tp->thin_lto = val; break; case TCP_THIN_DUPACK: if (val < 0 || val > 1) err = -EINVAL; break; case TCP_REPAIR: if (!tcp_can_repair_sock(sk)) err = -EPERM; else if (val == TCP_REPAIR_ON) { tp->repair = 1; sk->sk_reuse = SK_FORCE_REUSE; tp->repair_queue = TCP_NO_QUEUE; } else if (val == TCP_REPAIR_OFF) { tp->repair = 0; sk->sk_reuse = SK_NO_REUSE; tcp_send_window_probe(sk); } else if (val == TCP_REPAIR_OFF_NO_WP) { tp->repair = 0; sk->sk_reuse = SK_NO_REUSE; } else err = -EINVAL; break; case TCP_REPAIR_QUEUE: if (!tp->repair) err = -EPERM; else if ((unsigned int)val < TCP_QUEUES_NR) tp->repair_queue = val; else err = -EINVAL; break; case TCP_QUEUE_SEQ: if (sk->sk_state != TCP_CLOSE) { err = -EPERM; } else if (tp->repair_queue == TCP_SEND_QUEUE) { if (!tcp_rtx_queue_empty(sk)) err = -EPERM; else WRITE_ONCE(tp->write_seq, val); } else if (tp->repair_queue == TCP_RECV_QUEUE) { if (tp->rcv_nxt != tp->copied_seq) { err = -EPERM; } else { WRITE_ONCE(tp->rcv_nxt, val); WRITE_ONCE(tp->copied_seq, val); } } else { err = -EINVAL; } break; case TCP_REPAIR_OPTIONS: if (!tp->repair) err = -EINVAL; else if (sk->sk_state == TCP_ESTABLISHED && !tp->bytes_sent) err = tcp_repair_options_est(sk, optval, optlen); else err = -EPERM; break; case TCP_CORK: __tcp_sock_set_cork(sk, val); break; case TCP_KEEPIDLE: err = tcp_sock_set_keepidle_locked(sk, val); break; case TCP_KEEPINTVL: if (val < 1 || val > MAX_TCP_KEEPINTVL) err = -EINVAL; else WRITE_ONCE(tp->keepalive_intvl, val * HZ); break; case TCP_KEEPCNT: if (val < 1 || val > MAX_TCP_KEEPCNT) err = -EINVAL; else WRITE_ONCE(tp->keepalive_probes, val); break; case TCP_SYNCNT: if (val < 1 || val > MAX_TCP_SYNCNT) err = -EINVAL; else WRITE_ONCE(icsk->icsk_syn_retries, val); break; case TCP_SAVE_SYN: /* 0: disable, 1: enable, 2: start from ether_header */ if (val < 0 || val > 2) err = -EINVAL; else tp->save_syn = val; break; case TCP_LINGER2: if (val < 0) WRITE_ONCE(tp->linger2, -1); else if (val > TCP_FIN_TIMEOUT_MAX / HZ) WRITE_ONCE(tp->linger2, TCP_FIN_TIMEOUT_MAX); else WRITE_ONCE(tp->linger2, val * HZ); break; case TCP_DEFER_ACCEPT: /* Translate value in seconds to number of retransmits */ WRITE_ONCE(icsk->icsk_accept_queue.rskq_defer_accept, secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ)); break; case TCP_WINDOW_CLAMP: err = tcp_set_window_clamp(sk, val); break; case TCP_QUICKACK: __tcp_sock_set_quickack(sk, val); break; #ifdef CONFIG_TCP_MD5SIG case TCP_MD5SIG: case TCP_MD5SIG_EXT: err = tp->af_specific->md5_parse(sk, optname, optval, optlen); break; #endif case TCP_USER_TIMEOUT: /* Cap the max time in ms TCP will retry or probe the window * before giving up and aborting (ETIMEDOUT) a connection. */ if (val < 0) err = -EINVAL; else WRITE_ONCE(icsk->icsk_user_timeout, val); break; case TCP_FASTOPEN: if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { tcp_fastopen_init_key_once(net); fastopen_queue_tune(sk, val); } else { err = -EINVAL; } break; case TCP_FASTOPEN_CONNECT: if (val > 1 || val < 0) { err = -EINVAL; } else if (READ_ONCE(net->ipv4.sysctl_tcp_fastopen) & TFO_CLIENT_ENABLE) { if (sk->sk_state == TCP_CLOSE) tp->fastopen_connect = val; else err = -EINVAL; } else { err = -EOPNOTSUPP; } break; case TCP_FASTOPEN_NO_COOKIE: if (val > 1 || val < 0) err = -EINVAL; else if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) err = -EINVAL; else tp->fastopen_no_cookie = val; break; case TCP_TIMESTAMP: if (!tp->repair) err = -EPERM; else WRITE_ONCE(tp->tsoffset, val - tcp_time_stamp_raw()); break; case TCP_REPAIR_WINDOW: err = tcp_repair_set_window(tp, optval, optlen); break; case TCP_NOTSENT_LOWAT: WRITE_ONCE(tp->notsent_lowat, val); sk->sk_write_space(sk); break; case TCP_INQ: if (val > 1 || val < 0) err = -EINVAL; else tp->recvmsg_inq = val; break; case TCP_TX_DELAY: if (val) tcp_enable_tx_delay(); WRITE_ONCE(tp->tcp_tx_delay, val); break; default: err = -ENOPROTOOPT; break; } sockopt_release_sock(sk); return err; } int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { const struct inet_connection_sock *icsk = inet_csk(sk); if (level != SOL_TCP) /* Paired with WRITE_ONCE() in do_ipv6_setsockopt() and tcp_v6_connect() */ return READ_ONCE(icsk->icsk_af_ops)->setsockopt(sk, level, optname, optval, optlen); return do_tcp_setsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL(tcp_setsockopt); static void tcp_get_info_chrono_stats(const struct tcp_sock *tp, struct tcp_info *info) { u64 stats[__TCP_CHRONO_MAX], total = 0; enum tcp_chrono i; for (i = TCP_CHRONO_BUSY; i < __TCP_CHRONO_MAX; ++i) { stats[i] = tp->chrono_stat[i - 1]; if (i == tp->chrono_type) stats[i] += tcp_jiffies32 - tp->chrono_start; stats[i] *= USEC_PER_SEC / HZ; total += stats[i]; } info->tcpi_busy_time = total; info->tcpi_rwnd_limited = stats[TCP_CHRONO_RWND_LIMITED]; info->tcpi_sndbuf_limited = stats[TCP_CHRONO_SNDBUF_LIMITED]; } /* Return information about state of tcp endpoint in API format. */ void tcp_get_info(struct sock *sk, struct tcp_info *info) { const struct tcp_sock *tp = tcp_sk(sk); /* iff sk_type == SOCK_STREAM */ const struct inet_connection_sock *icsk = inet_csk(sk); unsigned long rate; u32 now; u64 rate64; bool slow; memset(info, 0, sizeof(*info)); if (sk->sk_type != SOCK_STREAM) return; info->tcpi_state = inet_sk_state_load(sk); /* Report meaningful fields for all TCP states, including listeners */ rate = READ_ONCE(sk->sk_pacing_rate); rate64 = (rate != ~0UL) ? rate : ~0ULL; info->tcpi_pacing_rate = rate64; rate = READ_ONCE(sk->sk_max_pacing_rate); rate64 = (rate != ~0UL) ? rate : ~0ULL; info->tcpi_max_pacing_rate = rate64; info->tcpi_reordering = tp->reordering; info->tcpi_snd_cwnd = tcp_snd_cwnd(tp); if (info->tcpi_state == TCP_LISTEN) { /* listeners aliased fields : * tcpi_unacked -> Number of children ready for accept() * tcpi_sacked -> max backlog */ info->tcpi_unacked = READ_ONCE(sk->sk_ack_backlog); info->tcpi_sacked = READ_ONCE(sk->sk_max_ack_backlog); return; } slow = lock_sock_fast(sk); info->tcpi_ca_state = icsk->icsk_ca_state; info->tcpi_retransmits = icsk->icsk_retransmits; info->tcpi_probes = icsk->icsk_probes_out; info->tcpi_backoff = icsk->icsk_backoff; if (tp->rx_opt.tstamp_ok) info->tcpi_options |= TCPI_OPT_TIMESTAMPS; if (tcp_is_sack(tp)) info->tcpi_options |= TCPI_OPT_SACK; if (tp->rx_opt.wscale_ok) { info->tcpi_options |= TCPI_OPT_WSCALE; info->tcpi_snd_wscale = tp->rx_opt.snd_wscale; info->tcpi_rcv_wscale = tp->rx_opt.rcv_wscale; } if (tp->ecn_flags & TCP_ECN_OK) info->tcpi_options |= TCPI_OPT_ECN; if (tp->ecn_flags & TCP_ECN_SEEN) info->tcpi_options |= TCPI_OPT_ECN_SEEN; if (tp->syn_data_acked) info->tcpi_options |= TCPI_OPT_SYN_DATA; info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto); info->tcpi_ato = jiffies_to_usecs(icsk->icsk_ack.ato); info->tcpi_snd_mss = tp->mss_cache; info->tcpi_rcv_mss = icsk->icsk_ack.rcv_mss; info->tcpi_unacked = tp->packets_out; info->tcpi_sacked = tp->sacked_out; info->tcpi_lost = tp->lost_out; info->tcpi_retrans = tp->retrans_out; now = tcp_jiffies32; info->tcpi_last_data_sent = jiffies_to_msecs(now - tp->lsndtime); info->tcpi_last_data_recv = jiffies_to_msecs(now - icsk->icsk_ack.lrcvtime); info->tcpi_last_ack_recv = jiffies_to_msecs(now - tp->rcv_tstamp); info->tcpi_pmtu = icsk->icsk_pmtu_cookie; info->tcpi_rcv_ssthresh = tp->rcv_ssthresh; info->tcpi_rtt = tp->srtt_us >> 3; info->tcpi_rttvar = tp->mdev_us >> 2; info->tcpi_snd_ssthresh = tp->snd_ssthresh; info->tcpi_advmss = tp->advmss; info->tcpi_rcv_rtt = tp->rcv_rtt_est.rtt_us >> 3; info->tcpi_rcv_space = tp->rcvq_space.space; info->tcpi_total_retrans = tp->total_retrans; info->tcpi_bytes_acked = tp->bytes_acked; info->tcpi_bytes_received = tp->bytes_received; info->tcpi_notsent_bytes = max_t(int, 0, tp->write_seq - tp->snd_nxt); tcp_get_info_chrono_stats(tp, info); info->tcpi_segs_out = tp->segs_out; /* segs_in and data_segs_in can be updated from tcp_segs_in() from BH */ info->tcpi_segs_in = READ_ONCE(tp->segs_in); info->tcpi_data_segs_in = READ_ONCE(tp->data_segs_in); info->tcpi_min_rtt = tcp_min_rtt(tp); info->tcpi_data_segs_out = tp->data_segs_out; info->tcpi_delivery_rate_app_limited = tp->rate_app_limited ? 1 : 0; rate64 = tcp_compute_delivery_rate(tp); if (rate64) info->tcpi_delivery_rate = rate64; info->tcpi_delivered = tp->delivered; info->tcpi_delivered_ce = tp->delivered_ce; info->tcpi_bytes_sent = tp->bytes_sent; info->tcpi_bytes_retrans = tp->bytes_retrans; info->tcpi_dsack_dups = tp->dsack_dups; info->tcpi_reord_seen = tp->reord_seen; info->tcpi_rcv_ooopack = tp->rcv_ooopack; info->tcpi_snd_wnd = tp->snd_wnd; info->tcpi_fastopen_client_fail = tp->fastopen_client_fail; unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(tcp_get_info); static size_t tcp_opt_stats_get_size(void) { return nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BUSY */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_RWND_LIMITED */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_SNDBUF_LIMITED */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_DATA_SEGS_OUT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_TOTAL_RETRANS */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_PACING_RATE */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_DELIVERY_RATE */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SND_CWND */ nla_total_size(sizeof(u32)) + /* TCP_NLA_REORDERING */ nla_total_size(sizeof(u32)) + /* TCP_NLA_MIN_RTT */ nla_total_size(sizeof(u8)) + /* TCP_NLA_RECUR_RETRANS */ nla_total_size(sizeof(u8)) + /* TCP_NLA_DELIVERY_RATE_APP_LMT */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SNDQ_SIZE */ nla_total_size(sizeof(u8)) + /* TCP_NLA_CA_STATE */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SND_SSTHRESH */ nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED */ nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED_CE */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_SENT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_RETRANS */ nla_total_size(sizeof(u32)) + /* TCP_NLA_DSACK_DUPS */ nla_total_size(sizeof(u32)) + /* TCP_NLA_REORD_SEEN */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SRTT */ nla_total_size(sizeof(u16)) + /* TCP_NLA_TIMEOUT_REHASH */ nla_total_size(sizeof(u32)) + /* TCP_NLA_BYTES_NOTSENT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_EDT */ nla_total_size(sizeof(u8)) + /* TCP_NLA_TTL */ 0; } /* Returns TTL or hop limit of an incoming packet from skb. */ static u8 tcp_skb_ttl_or_hop_limit(const struct sk_buff *skb) { if (skb->protocol == htons(ETH_P_IP)) return ip_hdr(skb)->ttl; else if (skb->protocol == htons(ETH_P_IPV6)) return ipv6_hdr(skb)->hop_limit; else return 0; } struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, const struct sk_buff *orig_skb, const struct sk_buff *ack_skb) { const struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *stats; struct tcp_info info; unsigned long rate; u64 rate64; stats = alloc_skb(tcp_opt_stats_get_size(), GFP_ATOMIC); if (!stats) return NULL; tcp_get_info_chrono_stats(tp, &info); nla_put_u64_64bit(stats, TCP_NLA_BUSY, info.tcpi_busy_time, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_RWND_LIMITED, info.tcpi_rwnd_limited, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_SNDBUF_LIMITED, info.tcpi_sndbuf_limited, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_DATA_SEGS_OUT, tp->data_segs_out, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_TOTAL_RETRANS, tp->total_retrans, TCP_NLA_PAD); rate = READ_ONCE(sk->sk_pacing_rate); rate64 = (rate != ~0UL) ? rate : ~0ULL; nla_put_u64_64bit(stats, TCP_NLA_PACING_RATE, rate64, TCP_NLA_PAD); rate64 = tcp_compute_delivery_rate(tp); nla_put_u64_64bit(stats, TCP_NLA_DELIVERY_RATE, rate64, TCP_NLA_PAD); nla_put_u32(stats, TCP_NLA_SND_CWND, tcp_snd_cwnd(tp)); nla_put_u32(stats, TCP_NLA_REORDERING, tp->reordering); nla_put_u32(stats, TCP_NLA_MIN_RTT, tcp_min_rtt(tp)); nla_put_u8(stats, TCP_NLA_RECUR_RETRANS, inet_csk(sk)->icsk_retransmits); nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, !!tp->rate_app_limited); nla_put_u32(stats, TCP_NLA_SND_SSTHRESH, tp->snd_ssthresh); nla_put_u32(stats, TCP_NLA_DELIVERED, tp->delivered); nla_put_u32(stats, TCP_NLA_DELIVERED_CE, tp->delivered_ce); nla_put_u32(stats, TCP_NLA_SNDQ_SIZE, tp->write_seq - tp->snd_una); nla_put_u8(stats, TCP_NLA_CA_STATE, inet_csk(sk)->icsk_ca_state); nla_put_u64_64bit(stats, TCP_NLA_BYTES_SENT, tp->bytes_sent, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS, tp->bytes_retrans, TCP_NLA_PAD); nla_put_u32(stats, TCP_NLA_DSACK_DUPS, tp->dsack_dups); nla_put_u32(stats, TCP_NLA_REORD_SEEN, tp->reord_seen); nla_put_u32(stats, TCP_NLA_SRTT, tp->srtt_us >> 3); nla_put_u16(stats, TCP_NLA_TIMEOUT_REHASH, tp->timeout_rehash); nla_put_u32(stats, TCP_NLA_BYTES_NOTSENT, max_t(int, 0, tp->write_seq - tp->snd_nxt)); nla_put_u64_64bit(stats, TCP_NLA_EDT, orig_skb->skb_mstamp_ns, TCP_NLA_PAD); if (ack_skb) nla_put_u8(stats, TCP_NLA_TTL, tcp_skb_ttl_or_hop_limit(ack_skb)); return stats; } int do_tcp_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); int val, len; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len < 0) return -EINVAL; len = min_t(unsigned int, len, sizeof(int)); switch (optname) { case TCP_MAXSEG: val = tp->mss_cache; if (tp->rx_opt.user_mss && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) val = tp->rx_opt.user_mss; if (tp->repair) val = tp->rx_opt.mss_clamp; break; case TCP_NODELAY: val = !!(tp->nonagle&TCP_NAGLE_OFF); break; case TCP_CORK: val = !!(tp->nonagle&TCP_NAGLE_CORK); break; case TCP_KEEPIDLE: val = keepalive_time_when(tp) / HZ; break; case TCP_KEEPINTVL: val = keepalive_intvl_when(tp) / HZ; break; case TCP_KEEPCNT: val = keepalive_probes(tp); break; case TCP_SYNCNT: val = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); break; case TCP_LINGER2: val = READ_ONCE(tp->linger2); if (val >= 0) val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ; break; case TCP_DEFER_ACCEPT: val = READ_ONCE(icsk->icsk_accept_queue.rskq_defer_accept); val = retrans_to_secs(val, TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ); break; case TCP_WINDOW_CLAMP: val = tp->window_clamp; break; case TCP_INFO: { struct tcp_info info; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; tcp_get_info(sk, &info); len = min_t(unsigned int, len, sizeof(info)); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &info, len)) return -EFAULT; return 0; } case TCP_CC_INFO: { const struct tcp_congestion_ops *ca_ops; union tcp_cc_info info; size_t sz = 0; int attr; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; ca_ops = icsk->icsk_ca_ops; if (ca_ops && ca_ops->get_info) sz = ca_ops->get_info(sk, ~0U, &attr, &info); len = min_t(unsigned int, len, sz); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &info, len)) return -EFAULT; return 0; } case TCP_QUICKACK: val = !inet_csk_in_pingpong_mode(sk); break; case TCP_CONGESTION: if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; len = min_t(unsigned int, len, TCP_CA_NAME_MAX); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, icsk->icsk_ca_ops->name, len)) return -EFAULT; return 0; case TCP_ULP: if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; len = min_t(unsigned int, len, TCP_ULP_NAME_MAX); if (!icsk->icsk_ulp_ops) { len = 0; if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; return 0; } if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, icsk->icsk_ulp_ops->name, len)) return -EFAULT; return 0; case TCP_FASTOPEN_KEY: { u64 key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(u64)]; unsigned int key_len; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; key_len = tcp_fastopen_get_cipher(net, icsk, key) * TCP_FASTOPEN_KEY_LENGTH; len = min_t(unsigned int, len, key_len); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, key, len)) return -EFAULT; return 0; } case TCP_THIN_LINEAR_TIMEOUTS: val = tp->thin_lto; break; case TCP_THIN_DUPACK: val = 0; break; case TCP_REPAIR: val = tp->repair; break; case TCP_REPAIR_QUEUE: if (tp->repair) val = tp->repair_queue; else return -EINVAL; break; case TCP_REPAIR_WINDOW: { struct tcp_repair_window opt; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len != sizeof(opt)) return -EINVAL; if (!tp->repair) return -EPERM; opt.snd_wl1 = tp->snd_wl1; opt.snd_wnd = tp->snd_wnd; opt.max_window = tp->max_window; opt.rcv_wnd = tp->rcv_wnd; opt.rcv_wup = tp->rcv_wup; if (copy_to_sockptr(optval, &opt, len)) return -EFAULT; return 0; } case TCP_QUEUE_SEQ: if (tp->repair_queue == TCP_SEND_QUEUE) val = tp->write_seq; else if (tp->repair_queue == TCP_RECV_QUEUE) val = tp->rcv_nxt; else return -EINVAL; break; case TCP_USER_TIMEOUT: val = READ_ONCE(icsk->icsk_user_timeout); break; case TCP_FASTOPEN: val = READ_ONCE(icsk->icsk_accept_queue.fastopenq.max_qlen); break; case TCP_FASTOPEN_CONNECT: val = tp->fastopen_connect; break; case TCP_FASTOPEN_NO_COOKIE: val = tp->fastopen_no_cookie; break; case TCP_TX_DELAY: val = READ_ONCE(tp->tcp_tx_delay); break; case TCP_TIMESTAMP: val = tcp_time_stamp_raw() + READ_ONCE(tp->tsoffset); break; case TCP_NOTSENT_LOWAT: val = READ_ONCE(tp->notsent_lowat); break; case TCP_INQ: val = tp->recvmsg_inq; break; case TCP_SAVE_SYN: val = tp->save_syn; break; case TCP_SAVED_SYN: { if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; sockopt_lock_sock(sk); if (tp->saved_syn) { if (len < tcp_saved_syn_len(tp->saved_syn)) { len = tcp_saved_syn_len(tp->saved_syn); if (copy_to_sockptr(optlen, &len, sizeof(int))) { sockopt_release_sock(sk); return -EFAULT; } sockopt_release_sock(sk); return -EINVAL; } len = tcp_saved_syn_len(tp->saved_syn); if (copy_to_sockptr(optlen, &len, sizeof(int))) { sockopt_release_sock(sk); return -EFAULT; } if (copy_to_sockptr(optval, tp->saved_syn->data, len)) { sockopt_release_sock(sk); return -EFAULT; } tcp_saved_syn_free(tp); sockopt_release_sock(sk); } else { sockopt_release_sock(sk); len = 0; if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; } return 0; } #ifdef CONFIG_MMU case TCP_ZEROCOPY_RECEIVE: { struct scm_timestamping_internal tss; struct tcp_zerocopy_receive zc = {}; int err; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len < 0 || len < offsetofend(struct tcp_zerocopy_receive, length)) return -EINVAL; if (unlikely(len > sizeof(zc))) { err = check_zeroed_sockptr(optval, sizeof(zc), len - sizeof(zc)); if (err < 1) return err == 0 ? -EINVAL : err; len = sizeof(zc); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; } if (copy_from_sockptr(&zc, optval, len)) return -EFAULT; if (zc.reserved) return -EINVAL; if (zc.msg_flags & ~(TCP_VALID_ZC_MSG_FLAGS)) return -EINVAL; sockopt_lock_sock(sk); err = tcp_zerocopy_receive(sk, &zc, &tss); err = BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sk, level, optname, &zc, &len, err); sockopt_release_sock(sk); if (len >= offsetofend(struct tcp_zerocopy_receive, msg_flags)) goto zerocopy_rcv_cmsg; switch (len) { case offsetofend(struct tcp_zerocopy_receive, msg_flags): goto zerocopy_rcv_cmsg; case offsetofend(struct tcp_zerocopy_receive, msg_controllen): case offsetofend(struct tcp_zerocopy_receive, msg_control): case offsetofend(struct tcp_zerocopy_receive, flags): case offsetofend(struct tcp_zerocopy_receive, copybuf_len): case offsetofend(struct tcp_zerocopy_receive, copybuf_address): case offsetofend(struct tcp_zerocopy_receive, err): goto zerocopy_rcv_sk_err; case offsetofend(struct tcp_zerocopy_receive, inq): goto zerocopy_rcv_inq; case offsetofend(struct tcp_zerocopy_receive, length): default: goto zerocopy_rcv_out; } zerocopy_rcv_cmsg: if (zc.msg_flags & TCP_CMSG_TS) tcp_zc_finalize_rx_tstamp(sk, &zc, &tss); else zc.msg_flags = 0; zerocopy_rcv_sk_err: if (!err) zc.err = sock_error(sk); zerocopy_rcv_inq: zc.inq = tcp_inq_hint(sk); zerocopy_rcv_out: if (!err && copy_to_sockptr(optval, &zc, len)) err = -EFAULT; return err; } #endif default: return -ENOPROTOOPT; } if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &val, len)) return -EFAULT; return 0; } bool tcp_bpf_bypass_getsockopt(int level, int optname) { /* TCP do_tcp_getsockopt has optimized getsockopt implementation * to avoid extra socket lock for TCP_ZEROCOPY_RECEIVE. */ if (level == SOL_TCP && optname == TCP_ZEROCOPY_RECEIVE) return true; return false; } EXPORT_SYMBOL(tcp_bpf_bypass_getsockopt); int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct inet_connection_sock *icsk = inet_csk(sk); if (level != SOL_TCP) /* Paired with WRITE_ONCE() in do_ipv6_setsockopt() and tcp_v6_connect() */ return READ_ONCE(icsk->icsk_af_ops)->getsockopt(sk, level, optname, optval, optlen); return do_tcp_getsockopt(sk, level, optname, USER_SOCKPTR(optval), USER_SOCKPTR(optlen)); } EXPORT_SYMBOL(tcp_getsockopt); #ifdef CONFIG_TCP_MD5SIG static DEFINE_PER_CPU(struct tcp_md5sig_pool, tcp_md5sig_pool); static DEFINE_MUTEX(tcp_md5sig_mutex); static bool tcp_md5sig_pool_populated = false; static void __tcp_alloc_md5sig_pool(void) { struct crypto_ahash *hash; int cpu; hash = crypto_alloc_ahash("md5", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(hash)) return; for_each_possible_cpu(cpu) { void *scratch = per_cpu(tcp_md5sig_pool, cpu).scratch; struct ahash_request *req; if (!scratch) { scratch = kmalloc_node(sizeof(union tcp_md5sum_block) + sizeof(struct tcphdr), GFP_KERNEL, cpu_to_node(cpu)); if (!scratch) return; per_cpu(tcp_md5sig_pool, cpu).scratch = scratch; } if (per_cpu(tcp_md5sig_pool, cpu).md5_req) continue; req = ahash_request_alloc(hash, GFP_KERNEL); if (!req) return; ahash_request_set_callback(req, 0, NULL, NULL); per_cpu(tcp_md5sig_pool, cpu).md5_req = req; } /* before setting tcp_md5sig_pool_populated, we must commit all writes * to memory. See smp_rmb() in tcp_get_md5sig_pool() */ smp_wmb(); /* Paired with READ_ONCE() from tcp_alloc_md5sig_pool() * and tcp_get_md5sig_pool(). */ WRITE_ONCE(tcp_md5sig_pool_populated, true); } bool tcp_alloc_md5sig_pool(void) { /* Paired with WRITE_ONCE() from __tcp_alloc_md5sig_pool() */ if (unlikely(!READ_ONCE(tcp_md5sig_pool_populated))) { mutex_lock(&tcp_md5sig_mutex); if (!tcp_md5sig_pool_populated) { __tcp_alloc_md5sig_pool(); if (tcp_md5sig_pool_populated) static_branch_inc(&tcp_md5_needed); } mutex_unlock(&tcp_md5sig_mutex); } /* Paired with WRITE_ONCE() from __tcp_alloc_md5sig_pool() */ return READ_ONCE(tcp_md5sig_pool_populated); } EXPORT_SYMBOL(tcp_alloc_md5sig_pool); /** * tcp_get_md5sig_pool - get md5sig_pool for this user * * We use percpu structure, so if we succeed, we exit with preemption * and BH disabled, to make sure another thread or softirq handling * wont try to get same context. */ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void) { local_bh_disable(); /* Paired with WRITE_ONCE() from __tcp_alloc_md5sig_pool() */ if (READ_ONCE(tcp_md5sig_pool_populated)) { /* coupled with smp_wmb() in __tcp_alloc_md5sig_pool() */ smp_rmb(); return this_cpu_ptr(&tcp_md5sig_pool); } local_bh_enable(); return NULL; } EXPORT_SYMBOL(tcp_get_md5sig_pool); int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp, const struct sk_buff *skb, unsigned int header_len) { struct scatterlist sg; const struct tcphdr *tp = tcp_hdr(skb); struct ahash_request *req = hp->md5_req; unsigned int i; const unsigned int head_data_len = skb_headlen(skb) > header_len ? skb_headlen(skb) - header_len : 0; const struct skb_shared_info *shi = skb_shinfo(skb); struct sk_buff *frag_iter; sg_init_table(&sg, 1); sg_set_buf(&sg, ((u8 *) tp) + header_len, head_data_len); ahash_request_set_crypt(req, &sg, NULL, head_data_len); if (crypto_ahash_update(req)) return 1; for (i = 0; i < shi->nr_frags; ++i) { const skb_frag_t *f = &shi->frags[i]; unsigned int offset = skb_frag_off(f); struct page *page = skb_frag_page(f) + (offset >> PAGE_SHIFT); sg_set_page(&sg, page, skb_frag_size(f), offset_in_page(offset)); ahash_request_set_crypt(req, &sg, NULL, skb_frag_size(f)); if (crypto_ahash_update(req)) return 1; } skb_walk_frags(skb, frag_iter) if (tcp_md5_hash_skb_data(hp, frag_iter, 0)) return 1; return 0; } EXPORT_SYMBOL(tcp_md5_hash_skb_data); int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key) { u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */ struct scatterlist sg; sg_init_one(&sg, key->key, keylen); ahash_request_set_crypt(hp->md5_req, &sg, NULL, keylen); /* We use data_race() because tcp_md5_do_add() might change key->key under us */ return data_race(crypto_ahash_update(hp->md5_req)); } EXPORT_SYMBOL(tcp_md5_hash_key); /* Called with rcu_read_lock() */ 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) { /* * This gets called for each TCP segment that arrives * so we want to be efficient. * We have 3 drop cases: * o No MD5 hash and one expected. * o MD5 hash and we're not expecting one. * o MD5 hash and its wrong. */ const __u8 *hash_location = NULL; struct tcp_md5sig_key *hash_expected; const struct tcphdr *th = tcp_hdr(skb); struct tcp_sock *tp = tcp_sk(sk); int genhash, l3index; u8 newhash[16]; /* sdif set, means packet ingressed via a device * in an L3 domain and dif is set to the l3mdev */ l3index = sdif ? dif : 0; hash_expected = tcp_md5_do_lookup(sk, l3index, saddr, family); hash_location = tcp_parse_md5sig_option(th); /* We've parsed the options - do we have a hash? */ if (!hash_expected && !hash_location) return SKB_NOT_DROPPED_YET; if (hash_expected && !hash_location) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); return SKB_DROP_REASON_TCP_MD5NOTFOUND; } if (!hash_expected && hash_location) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); return SKB_DROP_REASON_TCP_MD5UNEXPECTED; } /* Check the signature. * To support dual stack listeners, we need to handle * IPv4-mapped case. */ if (family == AF_INET) genhash = tcp_v4_md5_hash_skb(newhash, hash_expected, NULL, skb); else genhash = tp->af_specific->calc_md5_hash(newhash, hash_expected, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); if (family == AF_INET) { net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s L3 index %d\n", saddr, ntohs(th->source), daddr, ntohs(th->dest), genhash ? " tcp_v4_calc_md5_hash failed" : "", l3index); } else { net_info_ratelimited("MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u L3 index %d\n", genhash ? "failed" : "mismatch", saddr, ntohs(th->source), daddr, ntohs(th->dest), l3index); } return SKB_DROP_REASON_TCP_MD5FAILURE; } return SKB_NOT_DROPPED_YET; } EXPORT_SYMBOL(tcp_inbound_md5_hash); #endif void tcp_done(struct sock *sk) { struct request_sock *req; /* We might be called with a new socket, after * inet_csk_prepare_forced_close() has been called * so we can not use lockdep_sock_is_held(sk) */ req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, 1); if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV) TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS); tcp_set_state(sk, TCP_CLOSE); tcp_clear_xmit_timers(sk); if (req) reqsk_fastopen_remove(sk, req, false); WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_state_change(sk); else inet_csk_destroy_sock(sk); } EXPORT_SYMBOL_GPL(tcp_done); int tcp_abort(struct sock *sk, int err) { int state = inet_sk_state_load(sk); if (state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); local_bh_disable(); inet_csk_reqsk_queue_drop(req->rsk_listener, req); local_bh_enable(); return 0; } if (state == TCP_TIME_WAIT) { struct inet_timewait_sock *tw = inet_twsk(sk); refcount_inc(&tw->tw_refcnt); local_bh_disable(); inet_twsk_deschedule_put(tw); local_bh_enable(); return 0; } /* Don't race with userspace socket closes such as tcp_close. */ lock_sock(sk); if (sk->sk_state == TCP_LISTEN) { tcp_set_state(sk, TCP_CLOSE); inet_csk_listen_stop(sk); } /* Don't race with BH socket closes such as inet_csk_listen_stop. */ local_bh_disable(); bh_lock_sock(sk); if (!sock_flag(sk, SOCK_DEAD)) { WRITE_ONCE(sk->sk_err, err); /* This barrier is coupled with smp_rmb() in tcp_poll() */ smp_wmb(); sk_error_report(sk); if (tcp_need_reset(sk->sk_state)) tcp_send_active_reset(sk, GFP_ATOMIC); tcp_done(sk); } bh_unlock_sock(sk); local_bh_enable(); tcp_write_queue_purge(sk); release_sock(sk); return 0; } EXPORT_SYMBOL_GPL(tcp_abort); extern struct tcp_congestion_ops tcp_reno; static __initdata unsigned long thash_entries; static int __init set_thash_entries(char *str) { ssize_t ret; if (!str) return 0; ret = kstrtoul(str, 0, &thash_entries); if (ret) return 0; return 1; } __setup("thash_entries=", set_thash_entries); static void __init tcp_init_mem(void) { unsigned long limit = nr_free_buffer_pages() / 16; limit = max(limit, 128UL); sysctl_tcp_mem[0] = limit / 4 * 3; /* 4.68 % */ sysctl_tcp_mem[1] = limit; /* 6.25 % */ sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2; /* 9.37 % */ } void __init tcp_init(void) { int max_rshare, max_wshare, cnt; unsigned long limit; unsigned int i; BUILD_BUG_ON(TCP_MIN_SND_MSS <= MAX_TCP_OPTION_SPACE); BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof_field(struct sk_buff, cb)); percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL); timer_setup(&tcp_orphan_timer, tcp_orphan_update, TIMER_DEFERRABLE); mod_timer(&tcp_orphan_timer, jiffies + TCP_ORPHAN_TIMER_PERIOD); inet_hashinfo2_init(&tcp_hashinfo, "tcp_listen_portaddr_hash", thash_entries, 21, /* one slot per 2 MB*/ 0, 64 * 1024); tcp_hashinfo.bind_bucket_cachep = kmem_cache_create("tcp_bind_bucket", sizeof(struct inet_bind_bucket), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); tcp_hashinfo.bind2_bucket_cachep = kmem_cache_create("tcp_bind2_bucket", sizeof(struct inet_bind2_bucket), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); /* Size and allocate the main established and bind bucket * hash tables. * * The methodology is similar to that of the buffer cache. */ tcp_hashinfo.ehash = alloc_large_system_hash("TCP established", sizeof(struct inet_ehash_bucket), thash_entries, 17, /* one slot per 128 KB of memory */ 0, NULL, &tcp_hashinfo.ehash_mask, 0, thash_entries ? 0 : 512 * 1024); for (i = 0; i <= tcp_hashinfo.ehash_mask; i++) INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].chain, i); if (inet_ehash_locks_alloc(&tcp_hashinfo)) panic("TCP: failed to alloc ehash_locks"); tcp_hashinfo.bhash = alloc_large_system_hash("TCP bind", 2 * sizeof(struct inet_bind_hashbucket), tcp_hashinfo.ehash_mask + 1, 17, /* one slot per 128 KB of memory */ 0, &tcp_hashinfo.bhash_size, NULL, 0, 64 * 1024); tcp_hashinfo.bhash_size = 1U << tcp_hashinfo.bhash_size; tcp_hashinfo.bhash2 = tcp_hashinfo.bhash + tcp_hashinfo.bhash_size; for (i = 0; i < tcp_hashinfo.bhash_size; i++) { spin_lock_init(&tcp_hashinfo.bhash[i].lock); INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain); spin_lock_init(&tcp_hashinfo.bhash2[i].lock); INIT_HLIST_HEAD(&tcp_hashinfo.bhash2[i].chain); } tcp_hashinfo.pernet = false; cnt = tcp_hashinfo.ehash_mask + 1; sysctl_tcp_max_orphans = cnt / 2; tcp_init_mem(); /* Set per-socket limits to no more than 1/128 the pressure threshold */ limit = nr_free_buffer_pages() << (PAGE_SHIFT - 7); max_wshare = min(4UL*1024*1024, limit); max_rshare = min(6UL*1024*1024, limit); init_net.ipv4.sysctl_tcp_wmem[0] = PAGE_SIZE; init_net.ipv4.sysctl_tcp_wmem[1] = 16*1024; init_net.ipv4.sysctl_tcp_wmem[2] = max(64*1024, max_wshare); init_net.ipv4.sysctl_tcp_rmem[0] = PAGE_SIZE; init_net.ipv4.sysctl_tcp_rmem[1] = 131072; init_net.ipv4.sysctl_tcp_rmem[2] = max(131072, max_rshare); pr_info("Hash tables configured (established %u bind %u)\n", tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size); tcp_v4_init(); tcp_metrics_init(); BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0); tcp_tasklet_init(); mptcp_init(); } |
| 12420 1209 12414 9893 9897 9895 9892 12151 12148 12142 12144 12147 12139 38 38 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 | // SPDX-License-Identifier: GPL-2.0 #include <linux/debugfs.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/memblock.h> #include <linux/stacktrace.h> #include <linux/page_owner.h> #include <linux/jump_label.h> #include <linux/migrate.h> #include <linux/stackdepot.h> #include <linux/seq_file.h> #include <linux/memcontrol.h> #include <linux/sched/clock.h> #include "internal.h" /* * TODO: teach PAGE_OWNER_STACK_DEPTH (__dump_page_owner and save_stack) * to use off stack temporal storage */ #define PAGE_OWNER_STACK_DEPTH (16) struct page_owner { unsigned short order; short last_migrate_reason; gfp_t gfp_mask; depot_stack_handle_t handle; depot_stack_handle_t free_handle; u64 ts_nsec; u64 free_ts_nsec; char comm[TASK_COMM_LEN]; pid_t pid; pid_t tgid; }; static bool page_owner_enabled __initdata; DEFINE_STATIC_KEY_FALSE(page_owner_inited); EXPORT_SYMBOL_GPL(page_owner_inited); static depot_stack_handle_t dummy_handle; static depot_stack_handle_t failure_handle; static depot_stack_handle_t early_handle; static void init_early_allocated_pages(void); static int __init early_page_owner_param(char *buf) { int ret = kstrtobool(buf, &page_owner_enabled); if (page_owner_enabled) stack_depot_want_early_init(); return ret; } early_param("page_owner", early_page_owner_param); static __init bool need_page_owner(void) { return page_owner_enabled; } static __always_inline depot_stack_handle_t create_dummy_stack(void) { unsigned long entries[4]; unsigned int nr_entries; nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0); return stack_depot_save(entries, nr_entries, GFP_KERNEL); } static noinline void register_dummy_stack(void) { dummy_handle = create_dummy_stack(); } static noinline void register_failure_stack(void) { failure_handle = create_dummy_stack(); } static noinline void register_early_stack(void) { early_handle = create_dummy_stack(); } static __init void init_page_owner(void) { if (!page_owner_enabled) return; register_dummy_stack(); register_failure_stack(); register_early_stack(); static_branch_enable(&page_owner_inited); init_early_allocated_pages(); } struct page_ext_operations page_owner_ops = { .size = sizeof(struct page_owner), .need = need_page_owner, .init = init_page_owner, }; static inline struct page_owner *get_page_owner(struct page_ext *page_ext) { return (void *)page_ext + page_owner_ops.offset; } depot_stack_handle_t get_page_owner_handle(struct page_ext *page_ext, unsigned long pfn) { struct page_owner *page_owner; depot_stack_handle_t handle; if (!static_branch_unlikely(&page_owner_inited)) return 0; page_owner = get_page_owner(page_ext); /* skip handle for tail pages of higher order allocations */ if (!IS_ALIGNED(pfn, 1 << page_owner->order)) return 0; handle = READ_ONCE(page_owner->handle); return handle; } EXPORT_SYMBOL_NS_GPL(get_page_owner_handle, MINIDUMP); static noinline depot_stack_handle_t save_stack(gfp_t flags) { unsigned long entries[PAGE_OWNER_STACK_DEPTH]; depot_stack_handle_t handle; unsigned int nr_entries; /* * Avoid recursion. * * Sometimes page metadata allocation tracking requires more * memory to be allocated: * - when new stack trace is saved to stack depot * - when backtrace itself is calculated (ia64) */ if (current->in_page_owner) return dummy_handle; current->in_page_owner = 1; nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 2); handle = stack_depot_save(entries, nr_entries, flags); if (!handle) handle = failure_handle; current->in_page_owner = 0; return handle; } void __reset_page_owner(struct page *page, unsigned short order) { int i; struct page_ext *page_ext; depot_stack_handle_t handle; struct page_owner *page_owner; u64 free_ts_nsec = local_clock(); page_ext = page_ext_get(page); if (unlikely(!page_ext)) return; handle = save_stack(GFP_NOWAIT | __GFP_NOWARN); for (i = 0; i < (1 << order); i++) { __clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); page_owner = get_page_owner(page_ext); page_owner->free_handle = handle; page_owner->free_ts_nsec = free_ts_nsec; page_ext = page_ext_next(page_ext); } page_ext_put(page_ext); } static inline void __set_page_owner_handle(struct page_ext *page_ext, depot_stack_handle_t handle, unsigned short order, gfp_t gfp_mask) { struct page_owner *page_owner; int i; for (i = 0; i < (1 << order); i++) { page_owner = get_page_owner(page_ext); page_owner->handle = handle; page_owner->order = order; page_owner->gfp_mask = gfp_mask; page_owner->last_migrate_reason = -1; page_owner->pid = current->pid; page_owner->tgid = current->tgid; page_owner->ts_nsec = local_clock(); strscpy(page_owner->comm, current->comm, sizeof(page_owner->comm)); __set_bit(PAGE_EXT_OWNER, &page_ext->flags); __set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); page_ext = page_ext_next(page_ext); } } noinline void __set_page_owner(struct page *page, unsigned short order, gfp_t gfp_mask) { struct page_ext *page_ext; depot_stack_handle_t handle; handle = save_stack(gfp_mask); page_ext = page_ext_get(page); if (unlikely(!page_ext)) return; __set_page_owner_handle(page_ext, handle, order, gfp_mask); page_ext_put(page_ext); } EXPORT_SYMBOL_GPL(__set_page_owner); void __set_page_owner_migrate_reason(struct page *page, int reason) { struct page_ext *page_ext = page_ext_get(page); struct page_owner *page_owner; if (unlikely(!page_ext)) return; page_owner = get_page_owner(page_ext); page_owner->last_migrate_reason = reason; page_ext_put(page_ext); } void __split_page_owner(struct page *page, unsigned int nr) { int i; struct page_ext *page_ext = page_ext_get(page); struct page_owner *page_owner; if (unlikely(!page_ext)) return; for (i = 0; i < nr; i++) { page_owner = get_page_owner(page_ext); page_owner->order = 0; page_ext = page_ext_next(page_ext); } page_ext_put(page_ext); } void __folio_copy_owner(struct folio *newfolio, struct folio *old) { struct page_ext *old_ext; struct page_ext *new_ext; struct page_owner *old_page_owner, *new_page_owner; old_ext = page_ext_get(&old->page); if (unlikely(!old_ext)) return; new_ext = page_ext_get(&newfolio->page); if (unlikely(!new_ext)) { page_ext_put(old_ext); return; } old_page_owner = get_page_owner(old_ext); new_page_owner = get_page_owner(new_ext); new_page_owner->order = old_page_owner->order; new_page_owner->gfp_mask = old_page_owner->gfp_mask; new_page_owner->last_migrate_reason = old_page_owner->last_migrate_reason; new_page_owner->handle = old_page_owner->handle; new_page_owner->pid = old_page_owner->pid; new_page_owner->tgid = old_page_owner->tgid; new_page_owner->ts_nsec = old_page_owner->ts_nsec; new_page_owner->free_ts_nsec = old_page_owner->ts_nsec; strcpy(new_page_owner->comm, old_page_owner->comm); /* * We don't clear the bit on the old folio as it's going to be freed * after migration. Until then, the info can be useful in case of * a bug, and the overall stats will be off a bit only temporarily. * Also, migrate_misplaced_transhuge_page() can still fail the * migration and then we want the old folio to retain the info. But * in that case we also don't need to explicitly clear the info from * the new page, which will be freed. */ __set_bit(PAGE_EXT_OWNER, &new_ext->flags); __set_bit(PAGE_EXT_OWNER_ALLOCATED, &new_ext->flags); page_ext_put(new_ext); page_ext_put(old_ext); } void pagetypeinfo_showmixedcount_print(struct seq_file *m, pg_data_t *pgdat, struct zone *zone) { struct page *page; struct page_ext *page_ext; struct page_owner *page_owner; unsigned long pfn, block_end_pfn; unsigned long end_pfn = zone_end_pfn(zone); unsigned long count[MIGRATE_TYPES] = { 0, }; int pageblock_mt, page_mt; int i; /* Scan block by block. First and last block may be incomplete */ pfn = zone->zone_start_pfn; /* * Walk the zone in pageblock_nr_pages steps. If a page block spans * a zone boundary, it will be double counted between zones. This does * not matter as the mixed block count will still be correct */ for (; pfn < end_pfn; ) { page = pfn_to_online_page(pfn); if (!page) { pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES); continue; } block_end_pfn = pageblock_end_pfn(pfn); block_end_pfn = min(block_end_pfn, end_pfn); pageblock_mt = get_pageblock_migratetype(page); for (; pfn < block_end_pfn; pfn++) { /* The pageblock is online, no need to recheck. */ page = pfn_to_page(pfn); if (page_zone(page) != zone) continue; if (PageBuddy(page)) { unsigned long freepage_order; freepage_order = buddy_order_unsafe(page); if (freepage_order < MAX_ORDER) pfn += (1UL << freepage_order) - 1; continue; } if (PageReserved(page)) continue; page_ext = page_ext_get(page); if (unlikely(!page_ext)) continue; if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) goto ext_put_continue; page_owner = get_page_owner(page_ext); page_mt = gfp_migratetype(page_owner->gfp_mask); if (pageblock_mt != page_mt) { if (is_migrate_cma(pageblock_mt)) count[MIGRATE_MOVABLE]++; else count[pageblock_mt]++; pfn = block_end_pfn; page_ext_put(page_ext); break; } pfn += (1UL << page_owner->order) - 1; ext_put_continue: page_ext_put(page_ext); } } /* Print counts */ seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); for (i = 0; i < MIGRATE_TYPES; i++) seq_printf(m, "%12lu ", count[i]); seq_putc(m, '\n'); } /* * Looking for memcg information and print it out */ static inline int print_page_owner_memcg(char *kbuf, size_t count, int ret, struct page *page) { #ifdef CONFIG_MEMCG unsigned long memcg_data; struct mem_cgroup *memcg; bool online; char name[80]; rcu_read_lock(); memcg_data = READ_ONCE(page->memcg_data); if (!memcg_data) goto out_unlock; if (memcg_data & MEMCG_DATA_OBJCGS) ret += scnprintf(kbuf + ret, count - ret, "Slab cache page\n"); memcg = page_memcg_check(page); if (!memcg) goto out_unlock; online = (memcg->css.flags & CSS_ONLINE); cgroup_name(memcg->css.cgroup, name, sizeof(name)); ret += scnprintf(kbuf + ret, count - ret, "Charged %sto %smemcg %s\n", PageMemcgKmem(page) ? "(via objcg) " : "", online ? "" : "offline ", name); out_unlock: rcu_read_unlock(); #endif /* CONFIG_MEMCG */ return ret; } static ssize_t print_page_owner(char __user *buf, size_t count, unsigned long pfn, struct page *page, struct page_owner *page_owner, depot_stack_handle_t handle) { int ret, pageblock_mt, page_mt; char *kbuf; count = min_t(size_t, count, PAGE_SIZE); kbuf = kmalloc(count, GFP_KERNEL); if (!kbuf) return -ENOMEM; ret = scnprintf(kbuf, count, "Page allocated via order %u, mask %#x(%pGg), pid %d, tgid %d (%s), ts %llu ns, free_ts %llu ns\n", page_owner->order, page_owner->gfp_mask, &page_owner->gfp_mask, page_owner->pid, page_owner->tgid, page_owner->comm, page_owner->ts_nsec, page_owner->free_ts_nsec); /* Print information relevant to grouping pages by mobility */ pageblock_mt = get_pageblock_migratetype(page); page_mt = gfp_migratetype(page_owner->gfp_mask); ret += scnprintf(kbuf + ret, count - ret, "PFN %lu type %s Block %lu type %s Flags %pGp\n", pfn, migratetype_names[page_mt], pfn >> pageblock_order, migratetype_names[pageblock_mt], &page->flags); ret += stack_depot_snprint(handle, kbuf + ret, count - ret, 0); if (ret >= count) goto err; if (page_owner->last_migrate_reason != -1) { ret += scnprintf(kbuf + ret, count - ret, "Page has been migrated, last migrate reason: %s\n", migrate_reason_names[page_owner->last_migrate_reason]); } ret = print_page_owner_memcg(kbuf, count, ret, page); ret += snprintf(kbuf + ret, count - ret, "\n"); if (ret >= count) goto err; if (copy_to_user(buf, kbuf, ret)) ret = -EFAULT; kfree(kbuf); return ret; err: kfree(kbuf); return -ENOMEM; } void __dump_page_owner(const struct page *page) { struct page_ext *page_ext = page_ext_get((void *)page); struct page_owner *page_owner; depot_stack_handle_t handle; gfp_t gfp_mask; int mt; if (unlikely(!page_ext)) { pr_alert("There is not page extension available.\n"); return; } page_owner = get_page_owner(page_ext); gfp_mask = page_owner->gfp_mask; mt = gfp_migratetype(gfp_mask); if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) { pr_alert("page_owner info is not present (never set?)\n"); page_ext_put(page_ext); return; } if (test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) pr_alert("page_owner tracks the page as allocated\n"); else pr_alert("page_owner tracks the page as freed\n"); pr_alert("page last allocated via order %u, migratetype %s, gfp_mask %#x(%pGg), pid %d, tgid %d (%s), ts %llu, free_ts %llu\n", page_owner->order, migratetype_names[mt], gfp_mask, &gfp_mask, page_owner->pid, page_owner->tgid, page_owner->comm, page_owner->ts_nsec, page_owner->free_ts_nsec); handle = READ_ONCE(page_owner->handle); if (!handle) pr_alert("page_owner allocation stack trace missing\n"); else stack_depot_print(handle); handle = READ_ONCE(page_owner->free_handle); if (!handle) { pr_alert("page_owner free stack trace missing\n"); } else { pr_alert("page last free stack trace:\n"); stack_depot_print(handle); } if (page_owner->last_migrate_reason != -1) pr_alert("page has been migrated, last migrate reason: %s\n", migrate_reason_names[page_owner->last_migrate_reason]); page_ext_put(page_ext); } static ssize_t read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos) { unsigned long pfn; struct page *page; struct page_ext *page_ext; struct page_owner *page_owner; depot_stack_handle_t handle; if (!static_branch_unlikely(&page_owner_inited)) return -EINVAL; page = NULL; if (*ppos == 0) pfn = min_low_pfn; else pfn = *ppos; /* Find a valid PFN or the start of a MAX_ORDER_NR_PAGES area */ while (!pfn_valid(pfn) && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0) pfn++; /* Find an allocated page */ for (; pfn < max_pfn; pfn++) { /* * This temporary page_owner is required so * that we can avoid the context switches while holding * the rcu lock and copying the page owner information to * user through copy_to_user() or GFP_KERNEL allocations. */ struct page_owner page_owner_tmp; /* * If the new page is in a new MAX_ORDER_NR_PAGES area, * validate the area as existing, skip it if not */ if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0 && !pfn_valid(pfn)) { pfn += MAX_ORDER_NR_PAGES - 1; continue; } page = pfn_to_page(pfn); if (PageBuddy(page)) { unsigned long freepage_order = buddy_order_unsafe(page); if (freepage_order < MAX_ORDER) pfn += (1UL << freepage_order) - 1; continue; } page_ext = page_ext_get(page); if (unlikely(!page_ext)) continue; /* * Some pages could be missed by concurrent allocation or free, * because we don't hold the zone lock. */ if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) goto ext_put_continue; /* * Although we do have the info about past allocation of free * pages, it's not relevant for current memory usage. */ if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) goto ext_put_continue; page_owner = get_page_owner(page_ext); /* * Don't print "tail" pages of high-order allocations as that * would inflate the stats. */ if (!IS_ALIGNED(pfn, 1 << page_owner->order)) goto ext_put_continue; /* * Access to page_ext->handle isn't synchronous so we should * be careful to access it. */ handle = READ_ONCE(page_owner->handle); if (!handle) goto ext_put_continue; /* Record the next PFN to read in the file offset */ *ppos = pfn + 1; page_owner_tmp = *page_owner; page_ext_put(page_ext); return print_page_owner(buf, count, pfn, page, &page_owner_tmp, handle); ext_put_continue: page_ext_put(page_ext); } return 0; } static loff_t lseek_page_owner(struct file *file, loff_t offset, int orig) { switch (orig) { case SEEK_SET: file->f_pos = offset; break; case SEEK_CUR: file->f_pos += offset; break; default: return -EINVAL; } return file->f_pos; } static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone) { unsigned long pfn = zone->zone_start_pfn; unsigned long end_pfn = zone_end_pfn(zone); unsigned long count = 0; /* * Walk the zone in pageblock_nr_pages steps. If a page block spans * a zone boundary, it will be double counted between zones. This does * not matter as the mixed block count will still be correct */ for (; pfn < end_pfn; ) { unsigned long block_end_pfn; if (!pfn_valid(pfn)) { pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES); continue; } block_end_pfn = pageblock_end_pfn(pfn); block_end_pfn = min(block_end_pfn, end_pfn); for (; pfn < block_end_pfn; pfn++) { struct page *page = pfn_to_page(pfn); struct page_ext *page_ext; if (page_zone(page) != zone) continue; /* * To avoid having to grab zone->lock, be a little * careful when reading buddy page order. The only * danger is that we skip too much and potentially miss * some early allocated pages, which is better than * heavy lock contention. */ if (PageBuddy(page)) { unsigned long order = buddy_order_unsafe(page); if (order > 0 && order < MAX_ORDER) pfn += (1UL << order) - 1; continue; } if (PageReserved(page)) continue; page_ext = page_ext_get(page); if (unlikely(!page_ext)) continue; /* Maybe overlapping zone */ if (test_bit(PAGE_EXT_OWNER, &page_ext->flags)) goto ext_put_continue; /* Found early allocated page */ __set_page_owner_handle(page_ext, early_handle, 0, 0); count++; ext_put_continue: page_ext_put(page_ext); } cond_resched(); } pr_info("Node %d, zone %8s: page owner found early allocated %lu pages\n", pgdat->node_id, zone->name, count); } static void init_zones_in_node(pg_data_t *pgdat) { struct zone *zone; struct zone *node_zones = pgdat->node_zones; for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { if (!populated_zone(zone)) continue; init_pages_in_zone(pgdat, zone); } } static void init_early_allocated_pages(void) { pg_data_t *pgdat; for_each_online_pgdat(pgdat) init_zones_in_node(pgdat); } static const struct file_operations proc_page_owner_operations = { .read = read_page_owner, .llseek = lseek_page_owner, }; static int __init pageowner_init(void) { if (!static_branch_unlikely(&page_owner_inited)) { pr_info("page_owner is disabled\n"); return 0; } debugfs_create_file("page_owner", 0400, NULL, NULL, &proc_page_owner_operations); return 0; } late_initcall(pageowner_init) |
| 3 117 3 117 117 3 2 1 3 1001 1001 1 999 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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); } |
| 999 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_ACT_API_H #define __NET_ACT_API_H /* * Public action API for classifiers/qdiscs */ #include <linux/refcount.h> #include <net/flow_offload.h> #include <net/sch_generic.h> #include <net/pkt_sched.h> #include <net/net_namespace.h> #include <net/netns/generic.h> struct tcf_idrinfo { struct mutex lock; struct idr action_idr; struct net *net; }; struct tc_action_ops; struct tc_action { const struct tc_action_ops *ops; __u32 type; /* for backward compat(TCA_OLD_COMPAT) */ struct tcf_idrinfo *idrinfo; u32 tcfa_index; refcount_t tcfa_refcnt; atomic_t tcfa_bindcnt; int tcfa_action; struct tcf_t tcfa_tm; struct gnet_stats_basic_sync tcfa_bstats; struct gnet_stats_basic_sync tcfa_bstats_hw; struct gnet_stats_queue tcfa_qstats; struct net_rate_estimator __rcu *tcfa_rate_est; spinlock_t tcfa_lock; struct gnet_stats_basic_sync __percpu *cpu_bstats; struct gnet_stats_basic_sync __percpu *cpu_bstats_hw; struct gnet_stats_queue __percpu *cpu_qstats; struct tc_cookie __rcu *act_cookie; struct tcf_chain __rcu *goto_chain; u32 tcfa_flags; u8 hw_stats; u8 used_hw_stats; bool used_hw_stats_valid; u32 in_hw_count; }; #define tcf_index common.tcfa_index #define tcf_refcnt common.tcfa_refcnt #define tcf_bindcnt common.tcfa_bindcnt #define tcf_action common.tcfa_action #define tcf_tm common.tcfa_tm #define tcf_bstats common.tcfa_bstats #define tcf_qstats common.tcfa_qstats #define tcf_rate_est common.tcfa_rate_est #define tcf_lock common.tcfa_lock #define TCA_ACT_HW_STATS_ANY (TCA_ACT_HW_STATS_IMMEDIATE | \ TCA_ACT_HW_STATS_DELAYED) /* Reserve 16 bits for user-space. See TCA_ACT_FLAGS_NO_PERCPU_STATS. */ #define TCA_ACT_FLAGS_USER_BITS 16 #define TCA_ACT_FLAGS_USER_MASK 0xffff #define TCA_ACT_FLAGS_POLICE (1U << TCA_ACT_FLAGS_USER_BITS) #define TCA_ACT_FLAGS_BIND (1U << (TCA_ACT_FLAGS_USER_BITS + 1)) #define TCA_ACT_FLAGS_REPLACE (1U << (TCA_ACT_FLAGS_USER_BITS + 2)) #define TCA_ACT_FLAGS_NO_RTNL (1U << (TCA_ACT_FLAGS_USER_BITS + 3)) /* Update lastuse only if needed, to avoid dirtying a cache line. * We use a temp variable to avoid fetching jiffies twice. */ static inline void tcf_lastuse_update(struct tcf_t *tm) { unsigned long now = jiffies; if (tm->lastuse != now) tm->lastuse = now; if (unlikely(!tm->firstuse)) tm->firstuse = now; } static inline void tcf_tm_dump(struct tcf_t *dtm, const struct tcf_t *stm) { dtm->install = jiffies_to_clock_t(jiffies - stm->install); dtm->lastuse = jiffies_to_clock_t(jiffies - stm->lastuse); dtm->firstuse = stm->firstuse ? jiffies_to_clock_t(jiffies - stm->firstuse) : 0; dtm->expires = jiffies_to_clock_t(stm->expires); } static inline enum flow_action_hw_stats tc_act_hw_stats(u8 hw_stats) { if (WARN_ON_ONCE(hw_stats > TCA_ACT_HW_STATS_ANY)) return FLOW_ACTION_HW_STATS_DONT_CARE; else if (!hw_stats) return FLOW_ACTION_HW_STATS_DISABLED; return hw_stats; } #ifdef CONFIG_NET_CLS_ACT #define ACT_P_CREATED 1 #define ACT_P_DELETED 1 typedef void (*tc_action_priv_destructor)(void *priv); struct tc_action_ops { struct list_head head; char kind[IFNAMSIZ]; enum tca_id id; /* identifier should match kind */ unsigned int net_id; size_t size; struct module *owner; int (*act)(struct sk_buff *, const struct tc_action *, struct tcf_result *); /* called under RCU BH lock*/ int (*dump)(struct sk_buff *, struct tc_action *, int, int); void (*cleanup)(struct tc_action *); int (*lookup)(struct net *net, struct tc_action **a, u32 index); int (*init)(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **act, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack); int (*walk)(struct net *, struct sk_buff *, struct netlink_callback *, int, const struct tc_action_ops *, struct netlink_ext_ack *); void (*stats_update)(struct tc_action *, u64, u64, u64, u64, bool); size_t (*get_fill_size)(const struct tc_action *act); struct net_device *(*get_dev)(const struct tc_action *a, tc_action_priv_destructor *destructor); struct psample_group * (*get_psample_group)(const struct tc_action *a, tc_action_priv_destructor *destructor); int (*offload_act_setup)(struct tc_action *act, void *entry_data, u32 *index_inc, bool bind, struct netlink_ext_ack *extack); }; struct tc_action_net { struct tcf_idrinfo *idrinfo; const struct tc_action_ops *ops; }; static inline int tc_action_net_init(struct net *net, struct tc_action_net *tn, const struct tc_action_ops *ops) { int err = 0; tn->idrinfo = kmalloc(sizeof(*tn->idrinfo), GFP_KERNEL); if (!tn->idrinfo) return -ENOMEM; tn->ops = ops; tn->idrinfo->net = net; mutex_init(&tn->idrinfo->lock); idr_init(&tn->idrinfo->action_idr); return err; } void tcf_idrinfo_destroy(const struct tc_action_ops *ops, struct tcf_idrinfo *idrinfo); static inline void tc_action_net_exit(struct list_head *net_list, unsigned int id) { struct net *net; rtnl_lock(); list_for_each_entry(net, net_list, exit_list) { struct tc_action_net *tn = net_generic(net, id); tcf_idrinfo_destroy(tn->ops, tn->idrinfo); kfree(tn->idrinfo); } rtnl_unlock(); } int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, struct netlink_callback *cb, int type, const struct tc_action_ops *ops, struct netlink_ext_ack *extack); int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index); int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, int bind, bool cpustats, u32 flags); int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, int bind, u32 flags); void tcf_idr_insert_many(struct tc_action *actions[]); void tcf_idr_cleanup(struct tc_action_net *tn, u32 index); int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, struct tc_action **a, int bind); int tcf_idr_release(struct tc_action *a, bool bind); int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops); int tcf_unregister_action(struct tc_action_ops *a, struct pernet_operations *ops); int tcf_action_destroy(struct tc_action *actions[], int bind); int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, int nr_actions, struct tcf_result *res); int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, struct tc_action *actions[], int init_res[], size_t *attr_size, u32 flags, u32 fl_flags, struct netlink_ext_ack *extack); struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, bool police, bool rtnl_held, struct netlink_ext_ack *extack); struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, struct tc_action_ops *a_o, int *init_res, u32 flags, struct netlink_ext_ack *extack); int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int bind, int ref, bool terse); int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int); int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int); static inline void tcf_action_update_bstats(struct tc_action *a, struct sk_buff *skb) { if (likely(a->cpu_bstats)) { bstats_update(this_cpu_ptr(a->cpu_bstats), skb); return; } spin_lock(&a->tcfa_lock); bstats_update(&a->tcfa_bstats, skb); spin_unlock(&a->tcfa_lock); } static inline void tcf_action_inc_drop_qstats(struct tc_action *a) { if (likely(a->cpu_qstats)) { qstats_drop_inc(this_cpu_ptr(a->cpu_qstats)); return; } spin_lock(&a->tcfa_lock); qstats_drop_inc(&a->tcfa_qstats); spin_unlock(&a->tcfa_lock); } static inline void tcf_action_inc_overlimit_qstats(struct tc_action *a) { if (likely(a->cpu_qstats)) { qstats_overlimit_inc(this_cpu_ptr(a->cpu_qstats)); return; } spin_lock(&a->tcfa_lock); qstats_overlimit_inc(&a->tcfa_qstats); spin_unlock(&a->tcfa_lock); } void tcf_action_update_stats(struct tc_action *a, u64 bytes, u64 packets, u64 drops, bool hw); int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int); int tcf_action_update_hw_stats(struct tc_action *action); int tcf_action_reoffload_cb(flow_indr_block_bind_cb_t *cb, void *cb_priv, bool add); int tcf_action_check_ctrlact(int action, struct tcf_proto *tp, struct tcf_chain **handle, struct netlink_ext_ack *newchain); struct tcf_chain *tcf_action_set_ctrlact(struct tc_action *a, int action, struct tcf_chain *newchain); #ifdef CONFIG_INET DECLARE_STATIC_KEY_FALSE(tcf_frag_xmit_count); #endif int tcf_dev_queue_xmit(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb)); #else /* !CONFIG_NET_CLS_ACT */ static inline int tcf_action_reoffload_cb(flow_indr_block_bind_cb_t *cb, void *cb_priv, bool add) { return 0; } #endif /* CONFIG_NET_CLS_ACT */ static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes, u64 packets, u64 drops, u64 lastuse, bool hw) { #ifdef CONFIG_NET_CLS_ACT if (!a->ops->stats_update) return; a->ops->stats_update(a, bytes, packets, drops, lastuse, hw); #endif } #endif |
| 5112 4924 259 903 902 266 266 3943 2178 905 902 903 2 4917 1122 7 140 4928 259 968 140 140 6 137 140 140 2 259 218 99 2 259 259 1304 38 1282 260 3 163 140 259 259 3 3 4928 4924 4926 4928 316 4917 1188 4923 4927 1188 12 4433 4443 4919 2014 1109 96 4926 4930 4926 4874 965 4870 708 4442 513 4426 4450 1475 1475 1476 1479 1478 1037 1190 1085 497 1054 1086 900 3 902 29 29 7 7 7 7 7 7 228 228 225 227 229 228 229 229 229 227 228 975 7 29 7 973 975 163 903 901 903 902 903 902 901 38 904 904 904 904 903 968 968 968 968 968 968 968 968 968 968 968 968 968 968 968 968 968 968 968 968 968 968 968 968 968 968 968 968 968 968 968 968 968 967 968 968 968 968 968 968 968 968 968 968 1 1 1097 1096 1096 181 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * kernel/workqueue.c - generic async execution with shared worker pool * * Copyright (C) 2002 Ingo Molnar * * Derived from the taskqueue/keventd code by: * David Woodhouse <dwmw2@infradead.org> * Andrew Morton * Kai Petzke <wpp@marie.physik.tu-berlin.de> * Theodore Ts'o <tytso@mit.edu> * * Made to use alloc_percpu by Christoph Lameter. * * Copyright (C) 2010 SUSE Linux Products GmbH * Copyright (C) 2010 Tejun Heo <tj@kernel.org> * * This is the generic async execution mechanism. Work items as are * executed in process context. The worker pool is shared and * automatically managed. There are two worker pools for each CPU (one for * normal work items and the other for high priority ones) and some extra * pools for workqueues which are not bound to any specific CPU - the * number of these backing pools is dynamic. * * Please read Documentation/core-api/workqueue.rst for details. */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/signal.h> #include <linux/completion.h> #include <linux/workqueue.h> #include <linux/slab.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/kthread.h> #include <linux/hardirq.h> #include <linux/mempolicy.h> #include <linux/freezer.h> #include <linux/debug_locks.h> #include <linux/lockdep.h> #include <linux/idr.h> #include <linux/jhash.h> #include <linux/hashtable.h> #include <linux/rculist.h> #include <linux/nodemask.h> #include <linux/moduleparam.h> #include <linux/uaccess.h> #include <linux/sched/isolation.h> #include <linux/nmi.h> #include <linux/kvm_para.h> #include "workqueue_internal.h" #include <trace/hooks/wqlockup.h> /* events/workqueue.h uses default TRACE_INCLUDE_PATH */ #undef TRACE_INCLUDE_PATH enum { /* * worker_pool flags * * A bound pool is either associated or disassociated with its CPU. * While associated (!DISASSOCIATED), all workers are bound to the * CPU and none has %WORKER_UNBOUND set and concurrency management * is in effect. * * While DISASSOCIATED, the cpu may be offline and all workers have * %WORKER_UNBOUND set and concurrency management disabled, and may * be executing on any CPU. The pool behaves as an unbound one. * * Note that DISASSOCIATED should be flipped only while holding * wq_pool_attach_mutex to avoid changing binding state while * worker_attach_to_pool() is in progress. */ POOL_MANAGER_ACTIVE = 1 << 0, /* being managed */ POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */ /* worker flags */ WORKER_DIE = 1 << 1, /* die die die */ WORKER_IDLE = 1 << 2, /* is idle */ WORKER_PREP = 1 << 3, /* preparing to run works */ WORKER_CPU_INTENSIVE = 1 << 6, /* cpu intensive */ WORKER_UNBOUND = 1 << 7, /* worker is unbound */ WORKER_REBOUND = 1 << 8, /* worker was rebound */ WORKER_NOT_RUNNING = WORKER_PREP | WORKER_CPU_INTENSIVE | WORKER_UNBOUND | WORKER_REBOUND, NR_STD_WORKER_POOLS = 2, /* # standard pools per cpu */ UNBOUND_POOL_HASH_ORDER = 6, /* hashed by pool->attrs */ BUSY_WORKER_HASH_ORDER = 6, /* 64 pointers */ MAX_IDLE_WORKERS_RATIO = 4, /* 1/4 of busy can be idle */ IDLE_WORKER_TIMEOUT = 300 * HZ, /* keep idle ones for 5 mins */ MAYDAY_INITIAL_TIMEOUT = HZ / 100 >= 2 ? HZ / 100 : 2, /* call for help after 10ms (min two ticks) */ MAYDAY_INTERVAL = HZ / 10, /* and then every 100ms */ CREATE_COOLDOWN = HZ, /* time to breath after fail */ /* * Rescue workers are used only on emergencies and shared by * all cpus. Give MIN_NICE. */ RESCUER_NICE_LEVEL = MIN_NICE, HIGHPRI_NICE_LEVEL = MIN_NICE, WQ_NAME_LEN = 24, }; /* * Structure fields follow one of the following exclusion rules. * * I: Modifiable by initialization/destruction paths and read-only for * everyone else. * * P: Preemption protected. Disabling preemption is enough and should * only be modified and accessed from the local cpu. * * L: pool->lock protected. Access with pool->lock held. * * X: During normal operation, modification requires pool->lock and should * be done only from local cpu. Either disabling preemption on local * cpu or grabbing pool->lock is enough for read access. If * POOL_DISASSOCIATED is set, it's identical to L. * * A: wq_pool_attach_mutex protected. * * PL: wq_pool_mutex protected. * * PR: wq_pool_mutex protected for writes. RCU protected for reads. * * PW: wq_pool_mutex and wq->mutex protected for writes. Either for reads. * * PWR: wq_pool_mutex and wq->mutex protected for writes. Either or * RCU for reads. * * WQ: wq->mutex protected. * * WR: wq->mutex protected for writes. RCU protected for reads. * * MD: wq_mayday_lock protected. */ /* struct worker is defined in workqueue_internal.h */ struct worker_pool { raw_spinlock_t lock; /* the pool lock */ int cpu; /* I: the associated cpu */ int node; /* I: the associated node ID */ int id; /* I: pool ID */ unsigned int flags; /* X: flags */ unsigned long watchdog_ts; /* L: watchdog timestamp */ /* * The counter is incremented in a process context on the associated CPU * w/ preemption disabled, and decremented or reset in the same context * but w/ pool->lock held. The readers grab pool->lock and are * guaranteed to see if the counter reached zero. */ int nr_running; struct list_head worklist; /* L: list of pending works */ int nr_workers; /* L: total number of workers */ int nr_idle; /* L: currently idle workers */ struct list_head idle_list; /* L: list of idle workers */ struct timer_list idle_timer; /* L: worker idle timeout */ struct timer_list mayday_timer; /* L: SOS timer for workers */ /* a workers is either on busy_hash or idle_list, or the manager */ DECLARE_HASHTABLE(busy_hash, BUSY_WORKER_HASH_ORDER); /* L: hash of busy workers */ struct worker *manager; /* L: purely informational */ struct list_head workers; /* A: attached workers */ struct completion *detach_completion; /* all workers detached */ struct ida worker_ida; /* worker IDs for task name */ struct workqueue_attrs *attrs; /* I: worker attributes */ struct hlist_node hash_node; /* PL: unbound_pool_hash node */ int refcnt; /* PL: refcnt for unbound pools */ /* * Destruction of pool is RCU protected to allow dereferences * from get_work_pool(). */ struct rcu_head rcu; }; /* * The per-pool workqueue. While queued, the lower WORK_STRUCT_FLAG_BITS * of work_struct->data are used for flags and the remaining high bits * point to the pwq; thus, pwqs need to be aligned at two's power of the * number of flag bits. */ struct pool_workqueue { struct worker_pool *pool; /* I: the associated pool */ struct workqueue_struct *wq; /* I: the owning workqueue */ int work_color; /* L: current color */ int flush_color; /* L: flushing color */ int refcnt; /* L: reference count */ int nr_in_flight[WORK_NR_COLORS]; /* L: nr of in_flight works */ /* * nr_active management and WORK_STRUCT_INACTIVE: * * When pwq->nr_active >= max_active, new work item is queued to * pwq->inactive_works instead of pool->worklist and marked with * WORK_STRUCT_INACTIVE. * * All work items marked with WORK_STRUCT_INACTIVE do not participate * in pwq->nr_active and all work items in pwq->inactive_works are * marked with WORK_STRUCT_INACTIVE. But not all WORK_STRUCT_INACTIVE * work items are in pwq->inactive_works. Some of them are ready to * run in pool->worklist or worker->scheduled. Those work itmes are * only struct wq_barrier which is used for flush_work() and should * not participate in pwq->nr_active. For non-barrier work item, it * is marked with WORK_STRUCT_INACTIVE iff it is in pwq->inactive_works. */ int nr_active; /* L: nr of active works */ int max_active; /* L: max active works */ struct list_head inactive_works; /* L: inactive works */ struct list_head pwqs_node; /* WR: node on wq->pwqs */ struct list_head mayday_node; /* MD: node on wq->maydays */ /* * Release of unbound pwq is punted to system_wq. See put_pwq() * and pwq_unbound_release_workfn() for details. pool_workqueue * itself is also RCU protected so that the first pwq can be * determined without grabbing wq->mutex. */ struct work_struct unbound_release_work; struct rcu_head rcu; } __aligned(1 << WORK_STRUCT_FLAG_BITS); /* * Structure used to wait for workqueue flush. */ struct wq_flusher { struct list_head list; /* WQ: list of flushers */ int flush_color; /* WQ: flush color waiting for */ struct completion done; /* flush completion */ }; struct wq_device; /* * The externally visible workqueue. It relays the issued work items to * the appropriate worker_pool through its pool_workqueues. */ struct workqueue_struct { struct list_head pwqs; /* WR: all pwqs of this wq */ struct list_head list; /* PR: list of all workqueues */ struct mutex mutex; /* protects this wq */ int work_color; /* WQ: current work color */ int flush_color; /* WQ: current flush color */ atomic_t nr_pwqs_to_flush; /* flush in progress */ struct wq_flusher *first_flusher; /* WQ: first flusher */ struct list_head flusher_queue; /* WQ: flush waiters */ struct list_head flusher_overflow; /* WQ: flush overflow list */ struct list_head maydays; /* MD: pwqs requesting rescue */ struct worker *rescuer; /* MD: rescue worker */ int nr_drainers; /* WQ: drain in progress */ int saved_max_active; /* WQ: saved pwq max_active */ struct workqueue_attrs *unbound_attrs; /* PW: only for unbound wqs */ struct pool_workqueue *dfl_pwq; /* PW: only for unbound wqs */ #ifdef CONFIG_SYSFS struct wq_device *wq_dev; /* I: for sysfs interface */ #endif #ifdef CONFIG_LOCKDEP char *lock_name; struct lock_class_key key; struct lockdep_map lockdep_map; #endif char name[WQ_NAME_LEN]; /* I: workqueue name */ /* * Destruction of workqueue_struct is RCU protected to allow walking * the workqueues list without grabbing wq_pool_mutex. * This is used to dump all workqueues from sysrq. */ struct rcu_head rcu; /* hot fields used during command issue, aligned to cacheline */ unsigned int flags ____cacheline_aligned; /* WQ: WQ_* flags */ struct pool_workqueue __percpu *cpu_pwqs; /* I: per-cpu pwqs */ struct pool_workqueue __rcu *numa_pwq_tbl[]; /* PWR: unbound pwqs indexed by node */ }; static struct kmem_cache *pwq_cache; static cpumask_var_t *wq_numa_possible_cpumask; /* possible CPUs of each node */ static bool wq_disable_numa; module_param_named(disable_numa, wq_disable_numa, bool, 0444); /* see the comment above the definition of WQ_POWER_EFFICIENT */ static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT); module_param_named(power_efficient, wq_power_efficient, bool, 0444); static bool wq_online; /* can kworkers be created yet? */ static bool wq_numa_enabled; /* unbound NUMA affinity enabled */ /* buf for wq_update_unbound_numa_attrs(), protected by CPU hotplug exclusion */ static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf; static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */ static DEFINE_MUTEX(wq_pool_attach_mutex); /* protects worker attach/detach */ static DEFINE_RAW_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */ /* wait for manager to go away */ static struct rcuwait manager_wait = __RCUWAIT_INITIALIZER(manager_wait); static LIST_HEAD(workqueues); /* PR: list of all workqueues */ static bool workqueue_freezing; /* PL: have wqs started freezing? */ /* PL&A: allowable cpus for unbound wqs and work items */ static cpumask_var_t wq_unbound_cpumask; /* CPU where unbound work was last round robin scheduled from this CPU */ static DEFINE_PER_CPU(int, wq_rr_cpu_last); /* * Local execution of unbound work items is no longer guaranteed. The * following always forces round-robin CPU selection on unbound work items * to uncover usages which depend on it. */ #ifdef CONFIG_DEBUG_WQ_FORCE_RR_CPU static bool wq_debug_force_rr_cpu = true; #else static bool wq_debug_force_rr_cpu = false; #endif module_param_named(debug_force_rr_cpu, wq_debug_force_rr_cpu, bool, 0644); /* the per-cpu worker pools */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], cpu_worker_pools); static DEFINE_IDR(worker_pool_idr); /* PR: idr of all pools */ /* PL: hash of all unbound pools keyed by pool->attrs */ static DEFINE_HASHTABLE(unbound_pool_hash, UNBOUND_POOL_HASH_ORDER); /* I: attributes used when instantiating standard unbound pools on demand */ static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS]; /* I: attributes used when instantiating ordered pools on demand */ static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS]; struct workqueue_struct *system_wq __read_mostly; EXPORT_SYMBOL(system_wq); struct workqueue_struct *system_highpri_wq __read_mostly; EXPORT_SYMBOL_GPL(system_highpri_wq); struct workqueue_struct *system_long_wq __read_mostly; EXPORT_SYMBOL_GPL(system_long_wq); struct workqueue_struct *system_unbound_wq __read_mostly; EXPORT_SYMBOL_GPL(system_unbound_wq); struct workqueue_struct *system_freezable_wq __read_mostly; EXPORT_SYMBOL_GPL(system_freezable_wq); struct workqueue_struct *system_power_efficient_wq __read_mostly; EXPORT_SYMBOL_GPL(system_power_efficient_wq); struct workqueue_struct *system_freezable_power_efficient_wq __read_mostly; EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); static int worker_thread(void *__worker); static void workqueue_sysfs_unregister(struct workqueue_struct *wq); static void show_pwq(struct pool_workqueue *pwq); static void show_one_worker_pool(struct worker_pool *pool); #define CREATE_TRACE_POINTS #include <trace/events/workqueue.h> EXPORT_TRACEPOINT_SYMBOL_GPL(workqueue_execute_start); EXPORT_TRACEPOINT_SYMBOL_GPL(workqueue_execute_end); #define assert_rcu_or_pool_mutex() \ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ !lockdep_is_held(&wq_pool_mutex), \ "RCU or wq_pool_mutex should be held") #define assert_rcu_or_wq_mutex_or_pool_mutex(wq) \ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ !lockdep_is_held(&wq->mutex) && \ !lockdep_is_held(&wq_pool_mutex), \ "RCU, wq->mutex or wq_pool_mutex should be held") #define for_each_cpu_worker_pool(pool, cpu) \ for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ (pool) < &per_cpu(cpu_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \ (pool)++) /** * for_each_pool - iterate through all worker_pools in the system * @pool: iteration cursor * @pi: integer used for iteration * * This must be called either with wq_pool_mutex held or RCU read * locked. If the pool needs to be used beyond the locking in effect, the * caller is responsible for guaranteeing that the pool stays online. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pool(pool, pi) \ idr_for_each_entry(&worker_pool_idr, pool, pi) \ if (({ assert_rcu_or_pool_mutex(); false; })) { } \ else /** * for_each_pool_worker - iterate through all workers of a worker_pool * @worker: iteration cursor * @pool: worker_pool to iterate workers of * * This must be called with wq_pool_attach_mutex. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pool_worker(worker, pool) \ list_for_each_entry((worker), &(pool)->workers, node) \ if (({ lockdep_assert_held(&wq_pool_attach_mutex); false; })) { } \ else /** * for_each_pwq - iterate through all pool_workqueues of the specified workqueue * @pwq: iteration cursor * @wq: the target workqueue * * This must be called either with wq->mutex held or RCU read locked. * If the pwq needs to be used beyond the locking in effect, the caller is * responsible for guaranteeing that the pwq stays online. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pwq(pwq, wq) \ list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node, \ lockdep_is_held(&(wq->mutex))) #ifdef CONFIG_DEBUG_OBJECTS_WORK static const struct debug_obj_descr work_debug_descr; static void *work_debug_hint(void *addr) { return ((struct work_struct *) addr)->func; } static bool work_is_static_object(void *addr) { struct work_struct *work = addr; return test_bit(WORK_STRUCT_STATIC_BIT, work_data_bits(work)); } /* * fixup_init is called when: * - an active object is initialized */ static bool work_fixup_init(void *addr, enum debug_obj_state state) { struct work_struct *work = addr; switch (state) { case ODEBUG_STATE_ACTIVE: cancel_work_sync(work); debug_object_init(work, &work_debug_descr); return true; default: return false; } } /* * fixup_free is called when: * - an active object is freed */ static bool work_fixup_free(void *addr, enum debug_obj_state state) { struct work_struct *work = addr; switch (state) { case ODEBUG_STATE_ACTIVE: cancel_work_sync(work); debug_object_free(work, &work_debug_descr); return true; default: return false; } } static const struct debug_obj_descr work_debug_descr = { .name = "work_struct", .debug_hint = work_debug_hint, .is_static_object = work_is_static_object, .fixup_init = work_fixup_init, .fixup_free = work_fixup_free, }; static inline void debug_work_activate(struct work_struct *work) { debug_object_activate(work, &work_debug_descr); } static inline void debug_work_deactivate(struct work_struct *work) { debug_object_deactivate(work, &work_debug_descr); } void __init_work(struct work_struct *work, int onstack) { if (onstack) debug_object_init_on_stack(work, &work_debug_descr); else debug_object_init(work, &work_debug_descr); } EXPORT_SYMBOL_GPL(__init_work); void destroy_work_on_stack(struct work_struct *work) { debug_object_free(work, &work_debug_descr); } EXPORT_SYMBOL_GPL(destroy_work_on_stack); void destroy_delayed_work_on_stack(struct delayed_work *work) { destroy_timer_on_stack(&work->timer); debug_object_free(&work->work, &work_debug_descr); } EXPORT_SYMBOL_GPL(destroy_delayed_work_on_stack); #else static inline void debug_work_activate(struct work_struct *work) { } static inline void debug_work_deactivate(struct work_struct *work) { } #endif /** * worker_pool_assign_id - allocate ID and assign it to @pool * @pool: the pool pointer of interest * * Returns 0 if ID in [0, WORK_OFFQ_POOL_NONE) is allocated and assigned * successfully, -errno on failure. */ static int worker_pool_assign_id(struct worker_pool *pool) { int ret; lockdep_assert_held(&wq_pool_mutex); ret = idr_alloc(&worker_pool_idr, pool, 0, WORK_OFFQ_POOL_NONE, GFP_KERNEL); if (ret >= 0) { pool->id = ret; return 0; } return ret; } /** * unbound_pwq_by_node - return the unbound pool_workqueue for the given node * @wq: the target workqueue * @node: the node ID * * This must be called with any of wq_pool_mutex, wq->mutex or RCU * read locked. * If the pwq needs to be used beyond the locking in effect, the caller is * responsible for guaranteeing that the pwq stays online. * * Return: The unbound pool_workqueue for @node. */ static struct pool_workqueue *unbound_pwq_by_node(struct workqueue_struct *wq, int node) { assert_rcu_or_wq_mutex_or_pool_mutex(wq); /* * XXX: @node can be NUMA_NO_NODE if CPU goes offline while a * delayed item is pending. The plan is to keep CPU -> NODE * mapping valid and stable across CPU on/offlines. Once that * happens, this workaround can be removed. */ if (unlikely(node == NUMA_NO_NODE)) return wq->dfl_pwq; return rcu_dereference_raw(wq->numa_pwq_tbl[node]); } static unsigned int work_color_to_flags(int color) { return color << WORK_STRUCT_COLOR_SHIFT; } static int get_work_color(unsigned long work_data) { return (work_data >> WORK_STRUCT_COLOR_SHIFT) & ((1 << WORK_STRUCT_COLOR_BITS) - 1); } static int work_next_color(int color) { return (color + 1) % WORK_NR_COLORS; } /* * While queued, %WORK_STRUCT_PWQ is set and non flag bits of a work's data * contain the pointer to the queued pwq. Once execution starts, the flag * is cleared and the high bits contain OFFQ flags and pool ID. * * set_work_pwq(), set_work_pool_and_clear_pending(), mark_work_canceling() * and clear_work_data() can be used to set the pwq, pool or clear * work->data. These functions should only be called while the work is * owned - ie. while the PENDING bit is set. * * get_work_pool() and get_work_pwq() can be used to obtain the pool or pwq * corresponding to a work. Pool is available once the work has been * queued anywhere after initialization until it is sync canceled. pwq is * available only while the work item is queued. * * %WORK_OFFQ_CANCELING is used to mark a work item which is being * canceled. While being canceled, a work item may have its PENDING set * but stay off timer and worklist for arbitrarily long and nobody should * try to steal the PENDING bit. */ static inline void set_work_data(struct work_struct *work, unsigned long data, unsigned long flags) { WARN_ON_ONCE(!work_pending(work)); atomic_long_set(&work->data, data | flags | work_static(work)); } static void set_work_pwq(struct work_struct *work, struct pool_workqueue *pwq, unsigned long extra_flags) { set_work_data(work, (unsigned long)pwq, WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | extra_flags); } static void set_work_pool_and_keep_pending(struct work_struct *work, int pool_id) { set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, WORK_STRUCT_PENDING); } static void set_work_pool_and_clear_pending(struct work_struct *work, int pool_id) { /* * The following wmb is paired with the implied mb in * test_and_set_bit(PENDING) and ensures all updates to @work made * here are visible to and precede any updates by the next PENDING * owner. */ smp_wmb(); set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, 0); /* * The following mb guarantees that previous clear of a PENDING bit * will not be reordered with any speculative LOADS or STORES from * work->current_func, which is executed afterwards. This possible * reordering can lead to a missed execution on attempt to queue * the same @work. E.g. consider this case: * * CPU#0 CPU#1 * ---------------------------- -------------------------------- * * 1 STORE event_indicated * 2 queue_work_on() { * 3 test_and_set_bit(PENDING) * 4 } set_..._and_clear_pending() { * 5 set_work_data() # clear bit * 6 smp_mb() * 7 work->current_func() { * 8 LOAD event_indicated * } * * Without an explicit full barrier speculative LOAD on line 8 can * be executed before CPU#0 does STORE on line 1. If that happens, * CPU#0 observes the PENDING bit is still set and new execution of * a @work is not queued in a hope, that CPU#1 will eventually * finish the queued @work. Meanwhile CPU#1 does not see * event_indicated is set, because speculative LOAD was executed * before actual STORE. */ smp_mb(); } static void clear_work_data(struct work_struct *work) { smp_wmb(); /* see set_work_pool_and_clear_pending() */ set_work_data(work, WORK_STRUCT_NO_POOL, 0); } static inline struct pool_workqueue *work_struct_pwq(unsigned long data) { return (struct pool_workqueue *)(data & WORK_STRUCT_WQ_DATA_MASK); } static struct pool_workqueue *get_work_pwq(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); if (data & WORK_STRUCT_PWQ) return work_struct_pwq(data); else return NULL; } /** * get_work_pool - return the worker_pool a given work was associated with * @work: the work item of interest * * Pools are created and destroyed under wq_pool_mutex, and allows read * access under RCU read lock. As such, this function should be * called under wq_pool_mutex or inside of a rcu_read_lock() region. * * All fields of the returned pool are accessible as long as the above * mentioned locking is in effect. If the returned pool needs to be used * beyond the critical section, the caller is responsible for ensuring the * returned pool is and stays online. * * Return: The worker_pool @work was last associated with. %NULL if none. */ static struct worker_pool *get_work_pool(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); int pool_id; assert_rcu_or_pool_mutex(); if (data & WORK_STRUCT_PWQ) return work_struct_pwq(data)->pool; pool_id = data >> WORK_OFFQ_POOL_SHIFT; if (pool_id == WORK_OFFQ_POOL_NONE) return NULL; return idr_find(&worker_pool_idr, pool_id); } /** * get_work_pool_id - return the worker pool ID a given work is associated with * @work: the work item of interest * * Return: The worker_pool ID @work was last associated with. * %WORK_OFFQ_POOL_NONE if none. */ static int get_work_pool_id(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); if (data & WORK_STRUCT_PWQ) return work_struct_pwq(data)->pool->id; return data >> WORK_OFFQ_POOL_SHIFT; } static void mark_work_canceling(struct work_struct *work) { unsigned long pool_id = get_work_pool_id(work); pool_id <<= WORK_OFFQ_POOL_SHIFT; set_work_data(work, pool_id | WORK_OFFQ_CANCELING, WORK_STRUCT_PENDING); } static bool work_is_canceling(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); return !(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_CANCELING); } /* * Policy functions. These define the policies on how the global worker * pools are managed. Unless noted otherwise, these functions assume that * they're being called with pool->lock held. */ static bool __need_more_worker(struct worker_pool *pool) { return !pool->nr_running; } /* * Need to wake up a worker? Called from anything but currently * running workers. * * Note that, because unbound workers never contribute to nr_running, this * function will always return %true for unbound pools as long as the * worklist isn't empty. */ static bool need_more_worker(struct worker_pool *pool) { return !list_empty(&pool->worklist) && __need_more_worker(pool); } /* Can I start working? Called from busy but !running workers. */ static bool may_start_working(struct worker_pool *pool) { return pool->nr_idle; } /* Do I need to keep working? Called from currently running workers. */ static bool keep_working(struct worker_pool *pool) { return !list_empty(&pool->worklist) && (pool->nr_running <= 1); } /* Do we need a new worker? Called from manager. */ static bool need_to_create_worker(struct worker_pool *pool) { return need_more_worker(pool) && !may_start_working(pool); } /* Do we have too many workers and should some go away? */ static bool too_many_workers(struct worker_pool *pool) { bool managing = pool->flags & POOL_MANAGER_ACTIVE; int nr_idle = pool->nr_idle + managing; /* manager is considered idle */ int nr_busy = pool->nr_workers - nr_idle; return nr_idle > 2 && (nr_idle - 2) * MAX_IDLE_WORKERS_RATIO >= nr_busy; } /* * Wake up functions. */ /* Return the first idle worker. Called with pool->lock held. */ static struct worker *first_idle_worker(struct worker_pool *pool) { if (unlikely(list_empty(&pool->idle_list))) return NULL; return list_first_entry(&pool->idle_list, struct worker, entry); } /** * wake_up_worker - wake up an idle worker * @pool: worker pool to wake worker from * * Wake up the first idle worker of @pool. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void wake_up_worker(struct worker_pool *pool) { struct worker *worker = first_idle_worker(pool); if (likely(worker)) wake_up_process(worker->task); } /** * wq_worker_running - a worker is running again * @task: task waking up * * This function is called when a worker returns from schedule() */ void wq_worker_running(struct task_struct *task) { struct worker *worker = kthread_data(task); if (!worker->sleeping) return; /* * If preempted by unbind_workers() between the WORKER_NOT_RUNNING check * and the nr_running increment below, we may ruin the nr_running reset * and leave with an unexpected pool->nr_running == 1 on the newly unbound * pool. Protect against such race. */ preempt_disable(); if (!(worker->flags & WORKER_NOT_RUNNING)) worker->pool->nr_running++; preempt_enable(); worker->sleeping = 0; } /** * wq_worker_sleeping - a worker is going to sleep * @task: task going to sleep * * This function is called from schedule() when a busy worker is * going to sleep. */ void wq_worker_sleeping(struct task_struct *task) { struct worker *worker = kthread_data(task); struct worker_pool *pool; /* * Rescuers, which may not have all the fields set up like normal * workers, also reach here, let's not access anything before * checking NOT_RUNNING. */ if (worker->flags & WORKER_NOT_RUNNING) return; pool = worker->pool; /* Return if preempted before wq_worker_running() was reached */ if (worker->sleeping) return; worker->sleeping = 1; raw_spin_lock_irq(&pool->lock); /* * Recheck in case unbind_workers() preempted us. We don't * want to decrement nr_running after the worker is unbound * and nr_running has been reset. */ if (worker->flags & WORKER_NOT_RUNNING) { raw_spin_unlock_irq(&pool->lock); return; } pool->nr_running--; if (need_more_worker(pool)) wake_up_worker(pool); raw_spin_unlock_irq(&pool->lock); } /** * wq_worker_last_func - retrieve worker's last work function * @task: Task to retrieve last work function of. * * Determine the last function a worker executed. This is called from * the scheduler to get a worker's last known identity. * * CONTEXT: * raw_spin_lock_irq(rq->lock) * * This function is called during schedule() when a kworker is going * to sleep. It's used by psi to identify aggregation workers during * dequeuing, to allow periodic aggregation to shut-off when that * worker is the last task in the system or cgroup to go to sleep. * * As this function doesn't involve any workqueue-related locking, it * only returns stable values when called from inside the scheduler's * queuing and dequeuing paths, when @task, which must be a kworker, * is guaranteed to not be processing any works. * * Return: * The last work function %current executed as a worker, NULL if it * hasn't executed any work yet. */ work_func_t wq_worker_last_func(struct task_struct *task) { struct worker *worker = kthread_data(task); return worker->last_func; } /** * worker_set_flags - set worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to set * * Set @flags in @worker->flags and adjust nr_running accordingly. * * CONTEXT: * raw_spin_lock_irq(pool->lock) */ static inline void worker_set_flags(struct worker *worker, unsigned int flags) { struct worker_pool *pool = worker->pool; WARN_ON_ONCE(worker->task != current); /* If transitioning into NOT_RUNNING, adjust nr_running. */ if ((flags & WORKER_NOT_RUNNING) && !(worker->flags & WORKER_NOT_RUNNING)) { pool->nr_running--; } worker->flags |= flags; } /** * worker_clr_flags - clear worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to clear * * Clear @flags in @worker->flags and adjust nr_running accordingly. * * CONTEXT: * raw_spin_lock_irq(pool->lock) */ static inline void worker_clr_flags(struct worker *worker, unsigned int flags) { struct worker_pool *pool = worker->pool; unsigned int oflags = worker->flags; WARN_ON_ONCE(worker->task != current); worker->flags &= ~flags; /* * If transitioning out of NOT_RUNNING, increment nr_running. Note * that the nested NOT_RUNNING is not a noop. NOT_RUNNING is mask * of multiple flags, not a single flag. */ if ((flags & WORKER_NOT_RUNNING) && (oflags & WORKER_NOT_RUNNING)) if (!(worker->flags & WORKER_NOT_RUNNING)) pool->nr_running++; } /** * find_worker_executing_work - find worker which is executing a work * @pool: pool of interest * @work: work to find worker for * * Find a worker which is executing @work on @pool by searching * @pool->busy_hash which is keyed by the address of @work. For a worker * to match, its current execution should match the address of @work and * its work function. This is to avoid unwanted dependency between * unrelated work executions through a work item being recycled while still * being executed. * * This is a bit tricky. A work item may be freed once its execution * starts and nothing prevents the freed area from being recycled for * another work item. If the same work item address ends up being reused * before the original execution finishes, workqueue will identify the * recycled work item as currently executing and make it wait until the * current execution finishes, introducing an unwanted dependency. * * This function checks the work item address and work function to avoid * false positives. Note that this isn't complete as one may construct a * work function which can introduce dependency onto itself through a * recycled work item. Well, if somebody wants to shoot oneself in the * foot that badly, there's only so much we can do, and if such deadlock * actually occurs, it should be easy to locate the culprit work function. * * CONTEXT: * raw_spin_lock_irq(pool->lock). * * Return: * Pointer to worker which is executing @work if found, %NULL * otherwise. */ static struct worker *find_worker_executing_work(struct worker_pool *pool, struct work_struct *work) { struct worker *worker; hash_for_each_possible(pool->busy_hash, worker, hentry, (unsigned long)work) if (worker->current_work == work && worker->current_func == work->func) return worker; return NULL; } /** * move_linked_works - move linked works to a list * @work: start of series of works to be scheduled * @head: target list to append @work to * @nextp: out parameter for nested worklist walking * * Schedule linked works starting from @work to @head. Work series to * be scheduled starts at @work and includes any consecutive work with * WORK_STRUCT_LINKED set in its predecessor. * * If @nextp is not NULL, it's updated to point to the next work of * the last scheduled work. This allows move_linked_works() to be * nested inside outer list_for_each_entry_safe(). * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void move_linked_works(struct work_struct *work, struct list_head *head, struct work_struct **nextp) { struct work_struct *n; /* * Linked worklist will always end before the end of the list, * use NULL for list head. */ list_for_each_entry_safe_from(work, n, NULL, entry) { list_move_tail(&work->entry, head); if (!(*work_data_bits(work) & WORK_STRUCT_LINKED)) break; } /* * If we're already inside safe list traversal and have moved * multiple works to the scheduled queue, the next position * needs to be updated. */ if (nextp) *nextp = n; } /** * get_pwq - get an extra reference on the specified pool_workqueue * @pwq: pool_workqueue to get * * Obtain an extra reference on @pwq. The caller should guarantee that * @pwq has positive refcnt and be holding the matching pool->lock. */ static void get_pwq(struct pool_workqueue *pwq) { lockdep_assert_held(&pwq->pool->lock); WARN_ON_ONCE(pwq->refcnt <= 0); pwq->refcnt++; } /** * put_pwq - put a pool_workqueue reference * @pwq: pool_workqueue to put * * Drop a reference of @pwq. If its refcnt reaches zero, schedule its * destruction. The caller should be holding the matching pool->lock. */ static void put_pwq(struct pool_workqueue *pwq) { lockdep_assert_held(&pwq->pool->lock); if (likely(--pwq->refcnt)) return; if (WARN_ON_ONCE(!(pwq->wq->flags & WQ_UNBOUND))) return; /* * @pwq can't be released under pool->lock, bounce to * pwq_unbound_release_workfn(). This never recurses on the same * pool->lock as this path is taken only for unbound workqueues and * the release work item is scheduled on a per-cpu workqueue. To * avoid lockdep warning, unbound pool->locks are given lockdep * subclass of 1 in get_unbound_pool(). */ schedule_work(&pwq->unbound_release_work); } /** * put_pwq_unlocked - put_pwq() with surrounding pool lock/unlock * @pwq: pool_workqueue to put (can be %NULL) * * put_pwq() with locking. This function also allows %NULL @pwq. */ static void put_pwq_unlocked(struct pool_workqueue *pwq) { if (pwq) { /* * As both pwqs and pools are RCU protected, the * following lock operations are safe. */ raw_spin_lock_irq(&pwq->pool->lock); put_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); } } static void pwq_activate_inactive_work(struct work_struct *work) { struct pool_workqueue *pwq = get_work_pwq(work); trace_workqueue_activate_work(work); if (list_empty(&pwq->pool->worklist)) pwq->pool->watchdog_ts = jiffies; move_linked_works(work, &pwq->pool->worklist, NULL); __clear_bit(WORK_STRUCT_INACTIVE_BIT, work_data_bits(work)); pwq->nr_active++; } static void pwq_activate_first_inactive(struct pool_workqueue *pwq) { struct work_struct *work = list_first_entry(&pwq->inactive_works, struct work_struct, entry); pwq_activate_inactive_work(work); } /** * pwq_dec_nr_in_flight - decrement pwq's nr_in_flight * @pwq: pwq of interest * @work_data: work_data of work which left the queue * * A work either has completed or is removed from pending queue, * decrement nr_in_flight of its pwq and handle workqueue flushing. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, unsigned long work_data) { int color = get_work_color(work_data); if (!(work_data & WORK_STRUCT_INACTIVE)) { pwq->nr_active--; if (!list_empty(&pwq->inactive_works)) { /* one down, submit an inactive one */ if (pwq->nr_active < pwq->max_active) pwq_activate_first_inactive(pwq); } } pwq->nr_in_flight[color]--; /* is flush in progress and are we at the flushing tip? */ if (likely(pwq->flush_color != color)) goto out_put; /* are there still in-flight works? */ if (pwq->nr_in_flight[color]) goto out_put; /* this pwq is done, clear flush_color */ pwq->flush_color = -1; /* * If this was the last pwq, wake up the first flusher. It * will handle the rest. */ if (atomic_dec_and_test(&pwq->wq->nr_pwqs_to_flush)) complete(&pwq->wq->first_flusher->done); out_put: put_pwq(pwq); } /** * try_to_grab_pending - steal work item from worklist and disable irq * @work: work item to steal * @is_dwork: @work is a delayed_work * @flags: place to store irq state * * Try to grab PENDING bit of @work. This function can handle @work in any * stable state - idle, on timer or on worklist. * * Return: * * ======== ================================================================ * 1 if @work was pending and we successfully stole PENDING * 0 if @work was idle and we claimed PENDING * -EAGAIN if PENDING couldn't be grabbed at the moment, safe to busy-retry * -ENOENT if someone else is canceling @work, this state may persist * for arbitrarily long * ======== ================================================================ * * Note: * On >= 0 return, the caller owns @work's PENDING bit. To avoid getting * interrupted while holding PENDING and @work off queue, irq must be * disabled on entry. This, combined with delayed_work->timer being * irqsafe, ensures that we return -EAGAIN for finite short period of time. * * On successful return, >= 0, irq is disabled and the caller is * responsible for releasing it using local_irq_restore(*@flags). * * This function is safe to call from any context including IRQ handler. */ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, unsigned long *flags) { struct worker_pool *pool; struct pool_workqueue *pwq; local_irq_save(*flags); /* try to steal the timer if it exists */ if (is_dwork) { struct delayed_work *dwork = to_delayed_work(work); /* * dwork->timer is irqsafe. If del_timer() fails, it's * guaranteed that the timer is not queued anywhere and not * running on the local CPU. */ if (likely(del_timer(&dwork->timer))) return 1; } /* try to claim PENDING the normal way */ if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) return 0; rcu_read_lock(); /* * The queueing is in progress, or it is already queued. Try to * steal it from ->worklist without clearing WORK_STRUCT_PENDING. */ pool = get_work_pool(work); if (!pool) goto fail; raw_spin_lock(&pool->lock); /* * work->data is guaranteed to point to pwq only while the work * item is queued on pwq->wq, and both updating work->data to point * to pwq on queueing and to pool on dequeueing are done under * pwq->pool->lock. This in turn guarantees that, if work->data * points to pwq which is associated with a locked pool, the work * item is currently queued on that pool. */ pwq = get_work_pwq(work); if (pwq && pwq->pool == pool) { debug_work_deactivate(work); /* * A cancelable inactive work item must be in the * pwq->inactive_works since a queued barrier can't be * canceled (see the comments in insert_wq_barrier()). * * An inactive work item cannot be grabbed directly because * it might have linked barrier work items which, if left * on the inactive_works list, will confuse pwq->nr_active * management later on and cause stall. Make sure the work * item is activated before grabbing. */ if (*work_data_bits(work) & WORK_STRUCT_INACTIVE) pwq_activate_inactive_work(work); list_del_init(&work->entry); pwq_dec_nr_in_flight(pwq, *work_data_bits(work)); /* work->data points to pwq iff queued, point to pool */ set_work_pool_and_keep_pending(work, pool->id); raw_spin_unlock(&pool->lock); rcu_read_unlock(); return 1; } raw_spin_unlock(&pool->lock); fail: rcu_read_unlock(); local_irq_restore(*flags); if (work_is_canceling(work)) return -ENOENT; cpu_relax(); return -EAGAIN; } /** * insert_work - insert a work into a pool * @pwq: pwq @work belongs to * @work: work to insert * @head: insertion point * @extra_flags: extra WORK_STRUCT_* flags to set * * Insert @work which belongs to @pwq after @head. @extra_flags is or'd to * work_struct flags. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void insert_work(struct pool_workqueue *pwq, struct work_struct *work, struct list_head *head, unsigned int extra_flags) { struct worker_pool *pool = pwq->pool; /* record the work call stack in order to print it in KASAN reports */ kasan_record_aux_stack_noalloc(work); /* we own @work, set data and link */ set_work_pwq(work, pwq, extra_flags); list_add_tail(&work->entry, head); get_pwq(pwq); if (__need_more_worker(pool)) wake_up_worker(pool); } /* * Test whether @work is being queued from another work executing on the * same workqueue. */ static bool is_chained_work(struct workqueue_struct *wq) { struct worker *worker; worker = current_wq_worker(); /* * Return %true iff I'm a worker executing a work item on @wq. If * I'm @worker, it's safe to dereference it without locking. */ return worker && worker->current_pwq->wq == wq; } /* * When queueing an unbound work item to a wq, prefer local CPU if allowed * by wq_unbound_cpumask. Otherwise, round robin among the allowed ones to * avoid perturbing sensitive tasks. */ static int wq_select_unbound_cpu(int cpu) { static bool printed_dbg_warning; int new_cpu; if (likely(!wq_debug_force_rr_cpu)) { if (cpumask_test_cpu(cpu, wq_unbound_cpumask)) return cpu; } else if (!printed_dbg_warning) { pr_warn("workqueue: round-robin CPU selection forced, expect performance impact\n"); printed_dbg_warning = true; } if (cpumask_empty(wq_unbound_cpumask)) return cpu; new_cpu = __this_cpu_read(wq_rr_cpu_last); new_cpu = cpumask_next_and(new_cpu, wq_unbound_cpumask, cpu_online_mask); if (unlikely(new_cpu >= nr_cpu_ids)) { new_cpu = cpumask_first_and(wq_unbound_cpumask, cpu_online_mask); if (unlikely(new_cpu >= nr_cpu_ids)) return cpu; } __this_cpu_write(wq_rr_cpu_last, new_cpu); return new_cpu; } static void __queue_work(int cpu, struct workqueue_struct *wq, struct work_struct *work) { struct pool_workqueue *pwq; struct worker_pool *last_pool; struct list_head *worklist; unsigned int work_flags; unsigned int req_cpu = cpu; /* * While a work item is PENDING && off queue, a task trying to * steal the PENDING will busy-loop waiting for it to either get * queued or lose PENDING. Grabbing PENDING and queueing should * happen with IRQ disabled. */ lockdep_assert_irqs_disabled(); /* if draining, only works from the same workqueue are allowed */ if (unlikely(wq->flags & __WQ_DRAINING) && WARN_ON_ONCE(!is_chained_work(wq))) return; rcu_read_lock(); retry: /* pwq which will be used unless @work is executing elsewhere */ if (wq->flags & WQ_UNBOUND) { if (req_cpu == WORK_CPU_UNBOUND) cpu = wq_select_unbound_cpu(raw_smp_processor_id()); pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); } else { if (req_cpu == WORK_CPU_UNBOUND) cpu = raw_smp_processor_id(); pwq = per_cpu_ptr(wq->cpu_pwqs, cpu); } /* * If @work was previously on a different pool, it might still be * running there, in which case the work needs to be queued on that * pool to guarantee non-reentrancy. */ last_pool = get_work_pool(work); if (last_pool && last_pool != pwq->pool) { struct worker *worker; raw_spin_lock(&last_pool->lock); worker = find_worker_executing_work(last_pool, work); if (worker && worker->current_pwq->wq == wq) { pwq = worker->current_pwq; } else { /* meh... not running there, queue here */ raw_spin_unlock(&last_pool->lock); raw_spin_lock(&pwq->pool->lock); } } else { raw_spin_lock(&pwq->pool->lock); } /* * pwq is determined and locked. For unbound pools, we could have * raced with pwq release and it could already be dead. If its * refcnt is zero, repeat pwq selection. Note that pwqs never die * without another pwq replacing it in the numa_pwq_tbl or while * work items are executing on it, so the retrying is guaranteed to * make forward-progress. */ if (unlikely(!pwq->refcnt)) { if (wq->flags & WQ_UNBOUND) { raw_spin_unlock(&pwq->pool->lock); cpu_relax(); goto retry; } /* oops */ WARN_ONCE(true, "workqueue: per-cpu pwq for %s on cpu%d has 0 refcnt", wq->name, cpu); } /* pwq determined, queue */ trace_workqueue_queue_work(req_cpu, pwq, work); if (WARN_ON(!list_empty(&work->entry))) goto out; pwq->nr_in_flight[pwq->work_color]++; work_flags = work_color_to_flags(pwq->work_color); if (likely(pwq->nr_active < pwq->max_active)) { trace_workqueue_activate_work(work); pwq->nr_active++; worklist = &pwq->pool->worklist; if (list_empty(worklist)) pwq->pool->watchdog_ts = jiffies; } else { work_flags |= WORK_STRUCT_INACTIVE; worklist = &pwq->inactive_works; } debug_work_activate(work); insert_work(pwq, work, worklist, work_flags); out: raw_spin_unlock(&pwq->pool->lock); rcu_read_unlock(); } /** * queue_work_on - queue work on specific cpu * @cpu: CPU number to execute work on * @wq: workqueue to use * @work: work to queue * * We queue the work to a specific CPU, the caller must ensure it * can't go away. Callers that fail to ensure that the specified * CPU cannot go away will execute on a randomly chosen CPU. * * Return: %false if @work was already on a queue, %true otherwise. */ bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work) { bool ret = false; unsigned long flags; local_irq_save(flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { __queue_work(cpu, wq, work); ret = true; } local_irq_restore(flags); return ret; } EXPORT_SYMBOL(queue_work_on); /** * workqueue_select_cpu_near - Select a CPU based on NUMA node * @node: NUMA node ID that we want to select a CPU from * * This function will attempt to find a "random" cpu available on a given * node. If there are no CPUs available on the given node it will return * WORK_CPU_UNBOUND indicating that we should just schedule to any * available CPU if we need to schedule this work. */ static int workqueue_select_cpu_near(int node) { int cpu; /* No point in doing this if NUMA isn't enabled for workqueues */ if (!wq_numa_enabled) return WORK_CPU_UNBOUND; /* Delay binding to CPU if node is not valid or online */ if (node < 0 || node >= MAX_NUMNODES || !node_online(node)) return WORK_CPU_UNBOUND; /* Use local node/cpu if we are already there */ cpu = raw_smp_processor_id(); if (node == cpu_to_node(cpu)) return cpu; /* Use "random" otherwise know as "first" online CPU of node */ cpu = cpumask_any_and(cpumask_of_node(node), cpu_online_mask); /* If CPU is valid return that, otherwise just defer */ return cpu < nr_cpu_ids ? cpu : WORK_CPU_UNBOUND; } /** * queue_work_node - queue work on a "random" cpu for a given NUMA node * @node: NUMA node that we are targeting the work for * @wq: workqueue to use * @work: work to queue * * We queue the work to a "random" CPU within a given NUMA node. The basic * idea here is to provide a way to somehow associate work with a given * NUMA node. * * This function will only make a best effort attempt at getting this onto * the right NUMA node. If no node is requested or the requested node is * offline then we just fall back to standard queue_work behavior. * * Currently the "random" CPU ends up being the first available CPU in the * intersection of cpu_online_mask and the cpumask of the node, unless we * are running on the node. In that case we just use the current CPU. * * Return: %false if @work was already on a queue, %true otherwise. */ bool queue_work_node(int node, struct workqueue_struct *wq, struct work_struct *work) { unsigned long flags; bool ret = false; /* * This current implementation is specific to unbound workqueues. * Specifically we only return the first available CPU for a given * node instead of cycling through individual CPUs within the node. * * If this is used with a per-cpu workqueue then the logic in * workqueue_select_cpu_near would need to be updated to allow for * some round robin type logic. */ WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)); local_irq_save(flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { int cpu = workqueue_select_cpu_near(node); __queue_work(cpu, wq, work); ret = true; } local_irq_restore(flags); return ret; } EXPORT_SYMBOL_GPL(queue_work_node); void delayed_work_timer_fn(struct timer_list *t) { struct delayed_work *dwork = from_timer(dwork, t, timer); /* should have been called from irqsafe timer with irq already off */ __queue_work(dwork->cpu, dwork->wq, &dwork->work); } EXPORT_SYMBOL(delayed_work_timer_fn); static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { struct timer_list *timer = &dwork->timer; struct work_struct *work = &dwork->work; WARN_ON_ONCE(!wq); WARN_ON_ONCE(timer->function != delayed_work_timer_fn); WARN_ON_ONCE(timer_pending(timer)); WARN_ON_ONCE(!list_empty(&work->entry)); /* * If @delay is 0, queue @dwork->work immediately. This is for * both optimization and correctness. The earliest @timer can * expire is on the closest next tick and delayed_work users depend * on that there's no such delay when @delay is 0. */ if (!delay) { __queue_work(cpu, wq, &dwork->work); return; } dwork->wq = wq; dwork->cpu = cpu; timer->expires = jiffies + delay; if (unlikely(cpu != WORK_CPU_UNBOUND)) add_timer_on(timer, cpu); else add_timer(timer); } /** * queue_delayed_work_on - queue work on specific CPU after delay * @cpu: CPU number to execute work on * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * Return: %false if @work was already on a queue, %true otherwise. If * @delay is zero and @dwork is idle, it will be scheduled for immediate * execution. */ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { struct work_struct *work = &dwork->work; bool ret = false; unsigned long flags; /* read the comment in __queue_work() */ local_irq_save(flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { __queue_delayed_work(cpu, wq, dwork, delay); ret = true; } local_irq_restore(flags); return ret; } EXPORT_SYMBOL(queue_delayed_work_on); /** * mod_delayed_work_on - modify delay of or queue a delayed work on specific CPU * @cpu: CPU number to execute work on * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * If @dwork is idle, equivalent to queue_delayed_work_on(); otherwise, * modify @dwork's timer so that it expires after @delay. If @delay is * zero, @work is guaranteed to be scheduled immediately regardless of its * current state. * * Return: %false if @dwork was idle and queued, %true if @dwork was * pending and its timer was modified. * * This function is safe to call from any context including IRQ handler. * See try_to_grab_pending() for details. */ bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { unsigned long flags; int ret; do { ret = try_to_grab_pending(&dwork->work, true, &flags); } while (unlikely(ret == -EAGAIN)); if (likely(ret >= 0)) { __queue_delayed_work(cpu, wq, dwork, delay); local_irq_restore(flags); } /* -ENOENT from try_to_grab_pending() becomes %true */ return ret; } EXPORT_SYMBOL_GPL(mod_delayed_work_on); static void rcu_work_rcufn(struct rcu_head *rcu) { struct rcu_work *rwork = container_of(rcu, struct rcu_work, rcu); /* read the comment in __queue_work() */ local_irq_disable(); __queue_work(WORK_CPU_UNBOUND, rwork->wq, &rwork->work); local_irq_enable(); } /** * queue_rcu_work - queue work after a RCU grace period * @wq: workqueue to use * @rwork: work to queue * * Return: %false if @rwork was already pending, %true otherwise. Note * that a full RCU grace period is guaranteed only after a %true return. * While @rwork is guaranteed to be executed after a %false return, the * execution may happen before a full RCU grace period has passed. */ bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork) { struct work_struct *work = &rwork->work; if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { rwork->wq = wq; call_rcu_hurry(&rwork->rcu, rcu_work_rcufn); return true; } return false; } EXPORT_SYMBOL(queue_rcu_work); /** * worker_enter_idle - enter idle state * @worker: worker which is entering idle state * * @worker is entering idle state. Update stats and idle timer if * necessary. * * LOCKING: * raw_spin_lock_irq(pool->lock). */ static void worker_enter_idle(struct worker *worker) { struct worker_pool *pool = worker->pool; if (WARN_ON_ONCE(worker->flags & WORKER_IDLE) || WARN_ON_ONCE(!list_empty(&worker->entry) && (worker->hentry.next || worker->hentry.pprev))) return; /* can't use worker_set_flags(), also called from create_worker() */ worker->flags |= WORKER_IDLE; pool->nr_idle++; worker->last_active = jiffies; /* idle_list is LIFO */ list_add(&worker->entry, &pool->idle_list); if (too_many_workers(pool) && !timer_pending(&pool->idle_timer)) mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); /* Sanity check nr_running. */ WARN_ON_ONCE(pool->nr_workers == pool->nr_idle && pool->nr_running); } /** * worker_leave_idle - leave idle state * @worker: worker which is leaving idle state * * @worker is leaving idle state. Update stats. * * LOCKING: * raw_spin_lock_irq(pool->lock). */ static void worker_leave_idle(struct worker *worker) { struct worker_pool *pool = worker->pool; if (WARN_ON_ONCE(!(worker->flags & WORKER_IDLE))) return; worker_clr_flags(worker, WORKER_IDLE); pool->nr_idle--; list_del_init(&worker->entry); } static struct worker *alloc_worker(int node) { struct worker *worker; worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, node); if (worker) { INIT_LIST_HEAD(&worker->entry); INIT_LIST_HEAD(&worker->scheduled); INIT_LIST_HEAD(&worker->node); /* on creation a worker is in !idle && prep state */ worker->flags = WORKER_PREP; } return worker; } /** * worker_attach_to_pool() - attach a worker to a pool * @worker: worker to be attached * @pool: the target pool * * Attach @worker to @pool. Once attached, the %WORKER_UNBOUND flag and * cpu-binding of @worker are kept coordinated with the pool across * cpu-[un]hotplugs. */ static void worker_attach_to_pool(struct worker *worker, struct worker_pool *pool) { mutex_lock(&wq_pool_attach_mutex); /* * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains * stable across this function. See the comments above the flag * definition for details. */ if (pool->flags & POOL_DISASSOCIATED) worker->flags |= WORKER_UNBOUND; else kthread_set_per_cpu(worker->task, pool->cpu); if (worker->rescue_wq) set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask); list_add_tail(&worker->node, &pool->workers); worker->pool = pool; mutex_unlock(&wq_pool_attach_mutex); } /** * worker_detach_from_pool() - detach a worker from its pool * @worker: worker which is attached to its pool * * Undo the attaching which had been done in worker_attach_to_pool(). The * caller worker shouldn't access to the pool after detached except it has * other reference to the pool. */ static void worker_detach_from_pool(struct worker *worker) { struct worker_pool *pool = worker->pool; struct completion *detach_completion = NULL; mutex_lock(&wq_pool_attach_mutex); kthread_set_per_cpu(worker->task, -1); list_del(&worker->node); worker->pool = NULL; if (list_empty(&pool->workers)) detach_completion = pool->detach_completion; mutex_unlock(&wq_pool_attach_mutex); /* clear leftover flags without pool->lock after it is detached */ worker->flags &= ~(WORKER_UNBOUND | WORKER_REBOUND); if (detach_completion) complete(detach_completion); } /** * create_worker - create a new workqueue worker * @pool: pool the new worker will belong to * * Create and start a new worker which is attached to @pool. * * CONTEXT: * Might sleep. Does GFP_KERNEL allocations. * * Return: * Pointer to the newly created worker. */ static struct worker *create_worker(struct worker_pool *pool) { struct worker *worker; int id; char id_buf[16]; /* ID is needed to determine kthread name */ id = ida_alloc(&pool->worker_ida, GFP_KERNEL); if (id < 0) return NULL; worker = alloc_worker(pool->node); if (!worker) goto fail; worker->id = id; if (pool->cpu >= 0) snprintf(id_buf, sizeof(id_buf), "%d:%d%s", pool->cpu, id, pool->attrs->nice < 0 ? "H" : ""); else snprintf(id_buf, sizeof(id_buf), "u%d:%d", pool->id, id); worker->task = kthread_create_on_node(worker_thread, worker, pool->node, "kworker/%s", id_buf); if (IS_ERR(worker->task)) goto fail; set_user_nice(worker->task, pool->attrs->nice); kthread_bind_mask(worker->task, pool->attrs->cpumask); /* successful, attach the worker to the pool */ worker_attach_to_pool(worker, pool); /* start the newly created worker */ raw_spin_lock_irq(&pool->lock); worker->pool->nr_workers++; worker_enter_idle(worker); wake_up_process(worker->task); raw_spin_unlock_irq(&pool->lock); return worker; fail: ida_free(&pool->worker_ida, id); kfree(worker); return NULL; } /** * destroy_worker - destroy a workqueue worker * @worker: worker to be destroyed * * Destroy @worker and adjust @pool stats accordingly. The worker should * be idle. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void destroy_worker(struct worker *worker) { struct worker_pool *pool = worker->pool; lockdep_assert_held(&pool->lock); /* sanity check frenzy */ if (WARN_ON(worker->current_work) || WARN_ON(!list_empty(&worker->scheduled)) || WARN_ON(!(worker->flags & WORKER_IDLE))) return; pool->nr_workers--; pool->nr_idle--; list_del_init(&worker->entry); worker->flags |= WORKER_DIE; wake_up_process(worker->task); } static void idle_worker_timeout(struct timer_list *t) { struct worker_pool *pool = from_timer(pool, t, idle_timer); raw_spin_lock_irq(&pool->lock); while (too_many_workers(pool)) { struct worker *worker; unsigned long expires; /* idle_list is kept in LIFO order, check the last one */ worker = list_entry(pool->idle_list.prev, struct worker, entry); expires = worker->last_active + IDLE_WORKER_TIMEOUT; if (time_before(jiffies, expires)) { mod_timer(&pool->idle_timer, expires); break; } destroy_worker(worker); } raw_spin_unlock_irq(&pool->lock); } static void send_mayday(struct work_struct *work) { struct pool_workqueue *pwq = get_work_pwq(work); struct workqueue_struct *wq = pwq->wq; lockdep_assert_held(&wq_mayday_lock); if (!wq->rescuer) return; /* mayday mayday mayday */ if (list_empty(&pwq->mayday_node)) { /* * If @pwq is for an unbound wq, its base ref may be put at * any time due to an attribute change. Pin @pwq until the * rescuer is done with it. */ get_pwq(pwq); list_add_tail(&pwq->mayday_node, &wq->maydays); wake_up_process(wq->rescuer->task); } } static void pool_mayday_timeout(struct timer_list *t) { struct worker_pool *pool = from_timer(pool, t, mayday_timer); struct work_struct *work; raw_spin_lock_irq(&pool->lock); raw_spin_lock(&wq_mayday_lock); /* for wq->maydays */ if (need_to_create_worker(pool)) { /* * We've been trying to create a new worker but * haven't been successful. We might be hitting an * allocation deadlock. Send distress signals to * rescuers. */ list_for_each_entry(work, &pool->worklist, entry) send_mayday(work); } raw_spin_unlock(&wq_mayday_lock); raw_spin_unlock_irq(&pool->lock); mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INTERVAL); } /** * maybe_create_worker - create a new worker if necessary * @pool: pool to create a new worker for * * Create a new worker for @pool if necessary. @pool is guaranteed to * have at least one idle worker on return from this function. If * creating a new worker takes longer than MAYDAY_INTERVAL, mayday is * sent to all rescuers with works scheduled on @pool to resolve * possible allocation deadlock. * * On return, need_to_create_worker() is guaranteed to be %false and * may_start_working() %true. * * LOCKING: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. Called only from * manager. */ static void maybe_create_worker(struct worker_pool *pool) __releases(&pool->lock) __acquires(&pool->lock) { restart: raw_spin_unlock_irq(&pool->lock); /* if we don't make progress in MAYDAY_INITIAL_TIMEOUT, call for help */ mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INITIAL_TIMEOUT); while (true) { if (create_worker(pool) || !need_to_create_worker(pool)) break; schedule_timeout_interruptible(CREATE_COOLDOWN); if (!need_to_create_worker(pool)) break; } del_timer_sync(&pool->mayday_timer); raw_spin_lock_irq(&pool->lock); /* * This is necessary even after a new worker was just successfully * created as @pool->lock was dropped and the new worker might have * already become busy. */ if (need_to_create_worker(pool)) goto restart; } /** * manage_workers - manage worker pool * @worker: self * * Assume the manager role and manage the worker pool @worker belongs * to. At any given time, there can be only zero or one manager per * pool. The exclusion is handled automatically by this function. * * The caller can safely start processing works on false return. On * true return, it's guaranteed that need_to_create_worker() is false * and may_start_working() is true. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. * * Return: * %false if the pool doesn't need management and the caller can safely * start processing works, %true if management function was performed and * the conditions that the caller verified before calling the function may * no longer be true. */ static bool manage_workers(struct worker *worker) { struct worker_pool *pool = worker->pool; if (pool->flags & POOL_MANAGER_ACTIVE) return false; pool->flags |= POOL_MANAGER_ACTIVE; pool->manager = worker; maybe_create_worker(pool); pool->manager = NULL; pool->flags &= ~POOL_MANAGER_ACTIVE; rcuwait_wake_up(&manager_wait); return true; } /** * process_one_work - process single work * @worker: self * @work: work to process * * Process @work. This function contains all the logics necessary to * process a single work including synchronization against and * interaction with other workers on the same cpu, queueing and * flushing. As long as context requirement is met, any worker can * call this function to process a work. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which is released and regrabbed. */ static void process_one_work(struct worker *worker, struct work_struct *work) __releases(&pool->lock) __acquires(&pool->lock) { struct pool_workqueue *pwq = get_work_pwq(work); struct worker_pool *pool = worker->pool; bool cpu_intensive = pwq->wq->flags & WQ_CPU_INTENSIVE; unsigned long work_data; struct worker *collision; #ifdef CONFIG_LOCKDEP /* * It is permissible to free the struct work_struct from * inside the function that is called from it, this we need to * take into account for lockdep too. To avoid bogus "held * lock freed" warnings as well as problems when looking into * work->lockdep_map, make a copy and use that here. */ struct lockdep_map lockdep_map; lockdep_copy_map(&lockdep_map, &work->lockdep_map); #endif /* ensure we're on the correct CPU */ WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) && raw_smp_processor_id() != pool->cpu); /* * A single work shouldn't be executed concurrently by * multiple workers on a single cpu. Check whether anyone is * already processing the work. If so, defer the work to the * currently executing one. */ collision = find_worker_executing_work(pool, work); if (unlikely(collision)) { move_linked_works(work, &collision->scheduled, NULL); return; } /* claim and dequeue */ debug_work_deactivate(work); hash_add(pool->busy_hash, &worker->hentry, (unsigned long)work); worker->current_work = work; worker->current_func = work->func; worker->current_pwq = pwq; work_data = *work_data_bits(work); worker->current_color = get_work_color(work_data); /* * Record wq name for cmdline and debug reporting, may get * overridden through set_worker_desc(). */ strscpy(worker->desc, pwq->wq->name, WORKER_DESC_LEN); list_del_init(&work->entry); /* * CPU intensive works don't participate in concurrency management. * They're the scheduler's responsibility. This takes @worker out * of concurrency management and the next code block will chain * execution of the pending work items. */ if (unlikely(cpu_intensive)) worker_set_flags(worker, WORKER_CPU_INTENSIVE); /* * Wake up another worker if necessary. The condition is always * false for normal per-cpu workers since nr_running would always * be >= 1 at this point. This is used to chain execution of the * pending work items for WORKER_NOT_RUNNING workers such as the * UNBOUND and CPU_INTENSIVE ones. */ if (need_more_worker(pool)) wake_up_worker(pool); /* * Record the last pool and clear PENDING which should be the last * update to @work. Also, do this inside @pool->lock so that * PENDING and queued state changes happen together while IRQ is * disabled. */ set_work_pool_and_clear_pending(work, pool->id); raw_spin_unlock_irq(&pool->lock); lock_map_acquire(&pwq->wq->lockdep_map); lock_map_acquire(&lockdep_map); /* * Strictly speaking we should mark the invariant state without holding * any locks, that is, before these two lock_map_acquire()'s. * * However, that would result in: * * A(W1) * WFC(C) * A(W1) * C(C) * * Which would create W1->C->W1 dependencies, even though there is no * actual deadlock possible. There are two solutions, using a * read-recursive acquire on the work(queue) 'locks', but this will then * hit the lockdep limitation on recursive locks, or simply discard * these locks. * * AFAICT there is no possible deadlock scenario between the * flush_work() and complete() primitives (except for single-threaded * workqueues), so hiding them isn't a problem. */ lockdep_invariant_state(true); trace_workqueue_execute_start(work); worker->current_func(work); /* * While we must be careful to not use "work" after this, the trace * point will only record its address. */ trace_workqueue_execute_end(work, worker->current_func); lock_map_release(&lockdep_map); lock_map_release(&pwq->wq->lockdep_map); if (unlikely(in_atomic() || lockdep_depth(current) > 0)) { pr_err("BUG: workqueue leaked lock or atomic: %s/0x%08x/%d\n" " last function: %ps\n", current->comm, preempt_count(), task_pid_nr(current), worker->current_func); debug_show_held_locks(current); dump_stack(); } /* * The following prevents a kworker from hogging CPU on !PREEMPTION * kernels, where a requeueing work item waiting for something to * happen could deadlock with stop_machine as such work item could * indefinitely requeue itself while all other CPUs are trapped in * stop_machine. At the same time, report a quiescent RCU state so * the same condition doesn't freeze RCU. */ cond_resched(); raw_spin_lock_irq(&pool->lock); /* clear cpu intensive status */ if (unlikely(cpu_intensive)) worker_clr_flags(worker, WORKER_CPU_INTENSIVE); /* tag the worker for identification in schedule() */ worker->last_func = worker->current_func; /* we're done with it, release */ hash_del(&worker->hentry); worker->current_work = NULL; worker->current_func = NULL; worker->current_pwq = NULL; worker->current_color = INT_MAX; pwq_dec_nr_in_flight(pwq, work_data); } /** * process_scheduled_works - process scheduled works * @worker: self * * Process all scheduled works. Please note that the scheduled list * may change while processing a work, so this function repeatedly * fetches a work from the top and executes it. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. */ static void process_scheduled_works(struct worker *worker) { while (!list_empty(&worker->scheduled)) { struct work_struct *work = list_first_entry(&worker->scheduled, struct work_struct, entry); process_one_work(worker, work); } } static void set_pf_worker(bool val) { mutex_lock(&wq_pool_attach_mutex); if (val) current->flags |= PF_WQ_WORKER; else current->flags &= ~PF_WQ_WORKER; mutex_unlock(&wq_pool_attach_mutex); } /** * worker_thread - the worker thread function * @__worker: self * * The worker thread function. All workers belong to a worker_pool - * either a per-cpu one or dynamic unbound one. These workers process all * work items regardless of their specific target workqueue. The only * exception is work items which belong to workqueues with a rescuer which * will be explained in rescuer_thread(). * * Return: 0 */ static int worker_thread(void *__worker) { struct worker *worker = __worker; struct worker_pool *pool = worker->pool; /* tell the scheduler that this is a workqueue worker */ set_pf_worker(true); woke_up: raw_spin_lock_irq(&pool->lock); /* am I supposed to die? */ if (unlikely(worker->flags & WORKER_DIE)) { raw_spin_unlock_irq(&pool->lock); WARN_ON_ONCE(!list_empty(&worker->entry)); set_pf_worker(false); set_task_comm(worker->task, "kworker/dying"); ida_free(&pool->worker_ida, worker->id); worker_detach_from_pool(worker); kfree(worker); return 0; } worker_leave_idle(worker); recheck: /* no more worker necessary? */ if (!need_more_worker(pool)) goto sleep; /* do we need to manage? */ if (unlikely(!may_start_working(pool)) && manage_workers(worker)) goto recheck; /* * ->scheduled list can only be filled while a worker is * preparing to process a work or actually processing it. * Make sure nobody diddled with it while I was sleeping. */ WARN_ON_ONCE(!list_empty(&worker->scheduled)); /* * Finish PREP stage. We're guaranteed to have at least one idle * worker or that someone else has already assumed the manager * role. This is where @worker starts participating in concurrency * management if applicable and concurrency management is restored * after being rebound. See rebind_workers() for details. */ worker_clr_flags(worker, WORKER_PREP | WORKER_REBOUND); do { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); pool->watchdog_ts = jiffies; if (likely(!(*work_data_bits(work) & WORK_STRUCT_LINKED))) { /* optimization path, not strictly necessary */ process_one_work(worker, work); if (unlikely(!list_empty(&worker->scheduled))) process_scheduled_works(worker); } else { move_linked_works(work, &worker->scheduled, NULL); process_scheduled_works(worker); } } while (keep_working(pool)); worker_set_flags(worker, WORKER_PREP); sleep: /* * pool->lock is held and there's no work to process and no need to * manage, sleep. Workers are woken up only while holding * pool->lock or from local cpu, so setting the current state * before releasing pool->lock is enough to prevent losing any * event. */ worker_enter_idle(worker); __set_current_state(TASK_IDLE); raw_spin_unlock_irq(&pool->lock); schedule(); goto woke_up; } /** * rescuer_thread - the rescuer thread function * @__rescuer: self * * Workqueue rescuer thread function. There's one rescuer for each * workqueue which has WQ_MEM_RECLAIM set. * * Regular work processing on a pool may block trying to create a new * worker which uses GFP_KERNEL allocation which has slight chance of * developing into deadlock if some works currently on the same queue * need to be processed to satisfy the GFP_KERNEL allocation. This is * the problem rescuer solves. * * When such condition is possible, the pool summons rescuers of all * workqueues which have works queued on the pool and let them process * those works so that forward progress can be guaranteed. * * This should happen rarely. * * Return: 0 */ static int rescuer_thread(void *__rescuer) { struct worker *rescuer = __rescuer; struct workqueue_struct *wq = rescuer->rescue_wq; struct list_head *scheduled = &rescuer->scheduled; bool should_stop; set_user_nice(current, RESCUER_NICE_LEVEL); /* * Mark rescuer as worker too. As WORKER_PREP is never cleared, it * doesn't participate in concurrency management. */ set_pf_worker(true); repeat: set_current_state(TASK_IDLE); /* * By the time the rescuer is requested to stop, the workqueue * shouldn't have any work pending, but @wq->maydays may still have * pwq(s) queued. This can happen by non-rescuer workers consuming * all the work items before the rescuer got to them. Go through * @wq->maydays processing before acting on should_stop so that the * list is always empty on exit. */ should_stop = kthread_should_stop(); /* see whether any pwq is asking for help */ raw_spin_lock_irq(&wq_mayday_lock); while (!list_empty(&wq->maydays)) { struct pool_workqueue *pwq = list_first_entry(&wq->maydays, struct pool_workqueue, mayday_node); struct worker_pool *pool = pwq->pool; struct work_struct *work, *n; bool first = true; __set_current_state(TASK_RUNNING); list_del_init(&pwq->mayday_node); raw_spin_unlock_irq(&wq_mayday_lock); worker_attach_to_pool(rescuer, pool); raw_spin_lock_irq(&pool->lock); /* * Slurp in all works issued via this workqueue and * process'em. */ WARN_ON_ONCE(!list_empty(scheduled)); list_for_each_entry_safe(work, n, &pool->worklist, entry) { if (get_work_pwq(work) == pwq) { if (first) pool->watchdog_ts = jiffies; move_linked_works(work, scheduled, &n); } first = false; } if (!list_empty(scheduled)) { process_scheduled_works(rescuer); /* * The above execution of rescued work items could * have created more to rescue through * pwq_activate_first_inactive() or chained * queueing. Let's put @pwq back on mayday list so * that such back-to-back work items, which may be * being used to relieve memory pressure, don't * incur MAYDAY_INTERVAL delay inbetween. */ if (pwq->nr_active && need_to_create_worker(pool)) { raw_spin_lock(&wq_mayday_lock); /* * Queue iff we aren't racing destruction * and somebody else hasn't queued it already. */ if (wq->rescuer && list_empty(&pwq->mayday_node)) { get_pwq(pwq); list_add_tail(&pwq->mayday_node, &wq->maydays); } raw_spin_unlock(&wq_mayday_lock); } } /* * Put the reference grabbed by send_mayday(). @pool won't * go away while we're still attached to it. */ put_pwq(pwq); /* * Leave this pool. If need_more_worker() is %true, notify a * regular worker; otherwise, we end up with 0 concurrency * and stalling the execution. */ if (need_more_worker(pool)) wake_up_worker(pool); raw_spin_unlock_irq(&pool->lock); worker_detach_from_pool(rescuer); raw_spin_lock_irq(&wq_mayday_lock); } raw_spin_unlock_irq(&wq_mayday_lock); if (should_stop) { __set_current_state(TASK_RUNNING); set_pf_worker(false); return 0; } /* rescuers should never participate in concurrency management */ WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING)); schedule(); goto repeat; } /** * check_flush_dependency - check for flush dependency sanity * @target_wq: workqueue being flushed * @target_work: work item being flushed (NULL for workqueue flushes) * * %current is trying to flush the whole @target_wq or @target_work on it. * If @target_wq doesn't have %WQ_MEM_RECLAIM, verify that %current is not * reclaiming memory or running on a workqueue which doesn't have * %WQ_MEM_RECLAIM as that can break forward-progress guarantee leading to * a deadlock. */ static void check_flush_dependency(struct workqueue_struct *target_wq, struct work_struct *target_work) { work_func_t target_func = target_work ? target_work->func : NULL; struct worker *worker; if (target_wq->flags & WQ_MEM_RECLAIM) return; worker = current_wq_worker(); WARN_ONCE(current->flags & PF_MEMALLOC, "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%ps", current->pid, current->comm, target_wq->name, target_func); WARN_ONCE(worker && ((worker->current_pwq->wq->flags & (WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM), "workqueue: WQ_MEM_RECLAIM %s:%ps is flushing !WQ_MEM_RECLAIM %s:%ps", worker->current_pwq->wq->name, worker->current_func, target_wq->name, target_func); } struct wq_barrier { struct work_struct work; struct completion done; struct task_struct *task; /* purely informational */ }; static void wq_barrier_func(struct work_struct *work) { struct wq_barrier *barr = container_of(work, struct wq_barrier, work); complete(&barr->done); } /** * insert_wq_barrier - insert a barrier work * @pwq: pwq to insert barrier into * @barr: wq_barrier to insert * @target: target work to attach @barr to * @worker: worker currently executing @target, NULL if @target is not executing * * @barr is linked to @target such that @barr is completed only after * @target finishes execution. Please note that the ordering * guarantee is observed only with respect to @target and on the local * cpu. * * Currently, a queued barrier can't be canceled. This is because * try_to_grab_pending() can't determine whether the work to be * grabbed is at the head of the queue and thus can't clear LINKED * flag of the previous work while there must be a valid next work * after a work with LINKED flag set. * * Note that when @worker is non-NULL, @target may be modified * underneath us, so we can't reliably determine pwq from @target. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void insert_wq_barrier(struct pool_workqueue *pwq, struct wq_barrier *barr, struct work_struct *target, struct worker *worker) { unsigned int work_flags = 0; unsigned int work_color; struct list_head *head; /* * debugobject calls are safe here even with pool->lock locked * as we know for sure that this will not trigger any of the * checks and call back into the fixup functions where we * might deadlock. */ INIT_WORK_ONSTACK(&barr->work, wq_barrier_func); __set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work)); init_completion_map(&barr->done, &target->lockdep_map); barr->task = current; /* The barrier work item does not participate in pwq->nr_active. */ work_flags |= WORK_STRUCT_INACTIVE; /* * If @target is currently being executed, schedule the * barrier to the worker; otherwise, put it after @target. */ if (worker) { head = worker->scheduled.next; work_color = worker->current_color; } else { unsigned long *bits = work_data_bits(target); head = target->entry.next; /* there can already be other linked works, inherit and set */ work_flags |= *bits & WORK_STRUCT_LINKED; work_color = get_work_color(*bits); __set_bit(WORK_STRUCT_LINKED_BIT, bits); } pwq->nr_in_flight[work_color]++; work_flags |= work_color_to_flags(work_color); debug_work_activate(&barr->work); insert_work(pwq, &barr->work, head, work_flags); } /** * flush_workqueue_prep_pwqs - prepare pwqs for workqueue flushing * @wq: workqueue being flushed * @flush_color: new flush color, < 0 for no-op * @work_color: new work color, < 0 for no-op * * Prepare pwqs for workqueue flushing. * * If @flush_color is non-negative, flush_color on all pwqs should be * -1. If no pwq has in-flight commands at the specified color, all * pwq->flush_color's stay at -1 and %false is returned. If any pwq * has in flight commands, its pwq->flush_color is set to * @flush_color, @wq->nr_pwqs_to_flush is updated accordingly, pwq * wakeup logic is armed and %true is returned. * * The caller should have initialized @wq->first_flusher prior to * calling this function with non-negative @flush_color. If * @flush_color is negative, no flush color update is done and %false * is returned. * * If @work_color is non-negative, all pwqs should have the same * work_color which is previous to @work_color and all will be * advanced to @work_color. * * CONTEXT: * mutex_lock(wq->mutex). * * Return: * %true if @flush_color >= 0 and there's something to flush. %false * otherwise. */ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq, int flush_color, int work_color) { bool wait = false; struct pool_workqueue *pwq; if (flush_color >= 0) { WARN_ON_ONCE(atomic_read(&wq->nr_pwqs_to_flush)); atomic_set(&wq->nr_pwqs_to_flush, 1); } for_each_pwq(pwq, wq) { struct worker_pool *pool = pwq->pool; raw_spin_lock_irq(&pool->lock); if (flush_color >= 0) { WARN_ON_ONCE(pwq->flush_color != -1); if (pwq->nr_in_flight[flush_color]) { pwq->flush_color = flush_color; atomic_inc(&wq->nr_pwqs_to_flush); wait = true; } } if (work_color >= 0) { WARN_ON_ONCE(work_color != work_next_color(pwq->work_color)); pwq->work_color = work_color; } raw_spin_unlock_irq(&pool->lock); } if (flush_color >= 0 && atomic_dec_and_test(&wq->nr_pwqs_to_flush)) complete(&wq->first_flusher->done); return wait; } /** * __flush_workqueue - ensure that any scheduled work has run to completion. * @wq: workqueue to flush * * This function sleeps until all work items which were queued on entry * have finished execution, but it is not livelocked by new incoming ones. */ void __flush_workqueue(struct workqueue_struct *wq) { struct wq_flusher this_flusher = { .list = LIST_HEAD_INIT(this_flusher.list), .flush_color = -1, .done = COMPLETION_INITIALIZER_ONSTACK_MAP(this_flusher.done, wq->lockdep_map), }; int next_color; if (WARN_ON(!wq_online)) return; lock_map_acquire(&wq->lockdep_map); lock_map_release(&wq->lockdep_map); mutex_lock(&wq->mutex); /* * Start-to-wait phase */ next_color = work_next_color(wq->work_color); if (next_color != wq->flush_color) { /* * Color space is not full. The current work_color * becomes our flush_color and work_color is advanced * by one. */ WARN_ON_ONCE(!list_empty(&wq->flusher_overflow)); this_flusher.flush_color = wq->work_color; wq->work_color = next_color; if (!wq->first_flusher) { /* no flush in progress, become the first flusher */ WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); wq->first_flusher = &this_flusher; if (!flush_workqueue_prep_pwqs(wq, wq->flush_color, wq->work_color)) { /* nothing to flush, done */ wq->flush_color = next_color; wq->first_flusher = NULL; goto out_unlock; } } else { /* wait in queue */ WARN_ON_ONCE(wq->flush_color == this_flusher.flush_color); list_add_tail(&this_flusher.list, &wq->flusher_queue); flush_workqueue_prep_pwqs(wq, -1, wq->work_color); } } else { /* * Oops, color space is full, wait on overflow queue. * The next flush completion will assign us * flush_color and transfer to flusher_queue. */ list_add_tail(&this_flusher.list, &wq->flusher_overflow); } check_flush_dependency(wq, NULL); mutex_unlock(&wq->mutex); wait_for_completion(&this_flusher.done); /* * Wake-up-and-cascade phase * * First flushers are responsible for cascading flushes and * handling overflow. Non-first flushers can simply return. */ if (READ_ONCE(wq->first_flusher) != &this_flusher) return; mutex_lock(&wq->mutex); /* we might have raced, check again with mutex held */ if (wq->first_flusher != &this_flusher) goto out_unlock; WRITE_ONCE(wq->first_flusher, NULL); WARN_ON_ONCE(!list_empty(&this_flusher.list)); WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); while (true) { struct wq_flusher *next, *tmp; /* complete all the flushers sharing the current flush color */ list_for_each_entry_safe(next, tmp, &wq->flusher_queue, list) { if (next->flush_color != wq->flush_color) break; list_del_init(&next->list); complete(&next->done); } WARN_ON_ONCE(!list_empty(&wq->flusher_overflow) && wq->flush_color != work_next_color(wq->work_color)); /* this flush_color is finished, advance by one */ wq->flush_color = work_next_color(wq->flush_color); /* one color has been freed, handle overflow queue */ if (!list_empty(&wq->flusher_overflow)) { /* * Assign the same color to all overflowed * flushers, advance work_color and append to * flusher_queue. This is the start-to-wait * phase for these overflowed flushers. */ list_for_each_entry(tmp, &wq->flusher_overflow, list) tmp->flush_color = wq->work_color; wq->work_color = work_next_color(wq->work_color); list_splice_tail_init(&wq->flusher_overflow, &wq->flusher_queue); flush_workqueue_prep_pwqs(wq, -1, wq->work_color); } if (list_empty(&wq->flusher_queue)) { WARN_ON_ONCE(wq->flush_color != wq->work_color); break; } /* * Need to flush more colors. Make the next flusher * the new first flusher and arm pwqs. */ WARN_ON_ONCE(wq->flush_color == wq->work_color); WARN_ON_ONCE(wq->flush_color != next->flush_color); list_del_init(&next->list); wq->first_flusher = next; if (flush_workqueue_prep_pwqs(wq, wq->flush_color, -1)) break; /* * Meh... this color is already done, clear first * flusher and repeat cascading. */ wq->first_flusher = NULL; } out_unlock: mutex_unlock(&wq->mutex); } EXPORT_SYMBOL(__flush_workqueue); /** * drain_workqueue - drain a workqueue * @wq: workqueue to drain * * Wait until the workqueue becomes empty. While draining is in progress, * only chain queueing is allowed. IOW, only currently pending or running * work items on @wq can queue further work items on it. @wq is flushed * repeatedly until it becomes empty. The number of flushing is determined * by the depth of chaining and should be relatively short. Whine if it * takes too long. */ void drain_workqueue(struct workqueue_struct *wq) { unsigned int flush_cnt = 0; struct pool_workqueue *pwq; /* * __queue_work() needs to test whether there are drainers, is much * hotter than drain_workqueue() and already looks at @wq->flags. * Use __WQ_DRAINING so that queue doesn't have to check nr_drainers. */ mutex_lock(&wq->mutex); if (!wq->nr_drainers++) wq->flags |= __WQ_DRAINING; mutex_unlock(&wq->mutex); reflush: __flush_workqueue(wq); mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) { bool drained; raw_spin_lock_irq(&pwq->pool->lock); drained = !pwq->nr_active && list_empty(&pwq->inactive_works); raw_spin_unlock_irq(&pwq->pool->lock); if (drained) continue; if (++flush_cnt == 10 || (flush_cnt % 100 == 0 && flush_cnt <= 1000)) pr_warn("workqueue %s: %s() isn't complete after %u tries\n", wq->name, __func__, flush_cnt); mutex_unlock(&wq->mutex); goto reflush; } if (!--wq->nr_drainers) wq->flags &= ~__WQ_DRAINING; mutex_unlock(&wq->mutex); } EXPORT_SYMBOL_GPL(drain_workqueue); static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, bool from_cancel) { struct worker *worker = NULL; struct worker_pool *pool; struct pool_workqueue *pwq; might_sleep(); rcu_read_lock(); pool = get_work_pool(work); if (!pool) { rcu_read_unlock(); return false; } raw_spin_lock_irq(&pool->lock); /* see the comment in try_to_grab_pending() with the same code */ pwq = get_work_pwq(work); if (pwq) { if (unlikely(pwq->pool != pool)) goto already_gone; } else { worker = find_worker_executing_work(pool, work); if (!worker) goto already_gone; pwq = worker->current_pwq; } check_flush_dependency(pwq->wq, work); insert_wq_barrier(pwq, barr, work, worker); raw_spin_unlock_irq(&pool->lock); /* * Force a lock recursion deadlock when using flush_work() inside a * single-threaded or rescuer equipped workqueue. * * For single threaded workqueues the deadlock happens when the work * is after the work issuing the flush_work(). For rescuer equipped * workqueues the deadlock happens when the rescuer stalls, blocking * forward progress. */ if (!from_cancel && (pwq->wq->saved_max_active == 1 || pwq->wq->rescuer)) { lock_map_acquire(&pwq->wq->lockdep_map); lock_map_release(&pwq->wq->lockdep_map); } rcu_read_unlock(); return true; already_gone: raw_spin_unlock_irq(&pool->lock); rcu_read_unlock(); return false; } static bool __flush_work(struct work_struct *work, bool from_cancel) { struct wq_barrier barr; if (WARN_ON(!wq_online)) return false; if (WARN_ON(!work->func)) return false; lock_map_acquire(&work->lockdep_map); lock_map_release(&work->lockdep_map); if (start_flush_work(work, &barr, from_cancel)) { wait_for_completion(&barr.done); destroy_work_on_stack(&barr.work); return true; } else { return false; } } /** * flush_work - wait for a work to finish executing the last queueing instance * @work: the work to flush * * Wait until @work has finished execution. @work is guaranteed to be idle * on return if it hasn't been requeued since flush started. * * Return: * %true if flush_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_work(struct work_struct *work) { return __flush_work(work, false); } EXPORT_SYMBOL_GPL(flush_work); struct cwt_wait { wait_queue_entry_t wait; struct work_struct *work; }; static int cwt_wakefn(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct cwt_wait *cwait = container_of(wait, struct cwt_wait, wait); if (cwait->work != key) return 0; return autoremove_wake_function(wait, mode, sync, key); } static bool __cancel_work_timer(struct work_struct *work, bool is_dwork) { static DECLARE_WAIT_QUEUE_HEAD(cancel_waitq); unsigned long flags; int ret; do { ret = try_to_grab_pending(work, is_dwork, &flags); /* * If someone else is already canceling, wait for it to * finish. flush_work() doesn't work for PREEMPT_NONE * because we may get scheduled between @work's completion * and the other canceling task resuming and clearing * CANCELING - flush_work() will return false immediately * as @work is no longer busy, try_to_grab_pending() will * return -ENOENT as @work is still being canceled and the * other canceling task won't be able to clear CANCELING as * we're hogging the CPU. * * Let's wait for completion using a waitqueue. As this * may lead to the thundering herd problem, use a custom * wake function which matches @work along with exclusive * wait and wakeup. */ if (unlikely(ret == -ENOENT)) { struct cwt_wait cwait; init_wait(&cwait.wait); cwait.wait.func = cwt_wakefn; cwait.work = work; prepare_to_wait_exclusive(&cancel_waitq, &cwait.wait, TASK_UNINTERRUPTIBLE); if (work_is_canceling(work)) schedule(); finish_wait(&cancel_waitq, &cwait.wait); } } while (unlikely(ret < 0)); /* tell other tasks trying to grab @work to back off */ mark_work_canceling(work); local_irq_restore(flags); /* * This allows canceling during early boot. We know that @work * isn't executing. */ if (wq_online) __flush_work(work, true); clear_work_data(work); /* * Paired with prepare_to_wait() above so that either * waitqueue_active() is visible here or !work_is_canceling() is * visible there. */ smp_mb(); if (waitqueue_active(&cancel_waitq)) __wake_up(&cancel_waitq, TASK_NORMAL, 1, work); return ret; } /** * cancel_work_sync - cancel a work and wait for it to finish * @work: the work to cancel * * Cancel @work and wait for its execution to finish. This function * can be used even if the work re-queues itself or migrates to * another workqueue. On return from this function, @work is * guaranteed to be not pending or executing on any CPU. * * cancel_work_sync(&delayed_work->work) must not be used for * delayed_work's. Use cancel_delayed_work_sync() instead. * * The caller must ensure that the workqueue on which @work was last * queued can't be destroyed before this function returns. * * Return: * %true if @work was pending, %false otherwise. */ bool cancel_work_sync(struct work_struct *work) { return __cancel_work_timer(work, false); } EXPORT_SYMBOL_GPL(cancel_work_sync); /** * flush_delayed_work - wait for a dwork to finish executing the last queueing * @dwork: the delayed work to flush * * Delayed timer is cancelled and the pending work is queued for * immediate execution. Like flush_work(), this function only * considers the last queueing instance of @dwork. * * Return: * %true if flush_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_delayed_work(struct delayed_work *dwork) { local_irq_disable(); if (del_timer_sync(&dwork->timer)) __queue_work(dwork->cpu, dwork->wq, &dwork->work); local_irq_enable(); return flush_work(&dwork->work); } EXPORT_SYMBOL(flush_delayed_work); /** * flush_rcu_work - wait for a rwork to finish executing the last queueing * @rwork: the rcu work to flush * * Return: * %true if flush_rcu_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_rcu_work(struct rcu_work *rwork) { if (test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&rwork->work))) { rcu_barrier(); flush_work(&rwork->work); return true; } else { return flush_work(&rwork->work); } } EXPORT_SYMBOL(flush_rcu_work); static bool __cancel_work(struct work_struct *work, bool is_dwork) { unsigned long flags; int ret; do { ret = try_to_grab_pending(work, is_dwork, &flags); } while (unlikely(ret == -EAGAIN)); if (unlikely(ret < 0)) return false; set_work_pool_and_clear_pending(work, get_work_pool_id(work)); local_irq_restore(flags); return ret; } /* * See cancel_delayed_work() */ bool cancel_work(struct work_struct *work) { return __cancel_work(work, false); } EXPORT_SYMBOL(cancel_work); /** * cancel_delayed_work - cancel a delayed work * @dwork: delayed_work to cancel * * Kill off a pending delayed_work. * * Return: %true if @dwork was pending and canceled; %false if it wasn't * pending. * * Note: * The work callback function may still be running on return, unless * it returns %true and the work doesn't re-arm itself. Explicitly flush or * use cancel_delayed_work_sync() to wait on it. * * This function is safe to call from any context including IRQ handler. */ bool cancel_delayed_work(struct delayed_work *dwork) { return __cancel_work(&dwork->work, true); } EXPORT_SYMBOL(cancel_delayed_work); /** * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish * @dwork: the delayed work cancel * * This is cancel_work_sync() for delayed works. * * Return: * %true if @dwork was pending, %false otherwise. */ bool cancel_delayed_work_sync(struct delayed_work *dwork) { return __cancel_work_timer(&dwork->work, true); } EXPORT_SYMBOL(cancel_delayed_work_sync); /** * schedule_on_each_cpu - execute a function synchronously on each online CPU * @func: the function to call * * schedule_on_each_cpu() executes @func on each online CPU using the * system workqueue and blocks until all CPUs have completed. * schedule_on_each_cpu() is very slow. * * Return: * 0 on success, -errno on failure. */ int schedule_on_each_cpu(work_func_t func) { int cpu; struct work_struct __percpu *works; works = alloc_percpu(struct work_struct); if (!works) return -ENOMEM; cpus_read_lock(); for_each_online_cpu(cpu) { struct work_struct *work = per_cpu_ptr(works, cpu); INIT_WORK(work, func); schedule_work_on(cpu, work); } for_each_online_cpu(cpu) flush_work(per_cpu_ptr(works, cpu)); cpus_read_unlock(); free_percpu(works); return 0; } /** * execute_in_process_context - reliably execute the routine with user context * @fn: the function to execute * @ew: guaranteed storage for the execute work structure (must * be available when the work executes) * * Executes the function immediately if process context is available, * otherwise schedules the function for delayed execution. * * Return: 0 - function was executed * 1 - function was scheduled for execution */ int execute_in_process_context(work_func_t fn, struct execute_work *ew) { if (!in_interrupt()) { fn(&ew->work); return 0; } INIT_WORK(&ew->work, fn); schedule_work(&ew->work); return 1; } EXPORT_SYMBOL_GPL(execute_in_process_context); /** * free_workqueue_attrs - free a workqueue_attrs * @attrs: workqueue_attrs to free * * Undo alloc_workqueue_attrs(). */ void free_workqueue_attrs(struct workqueue_attrs *attrs) { if (attrs) { free_cpumask_var(attrs->cpumask); kfree(attrs); } } /** * alloc_workqueue_attrs - allocate a workqueue_attrs * * Allocate a new workqueue_attrs, initialize with default settings and * return it. * * Return: The allocated new workqueue_attr on success. %NULL on failure. */ struct workqueue_attrs *alloc_workqueue_attrs(void) { struct workqueue_attrs *attrs; attrs = kzalloc(sizeof(*attrs), GFP_KERNEL); if (!attrs) goto fail; if (!alloc_cpumask_var(&attrs->cpumask, GFP_KERNEL)) goto fail; cpumask_copy(attrs->cpumask, cpu_possible_mask); return attrs; fail: free_workqueue_attrs(attrs); return NULL; } static void copy_workqueue_attrs(struct workqueue_attrs *to, const struct workqueue_attrs *from) { to->nice = from->nice; cpumask_copy(to->cpumask, from->cpumask); /* * Unlike hash and equality test, this function doesn't ignore * ->no_numa as it is used for both pool and wq attrs. Instead, * get_unbound_pool() explicitly clears ->no_numa after copying. */ to->no_numa = from->no_numa; } /* hash value of the content of @attr */ static u32 wqattrs_hash(const struct workqueue_attrs *attrs) { u32 hash = 0; hash = jhash_1word(attrs->nice, hash); hash = jhash(cpumask_bits(attrs->cpumask), BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); return hash; } /* content equality test */ static bool wqattrs_equal(const struct workqueue_attrs *a, const struct workqueue_attrs *b) { if (a->nice != b->nice) return false; if (!cpumask_equal(a->cpumask, b->cpumask)) return false; return true; } /** * init_worker_pool - initialize a newly zalloc'd worker_pool * @pool: worker_pool to initialize * * Initialize a newly zalloc'd @pool. It also allocates @pool->attrs. * * Return: 0 on success, -errno on failure. Even on failure, all fields * inside @pool proper are initialized and put_unbound_pool() can be called * on @pool safely to release it. */ static int init_worker_pool(struct worker_pool *pool) { raw_spin_lock_init(&pool->lock); pool->id = -1; pool->cpu = -1; pool->node = NUMA_NO_NODE; pool->flags |= POOL_DISASSOCIATED; pool->watchdog_ts = jiffies; INIT_LIST_HEAD(&pool->worklist); INIT_LIST_HEAD(&pool->idle_list); hash_init(pool->busy_hash); timer_setup(&pool->idle_timer, idle_worker_timeout, TIMER_DEFERRABLE); timer_setup(&pool->mayday_timer, pool_mayday_timeout, 0); INIT_LIST_HEAD(&pool->workers); ida_init(&pool->worker_ida); INIT_HLIST_NODE(&pool->hash_node); pool->refcnt = 1; /* shouldn't fail above this point */ pool->attrs = alloc_workqueue_attrs(); if (!pool->attrs) return -ENOMEM; return 0; } #ifdef CONFIG_LOCKDEP static void wq_init_lockdep(struct workqueue_struct *wq) { char *lock_name; lockdep_register_key(&wq->key); lock_name = kasprintf(GFP_KERNEL, "%s%s", "(wq_completion)", wq->name); if (!lock_name) lock_name = wq->name; wq->lock_name = lock_name; lockdep_init_map(&wq->lockdep_map, lock_name, &wq->key, 0); } static void wq_unregister_lockdep(struct workqueue_struct *wq) { lockdep_unregister_key(&wq->key); } static void wq_free_lockdep(struct workqueue_struct *wq) { if (wq->lock_name != wq->name) kfree(wq->lock_name); } #else static void wq_init_lockdep(struct workqueue_struct *wq) { } static void wq_unregister_lockdep(struct workqueue_struct *wq) { } static void wq_free_lockdep(struct workqueue_struct *wq) { } #endif static void rcu_free_wq(struct rcu_head *rcu) { struct workqueue_struct *wq = container_of(rcu, struct workqueue_struct, rcu); wq_free_lockdep(wq); if (!(wq->flags & WQ_UNBOUND)) free_percpu(wq->cpu_pwqs); else free_workqueue_attrs(wq->unbound_attrs); kfree(wq); } static void rcu_free_pool(struct rcu_head *rcu) { struct worker_pool *pool = container_of(rcu, struct worker_pool, rcu); ida_destroy(&pool->worker_ida); free_workqueue_attrs(pool->attrs); kfree(pool); } /* This returns with the lock held on success (pool manager is inactive). */ static bool wq_manager_inactive(struct worker_pool *pool) { raw_spin_lock_irq(&pool->lock); if (pool->flags & POOL_MANAGER_ACTIVE) { raw_spin_unlock_irq(&pool->lock); return false; } return true; } /** * put_unbound_pool - put a worker_pool * @pool: worker_pool to put * * Put @pool. If its refcnt reaches zero, it gets destroyed in RCU * safe manner. get_unbound_pool() calls this function on its failure path * and this function should be able to release pools which went through, * successfully or not, init_worker_pool(). * * Should be called with wq_pool_mutex held. */ static void put_unbound_pool(struct worker_pool *pool) { DECLARE_COMPLETION_ONSTACK(detach_completion); struct worker *worker; lockdep_assert_held(&wq_pool_mutex); if (--pool->refcnt) return; /* sanity checks */ if (WARN_ON(!(pool->cpu < 0)) || WARN_ON(!list_empty(&pool->worklist))) return; /* release id and unhash */ if (pool->id >= 0) idr_remove(&worker_pool_idr, pool->id); hash_del(&pool->hash_node); /* * Become the manager and destroy all workers. This prevents * @pool's workers from blocking on attach_mutex. We're the last * manager and @pool gets freed with the flag set. * Because of how wq_manager_inactive() works, we will hold the * spinlock after a successful wait. */ rcuwait_wait_event(&manager_wait, wq_manager_inactive(pool), TASK_UNINTERRUPTIBLE); pool->flags |= POOL_MANAGER_ACTIVE; while ((worker = first_idle_worker(pool))) destroy_worker(worker); WARN_ON(pool->nr_workers || pool->nr_idle); raw_spin_unlock_irq(&pool->lock); mutex_lock(&wq_pool_attach_mutex); if (!list_empty(&pool->workers)) pool->detach_completion = &detach_completion; mutex_unlock(&wq_pool_attach_mutex); if (pool->detach_completion) wait_for_completion(pool->detach_completion); /* shut down the timers */ del_timer_sync(&pool->idle_timer); del_timer_sync(&pool->mayday_timer); /* RCU protected to allow dereferences from get_work_pool() */ call_rcu(&pool->rcu, rcu_free_pool); } /** * get_unbound_pool - get a worker_pool with the specified attributes * @attrs: the attributes of the worker_pool to get * * Obtain a worker_pool which has the same attributes as @attrs, bump the * reference count and return it. If there already is a matching * worker_pool, it will be used; otherwise, this function attempts to * create a new one. * * Should be called with wq_pool_mutex held. * * Return: On success, a worker_pool with the same attributes as @attrs. * On failure, %NULL. */ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs) { u32 hash = wqattrs_hash(attrs); struct worker_pool *pool; int node; int target_node = NUMA_NO_NODE; lockdep_assert_held(&wq_pool_mutex); /* do we already have a matching pool? */ hash_for_each_possible(unbound_pool_hash, pool, hash_node, hash) { if (wqattrs_equal(pool->attrs, attrs)) { pool->refcnt++; return pool; } } /* if cpumask is contained inside a NUMA node, we belong to that node */ if (wq_numa_enabled) { for_each_node(node) { if (cpumask_subset(attrs->cpumask, wq_numa_possible_cpumask[node])) { target_node = node; break; } } } /* nope, create a new one */ pool = kzalloc_node(sizeof(*pool), GFP_KERNEL, target_node); if (!pool || init_worker_pool(pool) < 0) goto fail; lockdep_set_subclass(&pool->lock, 1); /* see put_pwq() */ copy_workqueue_attrs(pool->attrs, attrs); pool->node = target_node; /* * no_numa isn't a worker_pool attribute, always clear it. See * 'struct workqueue_attrs' comments for detail. */ pool->attrs->no_numa = false; if (worker_pool_assign_id(pool) < 0) goto fail; /* create and start the initial worker */ if (wq_online && !create_worker(pool)) goto fail; /* install */ hash_add(unbound_pool_hash, &pool->hash_node, hash); return pool; fail: if (pool) put_unbound_pool(pool); return NULL; } static void rcu_free_pwq(struct rcu_head *rcu) { kmem_cache_free(pwq_cache, container_of(rcu, struct pool_workqueue, rcu)); } /* * Scheduled on system_wq by put_pwq() when an unbound pwq hits zero refcnt * and needs to be destroyed. */ static void pwq_unbound_release_workfn(struct work_struct *work) { struct pool_workqueue *pwq = container_of(work, struct pool_workqueue, unbound_release_work); struct workqueue_struct *wq = pwq->wq; struct worker_pool *pool = pwq->pool; bool is_last = false; /* * when @pwq is not linked, it doesn't hold any reference to the * @wq, and @wq is invalid to access. */ if (!list_empty(&pwq->pwqs_node)) { if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND))) return; mutex_lock(&wq->mutex); list_del_rcu(&pwq->pwqs_node); is_last = list_empty(&wq->pwqs); mutex_unlock(&wq->mutex); } mutex_lock(&wq_pool_mutex); put_unbound_pool(pool); mutex_unlock(&wq_pool_mutex); call_rcu(&pwq->rcu, rcu_free_pwq); /* * If we're the last pwq going away, @wq is already dead and no one * is gonna access it anymore. Schedule RCU free. */ if (is_last) { wq_unregister_lockdep(wq); call_rcu(&wq->rcu, rcu_free_wq); } } /** * pwq_adjust_max_active - update a pwq's max_active to the current setting * @pwq: target pool_workqueue * * If @pwq isn't freezing, set @pwq->max_active to the associated * workqueue's saved_max_active and activate inactive work items * accordingly. If @pwq is freezing, clear @pwq->max_active to zero. */ static void pwq_adjust_max_active(struct pool_workqueue *pwq) { struct workqueue_struct *wq = pwq->wq; bool freezable = wq->flags & WQ_FREEZABLE; unsigned long flags; /* for @wq->saved_max_active */ lockdep_assert_held(&wq->mutex); /* fast exit for non-freezable wqs */ if (!freezable && pwq->max_active == wq->saved_max_active) return; /* this function can be called during early boot w/ irq disabled */ raw_spin_lock_irqsave(&pwq->pool->lock, flags); /* * During [un]freezing, the caller is responsible for ensuring that * this function is called at least once after @workqueue_freezing * is updated and visible. */ if (!freezable || !workqueue_freezing) { bool kick = false; pwq->max_active = wq->saved_max_active; while (!list_empty(&pwq->inactive_works) && pwq->nr_active < pwq->max_active) { pwq_activate_first_inactive(pwq); kick = true; } /* * Need to kick a worker after thawed or an unbound wq's * max_active is bumped. In realtime scenarios, always kicking a * worker will cause interference on the isolated cpu cores, so * let's kick iff work items were activated. */ if (kick) wake_up_worker(pwq->pool); } else { pwq->max_active = 0; } raw_spin_unlock_irqrestore(&pwq->pool->lock, flags); } /* initialize newly allocated @pwq which is associated with @wq and @pool */ static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq, struct worker_pool *pool) { BUG_ON((unsigned long)pwq & WORK_STRUCT_FLAG_MASK); memset(pwq, 0, sizeof(*pwq)); pwq->pool = pool; pwq->wq = wq; pwq->flush_color = -1; pwq->refcnt = 1; INIT_LIST_HEAD(&pwq->inactive_works); INIT_LIST_HEAD(&pwq->pwqs_node); INIT_LIST_HEAD(&pwq->mayday_node); INIT_WORK(&pwq->unbound_release_work, pwq_unbound_release_workfn); } /* sync @pwq with the current state of its associated wq and link it */ static void link_pwq(struct pool_workqueue *pwq) { struct workqueue_struct *wq = pwq->wq; lockdep_assert_held(&wq->mutex); /* may be called multiple times, ignore if already linked */ if (!list_empty(&pwq->pwqs_node)) return; /* set the matching work_color */ pwq->work_color = wq->work_color; /* sync max_active to the current setting */ pwq_adjust_max_active(pwq); /* link in @pwq */ list_add_rcu(&pwq->pwqs_node, &wq->pwqs); } /* obtain a pool matching @attr and create a pwq associating the pool and @wq */ static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { struct worker_pool *pool; struct pool_workqueue *pwq; lockdep_assert_held(&wq_pool_mutex); pool = get_unbound_pool(attrs); if (!pool) return NULL; pwq = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL, pool->node); if (!pwq) { put_unbound_pool(pool); return NULL; } init_pwq(pwq, wq, pool); return pwq; } /** * wq_calc_node_cpumask - calculate a wq_attrs' cpumask for the specified node * @attrs: the wq_attrs of the default pwq of the target workqueue * @node: the target NUMA node * @cpu_going_down: if >= 0, the CPU to consider as offline * @cpumask: outarg, the resulting cpumask * * Calculate the cpumask a workqueue with @attrs should use on @node. If * @cpu_going_down is >= 0, that cpu is considered offline during * calculation. The result is stored in @cpumask. * * If NUMA affinity is not enabled, @attrs->cpumask is always used. If * enabled and @node has online CPUs requested by @attrs, the returned * cpumask is the intersection of the possible CPUs of @node and * @attrs->cpumask. * * The caller is responsible for ensuring that the cpumask of @node stays * stable. * * Return: %true if the resulting @cpumask is different from @attrs->cpumask, * %false if equal. */ static bool wq_calc_node_cpumask(const struct workqueue_attrs *attrs, int node, int cpu_going_down, cpumask_t *cpumask) { if (!wq_numa_enabled || attrs->no_numa) goto use_dfl; /* does @node have any online CPUs @attrs wants? */ cpumask_and(cpumask, cpumask_of_node(node), attrs->cpumask); if (cpu_going_down >= 0) cpumask_clear_cpu(cpu_going_down, cpumask); if (cpumask_empty(cpumask)) goto use_dfl; /* yeap, return possible CPUs in @node that @attrs wants */ cpumask_and(cpumask, attrs->cpumask, wq_numa_possible_cpumask[node]); if (cpumask_empty(cpumask)) { pr_warn_once("WARNING: workqueue cpumask: online intersect > " "possible intersect\n"); return false; } return !cpumask_equal(cpumask, attrs->cpumask); use_dfl: cpumask_copy(cpumask, attrs->cpumask); return false; } /* install @pwq into @wq's numa_pwq_tbl[] for @node and return the old pwq */ static struct pool_workqueue *numa_pwq_tbl_install(struct workqueue_struct *wq, int node, struct pool_workqueue *pwq) { struct pool_workqueue *old_pwq; lockdep_assert_held(&wq_pool_mutex); lockdep_assert_held(&wq->mutex); /* link_pwq() can handle duplicate calls */ link_pwq(pwq); old_pwq = rcu_access_pointer(wq->numa_pwq_tbl[node]); rcu_assign_pointer(wq->numa_pwq_tbl[node], pwq); return old_pwq; } /* context to store the prepared attrs & pwqs before applying */ struct apply_wqattrs_ctx { struct workqueue_struct *wq; /* target workqueue */ struct workqueue_attrs *attrs; /* attrs to apply */ struct list_head list; /* queued for batching commit */ struct pool_workqueue *dfl_pwq; struct pool_workqueue *pwq_tbl[]; }; /* free the resources after success or abort */ static void apply_wqattrs_cleanup(struct apply_wqattrs_ctx *ctx) { if (ctx) { int node; for_each_node(node) put_pwq_unlocked(ctx->pwq_tbl[node]); put_pwq_unlocked(ctx->dfl_pwq); free_workqueue_attrs(ctx->attrs); kfree(ctx); } } /* allocate the attrs and pwqs for later installation */ static struct apply_wqattrs_ctx * apply_wqattrs_prepare(struct workqueue_struct *wq, const struct workqueue_attrs *attrs, const cpumask_var_t unbound_cpumask) { struct apply_wqattrs_ctx *ctx; struct workqueue_attrs *new_attrs, *tmp_attrs; int node; lockdep_assert_held(&wq_pool_mutex); ctx = kzalloc(struct_size(ctx, pwq_tbl, nr_node_ids), GFP_KERNEL); new_attrs = alloc_workqueue_attrs(); tmp_attrs = alloc_workqueue_attrs(); if (!ctx || !new_attrs || !tmp_attrs) goto out_free; /* * Calculate the attrs of the default pwq with unbound_cpumask * which is wq_unbound_cpumask or to set to wq_unbound_cpumask. * If the user configured cpumask doesn't overlap with the * wq_unbound_cpumask, we fallback to the wq_unbound_cpumask. */ copy_workqueue_attrs(new_attrs, attrs); cpumask_and(new_attrs->cpumask, new_attrs->cpumask, unbound_cpumask); if (unlikely(cpumask_empty(new_attrs->cpumask))) cpumask_copy(new_attrs->cpumask, unbound_cpumask); /* * We may create multiple pwqs with differing cpumasks. Make a * copy of @new_attrs which will be modified and used to obtain * pools. */ copy_workqueue_attrs(tmp_attrs, new_attrs); /* * If something goes wrong during CPU up/down, we'll fall back to * the default pwq covering whole @attrs->cpumask. Always create * it even if we don't use it immediately. */ ctx->dfl_pwq = alloc_unbound_pwq(wq, new_attrs); if (!ctx->dfl_pwq) goto out_free; for_each_node(node) { if (wq_calc_node_cpumask(new_attrs, node, -1, tmp_attrs->cpumask)) { ctx->pwq_tbl[node] = alloc_unbound_pwq(wq, tmp_attrs); if (!ctx->pwq_tbl[node]) goto out_free; } else { ctx->dfl_pwq->refcnt++; ctx->pwq_tbl[node] = ctx->dfl_pwq; } } /* save the user configured attrs and sanitize it. */ copy_workqueue_attrs(new_attrs, attrs); cpumask_and(new_attrs->cpumask, new_attrs->cpumask, cpu_possible_mask); ctx->attrs = new_attrs; ctx->wq = wq; free_workqueue_attrs(tmp_attrs); return ctx; out_free: free_workqueue_attrs(tmp_attrs); free_workqueue_attrs(new_attrs); apply_wqattrs_cleanup(ctx); return NULL; } /* set attrs and install prepared pwqs, @ctx points to old pwqs on return */ static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx) { int node; /* all pwqs have been created successfully, let's install'em */ mutex_lock(&ctx->wq->mutex); copy_workqueue_attrs(ctx->wq->unbound_attrs, ctx->attrs); /* save the previous pwq and install the new one */ for_each_node(node) ctx->pwq_tbl[node] = numa_pwq_tbl_install(ctx->wq, node, ctx->pwq_tbl[node]); /* @dfl_pwq might not have been used, ensure it's linked */ link_pwq(ctx->dfl_pwq); swap(ctx->wq->dfl_pwq, ctx->dfl_pwq); mutex_unlock(&ctx->wq->mutex); } static void apply_wqattrs_lock(void) { /* CPUs should stay stable across pwq creations and installations */ cpus_read_lock(); mutex_lock(&wq_pool_mutex); } static void apply_wqattrs_unlock(void) { mutex_unlock(&wq_pool_mutex); cpus_read_unlock(); } static int apply_workqueue_attrs_locked(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { struct apply_wqattrs_ctx *ctx; /* only unbound workqueues can change attributes */ if (WARN_ON(!(wq->flags & WQ_UNBOUND))) return -EINVAL; /* creating multiple pwqs breaks ordering guarantee */ if (!list_empty(&wq->pwqs)) { if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT)) return -EINVAL; wq->flags &= ~__WQ_ORDERED; } ctx = apply_wqattrs_prepare(wq, attrs, wq_unbound_cpumask); if (!ctx) return -ENOMEM; /* the ctx has been prepared successfully, let's commit it */ apply_wqattrs_commit(ctx); apply_wqattrs_cleanup(ctx); return 0; } /** * apply_workqueue_attrs - apply new workqueue_attrs to an unbound workqueue * @wq: the target workqueue * @attrs: the workqueue_attrs to apply, allocated with alloc_workqueue_attrs() * * Apply @attrs to an unbound workqueue @wq. Unless disabled, on NUMA * machines, this function maps a separate pwq to each NUMA node with * possibles CPUs in @attrs->cpumask so that work items are affine to the * NUMA node it was issued on. Older pwqs are released as in-flight work * items finish. Note that a work item which repeatedly requeues itself * back-to-back will stay on its current pwq. * * Performs GFP_KERNEL allocations. * * Assumes caller has CPU hotplug read exclusion, i.e. cpus_read_lock(). * * Return: 0 on success and -errno on failure. */ int apply_workqueue_attrs(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { int ret; lockdep_assert_cpus_held(); mutex_lock(&wq_pool_mutex); ret = apply_workqueue_attrs_locked(wq, attrs); mutex_unlock(&wq_pool_mutex); return ret; } /** * wq_update_unbound_numa - update NUMA affinity of a wq for CPU hot[un]plug * @wq: the target workqueue * @cpu: the CPU coming up or going down * @online: whether @cpu is coming up or going down * * This function is to be called from %CPU_DOWN_PREPARE, %CPU_ONLINE and * %CPU_DOWN_FAILED. @cpu is being hot[un]plugged, update NUMA affinity of * @wq accordingly. * * If NUMA affinity can't be adjusted due to memory allocation failure, it * falls back to @wq->dfl_pwq which may not be optimal but is always * correct. * * Note that when the last allowed CPU of a NUMA node goes offline for a * workqueue with a cpumask spanning multiple nodes, the workers which were * already executing the work items for the workqueue will lose their CPU * affinity and may execute on any CPU. This is similar to how per-cpu * workqueues behave on CPU_DOWN. If a workqueue user wants strict * affinity, it's the user's responsibility to flush the work item from * CPU_DOWN_PREPARE. */ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu, bool online) { int node = cpu_to_node(cpu); int cpu_off = online ? -1 : cpu; struct pool_workqueue *old_pwq = NULL, *pwq; struct workqueue_attrs *target_attrs; cpumask_t *cpumask; lockdep_assert_held(&wq_pool_mutex); if (!wq_numa_enabled || !(wq->flags & WQ_UNBOUND) || wq->unbound_attrs->no_numa) return; /* * We don't wanna alloc/free wq_attrs for each wq for each CPU. * Let's use a preallocated one. The following buf is protected by * CPU hotplug exclusion. */ target_attrs = wq_update_unbound_numa_attrs_buf; cpumask = target_attrs->cpumask; copy_workqueue_attrs(target_attrs, wq->unbound_attrs); pwq = unbound_pwq_by_node(wq, node); /* * Let's determine what needs to be done. If the target cpumask is * different from the default pwq's, we need to compare it to @pwq's * and create a new one if they don't match. If the target cpumask * equals the default pwq's, the default pwq should be used. */ if (wq_calc_node_cpumask(wq->dfl_pwq->pool->attrs, node, cpu_off, cpumask)) { if (cpumask_equal(cpumask, pwq->pool->attrs->cpumask)) return; } else { goto use_dfl_pwq; } /* create a new pwq */ pwq = alloc_unbound_pwq(wq, target_attrs); if (!pwq) { pr_warn("workqueue: allocation failed while updating NUMA affinity of \"%s\"\n", wq->name); goto use_dfl_pwq; } /* Install the new pwq. */ mutex_lock(&wq->mutex); old_pwq = numa_pwq_tbl_install(wq, node, pwq); goto out_unlock; use_dfl_pwq: mutex_lock(&wq->mutex); raw_spin_lock_irq(&wq->dfl_pwq->pool->lock); get_pwq(wq->dfl_pwq); raw_spin_unlock_irq(&wq->dfl_pwq->pool->lock); old_pwq = numa_pwq_tbl_install(wq, node, wq->dfl_pwq); out_unlock: mutex_unlock(&wq->mutex); put_pwq_unlocked(old_pwq); } static int alloc_and_link_pwqs(struct workqueue_struct *wq) { bool highpri = wq->flags & WQ_HIGHPRI; int cpu, ret; if (!(wq->flags & WQ_UNBOUND)) { wq->cpu_pwqs = alloc_percpu(struct pool_workqueue); if (!wq->cpu_pwqs) return -ENOMEM; for_each_possible_cpu(cpu) { struct pool_workqueue *pwq = per_cpu_ptr(wq->cpu_pwqs, cpu); struct worker_pool *cpu_pools = per_cpu(cpu_worker_pools, cpu); init_pwq(pwq, wq, &cpu_pools[highpri]); mutex_lock(&wq->mutex); link_pwq(pwq); mutex_unlock(&wq->mutex); } return 0; } cpus_read_lock(); if (wq->flags & __WQ_ORDERED) { ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]); /* there should only be single pwq for ordering guarantee */ WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node || wq->pwqs.prev != &wq->dfl_pwq->pwqs_node), "ordering guarantee broken for workqueue %s\n", wq->name); } else { ret = apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]); } cpus_read_unlock(); return ret; } static int wq_clamp_max_active(int max_active, unsigned int flags, const char *name) { int lim = flags & WQ_UNBOUND ? WQ_UNBOUND_MAX_ACTIVE : WQ_MAX_ACTIVE; if (max_active < 1 || max_active > lim) pr_warn("workqueue: max_active %d requested for %s is out of range, clamping between %d and %d\n", max_active, name, 1, lim); return clamp_val(max_active, 1, lim); } /* * Workqueues which may be used during memory reclaim should have a rescuer * to guarantee forward progress. */ static int init_rescuer(struct workqueue_struct *wq) { struct worker *rescuer; int ret; if (!(wq->flags & WQ_MEM_RECLAIM)) return 0; rescuer = alloc_worker(NUMA_NO_NODE); if (!rescuer) return -ENOMEM; rescuer->rescue_wq = wq; rescuer->task = kthread_create(rescuer_thread, rescuer, "%s", wq->name); if (IS_ERR(rescuer->task)) { ret = PTR_ERR(rescuer->task); kfree(rescuer); return ret; } wq->rescuer = rescuer; kthread_bind_mask(rescuer->task, cpu_possible_mask); wake_up_process(rescuer->task); return 0; } __printf(1, 4) struct workqueue_struct *alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...) { size_t tbl_size = 0; va_list args; struct workqueue_struct *wq; struct pool_workqueue *pwq; /* * Unbound && max_active == 1 used to imply ordered, which is no * longer the case on NUMA machines due to per-node pools. While * alloc_ordered_workqueue() is the right way to create an ordered * workqueue, keep the previous behavior to avoid subtle breakages * on NUMA. */ if ((flags & WQ_UNBOUND) && max_active == 1) flags |= __WQ_ORDERED; /* see the comment above the definition of WQ_POWER_EFFICIENT */ if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient) flags |= WQ_UNBOUND; /* allocate wq and format name */ if (flags & WQ_UNBOUND) tbl_size = nr_node_ids * sizeof(wq->numa_pwq_tbl[0]); wq = kzalloc(sizeof(*wq) + tbl_size, GFP_KERNEL); if (!wq) return NULL; if (flags & WQ_UNBOUND) { wq->unbound_attrs = alloc_workqueue_attrs(); if (!wq->unbound_attrs) goto err_free_wq; } va_start(args, max_active); vsnprintf(wq->name, sizeof(wq->name), fmt, args); va_end(args); max_active = max_active ?: WQ_DFL_ACTIVE; max_active = wq_clamp_max_active(max_active, flags, wq->name); /* init wq */ wq->flags = flags; wq->saved_max_active = max_active; mutex_init(&wq->mutex); atomic_set(&wq->nr_pwqs_to_flush, 0); INIT_LIST_HEAD(&wq->pwqs); INIT_LIST_HEAD(&wq->flusher_queue); INIT_LIST_HEAD(&wq->flusher_overflow); INIT_LIST_HEAD(&wq->maydays); wq_init_lockdep(wq); INIT_LIST_HEAD(&wq->list); if (alloc_and_link_pwqs(wq) < 0) goto err_unreg_lockdep; if (wq_online && init_rescuer(wq) < 0) goto err_destroy; if ((wq->flags & WQ_SYSFS) && workqueue_sysfs_register(wq)) goto err_destroy; /* * wq_pool_mutex protects global freeze state and workqueues list. * Grab it, adjust max_active and add the new @wq to workqueues * list. */ mutex_lock(&wq_pool_mutex); mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) pwq_adjust_max_active(pwq); mutex_unlock(&wq->mutex); list_add_tail_rcu(&wq->list, &workqueues); mutex_unlock(&wq_pool_mutex); return wq; err_unreg_lockdep: wq_unregister_lockdep(wq); wq_free_lockdep(wq); err_free_wq: free_workqueue_attrs(wq->unbound_attrs); kfree(wq); return NULL; err_destroy: destroy_workqueue(wq); return NULL; } EXPORT_SYMBOL_GPL(alloc_workqueue); static bool pwq_busy(struct pool_workqueue *pwq) { int i; for (i = 0; i < WORK_NR_COLORS; i++) if (pwq->nr_in_flight[i]) return true; if ((pwq != pwq->wq->dfl_pwq) && (pwq->refcnt > 1)) return true; if (pwq->nr_active || !list_empty(&pwq->inactive_works)) return true; return false; } /** * destroy_workqueue - safely terminate a workqueue * @wq: target workqueue * * Safely destroy a workqueue. All work currently pending will be done first. */ void destroy_workqueue(struct workqueue_struct *wq) { struct pool_workqueue *pwq; int node; /* * Remove it from sysfs first so that sanity check failure doesn't * lead to sysfs name conflicts. */ workqueue_sysfs_unregister(wq); /* drain it before proceeding with destruction */ drain_workqueue(wq); /* kill rescuer, if sanity checks fail, leave it w/o rescuer */ if (wq->rescuer) { struct worker *rescuer = wq->rescuer; /* this prevents new queueing */ raw_spin_lock_irq(&wq_mayday_lock); wq->rescuer = NULL; raw_spin_unlock_irq(&wq_mayday_lock); /* rescuer will empty maydays list before exiting */ kthread_stop(rescuer->task); kfree(rescuer); } /* * Sanity checks - grab all the locks so that we wait for all * in-flight operations which may do put_pwq(). */ mutex_lock(&wq_pool_mutex); mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) { raw_spin_lock_irq(&pwq->pool->lock); if (WARN_ON(pwq_busy(pwq))) { pr_warn("%s: %s has the following busy pwq\n", __func__, wq->name); show_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); mutex_unlock(&wq->mutex); mutex_unlock(&wq_pool_mutex); show_one_workqueue(wq); return; } raw_spin_unlock_irq(&pwq->pool->lock); } mutex_unlock(&wq->mutex); /* * wq list is used to freeze wq, remove from list after * flushing is complete in case freeze races us. */ list_del_rcu(&wq->list); mutex_unlock(&wq_pool_mutex); if (!(wq->flags & WQ_UNBOUND)) { wq_unregister_lockdep(wq); /* * The base ref is never dropped on per-cpu pwqs. Directly * schedule RCU free. */ call_rcu(&wq->rcu, rcu_free_wq); } else { /* * We're the sole accessor of @wq at this point. Directly * access numa_pwq_tbl[] and dfl_pwq to put the base refs. * @wq will be freed when the last pwq is released. */ for_each_node(node) { pwq = rcu_access_pointer(wq->numa_pwq_tbl[node]); RCU_INIT_POINTER(wq->numa_pwq_tbl[node], NULL); put_pwq_unlocked(pwq); } /* * Put dfl_pwq. @wq may be freed any time after dfl_pwq is * put. Don't access it afterwards. */ pwq = wq->dfl_pwq; wq->dfl_pwq = NULL; put_pwq_unlocked(pwq); } } EXPORT_SYMBOL_GPL(destroy_workqueue); /** * workqueue_set_max_active - adjust max_active of a workqueue * @wq: target workqueue * @max_active: new max_active value. * * Set max_active of @wq to @max_active. * * CONTEXT: * Don't call from IRQ context. */ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) { struct pool_workqueue *pwq; /* disallow meddling with max_active for ordered workqueues */ if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT)) return; max_active = wq_clamp_max_active(max_active, wq->flags, wq->name); mutex_lock(&wq->mutex); wq->flags &= ~__WQ_ORDERED; wq->saved_max_active = max_active; for_each_pwq(pwq, wq) pwq_adjust_max_active(pwq); mutex_unlock(&wq->mutex); } EXPORT_SYMBOL_GPL(workqueue_set_max_active); /** * current_work - retrieve %current task's work struct * * Determine if %current task is a workqueue worker and what it's working on. * Useful to find out the context that the %current task is running in. * * Return: work struct if %current task is a workqueue worker, %NULL otherwise. */ struct work_struct *current_work(void) { struct worker *worker = current_wq_worker(); return worker ? worker->current_work : NULL; } EXPORT_SYMBOL(current_work); /** * current_is_workqueue_rescuer - is %current workqueue rescuer? * * Determine whether %current is a workqueue rescuer. Can be used from * work functions to determine whether it's being run off the rescuer task. * * Return: %true if %current is a workqueue rescuer. %false otherwise. */ bool current_is_workqueue_rescuer(void) { struct worker *worker = current_wq_worker(); return worker && worker->rescue_wq; } /** * workqueue_congested - test whether a workqueue is congested * @cpu: CPU in question * @wq: target workqueue * * Test whether @wq's cpu workqueue for @cpu is congested. There is * no synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. * * If @cpu is WORK_CPU_UNBOUND, the test is performed on the local CPU. * Note that both per-cpu and unbound workqueues may be associated with * multiple pool_workqueues which have separate congested states. A * workqueue being congested on one CPU doesn't mean the workqueue is also * contested on other CPUs / NUMA nodes. * * Return: * %true if congested, %false otherwise. */ bool workqueue_congested(int cpu, struct workqueue_struct *wq) { struct pool_workqueue *pwq; bool ret; rcu_read_lock(); preempt_disable(); if (cpu == WORK_CPU_UNBOUND) cpu = smp_processor_id(); if (!(wq->flags & WQ_UNBOUND)) pwq = per_cpu_ptr(wq->cpu_pwqs, cpu); else pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); ret = !list_empty(&pwq->inactive_works); preempt_enable(); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(workqueue_congested); /** * work_busy - test whether a work is currently pending or running * @work: the work to be tested * * Test whether @work is currently pending or running. There is no * synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. * * Return: * OR'd bitmask of WORK_BUSY_* bits. */ unsigned int work_busy(struct work_struct *work) { struct worker_pool *pool; unsigned long flags; unsigned int ret = 0; if (work_pending(work)) ret |= WORK_BUSY_PENDING; rcu_read_lock(); pool = get_work_pool(work); if (pool) { raw_spin_lock_irqsave(&pool->lock, flags); if (find_worker_executing_work(pool, work)) ret |= WORK_BUSY_RUNNING; raw_spin_unlock_irqrestore(&pool->lock, flags); } rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(work_busy); /** * set_worker_desc - set description for the current work item * @fmt: printf-style format string * @...: arguments for the format string * * This function can be called by a running work function to describe what * the work item is about. If the worker task gets dumped, this * information will be printed out together to help debugging. The * description can be at most WORKER_DESC_LEN including the trailing '\0'. */ void set_worker_desc(const char *fmt, ...) { struct worker *worker = current_wq_worker(); va_list args; if (worker) { va_start(args, fmt); vsnprintf(worker->desc, sizeof(worker->desc), fmt, args); va_end(args); } } EXPORT_SYMBOL_GPL(set_worker_desc); /** * print_worker_info - print out worker information and description * @log_lvl: the log level to use when printing * @task: target task * * If @task is a worker and currently executing a work item, print out the * name of the workqueue being serviced and worker description set with * set_worker_desc() by the currently executing work item. * * This function can be safely called on any task as long as the * task_struct itself is accessible. While safe, this function isn't * synchronized and may print out mixups or garbages of limited length. */ void print_worker_info(const char *log_lvl, struct task_struct *task) { work_func_t *fn = NULL; char name[WQ_NAME_LEN] = { }; char desc[WORKER_DESC_LEN] = { }; struct pool_workqueue *pwq = NULL; struct workqueue_struct *wq = NULL; struct worker *worker; if (!(task->flags & PF_WQ_WORKER)) return; /* * This function is called without any synchronization and @task * could be in any state. Be careful with dereferences. */ worker = kthread_probe_data(task); /* * Carefully copy the associated workqueue's workfn, name and desc. * Keep the original last '\0' in case the original is garbage. */ copy_from_kernel_nofault(&fn, &worker->current_func, sizeof(fn)); copy_from_kernel_nofault(&pwq, &worker->current_pwq, sizeof(pwq)); copy_from_kernel_nofault(&wq, &pwq->wq, sizeof(wq)); copy_from_kernel_nofault(name, wq->name, sizeof(name) - 1); copy_from_kernel_nofault(desc, worker->desc, sizeof(desc) - 1); if (fn || name[0] || desc[0]) { printk("%sWorkqueue: %s %ps", log_lvl, name, fn); if (strcmp(name, desc)) pr_cont(" (%s)", desc); pr_cont("\n"); } } static void pr_cont_pool_info(struct worker_pool *pool) { pr_cont(" cpus=%*pbl", nr_cpumask_bits, pool->attrs->cpumask); if (pool->node != NUMA_NO_NODE) pr_cont(" node=%d", pool->node); pr_cont(" flags=0x%x nice=%d", pool->flags, pool->attrs->nice); } static void pr_cont_work(bool comma, struct work_struct *work) { if (work->func == wq_barrier_func) { struct wq_barrier *barr; barr = container_of(work, struct wq_barrier, work); pr_cont("%s BAR(%d)", comma ? "," : "", task_pid_nr(barr->task)); } else { pr_cont("%s %ps", comma ? "," : "", work->func); } } static void show_pwq(struct pool_workqueue *pwq) { struct worker_pool *pool = pwq->pool; struct work_struct *work; struct worker *worker; bool has_in_flight = false, has_pending = false; int bkt; pr_info(" pwq %d:", pool->id); pr_cont_pool_info(pool); pr_cont(" active=%d/%d refcnt=%d%s\n", pwq->nr_active, pwq->max_active, pwq->refcnt, !list_empty(&pwq->mayday_node) ? " MAYDAY" : ""); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (worker->current_pwq == pwq) { has_in_flight = true; break; } } if (has_in_flight) { bool comma = false; pr_info(" in-flight:"); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (worker->current_pwq != pwq) continue; pr_cont("%s %d%s:%ps", comma ? "," : "", task_pid_nr(worker->task), worker->rescue_wq ? "(RESCUER)" : "", worker->current_func); list_for_each_entry(work, &worker->scheduled, entry) pr_cont_work(false, work); comma = true; } pr_cont("\n"); } list_for_each_entry(work, &pool->worklist, entry) { if (get_work_pwq(work) == pwq) { has_pending = true; break; } } if (has_pending) { bool comma = false; pr_info(" pending:"); list_for_each_entry(work, &pool->worklist, entry) { if (get_work_pwq(work) != pwq) continue; pr_cont_work(comma, work); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } pr_cont("\n"); } if (!list_empty(&pwq->inactive_works)) { bool comma = false; pr_info(" inactive:"); list_for_each_entry(work, &pwq->inactive_works, entry) { pr_cont_work(comma, work); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } pr_cont("\n"); } } /** * show_one_workqueue - dump state of specified workqueue * @wq: workqueue whose state will be printed */ void show_one_workqueue(struct workqueue_struct *wq) { struct pool_workqueue *pwq; bool idle = true; unsigned long flags; for_each_pwq(pwq, wq) { if (pwq->nr_active || !list_empty(&pwq->inactive_works)) { idle = false; break; } } if (idle) /* Nothing to print for idle workqueue */ return; pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags); for_each_pwq(pwq, wq) { raw_spin_lock_irqsave(&pwq->pool->lock, flags); if (pwq->nr_active || !list_empty(&pwq->inactive_works)) { /* * Defer printing to avoid deadlocks in console * drivers that queue work while holding locks * also taken in their write paths. */ printk_deferred_enter(); show_pwq(pwq); printk_deferred_exit(); } raw_spin_unlock_irqrestore(&pwq->pool->lock, flags); /* * We could be printing a lot from atomic context, e.g. * sysrq-t -> show_all_workqueues(). Avoid triggering * hard lockup. */ touch_nmi_watchdog(); } } /** * show_one_worker_pool - dump state of specified worker pool * @pool: worker pool whose state will be printed */ static void show_one_worker_pool(struct worker_pool *pool) { struct worker *worker; bool first = true; unsigned long flags; unsigned long hung = 0; raw_spin_lock_irqsave(&pool->lock, flags); if (pool->nr_workers == pool->nr_idle) goto next_pool; /* How long the first pending work is waiting for a worker. */ if (!list_empty(&pool->worklist)) hung = jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000; /* * Defer printing to avoid deadlocks in console drivers that * queue work while holding locks also taken in their write * paths. */ printk_deferred_enter(); pr_info("pool %d:", pool->id); pr_cont_pool_info(pool); pr_cont(" hung=%lus workers=%d", hung, pool->nr_workers); if (pool->manager) pr_cont(" manager: %d", task_pid_nr(pool->manager->task)); list_for_each_entry(worker, &pool->idle_list, entry) { pr_cont(" %s%d", first ? "idle: " : "", task_pid_nr(worker->task)); first = false; } pr_cont("\n"); printk_deferred_exit(); next_pool: raw_spin_unlock_irqrestore(&pool->lock, flags); /* * We could be printing a lot from atomic context, e.g. * sysrq-t -> show_all_workqueues(). Avoid triggering * hard lockup. */ touch_nmi_watchdog(); } /** * show_all_workqueues - dump workqueue state * * Called from a sysrq handler or try_to_freeze_tasks() and prints out * all busy workqueues and pools. */ void show_all_workqueues(void) { struct workqueue_struct *wq; struct worker_pool *pool; int pi; rcu_read_lock(); pr_info("Showing busy workqueues and worker pools:\n"); list_for_each_entry_rcu(wq, &workqueues, list) show_one_workqueue(wq); for_each_pool(pool, pi) show_one_worker_pool(pool); rcu_read_unlock(); } /* used to show worker information through /proc/PID/{comm,stat,status} */ void wq_worker_comm(char *buf, size_t size, struct task_struct *task) { int off; /* always show the actual comm */ off = strscpy(buf, task->comm, size); if (off < 0) return; /* stabilize PF_WQ_WORKER and worker pool association */ mutex_lock(&wq_pool_attach_mutex); if (task->flags & PF_WQ_WORKER) { struct worker *worker = kthread_data(task); struct worker_pool *pool = worker->pool; if (pool) { raw_spin_lock_irq(&pool->lock); /* * ->desc tracks information (wq name or * set_worker_desc()) for the latest execution. If * current, prepend '+', otherwise '-'. */ if (worker->desc[0] != '\0') { if (worker->current_work) scnprintf(buf + off, size - off, "+%s", worker->desc); else scnprintf(buf + off, size - off, "-%s", worker->desc); } raw_spin_unlock_irq(&pool->lock); } } mutex_unlock(&wq_pool_attach_mutex); } EXPORT_SYMBOL_GPL(wq_worker_comm); #ifdef CONFIG_SMP /* * CPU hotplug. * * There are two challenges in supporting CPU hotplug. Firstly, there * are a lot of assumptions on strong associations among work, pwq and * pool which make migrating pending and scheduled works very * difficult to implement without impacting hot paths. Secondly, * worker pools serve mix of short, long and very long running works making * blocked draining impractical. * * This is solved by allowing the pools to be disassociated from the CPU * running as an unbound one and allowing it to be reattached later if the * cpu comes back online. */ static void unbind_workers(int cpu) { struct worker_pool *pool; struct worker *worker; for_each_cpu_worker_pool(pool, cpu) { mutex_lock(&wq_pool_attach_mutex); raw_spin_lock_irq(&pool->lock); /* * We've blocked all attach/detach operations. Make all workers * unbound and set DISASSOCIATED. Before this, all workers * must be on the cpu. After this, they may become diasporas. * And the preemption disabled section in their sched callbacks * are guaranteed to see WORKER_UNBOUND since the code here * is on the same cpu. */ for_each_pool_worker(worker, pool) worker->flags |= WORKER_UNBOUND; pool->flags |= POOL_DISASSOCIATED; /* * The handling of nr_running in sched callbacks are disabled * now. Zap nr_running. After this, nr_running stays zero and * need_more_worker() and keep_working() are always true as * long as the worklist is not empty. This pool now behaves as * an unbound (in terms of concurrency management) pool which * are served by workers tied to the pool. */ pool->nr_running = 0; /* * With concurrency management just turned off, a busy * worker blocking could lead to lengthy stalls. Kick off * unbound chain execution of currently pending work items. */ wake_up_worker(pool); raw_spin_unlock_irq(&pool->lock); for_each_pool_worker(worker, pool) { kthread_set_per_cpu(worker->task, -1); if (cpumask_intersects(wq_unbound_cpumask, cpu_active_mask)) WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, wq_unbound_cpumask) < 0); else WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_possible_mask) < 0); } mutex_unlock(&wq_pool_attach_mutex); } } /** * rebind_workers - rebind all workers of a pool to the associated CPU * @pool: pool of interest * * @pool->cpu is coming online. Rebind all workers to the CPU. */ static void rebind_workers(struct worker_pool *pool) { struct worker *worker; lockdep_assert_held(&wq_pool_attach_mutex); /* * Restore CPU affinity of all workers. As all idle workers should * be on the run-queue of the associated CPU before any local * wake-ups for concurrency management happen, restore CPU affinity * of all workers first and then clear UNBOUND. As we're called * from CPU_ONLINE, the following shouldn't fail. */ for_each_pool_worker(worker, pool) { kthread_set_per_cpu(worker->task, pool->cpu); WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask) < 0); } raw_spin_lock_irq(&pool->lock); pool->flags &= ~POOL_DISASSOCIATED; for_each_pool_worker(worker, pool) { unsigned int worker_flags = worker->flags; /* * We want to clear UNBOUND but can't directly call * worker_clr_flags() or adjust nr_running. Atomically * replace UNBOUND with another NOT_RUNNING flag REBOUND. * @worker will clear REBOUND using worker_clr_flags() when * it initiates the next execution cycle thus restoring * concurrency management. Note that when or whether * @worker clears REBOUND doesn't affect correctness. * * WRITE_ONCE() is necessary because @worker->flags may be * tested without holding any lock in * wq_worker_running(). Without it, NOT_RUNNING test may * fail incorrectly leading to premature concurrency * management operations. */ WARN_ON_ONCE(!(worker_flags & WORKER_UNBOUND)); worker_flags |= WORKER_REBOUND; worker_flags &= ~WORKER_UNBOUND; WRITE_ONCE(worker->flags, worker_flags); } raw_spin_unlock_irq(&pool->lock); } /** * restore_unbound_workers_cpumask - restore cpumask of unbound workers * @pool: unbound pool of interest * @cpu: the CPU which is coming up * * An unbound pool may end up with a cpumask which doesn't have any online * CPUs. When a worker of such pool get scheduled, the scheduler resets * its cpus_allowed. If @cpu is in @pool's cpumask which didn't have any * online CPU before, cpus_allowed of all its workers should be restored. */ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu) { static cpumask_t cpumask; struct worker *worker; lockdep_assert_held(&wq_pool_attach_mutex); /* is @cpu allowed for @pool? */ if (!cpumask_test_cpu(cpu, pool->attrs->cpumask)) return; cpumask_and(&cpumask, pool->attrs->cpumask, cpu_online_mask); /* as we're called from CPU_ONLINE, the following shouldn't fail */ for_each_pool_worker(worker, pool) WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, &cpumask) < 0); } int workqueue_prepare_cpu(unsigned int cpu) { struct worker_pool *pool; for_each_cpu_worker_pool(pool, cpu) { if (pool->nr_workers) continue; if (!create_worker(pool)) return -ENOMEM; } return 0; } int workqueue_online_cpu(unsigned int cpu) { struct worker_pool *pool; struct workqueue_struct *wq; int pi; mutex_lock(&wq_pool_mutex); for_each_pool(pool, pi) { mutex_lock(&wq_pool_attach_mutex); if (pool->cpu == cpu) rebind_workers(pool); else if (pool->cpu < 0) restore_unbound_workers_cpumask(pool, cpu); mutex_unlock(&wq_pool_attach_mutex); } /* update NUMA affinity of unbound workqueues */ list_for_each_entry(wq, &workqueues, list) wq_update_unbound_numa(wq, cpu, true); mutex_unlock(&wq_pool_mutex); return 0; } int workqueue_offline_cpu(unsigned int cpu) { struct workqueue_struct *wq; /* unbinding per-cpu workers should happen on the local CPU */ if (WARN_ON(cpu != smp_processor_id())) return -1; unbind_workers(cpu); /* update NUMA affinity of unbound workqueues */ mutex_lock(&wq_pool_mutex); list_for_each_entry(wq, &workqueues, list) wq_update_unbound_numa(wq, cpu, false); mutex_unlock(&wq_pool_mutex); return 0; } struct work_for_cpu { struct work_struct work; long (*fn)(void *); void *arg; long ret; }; static void work_for_cpu_fn(struct work_struct *work) { struct work_for_cpu *wfc = container_of(work, struct work_for_cpu, work); wfc->ret = wfc->fn(wfc->arg); } /** * work_on_cpu - run a function in thread context on a particular cpu * @cpu: the cpu to run on * @fn: the function to run * @arg: the function arg * * It is up to the caller to ensure that the cpu doesn't go offline. * The caller must not hold any locks which would prevent @fn from completing. * * Return: The value @fn returns. */ long work_on_cpu(int cpu, long (*fn)(void *), void *arg) { struct work_for_cpu wfc = { .fn = fn, .arg = arg }; INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn); schedule_work_on(cpu, &wfc.work); flush_work(&wfc.work); destroy_work_on_stack(&wfc.work); return wfc.ret; } EXPORT_SYMBOL_GPL(work_on_cpu); /** * work_on_cpu_safe - run a function in thread context on a particular cpu * @cpu: the cpu to run on * @fn: the function to run * @arg: the function argument * * Disables CPU hotplug and calls work_on_cpu(). The caller must not hold * any locks which would prevent @fn from completing. * * Return: The value @fn returns. */ long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg) { long ret = -ENODEV; cpus_read_lock(); if (cpu_online(cpu)) ret = work_on_cpu(cpu, fn, arg); cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(work_on_cpu_safe); #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER /** * freeze_workqueues_begin - begin freezing workqueues * * Start freezing workqueues. After this function returns, all freezable * workqueues will queue new works to their inactive_works list instead of * pool->worklist. * * CONTEXT: * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's. */ void freeze_workqueues_begin(void) { struct workqueue_struct *wq; struct pool_workqueue *pwq; mutex_lock(&wq_pool_mutex); WARN_ON_ONCE(workqueue_freezing); workqueue_freezing = true; list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) pwq_adjust_max_active(pwq); mutex_unlock(&wq->mutex); } mutex_unlock(&wq_pool_mutex); } /** * freeze_workqueues_busy - are freezable workqueues still busy? * * Check whether freezing is complete. This function must be called * between freeze_workqueues_begin() and thaw_workqueues(). * * CONTEXT: * Grabs and releases wq_pool_mutex. * * Return: * %true if some freezable workqueues are still busy. %false if freezing * is complete. */ bool freeze_workqueues_busy(void) { bool busy = false; struct workqueue_struct *wq; struct pool_workqueue *pwq; mutex_lock(&wq_pool_mutex); WARN_ON_ONCE(!workqueue_freezing); list_for_each_entry(wq, &workqueues, list) { if (!(wq->flags & WQ_FREEZABLE)) continue; /* * nr_active is monotonically decreasing. It's safe * to peek without lock. */ rcu_read_lock(); for_each_pwq(pwq, wq) { WARN_ON_ONCE(pwq->nr_active < 0); if (pwq->nr_active) { busy = true; rcu_read_unlock(); goto out_unlock; } } rcu_read_unlock(); } out_unlock: mutex_unlock(&wq_pool_mutex); return busy; } /** * thaw_workqueues - thaw workqueues * * Thaw workqueues. Normal queueing is restored and all collected * frozen works are transferred to their respective pool worklists. * * CONTEXT: * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's. */ void thaw_workqueues(void) { struct workqueue_struct *wq; struct pool_workqueue *pwq; mutex_lock(&wq_pool_mutex); if (!workqueue_freezing) goto out_unlock; workqueue_freezing = false; /* restore max_active and repopulate worklist */ list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) pwq_adjust_max_active(pwq); mutex_unlock(&wq->mutex); } out_unlock: mutex_unlock(&wq_pool_mutex); } #endif /* CONFIG_FREEZER */ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask) { LIST_HEAD(ctxs); int ret = 0; struct workqueue_struct *wq; struct apply_wqattrs_ctx *ctx, *n; lockdep_assert_held(&wq_pool_mutex); list_for_each_entry(wq, &workqueues, list) { if (!(wq->flags & WQ_UNBOUND)) continue; /* creating multiple pwqs breaks ordering guarantee */ if (!list_empty(&wq->pwqs)) { if (wq->flags & __WQ_ORDERED_EXPLICIT) continue; wq->flags &= ~__WQ_ORDERED; } ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs, unbound_cpumask); if (!ctx) { ret = -ENOMEM; break; } list_add_tail(&ctx->list, &ctxs); } list_for_each_entry_safe(ctx, n, &ctxs, list) { if (!ret) apply_wqattrs_commit(ctx); apply_wqattrs_cleanup(ctx); } if (!ret) { mutex_lock(&wq_pool_attach_mutex); cpumask_copy(wq_unbound_cpumask, unbound_cpumask); mutex_unlock(&wq_pool_attach_mutex); } return ret; } /** * workqueue_set_unbound_cpumask - Set the low-level unbound cpumask * @cpumask: the cpumask to set * * The low-level workqueues cpumask is a global cpumask that limits * the affinity of all unbound workqueues. This function check the @cpumask * and apply it to all unbound workqueues and updates all pwqs of them. * * Return: 0 - Success * -EINVAL - Invalid @cpumask * -ENOMEM - Failed to allocate memory for attrs or pwqs. */ int workqueue_set_unbound_cpumask(cpumask_var_t cpumask) { int ret = -EINVAL; /* * Not excluding isolated cpus on purpose. * If the user wishes to include them, we allow that. */ cpumask_and(cpumask, cpumask, cpu_possible_mask); if (!cpumask_empty(cpumask)) { apply_wqattrs_lock(); if (cpumask_equal(cpumask, wq_unbound_cpumask)) { ret = 0; goto out_unlock; } ret = workqueue_apply_unbound_cpumask(cpumask); out_unlock: apply_wqattrs_unlock(); } return ret; } #ifdef CONFIG_SYSFS /* * Workqueues with WQ_SYSFS flag set is visible to userland via * /sys/bus/workqueue/devices/WQ_NAME. All visible workqueues have the * following attributes. * * per_cpu RO bool : whether the workqueue is per-cpu or unbound * max_active RW int : maximum number of in-flight work items * * Unbound workqueues have the following extra attributes. * * pool_ids RO int : the associated pool IDs for each node * nice RW int : nice value of the workers * cpumask RW mask : bitmask of allowed CPUs for the workers * numa RW bool : whether enable NUMA affinity */ struct wq_device { struct workqueue_struct *wq; struct device dev; }; static struct workqueue_struct *dev_to_wq(struct device *dev) { struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); return wq_dev->wq; } static ssize_t per_cpu_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", (bool)!(wq->flags & WQ_UNBOUND)); } static DEVICE_ATTR_RO(per_cpu); static ssize_t max_active_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", wq->saved_max_active); } static ssize_t max_active_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); int val; if (sscanf(buf, "%d", &val) != 1 || val <= 0) return -EINVAL; workqueue_set_max_active(wq, val); return count; } static DEVICE_ATTR_RW(max_active); static struct attribute *wq_sysfs_attrs[] = { &dev_attr_per_cpu.attr, &dev_attr_max_active.attr, NULL, }; ATTRIBUTE_GROUPS(wq_sysfs); static ssize_t wq_pool_ids_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); const char *delim = ""; int node, written = 0; cpus_read_lock(); rcu_read_lock(); for_each_node(node) { written += scnprintf(buf + written, PAGE_SIZE - written, "%s%d:%d", delim, node, unbound_pwq_by_node(wq, node)->pool->id); delim = " "; } written += scnprintf(buf + written, PAGE_SIZE - written, "\n"); rcu_read_unlock(); cpus_read_unlock(); return written; } static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); written = scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->nice); mutex_unlock(&wq->mutex); return written; } /* prepare workqueue_attrs for sysfs store operations */ static struct workqueue_attrs *wq_sysfs_prep_attrs(struct workqueue_struct *wq) { struct workqueue_attrs *attrs; lockdep_assert_held(&wq_pool_mutex); attrs = alloc_workqueue_attrs(); if (!attrs) return NULL; copy_workqueue_attrs(attrs, wq->unbound_attrs); return attrs; } static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int ret = -ENOMEM; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (!attrs) goto out_unlock; if (sscanf(buf, "%d", &attrs->nice) == 1 && attrs->nice >= MIN_NICE && attrs->nice <= MAX_NICE) ret = apply_workqueue_attrs_locked(wq, attrs); else ret = -EINVAL; out_unlock: apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(wq->unbound_attrs->cpumask)); mutex_unlock(&wq->mutex); return written; } static ssize_t wq_cpumask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int ret = -ENOMEM; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (!attrs) goto out_unlock; ret = cpumask_parse(buf, attrs->cpumask); if (!ret) ret = apply_workqueue_attrs_locked(wq, attrs); out_unlock: apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_numa_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); written = scnprintf(buf, PAGE_SIZE, "%d\n", !wq->unbound_attrs->no_numa); mutex_unlock(&wq->mutex); return written; } static ssize_t wq_numa_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int v, ret = -ENOMEM; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (!attrs) goto out_unlock; ret = -EINVAL; if (sscanf(buf, "%d", &v) == 1) { attrs->no_numa = !v; ret = apply_workqueue_attrs_locked(wq, attrs); } out_unlock: apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static struct device_attribute wq_sysfs_unbound_attrs[] = { __ATTR(pool_ids, 0444, wq_pool_ids_show, NULL), __ATTR(nice, 0644, wq_nice_show, wq_nice_store), __ATTR(cpumask, 0644, wq_cpumask_show, wq_cpumask_store), __ATTR(numa, 0644, wq_numa_show, wq_numa_store), __ATTR_NULL, }; static struct bus_type wq_subsys = { .name = "workqueue", .dev_groups = wq_sysfs_groups, }; static ssize_t wq_unbound_cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) { int written; mutex_lock(&wq_pool_mutex); written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(wq_unbound_cpumask)); mutex_unlock(&wq_pool_mutex); return written; } static ssize_t wq_unbound_cpumask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { cpumask_var_t cpumask; int ret; if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL)) return -ENOMEM; ret = cpumask_parse(buf, cpumask); if (!ret) ret = workqueue_set_unbound_cpumask(cpumask); free_cpumask_var(cpumask); return ret ? ret : count; } static struct device_attribute wq_sysfs_cpumask_attr = __ATTR(cpumask, 0644, wq_unbound_cpumask_show, wq_unbound_cpumask_store); static int __init wq_sysfs_init(void) { int err; err = subsys_virtual_register(&wq_subsys, NULL); if (err) return err; return device_create_file(wq_subsys.dev_root, &wq_sysfs_cpumask_attr); } core_initcall(wq_sysfs_init); static void wq_device_release(struct device *dev) { struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); kfree(wq_dev); } /** * workqueue_sysfs_register - make a workqueue visible in sysfs * @wq: the workqueue to register * * Expose @wq in sysfs under /sys/bus/workqueue/devices. * alloc_workqueue*() automatically calls this function if WQ_SYSFS is set * which is the preferred method. * * Workqueue user should use this function directly iff it wants to apply * workqueue_attrs before making the workqueue visible in sysfs; otherwise, * apply_workqueue_attrs() may race against userland updating the * attributes. * * Return: 0 on success, -errno on failure. */ int workqueue_sysfs_register(struct workqueue_struct *wq) { struct wq_device *wq_dev; int ret; /* * Adjusting max_active or creating new pwqs by applying * attributes breaks ordering guarantee. Disallow exposing ordered * workqueues. */ if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT)) return -EINVAL; wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL); if (!wq_dev) return -ENOMEM; wq_dev->wq = wq; wq_dev->dev.bus = &wq_subsys; wq_dev->dev.release = wq_device_release; dev_set_name(&wq_dev->dev, "%s", wq->name); /* * unbound_attrs are created separately. Suppress uevent until * everything is ready. */ dev_set_uevent_suppress(&wq_dev->dev, true); ret = device_register(&wq_dev->dev); if (ret) { put_device(&wq_dev->dev); wq->wq_dev = NULL; return ret; } if (wq->flags & WQ_UNBOUND) { struct device_attribute *attr; for (attr = wq_sysfs_unbound_attrs; attr->attr.name; attr++) { ret = device_create_file(&wq_dev->dev, attr); if (ret) { device_unregister(&wq_dev->dev); wq->wq_dev = NULL; return ret; } } } dev_set_uevent_suppress(&wq_dev->dev, false); kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD); return 0; } /** * workqueue_sysfs_unregister - undo workqueue_sysfs_register() * @wq: the workqueue to unregister * * If @wq is registered to sysfs by workqueue_sysfs_register(), unregister. */ static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { struct wq_device *wq_dev = wq->wq_dev; if (!wq->wq_dev) return; wq->wq_dev = NULL; device_unregister(&wq_dev->dev); } #else /* CONFIG_SYSFS */ static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { } #endif /* CONFIG_SYSFS */ /* * Workqueue watchdog. * * Stall may be caused by various bugs - missing WQ_MEM_RECLAIM, illegal * flush dependency, a concurrency managed work item which stays RUNNING * indefinitely. Workqueue stalls can be very difficult to debug as the * usual warning mechanisms don't trigger and internal workqueue state is * largely opaque. * * Workqueue watchdog monitors all worker pools periodically and dumps * state if some pools failed to make forward progress for a while where * forward progress is defined as the first item on ->worklist changing. * * This mechanism is controlled through the kernel parameter * "workqueue.watchdog_thresh" which can be updated at runtime through the * corresponding sysfs parameter file. */ #ifdef CONFIG_WQ_WATCHDOG static unsigned long wq_watchdog_thresh = 30; static struct timer_list wq_watchdog_timer; static unsigned long wq_watchdog_touched = INITIAL_JIFFIES; static DEFINE_PER_CPU(unsigned long, wq_watchdog_touched_cpu) = INITIAL_JIFFIES; static void wq_watchdog_reset_touched(void) { int cpu; wq_watchdog_touched = jiffies; for_each_possible_cpu(cpu) per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies; } static void wq_watchdog_timer_fn(struct timer_list *unused) { unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; bool lockup_detected = false; unsigned long now = jiffies; struct worker_pool *pool; int pi; if (!thresh) return; rcu_read_lock(); for_each_pool(pool, pi) { unsigned long pool_ts, touched, ts; if (list_empty(&pool->worklist)) continue; /* * If a virtual machine is stopped by the host it can look to * the watchdog like a stall. */ kvm_check_and_clear_guest_paused(); /* get the latest of pool and touched timestamps */ if (pool->cpu >= 0) touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu)); else touched = READ_ONCE(wq_watchdog_touched); pool_ts = READ_ONCE(pool->watchdog_ts); if (time_after(pool_ts, touched)) ts = pool_ts; else ts = touched; /* did we stall? */ if (time_after(now, ts + thresh)) { lockup_detected = true; pr_emerg("BUG: workqueue lockup - pool"); pr_cont_pool_info(pool); pr_cont(" stuck for %us!\n", jiffies_to_msecs(now - pool_ts) / 1000); trace_android_vh_wq_lockup_pool(pool->cpu, pool_ts); } } rcu_read_unlock(); if (lockup_detected) show_all_workqueues(); wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh); } notrace void wq_watchdog_touch(int cpu) { unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; unsigned long touch_ts = READ_ONCE(wq_watchdog_touched); unsigned long now = jiffies; if (cpu >= 0) per_cpu(wq_watchdog_touched_cpu, cpu) = now; else WARN_ONCE(1, "%s should be called with valid CPU", __func__); /* Don't unnecessarily store to global cacheline */ if (time_after(now, touch_ts + thresh / 4)) WRITE_ONCE(wq_watchdog_touched, jiffies); } static void wq_watchdog_set_thresh(unsigned long thresh) { wq_watchdog_thresh = 0; del_timer_sync(&wq_watchdog_timer); if (thresh) { wq_watchdog_thresh = thresh; wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh * HZ); } } static int wq_watchdog_param_set_thresh(const char *val, const struct kernel_param *kp) { unsigned long thresh; int ret; ret = kstrtoul(val, 0, &thresh); if (ret) return ret; if (system_wq) wq_watchdog_set_thresh(thresh); else wq_watchdog_thresh = thresh; return 0; } static const struct kernel_param_ops wq_watchdog_thresh_ops = { .set = wq_watchdog_param_set_thresh, .get = param_get_ulong, }; module_param_cb(watchdog_thresh, &wq_watchdog_thresh_ops, &wq_watchdog_thresh, 0644); static void wq_watchdog_init(void) { timer_setup(&wq_watchdog_timer, wq_watchdog_timer_fn, TIMER_DEFERRABLE); wq_watchdog_set_thresh(wq_watchdog_thresh); } #else /* CONFIG_WQ_WATCHDOG */ static inline void wq_watchdog_init(void) { } #endif /* CONFIG_WQ_WATCHDOG */ static void __init wq_numa_init(void) { cpumask_var_t *tbl; int node, cpu; if (num_possible_nodes() <= 1) return; if (wq_disable_numa) { pr_info("workqueue: NUMA affinity support disabled\n"); return; } for_each_possible_cpu(cpu) { if (WARN_ON(cpu_to_node(cpu) == NUMA_NO_NODE)) { pr_warn("workqueue: NUMA node mapping not available for cpu%d, disabling NUMA support\n", cpu); return; } } wq_update_unbound_numa_attrs_buf = alloc_workqueue_attrs(); BUG_ON(!wq_update_unbound_numa_attrs_buf); /* * We want masks of possible CPUs of each node which isn't readily * available. Build one from cpu_to_node() which should have been * fully initialized by now. */ tbl = kcalloc(nr_node_ids, sizeof(tbl[0]), GFP_KERNEL); BUG_ON(!tbl); for_each_node(node) BUG_ON(!zalloc_cpumask_var_node(&tbl[node], GFP_KERNEL, node_online(node) ? node : NUMA_NO_NODE)); for_each_possible_cpu(cpu) { node = cpu_to_node(cpu); cpumask_set_cpu(cpu, tbl[node]); } wq_numa_possible_cpumask = tbl; wq_numa_enabled = true; } /** * workqueue_init_early - early init for workqueue subsystem * * This is the first half of two-staged workqueue subsystem initialization * and invoked as soon as the bare basics - memory allocation, cpumasks and * idr are up. It sets up all the data structures and system workqueues * and allows early boot code to create workqueues and queue/cancel work * items. Actual work item execution starts only after kthreads can be * created and scheduled right before early initcalls. */ void __init workqueue_init_early(void) { int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL }; int i, cpu; BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long)); BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL)); cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(HK_TYPE_WQ)); cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, housekeeping_cpumask(HK_TYPE_DOMAIN)); pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); /* initialize CPU pools */ for_each_possible_cpu(cpu) { struct worker_pool *pool; i = 0; for_each_cpu_worker_pool(pool, cpu) { BUG_ON(init_worker_pool(pool)); pool->cpu = cpu; cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu)); pool->attrs->nice = std_nice[i++]; pool->node = cpu_to_node(cpu); /* alloc pool ID */ mutex_lock(&wq_pool_mutex); BUG_ON(worker_pool_assign_id(pool)); mutex_unlock(&wq_pool_mutex); } } /* create default unbound and ordered wq attrs */ for (i = 0; i < NR_STD_WORKER_POOLS; i++) { struct workqueue_attrs *attrs; BUG_ON(!(attrs = alloc_workqueue_attrs())); attrs->nice = std_nice[i]; unbound_std_wq_attrs[i] = attrs; /* * An ordered wq should have only one pwq as ordering is * guaranteed by max_active which is enforced by pwqs. * Turn off NUMA so that dfl_pwq is used for all nodes. */ BUG_ON(!(attrs = alloc_workqueue_attrs())); attrs->nice = std_nice[i]; attrs->no_numa = true; ordered_wq_attrs[i] = attrs; } system_wq = alloc_workqueue("events", 0, 0); system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI, 0); system_long_wq = alloc_workqueue("events_long", 0, 0); system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_UNBOUND_MAX_ACTIVE); system_freezable_wq = alloc_workqueue("events_freezable", WQ_FREEZABLE, 0); system_power_efficient_wq = alloc_workqueue("events_power_efficient", WQ_POWER_EFFICIENT, 0); system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_power_efficient", WQ_FREEZABLE | WQ_POWER_EFFICIENT, 0); BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq || !system_unbound_wq || !system_freezable_wq || !system_power_efficient_wq || !system_freezable_power_efficient_wq); } /** * workqueue_init - bring workqueue subsystem fully online * * This is the latter half of two-staged workqueue subsystem initialization * and invoked as soon as kthreads can be created and scheduled. * Workqueues have been created and work items queued on them, but there * are no kworkers executing the work items yet. Populate the worker pools * with the initial workers and enable future kworker creations. */ void __init workqueue_init(void) { struct workqueue_struct *wq; struct worker_pool *pool; int cpu, bkt; /* * It'd be simpler to initialize NUMA in workqueue_init_early() but * CPU to node mapping may not be available that early on some * archs such as power and arm64. As per-cpu pools created * previously could be missing node hint and unbound pools NUMA * affinity, fix them up. * * Also, while iterating workqueues, create rescuers if requested. */ wq_numa_init(); mutex_lock(&wq_pool_mutex); for_each_possible_cpu(cpu) { for_each_cpu_worker_pool(pool, cpu) { pool->node = cpu_to_node(cpu); } } list_for_each_entry(wq, &workqueues, list) { wq_update_unbound_numa(wq, smp_processor_id(), true); WARN(init_rescuer(wq), "workqueue: failed to create early rescuer for %s", wq->name); } mutex_unlock(&wq_pool_mutex); /* create the initial workers */ for_each_online_cpu(cpu) { for_each_cpu_worker_pool(pool, cpu) { pool->flags &= ~POOL_DISASSOCIATED; BUG_ON(!create_worker(pool)); } } hash_for_each(unbound_pool_hash, bkt, pool, hash_node) BUG_ON(!create_worker(pool)); wq_online = true; wq_watchdog_init(); } /* * Despite the naming, this is a no-op function which is here only for avoiding * link error. Since compile-time warning may fail to catch, we will need to * emit run-time warning from __flush_workqueue(). */ void __warn_flushing_systemwide_wq(void) { } EXPORT_SYMBOL(__warn_flushing_systemwide_wq); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM vsyscall #if !defined(__VSYSCALL_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) #define __VSYSCALL_TRACE_H #include <linux/tracepoint.h> TRACE_EVENT(emulate_vsyscall, TP_PROTO(int nr), TP_ARGS(nr), TP_STRUCT__entry(__field(int, nr)), TP_fast_assign( __entry->nr = nr; ), TP_printk("nr = %d", __entry->nr) ); #endif #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH ../../arch/x86/entry/vsyscall/ #define TRACE_INCLUDE_FILE vsyscall_trace #include <trace/define_trace.h> |
| 2107 2106 2106 2107 2107 583 583 583 583 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 | // SPDX-License-Identifier: GPL-2.0 /* sysfs entries for device PM */ #include <linux/device.h> #include <linux/kobject.h> #include <linux/string.h> #include <linux/export.h> #include <linux/pm_qos.h> #include <linux/pm_runtime.h> #include <linux/pm_wakeup.h> #include <linux/atomic.h> #include <linux/jiffies.h> #include "power.h" /* * control - Report/change current runtime PM setting of the device * * Runtime power management of a device can be blocked with the help of * this attribute. All devices have one of the following two values for * the power/control file: * * + "auto\n" to allow the device to be power managed at run time; * + "on\n" to prevent the device from being power managed at run time; * * The default for all devices is "auto", which means that devices may be * subject to automatic power management, depending on their drivers. * Changing this attribute to "on" prevents the driver from power managing * the device at run time. Doing that while the device is suspended causes * it to be woken up. * * wakeup - Report/change current wakeup option for device * * Some devices support "wakeup" events, which are hardware signals * used to activate devices from suspended or low power states. Such * devices have one of three values for the sysfs power/wakeup file: * * + "enabled\n" to issue the events; * + "disabled\n" not to do so; or * + "\n" for temporary or permanent inability to issue wakeup. * * (For example, unconfigured USB devices can't issue wakeups.) * * Familiar examples of devices that can issue wakeup events include * keyboards and mice (both PS2 and USB styles), power buttons, modems, * "Wake-On-LAN" Ethernet links, GPIO lines, and more. Some events * will wake the entire system from a suspend state; others may just * wake up the device (if the system as a whole is already active). * Some wakeup events use normal IRQ lines; other use special out * of band signaling. * * It is the responsibility of device drivers to enable (or disable) * wakeup signaling as part of changing device power states, respecting * the policy choices provided through the driver model. * * Devices may not be able to generate wakeup events from all power * states. Also, the events may be ignored in some configurations; * for example, they might need help from other devices that aren't * active, or which may have wakeup disabled. Some drivers rely on * wakeup events internally (unless they are disabled), keeping * their hardware in low power modes whenever they're unused. This * saves runtime power, without requiring system-wide sleep states. * * async - Report/change current async suspend setting for the device * * Asynchronous suspend and resume of the device during system-wide power * state transitions can be enabled by writing "enabled" to this file. * Analogously, if "disabled" is written to this file, the device will be * suspended and resumed synchronously. * * All devices have one of the following two values for power/async: * * + "enabled\n" to permit the asynchronous suspend/resume of the device; * + "disabled\n" to forbid it; * * NOTE: It generally is unsafe to permit the asynchronous suspend/resume * of a device unless it is certain that all of the PM dependencies of the * device are known to the PM core. However, for some devices this * attribute is set to "enabled" by bus type code or device drivers and in * that cases it should be safe to leave the default value. * * autosuspend_delay_ms - Report/change a device's autosuspend_delay value * * Some drivers don't want to carry out a runtime suspend as soon as a * device becomes idle; they want it always to remain idle for some period * of time before suspending it. This period is the autosuspend_delay * value (expressed in milliseconds) and it can be controlled by the user. * If the value is negative then the device will never be runtime * suspended. * * NOTE: The autosuspend_delay_ms attribute and the autosuspend_delay * value are used only if the driver calls pm_runtime_use_autosuspend(). * * wakeup_count - Report the number of wakeup events related to the device */ const char power_group_name[] = "power"; EXPORT_SYMBOL_GPL(power_group_name); static const char ctrl_auto[] = "auto"; static const char ctrl_on[] = "on"; static ssize_t control_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%s\n", dev->power.runtime_auto ? ctrl_auto : ctrl_on); } static ssize_t control_store(struct device * dev, struct device_attribute *attr, const char * buf, size_t n) { device_lock(dev); if (sysfs_streq(buf, ctrl_auto)) pm_runtime_allow(dev); else if (sysfs_streq(buf, ctrl_on)) pm_runtime_forbid(dev); else n = -EINVAL; device_unlock(dev); return n; } static DEVICE_ATTR_RW(control); static ssize_t runtime_active_time_show(struct device *dev, struct device_attribute *attr, char *buf) { u64 tmp = pm_runtime_active_time(dev); do_div(tmp, NSEC_PER_MSEC); return sysfs_emit(buf, "%llu\n", tmp); } static DEVICE_ATTR_RO(runtime_active_time); static ssize_t runtime_suspended_time_show(struct device *dev, struct device_attribute *attr, char *buf) { u64 tmp = pm_runtime_suspended_time(dev); do_div(tmp, NSEC_PER_MSEC); return sysfs_emit(buf, "%llu\n", tmp); } static DEVICE_ATTR_RO(runtime_suspended_time); static ssize_t runtime_status_show(struct device *dev, struct device_attribute *attr, char *buf) { const char *output; if (dev->power.runtime_error) { output = "error"; } else if (dev->power.disable_depth) { output = "unsupported"; } else { switch (dev->power.runtime_status) { case RPM_SUSPENDED: output = "suspended"; break; case RPM_SUSPENDING: output = "suspending"; break; case RPM_RESUMING: output = "resuming"; break; case RPM_ACTIVE: output = "active"; break; default: return -EIO; } } return sysfs_emit(buf, "%s\n", output); } static DEVICE_ATTR_RO(runtime_status); static ssize_t autosuspend_delay_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { if (!dev->power.use_autosuspend) return -EIO; return sysfs_emit(buf, "%d\n", dev->power.autosuspend_delay); } static ssize_t autosuspend_delay_ms_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { long delay; if (!dev->power.use_autosuspend) return -EIO; if (kstrtol(buf, 10, &delay) != 0 || delay != (int) delay) return -EINVAL; device_lock(dev); pm_runtime_set_autosuspend_delay(dev, delay); device_unlock(dev); return n; } static DEVICE_ATTR_RW(autosuspend_delay_ms); static ssize_t pm_qos_resume_latency_us_show(struct device *dev, struct device_attribute *attr, char *buf) { s32 value = dev_pm_qos_requested_resume_latency(dev); if (value == 0) return sysfs_emit(buf, "n/a\n"); if (value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT) value = 0; return sysfs_emit(buf, "%d\n", value); } static ssize_t pm_qos_resume_latency_us_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { s32 value; int ret; if (!kstrtos32(buf, 0, &value)) { /* * Prevent users from writing negative or "no constraint" values * directly. */ if (value < 0 || value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT) return -EINVAL; if (value == 0) value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; } else if (sysfs_streq(buf, "n/a")) { value = 0; } else { return -EINVAL; } ret = dev_pm_qos_update_request(dev->power.qos->resume_latency_req, value); return ret < 0 ? ret : n; } static DEVICE_ATTR_RW(pm_qos_resume_latency_us); static ssize_t pm_qos_latency_tolerance_us_show(struct device *dev, struct device_attribute *attr, char *buf) { s32 value = dev_pm_qos_get_user_latency_tolerance(dev); if (value < 0) return sysfs_emit(buf, "%s\n", "auto"); if (value == PM_QOS_LATENCY_ANY) return sysfs_emit(buf, "%s\n", "any"); return sysfs_emit(buf, "%d\n", value); } static ssize_t pm_qos_latency_tolerance_us_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { s32 value; int ret; if (kstrtos32(buf, 0, &value) == 0) { /* Users can't write negative values directly */ if (value < 0) return -EINVAL; } else { if (sysfs_streq(buf, "auto")) value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT; else if (sysfs_streq(buf, "any")) value = PM_QOS_LATENCY_ANY; else return -EINVAL; } ret = dev_pm_qos_update_user_latency_tolerance(dev, value); return ret < 0 ? ret : n; } static DEVICE_ATTR_RW(pm_qos_latency_tolerance_us); static ssize_t pm_qos_no_power_off_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%d\n", !!(dev_pm_qos_requested_flags(dev) & PM_QOS_FLAG_NO_POWER_OFF)); } static ssize_t pm_qos_no_power_off_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { int ret; if (kstrtoint(buf, 0, &ret)) return -EINVAL; if (ret != 0 && ret != 1) return -EINVAL; ret = dev_pm_qos_update_flags(dev, PM_QOS_FLAG_NO_POWER_OFF, ret); return ret < 0 ? ret : n; } static DEVICE_ATTR_RW(pm_qos_no_power_off); #ifdef CONFIG_PM_SLEEP static const char _enabled[] = "enabled"; static const char _disabled[] = "disabled"; static ssize_t wakeup_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%s\n", device_can_wakeup(dev) ? (device_may_wakeup(dev) ? _enabled : _disabled) : ""); } static ssize_t wakeup_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { if (!device_can_wakeup(dev)) return -EINVAL; if (sysfs_streq(buf, _enabled)) device_set_wakeup_enable(dev, 1); else if (sysfs_streq(buf, _disabled)) device_set_wakeup_enable(dev, 0); else return -EINVAL; return n; } static DEVICE_ATTR_RW(wakeup); static ssize_t wakeup_count_show(struct device *dev, struct device_attribute *attr, char *buf) { unsigned long count; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { count = dev->power.wakeup->wakeup_count; enabled = true; } spin_unlock_irq(&dev->power.lock); if (!enabled) return sysfs_emit(buf, "\n"); return sysfs_emit(buf, "%lu\n", count); } static DEVICE_ATTR_RO(wakeup_count); static ssize_t wakeup_active_count_show(struct device *dev, struct device_attribute *attr, char *buf) { unsigned long count; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { count = dev->power.wakeup->active_count; enabled = true; } spin_unlock_irq(&dev->power.lock); if (!enabled) return sysfs_emit(buf, "\n"); return sysfs_emit(buf, "%lu\n", count); } static DEVICE_ATTR_RO(wakeup_active_count); static ssize_t wakeup_abort_count_show(struct device *dev, struct device_attribute *attr, char *buf) { unsigned long count; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { count = dev->power.wakeup->wakeup_count; enabled = true; } spin_unlock_irq(&dev->power.lock); if (!enabled) return sysfs_emit(buf, "\n"); return sysfs_emit(buf, "%lu\n", count); } static DEVICE_ATTR_RO(wakeup_abort_count); static ssize_t wakeup_expire_count_show(struct device *dev, struct device_attribute *attr, char *buf) { unsigned long count; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { count = dev->power.wakeup->expire_count; enabled = true; } spin_unlock_irq(&dev->power.lock); if (!enabled) return sysfs_emit(buf, "\n"); return sysfs_emit(buf, "%lu\n", count); } static DEVICE_ATTR_RO(wakeup_expire_count); static ssize_t wakeup_active_show(struct device *dev, struct device_attribute *attr, char *buf) { unsigned int active; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { active = dev->power.wakeup->active; enabled = true; } spin_unlock_irq(&dev->power.lock); if (!enabled) return sysfs_emit(buf, "\n"); return sysfs_emit(buf, "%u\n", active); } static DEVICE_ATTR_RO(wakeup_active); static ssize_t wakeup_total_time_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { s64 msec; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { msec = ktime_to_ms(dev->power.wakeup->total_time); enabled = true; } spin_unlock_irq(&dev->power.lock); if (!enabled) return sysfs_emit(buf, "\n"); return sysfs_emit(buf, "%lld\n", msec); } static DEVICE_ATTR_RO(wakeup_total_time_ms); static ssize_t wakeup_max_time_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { s64 msec; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { msec = ktime_to_ms(dev->power.wakeup->max_time); enabled = true; } spin_unlock_irq(&dev->power.lock); if (!enabled) return sysfs_emit(buf, "\n"); return sysfs_emit(buf, "%lld\n", msec); } static DEVICE_ATTR_RO(wakeup_max_time_ms); static ssize_t wakeup_last_time_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { s64 msec; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { msec = ktime_to_ms(dev->power.wakeup->last_time); enabled = true; } spin_unlock_irq(&dev->power.lock); if (!enabled) return sysfs_emit(buf, "\n"); return sysfs_emit(buf, "%lld\n", msec); } static inline int dpm_sysfs_wakeup_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) { if (dev->power.wakeup && dev->power.wakeup->dev) return device_change_owner(dev->power.wakeup->dev, kuid, kgid); return 0; } static DEVICE_ATTR_RO(wakeup_last_time_ms); #ifdef CONFIG_PM_AUTOSLEEP static ssize_t wakeup_prevent_sleep_time_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { s64 msec; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { msec = ktime_to_ms(dev->power.wakeup->prevent_sleep_time); enabled = true; } spin_unlock_irq(&dev->power.lock); if (!enabled) return sysfs_emit(buf, "\n"); return sysfs_emit(buf, "%lld\n", msec); } static DEVICE_ATTR_RO(wakeup_prevent_sleep_time_ms); #endif /* CONFIG_PM_AUTOSLEEP */ #else /* CONFIG_PM_SLEEP */ static inline int dpm_sysfs_wakeup_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) { return 0; } #endif #ifdef CONFIG_PM_ADVANCED_DEBUG static ssize_t runtime_usage_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%d\n", atomic_read(&dev->power.usage_count)); } static DEVICE_ATTR_RO(runtime_usage); static ssize_t runtime_active_kids_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%d\n", dev->power.ignore_children ? 0 : atomic_read(&dev->power.child_count)); } static DEVICE_ATTR_RO(runtime_active_kids); static ssize_t runtime_enabled_show(struct device *dev, struct device_attribute *attr, char *buf) { const char *output; if (dev->power.disable_depth && !dev->power.runtime_auto) output = "disabled & forbidden"; else if (dev->power.disable_depth) output = "disabled"; else if (!dev->power.runtime_auto) output = "forbidden"; else output = "enabled"; return sysfs_emit(buf, "%s\n", output); } static DEVICE_ATTR_RO(runtime_enabled); #ifdef CONFIG_PM_SLEEP static ssize_t async_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%s\n", device_async_suspend_enabled(dev) ? _enabled : _disabled); } static ssize_t async_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { if (sysfs_streq(buf, _enabled)) device_enable_async_suspend(dev); else if (sysfs_streq(buf, _disabled)) device_disable_async_suspend(dev); else return -EINVAL; return n; } static DEVICE_ATTR_RW(async); #endif /* CONFIG_PM_SLEEP */ #endif /* CONFIG_PM_ADVANCED_DEBUG */ static struct attribute *power_attrs[] = { #ifdef CONFIG_PM_ADVANCED_DEBUG #ifdef CONFIG_PM_SLEEP &dev_attr_async.attr, #endif &dev_attr_runtime_status.attr, &dev_attr_runtime_usage.attr, &dev_attr_runtime_active_kids.attr, &dev_attr_runtime_enabled.attr, #endif /* CONFIG_PM_ADVANCED_DEBUG */ NULL, }; static const struct attribute_group pm_attr_group = { .name = power_group_name, .attrs = power_attrs, }; static struct attribute *wakeup_attrs[] = { #ifdef CONFIG_PM_SLEEP &dev_attr_wakeup.attr, &dev_attr_wakeup_count.attr, &dev_attr_wakeup_active_count.attr, &dev_attr_wakeup_abort_count.attr, &dev_attr_wakeup_expire_count.attr, &dev_attr_wakeup_active.attr, &dev_attr_wakeup_total_time_ms.attr, &dev_attr_wakeup_max_time_ms.attr, &dev_attr_wakeup_last_time_ms.attr, #ifdef CONFIG_PM_AUTOSLEEP &dev_attr_wakeup_prevent_sleep_time_ms.attr, #endif #endif NULL, }; static const struct attribute_group pm_wakeup_attr_group = { .name = power_group_name, .attrs = wakeup_attrs, }; static struct attribute *runtime_attrs[] = { #ifndef CONFIG_PM_ADVANCED_DEBUG &dev_attr_runtime_status.attr, #endif &dev_attr_control.attr, &dev_attr_runtime_suspended_time.attr, &dev_attr_runtime_active_time.attr, &dev_attr_autosuspend_delay_ms.attr, NULL, }; static const struct attribute_group pm_runtime_attr_group = { .name = power_group_name, .attrs = runtime_attrs, }; static struct attribute *pm_qos_resume_latency_attrs[] = { &dev_attr_pm_qos_resume_latency_us.attr, NULL, }; static const struct attribute_group pm_qos_resume_latency_attr_group = { .name = power_group_name, .attrs = pm_qos_resume_latency_attrs, }; static struct attribute *pm_qos_latency_tolerance_attrs[] = { &dev_attr_pm_qos_latency_tolerance_us.attr, NULL, }; static const struct attribute_group pm_qos_latency_tolerance_attr_group = { .name = power_group_name, .attrs = pm_qos_latency_tolerance_attrs, }; static struct attribute *pm_qos_flags_attrs[] = { &dev_attr_pm_qos_no_power_off.attr, NULL, }; static const struct attribute_group pm_qos_flags_attr_group = { .name = power_group_name, .attrs = pm_qos_flags_attrs, }; int dpm_sysfs_add(struct device *dev) { int rc; /* No need to create PM sysfs if explicitly disabled. */ if (device_pm_not_required(dev)) return 0; rc = sysfs_create_group(&dev->kobj, &pm_attr_group); if (rc) return rc; if (!pm_runtime_has_no_callbacks(dev)) { rc = sysfs_merge_group(&dev->kobj, &pm_runtime_attr_group); if (rc) goto err_out; } if (device_can_wakeup(dev)) { rc = sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group); if (rc) goto err_runtime; } if (dev->power.set_latency_tolerance) { rc = sysfs_merge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group); if (rc) goto err_wakeup; } rc = pm_wakeup_source_sysfs_add(dev); if (rc) goto err_latency; return 0; err_latency: sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group); err_wakeup: sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group); err_runtime: sysfs_unmerge_group(&dev->kobj, &pm_runtime_attr_group); err_out: sysfs_remove_group(&dev->kobj, &pm_attr_group); return rc; } int dpm_sysfs_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) { int rc; if (device_pm_not_required(dev)) return 0; rc = sysfs_group_change_owner(&dev->kobj, &pm_attr_group, kuid, kgid); if (rc) return rc; if (!pm_runtime_has_no_callbacks(dev)) { rc = sysfs_group_change_owner( &dev->kobj, &pm_runtime_attr_group, kuid, kgid); if (rc) return rc; } if (device_can_wakeup(dev)) { rc = sysfs_group_change_owner(&dev->kobj, &pm_wakeup_attr_group, kuid, kgid); if (rc) return rc; rc = dpm_sysfs_wakeup_change_owner(dev, kuid, kgid); if (rc) return rc; } if (dev->power.set_latency_tolerance) { rc = sysfs_group_change_owner( &dev->kobj, &pm_qos_latency_tolerance_attr_group, kuid, kgid); if (rc) return rc; } return 0; } int wakeup_sysfs_add(struct device *dev) { int ret = sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group); if (!ret) kobject_uevent(&dev->kobj, KOBJ_CHANGE); return ret; } void wakeup_sysfs_remove(struct device *dev) { sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group); kobject_uevent(&dev->kobj, KOBJ_CHANGE); } int pm_qos_sysfs_add_resume_latency(struct device *dev) { return sysfs_merge_group(&dev->kobj, &pm_qos_resume_latency_attr_group); } void pm_qos_sysfs_remove_resume_latency(struct device *dev) { sysfs_unmerge_group(&dev->kobj, &pm_qos_resume_latency_attr_group); } int pm_qos_sysfs_add_flags(struct device *dev) { return sysfs_merge_group(&dev->kobj, &pm_qos_flags_attr_group); } void pm_qos_sysfs_remove_flags(struct device *dev) { sysfs_unmerge_group(&dev->kobj, &pm_qos_flags_attr_group); } int pm_qos_sysfs_add_latency_tolerance(struct device *dev) { return sysfs_merge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group); } void pm_qos_sysfs_remove_latency_tolerance(struct device *dev) { sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group); } void rpm_sysfs_remove(struct device *dev) { sysfs_unmerge_group(&dev->kobj, &pm_runtime_attr_group); } void dpm_sysfs_remove(struct device *dev) { if (device_pm_not_required(dev)) return; sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group); dev_pm_qos_constraints_destroy(dev); rpm_sysfs_remove(dev); sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group); sysfs_remove_group(&dev->kobj, &pm_attr_group); } |
| 3324 57 3224 125 3 118 120 32 1 38 44 43 1 249 115 113 61 80 18 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Generic parts * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/init.h> #include <linux/llc.h> #include <net/llc.h> #include <net/stp.h> #include <net/switchdev.h> #include "br_private.h" /* * Handle changes in state of network devices enslaved to a bridge. * * Note: don't care about up/down if bridge itself is down, because * port state is checked when bridge is brought up. */ static int br_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr); struct netdev_notifier_pre_changeaddr_info *prechaddr_info; struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net_bridge_port *p; struct net_bridge *br; bool notified = false; bool changed_addr; int err; if (netif_is_bridge_master(dev)) { err = br_vlan_bridge_event(dev, event, ptr); if (err) return notifier_from_errno(err); if (event == NETDEV_REGISTER) { /* register of bridge completed, add sysfs entries */ err = br_sysfs_addbr(dev); if (err) return notifier_from_errno(err); return NOTIFY_DONE; } } /* not a port of a bridge */ p = br_port_get_rtnl(dev); if (!p) return NOTIFY_DONE; br = p->br; switch (event) { case NETDEV_CHANGEMTU: br_mtu_auto_adjust(br); break; case NETDEV_PRE_CHANGEADDR: if (br->dev->addr_assign_type == NET_ADDR_SET) break; prechaddr_info = ptr; err = dev_pre_changeaddr_notify(br->dev, prechaddr_info->dev_addr, extack); if (err) return notifier_from_errno(err); break; case NETDEV_CHANGEADDR: spin_lock_bh(&br->lock); br_fdb_changeaddr(p, dev->dev_addr); changed_addr = br_stp_recalculate_bridge_id(br); spin_unlock_bh(&br->lock); if (changed_addr) call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev); break; case NETDEV_CHANGE: br_port_carrier_check(p, ¬ified); break; case NETDEV_FEAT_CHANGE: netdev_update_features(br->dev); break; case NETDEV_DOWN: spin_lock_bh(&br->lock); if (br->dev->flags & IFF_UP) { br_stp_disable_port(p); notified = true; } spin_unlock_bh(&br->lock); break; case NETDEV_UP: if (netif_running(br->dev) && netif_oper_up(dev)) { spin_lock_bh(&br->lock); br_stp_enable_port(p); notified = true; spin_unlock_bh(&br->lock); } break; case NETDEV_UNREGISTER: br_del_if(br, dev); break; case NETDEV_CHANGENAME: err = br_sysfs_renameif(p); if (err) return notifier_from_errno(err); break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlying device to change its type. */ return NOTIFY_BAD; case NETDEV_RESEND_IGMP: /* Propagate to master device */ call_netdevice_notifiers(event, br->dev); break; } if (event != NETDEV_UNREGISTER) br_vlan_port_event(p, event); /* Events that may cause spanning tree to refresh */ if (!notified && (event == NETDEV_CHANGEADDR || event == NETDEV_UP || event == NETDEV_CHANGE || event == NETDEV_DOWN)) br_ifinfo_notify(RTM_NEWLINK, NULL, p); return NOTIFY_DONE; } static struct notifier_block br_device_notifier = { .notifier_call = br_device_event }; /* called with RTNL or RCU */ static int br_switchdev_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); struct net_bridge_port *p; struct net_bridge *br; struct switchdev_notifier_fdb_info *fdb_info; int err = NOTIFY_DONE; p = br_port_get_rtnl_rcu(dev); if (!p) goto out; br = p->br; switch (event) { case SWITCHDEV_FDB_ADD_TO_BRIDGE: fdb_info = ptr; err = br_fdb_external_learn_add(br, p, fdb_info->addr, fdb_info->vid, false); if (err) { err = notifier_from_errno(err); break; } br_fdb_offloaded_set(br, p, fdb_info->addr, fdb_info->vid, true); break; case SWITCHDEV_FDB_DEL_TO_BRIDGE: fdb_info = ptr; err = br_fdb_external_learn_del(br, p, fdb_info->addr, fdb_info->vid, false); if (err) err = notifier_from_errno(err); break; case SWITCHDEV_FDB_OFFLOADED: fdb_info = ptr; br_fdb_offloaded_set(br, p, fdb_info->addr, fdb_info->vid, fdb_info->offloaded); break; case SWITCHDEV_FDB_FLUSH_TO_BRIDGE: fdb_info = ptr; /* Don't delete static entries */ br_fdb_delete_by_port(br, p, fdb_info->vid, 0); break; } out: return err; } static struct notifier_block br_switchdev_notifier = { .notifier_call = br_switchdev_event, }; /* called under rtnl_mutex */ static int br_switchdev_blocking_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr); struct net_device *dev = switchdev_notifier_info_to_dev(ptr); struct switchdev_notifier_brport_info *brport_info; const struct switchdev_brport *b; struct net_bridge_port *p; int err = NOTIFY_DONE; p = br_port_get_rtnl(dev); if (!p) goto out; switch (event) { case SWITCHDEV_BRPORT_OFFLOADED: brport_info = ptr; b = &brport_info->brport; err = br_switchdev_port_offload(p, b->dev, b->ctx, b->atomic_nb, b->blocking_nb, b->tx_fwd_offload, extack); err = notifier_from_errno(err); break; case SWITCHDEV_BRPORT_UNOFFLOADED: brport_info = ptr; b = &brport_info->brport; br_switchdev_port_unoffload(p, b->ctx, b->atomic_nb, b->blocking_nb); break; } out: return err; } static struct notifier_block br_switchdev_blocking_notifier = { .notifier_call = br_switchdev_blocking_event, }; /* br_boolopt_toggle - change user-controlled boolean option * * @br: bridge device * @opt: id of the option to change * @on: new option value * @extack: extack for error messages * * Changes the value of the respective boolean option to @on taking care of * any internal option value mapping and configuration. */ int br_boolopt_toggle(struct net_bridge *br, enum br_boolopt_id opt, bool on, struct netlink_ext_ack *extack) { int err = 0; switch (opt) { case BR_BOOLOPT_NO_LL_LEARN: br_opt_toggle(br, BROPT_NO_LL_LEARN, on); break; case BR_BOOLOPT_MCAST_VLAN_SNOOPING: err = br_multicast_toggle_vlan_snooping(br, on, extack); break; case BR_BOOLOPT_MST_ENABLE: err = br_mst_set_enabled(br, on, extack); break; default: /* shouldn't be called with unsupported options */ WARN_ON(1); break; } return err; } int br_boolopt_get(const struct net_bridge *br, enum br_boolopt_id opt) { switch (opt) { case BR_BOOLOPT_NO_LL_LEARN: return br_opt_get(br, BROPT_NO_LL_LEARN); case BR_BOOLOPT_MCAST_VLAN_SNOOPING: return br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED); case BR_BOOLOPT_MST_ENABLE: return br_opt_get(br, BROPT_MST_ENABLED); default: /* shouldn't be called with unsupported options */ WARN_ON(1); break; } return 0; } int br_boolopt_multi_toggle(struct net_bridge *br, struct br_boolopt_multi *bm, struct netlink_ext_ack *extack) { unsigned long bitmap = bm->optmask; int err = 0; int opt_id; for_each_set_bit(opt_id, &bitmap, BR_BOOLOPT_MAX) { bool on = !!(bm->optval & BIT(opt_id)); err = br_boolopt_toggle(br, opt_id, on, extack); if (err) { br_debug(br, "boolopt multi-toggle error: option: %d current: %d new: %d error: %d\n", opt_id, br_boolopt_get(br, opt_id), on, err); break; } } return err; } void br_boolopt_multi_get(const struct net_bridge *br, struct br_boolopt_multi *bm) { u32 optval = 0; int opt_id; for (opt_id = 0; opt_id < BR_BOOLOPT_MAX; opt_id++) optval |= (br_boolopt_get(br, opt_id) << opt_id); bm->optval = optval; bm->optmask = GENMASK((BR_BOOLOPT_MAX - 1), 0); } /* private bridge options, controlled by the kernel */ void br_opt_toggle(struct net_bridge *br, enum net_bridge_opts opt, bool on) { bool cur = !!br_opt_get(br, opt); br_debug(br, "toggle option: %d state: %d -> %d\n", opt, cur, on); if (cur == on) return; if (on) set_bit(opt, &br->options); else clear_bit(opt, &br->options); } static void __net_exit br_net_exit_batch(struct list_head *net_list) { struct net_device *dev; struct net *net; LIST_HEAD(list); rtnl_lock(); list_for_each_entry(net, net_list, exit_list) for_each_netdev(net, dev) if (netif_is_bridge_master(dev)) br_dev_delete(dev, &list); unregister_netdevice_many(&list); rtnl_unlock(); } static struct pernet_operations br_net_ops = { .exit_batch = br_net_exit_batch, }; static const struct stp_proto br_stp_proto = { .rcv = br_stp_rcv, }; static int __init br_init(void) { int err; BUILD_BUG_ON(sizeof(struct br_input_skb_cb) > sizeof_field(struct sk_buff, cb)); err = stp_proto_register(&br_stp_proto); if (err < 0) { pr_err("bridge: can't register sap for STP\n"); return err; } err = br_fdb_init(); if (err) goto err_out; err = register_pernet_subsys(&br_net_ops); if (err) goto err_out1; err = br_nf_core_init(); if (err) goto err_out2; err = register_netdevice_notifier(&br_device_notifier); if (err) goto err_out3; err = register_switchdev_notifier(&br_switchdev_notifier); if (err) goto err_out4; err = register_switchdev_blocking_notifier(&br_switchdev_blocking_notifier); if (err) goto err_out5; err = br_netlink_init(); if (err) goto err_out6; brioctl_set(br_ioctl_stub); #if IS_ENABLED(CONFIG_ATM_LANE) br_fdb_test_addr_hook = br_fdb_test_addr; #endif #if IS_MODULE(CONFIG_BRIDGE_NETFILTER) pr_info("bridge: filtering via arp/ip/ip6tables is no longer available " "by default. Update your scripts to load br_netfilter if you " "need this.\n"); #endif return 0; err_out6: unregister_switchdev_blocking_notifier(&br_switchdev_blocking_notifier); err_out5: unregister_switchdev_notifier(&br_switchdev_notifier); err_out4: unregister_netdevice_notifier(&br_device_notifier); err_out3: br_nf_core_fini(); err_out2: unregister_pernet_subsys(&br_net_ops); err_out1: br_fdb_fini(); err_out: stp_proto_unregister(&br_stp_proto); return err; } static void __exit br_deinit(void) { stp_proto_unregister(&br_stp_proto); br_netlink_fini(); unregister_switchdev_blocking_notifier(&br_switchdev_blocking_notifier); unregister_switchdev_notifier(&br_switchdev_notifier); unregister_netdevice_notifier(&br_device_notifier); brioctl_set(NULL); unregister_pernet_subsys(&br_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ br_nf_core_fini(); #if IS_ENABLED(CONFIG_ATM_LANE) br_fdb_test_addr_hook = NULL; #endif br_fdb_fini(); } module_init(br_init) module_exit(br_deinit) MODULE_LICENSE("GPL"); MODULE_VERSION(BR_VERSION); MODULE_ALIAS_RTNL_LINK("bridge"); |
| 5870 6908 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_USER_H #define _LINUX_SCHED_USER_H #include <linux/uidgid.h> #include <linux/atomic.h> #include <linux/percpu_counter.h> #include <linux/refcount.h> #include <linux/ratelimit.h> #include <linux/android_kabi.h> /* * Some day this will be a full-fledged user tracking system.. */ struct user_struct { refcount_t __count; /* reference count */ #ifdef CONFIG_EPOLL struct percpu_counter epoll_watches; /* The number of file descriptors currently watched */ #endif unsigned long unix_inflight; /* How many files in flight in unix sockets */ atomic_long_t pipe_bufs; /* how many pages are allocated in pipe buffers */ /* Hash table maintenance information */ struct hlist_node uidhash_node; kuid_t uid; #if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \ defined(CONFIG_NET) || defined(CONFIG_IO_URING) || \ defined(CONFIG_VFIO_PCI_ZDEV_KVM) atomic_long_t locked_vm; #endif #ifdef CONFIG_WATCH_QUEUE atomic_t nr_watches; /* The number of watches this user currently has */ #endif /* Miscellaneous per-user rate limit */ struct ratelimit_state ratelimit; ANDROID_OEM_DATA_ARRAY(1, 2); ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); }; extern int uids_sysfs_init(void); extern struct user_struct *find_user(kuid_t); extern struct user_struct root_user; #define INIT_USER (&root_user) /* per-UID process charging. */ extern struct user_struct * alloc_uid(kuid_t); static inline struct user_struct *get_uid(struct user_struct *u) { refcount_inc(&u->__count); return u; } extern void free_uid(struct user_struct *); #endif /* _LINUX_SCHED_USER_H */ |
| 796 1199 408 1200 1196 6636 6066 1197 1195 1193 1198 1200 1197 14 1200 1173 1174 6634 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 | // SPDX-License-Identifier: GPL-2.0 /* * A fast, small, non-recursive O(n log n) sort for the Linux kernel * * This performs n*log2(n) + 0.37*n + o(n) comparisons on average, * and 1.5*n*log2(n) + O(n) in the (very contrived) worst case. * * Glibc qsort() manages n*log2(n) - 1.26*n for random inputs (1.63*n * better) at the expense of stack usage and much larger code to avoid * quicksort's O(n^2) worst case. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/export.h> #include <linux/sort.h> /** * is_aligned - is this pointer & size okay for word-wide copying? * @base: pointer to data * @size: size of each element * @align: required alignment (typically 4 or 8) * * Returns true if elements can be copied using word loads and stores. * The size must be a multiple of the alignment, and the base address must * be if we do not have CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS. * * For some reason, gcc doesn't know to optimize "if (a & mask || b & mask)" * to "if ((a | b) & mask)", so we do that by hand. */ __attribute_const__ __always_inline static bool is_aligned(const void *base, size_t size, unsigned char align) { unsigned char lsbits = (unsigned char)size; (void)base; #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS lsbits |= (unsigned char)(uintptr_t)base; #endif return (lsbits & (align - 1)) == 0; } /** * swap_words_32 - swap two elements in 32-bit chunks * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size (must be a multiple of 4) * * Exchange the two objects in memory. This exploits base+index addressing, * which basically all CPUs have, to minimize loop overhead computations. * * For some reason, on x86 gcc 7.3.0 adds a redundant test of n at the * bottom of the loop, even though the zero flag is still valid from the * subtract (since the intervening mov instructions don't alter the flags). * Gcc 8.1.0 doesn't have that problem. */ static void swap_words_32(void *a, void *b, size_t n) { do { u32 t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; } while (n); } /** * swap_words_64 - swap two elements in 64-bit chunks * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size (must be a multiple of 8) * * Exchange the two objects in memory. This exploits base+index * addressing, which basically all CPUs have, to minimize loop overhead * computations. * * We'd like to use 64-bit loads if possible. If they're not, emulating * one requires base+index+4 addressing which x86 has but most other * processors do not. If CONFIG_64BIT, we definitely have 64-bit loads, * but it's possible to have 64-bit loads without 64-bit pointers (e.g. * x32 ABI). Are there any cases the kernel needs to worry about? */ static void swap_words_64(void *a, void *b, size_t n) { do { #ifdef CONFIG_64BIT u64 t = *(u64 *)(a + (n -= 8)); *(u64 *)(a + n) = *(u64 *)(b + n); *(u64 *)(b + n) = t; #else /* Use two 32-bit transfers to avoid base+index+4 addressing */ u32 t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; #endif } while (n); } /** * swap_bytes - swap two elements a byte at a time * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size * * This is the fallback if alignment doesn't allow using larger chunks. */ static void swap_bytes(void *a, void *b, size_t n) { do { char t = ((char *)a)[--n]; ((char *)a)[n] = ((char *)b)[n]; ((char *)b)[n] = t; } while (n); } /* * The values are arbitrary as long as they can't be confused with * a pointer, but small integers make for the smallest compare * instructions. */ #define SWAP_WORDS_64 (swap_r_func_t)0 #define SWAP_WORDS_32 (swap_r_func_t)1 #define SWAP_BYTES (swap_r_func_t)2 #define SWAP_WRAPPER (swap_r_func_t)3 struct wrapper { cmp_func_t cmp; swap_func_t swap; }; /* * The function pointer is last to make tail calls most efficient if the * compiler decides not to inline this function. */ static void do_swap(void *a, void *b, size_t size, swap_r_func_t swap_func, const void *priv) { if (swap_func == SWAP_WRAPPER) { ((const struct wrapper *)priv)->swap(a, b, (int)size); return; } if (swap_func == SWAP_WORDS_64) swap_words_64(a, b, size); else if (swap_func == SWAP_WORDS_32) swap_words_32(a, b, size); else if (swap_func == SWAP_BYTES) swap_bytes(a, b, size); else swap_func(a, b, (int)size, priv); } #define _CMP_WRAPPER ((cmp_r_func_t)0L) static int do_cmp(const void *a, const void *b, cmp_r_func_t cmp, const void *priv) { if (cmp == _CMP_WRAPPER) return ((const struct wrapper *)priv)->cmp(a, b); return cmp(a, b, priv); } /** * parent - given the offset of the child, find the offset of the parent. * @i: the offset of the heap element whose parent is sought. Non-zero. * @lsbit: a precomputed 1-bit mask, equal to "size & -size" * @size: size of each element * * In terms of array indexes, the parent of element j = @i/@size is simply * (j-1)/2. But when working in byte offsets, we can't use implicit * truncation of integer divides. * * Fortunately, we only need one bit of the quotient, not the full divide. * @size has a least significant bit. That bit will be clear if @i is * an even multiple of @size, and set if it's an odd multiple. * * Logically, we're doing "if (i & lsbit) i -= size;", but since the * branch is unpredictable, it's done with a bit of clever branch-free * code instead. */ __attribute_const__ __always_inline static size_t parent(size_t i, unsigned int lsbit, size_t size) { i -= size; i -= size & -(i & lsbit); return i / 2; } /** * sort_r - sort an array of elements * @base: pointer to data to sort * @num: number of elements * @size: size of each element * @cmp_func: pointer to comparison function * @swap_func: pointer to swap function or NULL * @priv: third argument passed to comparison function * * This function does a heapsort on the given array. You may provide * a swap_func function if you need to do something more than a memory * copy (e.g. fix up pointers or auxiliary data), but the built-in swap * avoids a slow retpoline and so is significantly faster. * * Sorting time is O(n log n) both on average and worst-case. While * quicksort is slightly faster on average, it suffers from exploitable * O(n*n) worst-case behavior and extra memory requirements that make * it less suitable for kernel use. */ void sort_r(void *base, size_t num, size_t size, cmp_r_func_t cmp_func, swap_r_func_t swap_func, const void *priv) { /* pre-scale counters for performance */ size_t n = num * size, a = (num/2) * size; const unsigned int lsbit = size & -size; /* Used to find parent */ if (!a) /* num < 2 || size == 0 */ return; /* called from 'sort' without swap function, let's pick the default */ if (swap_func == SWAP_WRAPPER && !((struct wrapper *)priv)->swap) swap_func = NULL; if (!swap_func) { if (is_aligned(base, size, 8)) swap_func = SWAP_WORDS_64; else if (is_aligned(base, size, 4)) swap_func = SWAP_WORDS_32; else swap_func = SWAP_BYTES; } /* * Loop invariants: * 1. elements [a,n) satisfy the heap property (compare greater than * all of their children), * 2. elements [n,num*size) are sorted, and * 3. a <= b <= c <= d <= n (whenever they are valid). */ for (;;) { size_t b, c, d; if (a) /* Building heap: sift down --a */ a -= size; else if (n -= size) /* Sorting: Extract root to --n */ do_swap(base, base + n, size, swap_func, priv); else /* Sort complete */ break; /* * Sift element at "a" down into heap. This is the * "bottom-up" variant, which significantly reduces * calls to cmp_func(): we find the sift-down path all * the way to the leaves (one compare per level), then * backtrack to find where to insert the target element. * * Because elements tend to sift down close to the leaves, * this uses fewer compares than doing two per level * on the way down. (A bit more than half as many on * average, 3/4 worst-case.) */ for (b = a; c = 2*b + size, (d = c + size) < n;) b = do_cmp(base + c, base + d, cmp_func, priv) >= 0 ? c : d; if (d == n) /* Special case last leaf with no sibling */ b = c; /* Now backtrack from "b" to the correct location for "a" */ while (b != a && do_cmp(base + a, base + b, cmp_func, priv) >= 0) b = parent(b, lsbit, size); c = b; /* Where "a" belongs */ while (b != a) { /* Shift it into place */ b = parent(b, lsbit, size); do_swap(base + b, base + c, size, swap_func, priv); } } } EXPORT_SYMBOL(sort_r); void sort(void *base, size_t num, size_t size, cmp_func_t cmp_func, swap_func_t swap_func) { struct wrapper w = { .cmp = cmp_func, .swap = swap_func, }; return sort_r(base, num, size, _CMP_WRAPPER, SWAP_WRAPPER, &w); } EXPORT_SYMBOL(sort); |
| 129 2 1499 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * net busy poll support * Copyright(c) 2013 Intel Corporation. * * Author: Eliezer Tamir * * Contact Information: * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> */ #ifndef _LINUX_NET_BUSY_POLL_H #define _LINUX_NET_BUSY_POLL_H #include <linux/netdevice.h> #include <linux/sched/clock.h> #include <linux/sched/signal.h> #include <net/ip.h> /* 0 - Reserved to indicate value not set * 1..NR_CPUS - Reserved for sender_cpu * NR_CPUS+1..~0 - Region available for NAPI IDs */ #define MIN_NAPI_ID ((unsigned int)(NR_CPUS + 1)) #define BUSY_POLL_BUDGET 8 #ifdef CONFIG_NET_RX_BUSY_POLL struct napi_struct; extern unsigned int sysctl_net_busy_read __read_mostly; extern unsigned int sysctl_net_busy_poll __read_mostly; static inline bool net_busy_loop_on(void) { return READ_ONCE(sysctl_net_busy_poll); } static inline bool sk_can_busy_loop(const struct sock *sk) { return READ_ONCE(sk->sk_ll_usec) && !signal_pending(current); } bool sk_busy_loop_end(void *p, unsigned long start_time); void napi_busy_loop(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), void *loop_end_arg, bool prefer_busy_poll, u16 budget); #else /* CONFIG_NET_RX_BUSY_POLL */ static inline unsigned long net_busy_loop_on(void) { return 0; } static inline bool sk_can_busy_loop(struct sock *sk) { return false; } #endif /* CONFIG_NET_RX_BUSY_POLL */ static inline unsigned long busy_loop_current_time(void) { #ifdef CONFIG_NET_RX_BUSY_POLL return (unsigned long)(ktime_get_ns() >> 10); #else return 0; #endif } /* in poll/select we use the global sysctl_net_ll_poll value */ static inline bool busy_loop_timeout(unsigned long start_time) { #ifdef CONFIG_NET_RX_BUSY_POLL unsigned long bp_usec = READ_ONCE(sysctl_net_busy_poll); if (bp_usec) { unsigned long end_time = start_time + bp_usec; unsigned long now = busy_loop_current_time(); return time_after(now, end_time); } #endif return true; } static inline bool sk_busy_loop_timeout(struct sock *sk, unsigned long start_time) { #ifdef CONFIG_NET_RX_BUSY_POLL unsigned long bp_usec = READ_ONCE(sk->sk_ll_usec); if (bp_usec) { unsigned long end_time = start_time + bp_usec; unsigned long now = busy_loop_current_time(); return time_after(now, end_time); } #endif return true; } static inline void sk_busy_loop(struct sock *sk, int nonblock) { #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int napi_id = READ_ONCE(sk->sk_napi_id); if (napi_id >= MIN_NAPI_ID) napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk, READ_ONCE(sk->sk_prefer_busy_poll), READ_ONCE(sk->sk_busy_poll_budget) ?: BUSY_POLL_BUDGET); #endif } /* used in the NIC receive handler to mark the skb */ static inline void skb_mark_napi_id(struct sk_buff *skb, struct napi_struct *napi) { #ifdef CONFIG_NET_RX_BUSY_POLL /* If the skb was already marked with a valid NAPI ID, avoid overwriting * it. */ if (skb->napi_id < MIN_NAPI_ID) skb->napi_id = napi->napi_id; #endif } /* used in the protocol hanlder to propagate the napi_id to the socket */ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL if (unlikely(READ_ONCE(sk->sk_napi_id) != skb->napi_id)) WRITE_ONCE(sk->sk_napi_id, skb->napi_id); #endif sk_rx_queue_update(sk, skb); } /* Variant of sk_mark_napi_id() for passive flow setup, * as sk->sk_napi_id and sk->sk_rx_queue_mapping content * needs to be set. */ static inline void sk_mark_napi_id_set(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL WRITE_ONCE(sk->sk_napi_id, skb->napi_id); #endif sk_rx_queue_set(sk, skb); } static inline void __sk_mark_napi_id_once(struct sock *sk, unsigned int napi_id) { #ifdef CONFIG_NET_RX_BUSY_POLL if (!READ_ONCE(sk->sk_napi_id)) WRITE_ONCE(sk->sk_napi_id, napi_id); #endif } /* variant used for unconnected sockets */ static inline void sk_mark_napi_id_once(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL __sk_mark_napi_id_once(sk, skb->napi_id); #endif } static inline void sk_mark_napi_id_once_xdp(struct sock *sk, const struct xdp_buff *xdp) { #ifdef CONFIG_NET_RX_BUSY_POLL __sk_mark_napi_id_once(sk, xdp->rxq->napi_id); #endif } #endif /* _LINUX_NET_BUSY_POLL_H */ |
| 80 1459 1447 371 1109 1538 1 1 1 1535 1535 89 1454 422 1144 1440 1576 178 81 1460 371 1200 1444 1578 382 382 395 16 196 195 382 382 395 395 5 1 1 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/read_write.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/slab.h> #include <linux/stat.h> #include <linux/sched/xacct.h> #include <linux/fcntl.h> #include <linux/file.h> #include <linux/uio.h> #include <linux/fsnotify.h> #include <linux/security.h> #include <linux/export.h> #include <linux/syscalls.h> #include <linux/pagemap.h> #include <linux/splice.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/fs.h> #include "internal.h" #include <linux/uaccess.h> #include <asm/unistd.h> const struct file_operations generic_ro_fops = { .llseek = generic_file_llseek, .read_iter = generic_file_read_iter, .mmap = generic_file_readonly_mmap, .splice_read = generic_file_splice_read, }; EXPORT_SYMBOL(generic_ro_fops); static inline bool unsigned_offsets(struct file *file) { return file->f_mode & FMODE_UNSIGNED_OFFSET; } /** * vfs_setpos - update the file offset for lseek * @file: file structure in question * @offset: file offset to seek to * @maxsize: maximum file size * * This is a low-level filesystem helper for updating the file offset to * the value specified by @offset if the given offset is valid and it is * not equal to the current file offset. * * Return the specified offset on success and -EINVAL on invalid offset. */ loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize) { if (offset < 0 && !unsigned_offsets(file)) return -EINVAL; if (offset > maxsize) return -EINVAL; if (offset != file->f_pos) { file->f_pos = offset; file->f_version = 0; } return offset; } EXPORT_SYMBOL(vfs_setpos); /** * generic_file_llseek_size - generic llseek implementation for regular files * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @size: max size of this file in file system * @eof: offset used for SEEK_END position * * This is a variant of generic_file_llseek that allows passing in a custom * maximum file size and a custom EOF position, for e.g. hashed directories * * Synchronization: * SEEK_SET and SEEK_END are unsynchronized (but atomic on 64bit platforms) * SEEK_CUR is synchronized against other SEEK_CURs, but not read/writes. * read/writes behave like SEEK_SET against seeks. */ loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof) { switch (whence) { case SEEK_END: offset += eof; break; case SEEK_CUR: /* * Here we special-case the lseek(fd, 0, SEEK_CUR) * position-querying operation. Avoid rewriting the "same" * f_pos value back to the file because a concurrent read(), * write() or lseek() might have altered it */ if (offset == 0) return file->f_pos; /* * f_lock protects against read/modify/write race with other * SEEK_CURs. Note that parallel writes and reads behave * like SEEK_SET. */ spin_lock(&file->f_lock); offset = vfs_setpos(file, file->f_pos + offset, maxsize); spin_unlock(&file->f_lock); return offset; case SEEK_DATA: /* * In the generic case the entire file is data, so as long as * offset isn't at the end of the file then the offset is data. */ if ((unsigned long long)offset >= eof) return -ENXIO; break; case SEEK_HOLE: /* * There is a virtual hole at the end of the file, so as long as * offset isn't i_size or larger, return i_size. */ if ((unsigned long long)offset >= eof) return -ENXIO; offset = eof; break; } return vfs_setpos(file, offset, maxsize); } EXPORT_SYMBOL(generic_file_llseek_size); /** * generic_file_llseek - generic llseek implementation for regular files * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * * This is a generic implemenation of ->llseek useable for all normal local * filesystems. It just updates the file offset to the value specified by * @offset and @whence. */ loff_t generic_file_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; return generic_file_llseek_size(file, offset, whence, inode->i_sb->s_maxbytes, i_size_read(inode)); } EXPORT_SYMBOL(generic_file_llseek); /** * fixed_size_llseek - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @size: size of the file * */ loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size) { switch (whence) { case SEEK_SET: case SEEK_CUR: case SEEK_END: return generic_file_llseek_size(file, offset, whence, size, size); default: return -EINVAL; } } EXPORT_SYMBOL(fixed_size_llseek); /** * no_seek_end_llseek - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * */ loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence) { switch (whence) { case SEEK_SET: case SEEK_CUR: return generic_file_llseek_size(file, offset, whence, OFFSET_MAX, 0); default: return -EINVAL; } } EXPORT_SYMBOL(no_seek_end_llseek); /** * no_seek_end_llseek_size - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @size: maximal offset allowed * */ loff_t no_seek_end_llseek_size(struct file *file, loff_t offset, int whence, loff_t size) { switch (whence) { case SEEK_SET: case SEEK_CUR: return generic_file_llseek_size(file, offset, whence, size, 0); default: return -EINVAL; } } EXPORT_SYMBOL(no_seek_end_llseek_size); /** * noop_llseek - No Operation Performed llseek implementation * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * * This is an implementation of ->llseek useable for the rare special case when * userspace expects the seek to succeed but the (device) file is actually not * able to perform the seek. In this case you use noop_llseek() instead of * falling back to the default implementation of ->llseek. */ loff_t noop_llseek(struct file *file, loff_t offset, int whence) { return file->f_pos; } EXPORT_SYMBOL(noop_llseek); loff_t default_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file_inode(file); loff_t retval; inode_lock(inode); switch (whence) { case SEEK_END: offset += i_size_read(inode); break; case SEEK_CUR: if (offset == 0) { retval = file->f_pos; goto out; } offset += file->f_pos; break; case SEEK_DATA: /* * In the generic case the entire file is data, so as * long as offset isn't at the end of the file then the * offset is data. */ if (offset >= inode->i_size) { retval = -ENXIO; goto out; } break; case SEEK_HOLE: /* * There is a virtual hole at the end of the file, so * as long as offset isn't i_size or larger, return * i_size. */ if (offset >= inode->i_size) { retval = -ENXIO; goto out; } offset = inode->i_size; break; } retval = -EINVAL; if (offset >= 0 || unsigned_offsets(file)) { if (offset != file->f_pos) { file->f_pos = offset; file->f_version = 0; } retval = offset; } out: inode_unlock(inode); return retval; } EXPORT_SYMBOL(default_llseek); loff_t vfs_llseek(struct file *file, loff_t offset, int whence) { if (!(file->f_mode & FMODE_LSEEK)) return -ESPIPE; return file->f_op->llseek(file, offset, whence); } EXPORT_SYMBOL(vfs_llseek); static off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence) { off_t retval; struct fd f = fdget_pos(fd); if (!f.file) return -EBADF; retval = -EINVAL; if (whence <= SEEK_MAX) { loff_t res = vfs_llseek(f.file, offset, whence); retval = res; if (res != (loff_t)retval) retval = -EOVERFLOW; /* LFS: should only happen on 32 bit platforms */ } fdput_pos(f); return retval; } SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence) { return ksys_lseek(fd, offset, whence); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE3(lseek, unsigned int, fd, compat_off_t, offset, unsigned int, whence) { return ksys_lseek(fd, offset, whence); } #endif #if !defined(CONFIG_64BIT) || defined(CONFIG_COMPAT) || \ defined(__ARCH_WANT_SYS_LLSEEK) SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high, unsigned long, offset_low, loff_t __user *, result, unsigned int, whence) { int retval; struct fd f = fdget_pos(fd); loff_t offset; if (!f.file) return -EBADF; retval = -EINVAL; if (whence > SEEK_MAX) goto out_putf; offset = vfs_llseek(f.file, ((loff_t) offset_high << 32) | offset_low, whence); retval = (int)offset; if (offset >= 0) { retval = -EFAULT; if (!copy_to_user(result, &offset, sizeof(offset))) retval = 0; } out_putf: fdput_pos(f); return retval; } #endif int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count) { if (unlikely((ssize_t) count < 0)) return -EINVAL; if (ppos) { loff_t pos = *ppos; if (unlikely(pos < 0)) { if (!unsigned_offsets(file)) return -EINVAL; if (count >= -pos) /* both values are in 0..LLONG_MAX */ return -EOVERFLOW; } else if (unlikely((loff_t) (pos + count) < 0)) { if (!unsigned_offsets(file)) return -EINVAL; } } return security_file_permission(file, read_write == READ ? MAY_READ : MAY_WRITE); } EXPORT_SYMBOL(rw_verify_area); static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) { struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = (ppos ? *ppos : 0); iov_iter_ubuf(&iter, ITER_DEST, buf, len); ret = call_read_iter(filp, &kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); if (ppos) *ppos = kiocb.ki_pos; return ret; } static int warn_unsupported(struct file *file, const char *op) { pr_warn_ratelimited( "kernel %s not supported for file %pD4 (pid: %d comm: %.20s)\n", op, file, current->pid, current->comm); return -EINVAL; } ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { struct kvec iov = { .iov_base = buf, .iov_len = min_t(size_t, count, MAX_RW_COUNT), }; struct kiocb kiocb; struct iov_iter iter; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_READ))) return -EINVAL; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; /* * Also fail if ->read_iter and ->read are both wired up as that * implies very convoluted semantics. */ if (unlikely(!file->f_op->read_iter || file->f_op->read)) return warn_unsupported(file, "read"); init_sync_kiocb(&kiocb, file); kiocb.ki_pos = pos ? *pos : 0; iov_iter_kvec(&iter, ITER_DEST, &iov, 1, iov.iov_len); ret = file->f_op->read_iter(&kiocb, &iter); if (ret > 0) { if (pos) *pos = kiocb.ki_pos; fsnotify_access(file); add_rchar(current, ret); } inc_syscr(current); return ret; } ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { ssize_t ret; ret = rw_verify_area(READ, file, pos, count); if (ret) return ret; return __kernel_read(file, buf, count, pos); } EXPORT_SYMBOL(kernel_read); ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { ssize_t ret; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; if (unlikely(!access_ok(buf, count))) return -EFAULT; ret = rw_verify_area(READ, file, pos, count); if (ret) return ret; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; if (file->f_op->read) ret = file->f_op->read(file, buf, count, pos); else if (file->f_op->read_iter) ret = new_sync_read(file, buf, count, pos); else ret = -EINVAL; if (ret > 0) { fsnotify_access(file); add_rchar(current, ret); } inc_syscr(current); return ret; } static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos) { struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = (ppos ? *ppos : 0); iov_iter_ubuf(&iter, ITER_SOURCE, (void __user *)buf, len); ret = call_write_iter(filp, &kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); if (ret > 0 && ppos) *ppos = kiocb.ki_pos; return ret; } /* caller is responsible for file_start_write/file_end_write */ ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *pos) { struct kiocb kiocb; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE))) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; /* * Also fail if ->write_iter and ->write are both wired up as that * implies very convoluted semantics. */ if (unlikely(!file->f_op->write_iter || file->f_op->write)) return warn_unsupported(file, "write"); init_sync_kiocb(&kiocb, file); kiocb.ki_pos = pos ? *pos : 0; ret = file->f_op->write_iter(&kiocb, from); if (ret > 0) { if (pos) *pos = kiocb.ki_pos; fsnotify_modify(file); add_wchar(current, ret); } inc_syscw(current); return ret; } /* caller is responsible for file_start_write/file_end_write */ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { struct kvec iov = { .iov_base = (void *)buf, .iov_len = min_t(size_t, count, MAX_RW_COUNT), }; struct iov_iter iter; iov_iter_kvec(&iter, ITER_SOURCE, &iov, 1, iov.iov_len); return __kernel_write_iter(file, &iter, pos); } /* * This "EXPORT_SYMBOL_GPL()" is more of a "EXPORT_SYMBOL_DONTUSE()", * but autofs is one of the few internal kernel users that actually * wants this _and_ can be built as a module. So we need to export * this symbol for autofs, even though it really isn't appropriate * for any other kernel modules. */ EXPORT_SYMBOL_GPL(__kernel_write); ssize_t kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { ssize_t ret; ret = rw_verify_area(WRITE, file, pos, count); if (ret) return ret; file_start_write(file); ret = __kernel_write(file, buf, count, pos); file_end_write(file); return ret; } EXPORT_SYMBOL(kernel_write); ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { ssize_t ret; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; if (unlikely(!access_ok(buf, count))) return -EFAULT; ret = rw_verify_area(WRITE, file, pos, count); if (ret) return ret; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; file_start_write(file); if (file->f_op->write) ret = file->f_op->write(file, buf, count, pos); else if (file->f_op->write_iter) ret = new_sync_write(file, buf, count, pos); else ret = -EINVAL; if (ret > 0) { fsnotify_modify(file); add_wchar(current, ret); } inc_syscw(current); file_end_write(file); return ret; } /* file_ppos returns &file->f_pos or NULL if file is stream */ static inline loff_t *file_ppos(struct file *file) { return file->f_mode & FMODE_STREAM ? NULL : &file->f_pos; } ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { loff_t pos, *ppos = file_ppos(f.file); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_read(f.file, buf, count, ppos); if (ret >= 0 && ppos) f.file->f_pos = pos; fdput_pos(f); } return ret; } SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) { return ksys_read(fd, buf, count); } ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { loff_t pos, *ppos = file_ppos(f.file); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_write(f.file, buf, count, ppos); if (ret >= 0 && ppos) f.file->f_pos = pos; fdput_pos(f); } return ret; } SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf, size_t, count) { return ksys_write(fd, buf, count); } ssize_t ksys_pread64(unsigned int fd, char __user *buf, size_t count, loff_t pos) { struct fd f; ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; f = fdget(fd); if (f.file) { ret = -ESPIPE; if (f.file->f_mode & FMODE_PREAD) ret = vfs_read(f.file, buf, count, &pos); fdput(f); } return ret; } SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf, size_t, count, loff_t, pos) { return ksys_pread64(fd, buf, count, pos); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_PREAD64) COMPAT_SYSCALL_DEFINE5(pread64, unsigned int, fd, char __user *, buf, size_t, count, compat_arg_u64_dual(pos)) { return ksys_pread64(fd, buf, count, compat_arg_u64_glue(pos)); } #endif ssize_t ksys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos) { struct fd f; ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; f = fdget(fd); if (f.file) { ret = -ESPIPE; if (f.file->f_mode & FMODE_PWRITE) ret = vfs_write(f.file, buf, count, &pos); fdput(f); } return ret; } SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf, size_t, count, loff_t, pos) { return ksys_pwrite64(fd, buf, count, pos); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_PWRITE64) COMPAT_SYSCALL_DEFINE5(pwrite64, unsigned int, fd, const char __user *, buf, size_t, count, compat_arg_u64_dual(pos)) { return ksys_pwrite64(fd, buf, count, compat_arg_u64_glue(pos)); } #endif static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, loff_t *ppos, int type, rwf_t flags) { struct kiocb kiocb; ssize_t ret; init_sync_kiocb(&kiocb, filp); ret = kiocb_set_rw_flags(&kiocb, flags); if (ret) return ret; kiocb.ki_pos = (ppos ? *ppos : 0); if (type == READ) ret = call_read_iter(filp, &kiocb, iter); else ret = call_write_iter(filp, &kiocb, iter); BUG_ON(ret == -EIOCBQUEUED); if (ppos) *ppos = kiocb.ki_pos; return ret; } /* Do it by hand, with file-ops */ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, loff_t *ppos, int type, rwf_t flags) { ssize_t ret = 0; if (flags & ~RWF_HIPRI) return -EOPNOTSUPP; while (iov_iter_count(iter)) { struct iovec iovec = iov_iter_iovec(iter); ssize_t nr; if (type == READ) { nr = filp->f_op->read(filp, iovec.iov_base, iovec.iov_len, ppos); } else { nr = filp->f_op->write(filp, iovec.iov_base, iovec.iov_len, ppos); } if (nr < 0) { if (!ret) ret = nr; break; } ret += nr; if (nr != iovec.iov_len) break; iov_iter_advance(iter, nr); } return ret; } static ssize_t do_iter_read(struct file *file, struct iov_iter *iter, loff_t *pos, rwf_t flags) { size_t tot_len; ssize_t ret = 0; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) goto out; ret = rw_verify_area(READ, file, pos, tot_len); if (ret < 0) return ret; if (file->f_op->read_iter) ret = do_iter_readv_writev(file, iter, pos, READ, flags); else ret = do_loop_readv_writev(file, iter, pos, READ, flags); out: if (ret >= 0) fsnotify_access(file); return ret; } ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, struct iov_iter *iter) { size_t tot_len; ssize_t ret = 0; if (!file->f_op->read_iter) return -EINVAL; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) goto out; ret = rw_verify_area(READ, file, &iocb->ki_pos, tot_len); if (ret < 0) return ret; ret = call_read_iter(file, iocb, iter); out: if (ret >= 0) fsnotify_access(file); return ret; } EXPORT_SYMBOL(vfs_iocb_iter_read); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags) { if (!file->f_op->read_iter) return -EINVAL; return do_iter_read(file, iter, ppos, flags); } EXPORT_SYMBOL(vfs_iter_read); static ssize_t do_iter_write(struct file *file, struct iov_iter *iter, loff_t *pos, rwf_t flags) { size_t tot_len; ssize_t ret = 0; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) return 0; ret = rw_verify_area(WRITE, file, pos, tot_len); if (ret < 0) return ret; if (file->f_op->write_iter) ret = do_iter_readv_writev(file, iter, pos, WRITE, flags); else ret = do_loop_readv_writev(file, iter, pos, WRITE, flags); if (ret > 0) fsnotify_modify(file); return ret; } ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter) { size_t tot_len; ssize_t ret = 0; if (!file->f_op->write_iter) return -EINVAL; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) return 0; ret = rw_verify_area(WRITE, file, &iocb->ki_pos, tot_len); if (ret < 0) return ret; ret = call_write_iter(file, iocb, iter); if (ret > 0) fsnotify_modify(file); return ret; } EXPORT_SYMBOL(vfs_iocb_iter_write); ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags) { if (!file->f_op->write_iter) return -EINVAL; return do_iter_write(file, iter, ppos, flags); } EXPORT_SYMBOL(vfs_iter_write); static ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; ssize_t ret; ret = import_iovec(ITER_DEST, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); if (ret >= 0) { ret = do_iter_read(file, &iter, pos, flags); kfree(iov); } return ret; } static ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; ssize_t ret; ret = import_iovec(ITER_SOURCE, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); if (ret >= 0) { file_start_write(file); ret = do_iter_write(file, &iter, pos, flags); file_end_write(file); kfree(iov); } return ret; } static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, rwf_t flags) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { loff_t pos, *ppos = file_ppos(f.file); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_readv(f.file, vec, vlen, ppos, flags); if (ret >= 0 && ppos) f.file->f_pos = pos; fdput_pos(f); } if (ret > 0) add_rchar(current, ret); inc_syscr(current); return ret; } static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, rwf_t flags) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { loff_t pos, *ppos = file_ppos(f.file); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_writev(f.file, vec, vlen, ppos, flags); if (ret >= 0 && ppos) f.file->f_pos = pos; fdput_pos(f); } if (ret > 0) add_wchar(current, ret); inc_syscw(current); return ret; } static inline loff_t pos_from_hilo(unsigned long high, unsigned long low) { #define HALF_LONG_BITS (BITS_PER_LONG / 2) return (((loff_t)high << HALF_LONG_BITS) << HALF_LONG_BITS) | low; } static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags) { struct fd f; ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; f = fdget(fd); if (f.file) { ret = -ESPIPE; if (f.file->f_mode & FMODE_PREAD) ret = vfs_readv(f.file, vec, vlen, &pos, flags); fdput(f); } if (ret > 0) add_rchar(current, ret); inc_syscr(current); return ret; } static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags) { struct fd f; ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; f = fdget(fd); if (f.file) { ret = -ESPIPE; if (f.file->f_mode & FMODE_PWRITE) ret = vfs_writev(f.file, vec, vlen, &pos, flags); fdput(f); } if (ret > 0) add_wchar(current, ret); inc_syscw(current); return ret; } SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen) { return do_readv(fd, vec, vlen, 0); } SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen) { return do_writev(fd, vec, vlen, 0); } SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) { loff_t pos = pos_from_hilo(pos_h, pos_l); return do_preadv(fd, vec, vlen, pos, 0); } SYSCALL_DEFINE6(preadv2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, rwf_t, flags) { loff_t pos = pos_from_hilo(pos_h, pos_l); if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) { loff_t pos = pos_from_hilo(pos_h, pos_l); return do_pwritev(fd, vec, vlen, pos, 0); } SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, rwf_t, flags) { loff_t pos = pos_from_hilo(pos_h, pos_l); if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } /* * Various compat syscalls. Note that they all pretend to take a native * iovec - import_iovec will properly treat those as compat_iovecs based on * in_compat_syscall(). */ #ifdef CONFIG_COMPAT #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos) { return do_preadv(fd, vec, vlen, pos, 0); } #endif COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd, const struct iovec __user *, vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; return do_preadv(fd, vec, vlen, pos, 0); } #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos, rwf_t, flags) { if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } #endif COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd, const struct iovec __user *, vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64 COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos) { return do_pwritev(fd, vec, vlen, pos, 0); } #endif COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd, const struct iovec __user *,vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; return do_pwritev(fd, vec, vlen, pos, 0); } #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos, rwf_t, flags) { if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } #endif COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd, const struct iovec __user *,vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } #endif /* CONFIG_COMPAT */ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, size_t count, loff_t max) { struct fd in, out; struct inode *in_inode, *out_inode; struct pipe_inode_info *opipe; loff_t pos; loff_t out_pos; ssize_t retval; int fl; /* * Get input file, and verify that it is ok.. */ retval = -EBADF; in = fdget(in_fd); if (!in.file) goto out; if (!(in.file->f_mode & FMODE_READ)) goto fput_in; retval = -ESPIPE; if (!ppos) { pos = in.file->f_pos; } else { pos = *ppos; if (!(in.file->f_mode & FMODE_PREAD)) goto fput_in; } retval = rw_verify_area(READ, in.file, &pos, count); if (retval < 0) goto fput_in; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; /* * Get output file, and verify that it is ok.. */ retval = -EBADF; out = fdget(out_fd); if (!out.file) goto fput_in; if (!(out.file->f_mode & FMODE_WRITE)) goto fput_out; in_inode = file_inode(in.file); out_inode = file_inode(out.file); out_pos = out.file->f_pos; if (!max) max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes); if (unlikely(pos + count > max)) { retval = -EOVERFLOW; if (pos >= max) goto fput_out; count = max - pos; } fl = 0; #if 0 /* * We need to debate whether we can enable this or not. The * man page documents EAGAIN return for the output at least, * and the application is arguably buggy if it doesn't expect * EAGAIN on a non-blocking file descriptor. */ if (in.file->f_flags & O_NONBLOCK) fl = SPLICE_F_NONBLOCK; #endif opipe = get_pipe_info(out.file, true); if (!opipe) { retval = rw_verify_area(WRITE, out.file, &out_pos, count); if (retval < 0) goto fput_out; file_start_write(out.file); retval = do_splice_direct(in.file, &pos, out.file, &out_pos, count, fl); file_end_write(out.file); } else { if (out.file->f_flags & O_NONBLOCK) fl |= SPLICE_F_NONBLOCK; retval = splice_file_to_pipe(in.file, opipe, &pos, count, fl); } if (retval > 0) { add_rchar(current, retval); add_wchar(current, retval); fsnotify_access(in.file); fsnotify_modify(out.file); out.file->f_pos = out_pos; if (ppos) *ppos = pos; else in.file->f_pos = pos; } inc_syscr(current); inc_syscw(current); if (pos > max) retval = -EOVERFLOW; fput_out: fdput(out); fput_in: fdput(in); out: return retval; } SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, off_t __user *, offset, size_t, count) { loff_t pos; off_t off; ssize_t ret; if (offset) { if (unlikely(get_user(off, offset))) return -EFAULT; pos = off; ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, loff_t __user *, offset, size_t, count) { loff_t pos; ssize_t ret; if (offset) { if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t)))) return -EFAULT; ret = do_sendfile(out_fd, in_fd, &pos, count, 0); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, compat_off_t __user *, offset, compat_size_t, count) { loff_t pos; off_t off; ssize_t ret; if (offset) { if (unlikely(get_user(off, offset))) return -EFAULT; pos = off; ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, compat_loff_t __user *, offset, compat_size_t, count) { loff_t pos; ssize_t ret; if (offset) { if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t)))) return -EFAULT; ret = do_sendfile(out_fd, in_fd, &pos, count, 0); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } #endif /** * generic_copy_file_range - copy data between two files * @file_in: file structure to read from * @pos_in: file offset to read from * @file_out: file structure to write data to * @pos_out: file offset to write data to * @len: amount of data to copy * @flags: copy flags * * This is a generic filesystem helper to copy data from one file to another. * It has no constraints on the source or destination file owners - the files * can belong to different superblocks and different filesystem types. Short * copies are allowed. * * This should be called from the @file_out filesystem, as per the * ->copy_file_range() method. * * Returns the number of bytes copied or a negative error indicating the * failure. */ ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len, unsigned int flags) { lockdep_assert(sb_write_started(file_inode(file_out)->i_sb)); return do_splice_direct(file_in, &pos_in, file_out, &pos_out, len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0); } EXPORT_SYMBOL(generic_copy_file_range); /* * Performs necessary checks before doing a file copy * * Can adjust amount of bytes to copy via @req_count argument. * Returns appropriate error code that caller should return or * zero in case the copy should be allowed. */ static int generic_copy_file_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t *req_count, unsigned int flags) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); uint64_t count = *req_count; loff_t size_in; int ret; ret = generic_file_rw_checks(file_in, file_out); if (ret) return ret; /* * We allow some filesystems to handle cross sb copy, but passing * a file of the wrong filesystem type to filesystem driver can result * in an attempt to dereference the wrong type of ->private_data, so * avoid doing that until we really have a good reason. * * nfs and cifs define several different file_system_type structures * and several different sets of file_operations, but they all end up * using the same ->copy_file_range() function pointer. */ if (flags & COPY_FILE_SPLICE) { /* cross sb splice is allowed */ } else if (file_out->f_op->copy_file_range) { if (file_in->f_op->copy_file_range != file_out->f_op->copy_file_range) return -EXDEV; } else if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) { return -EXDEV; } /* Don't touch certain kinds of inodes */ if (IS_IMMUTABLE(inode_out)) return -EPERM; if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out)) return -ETXTBSY; /* Ensure offsets don't wrap. */ if (pos_in + count < pos_in || pos_out + count < pos_out) return -EOVERFLOW; /* Shorten the copy to EOF */ size_in = i_size_read(inode_in); if (pos_in >= size_in) count = 0; else count = min(count, size_in - (uint64_t)pos_in); ret = generic_write_check_limits(file_out, pos_out, &count); if (ret) return ret; /* Don't allow overlapped copying within the same file. */ if (inode_in == inode_out && pos_out + count > pos_in && pos_out < pos_in + count) return -EINVAL; *req_count = count; return 0; } /* * copy_file_range() differs from regular file read and write in that it * specifically allows return partial success. When it does so is up to * the copy_file_range method. */ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len, unsigned int flags) { ssize_t ret; bool splice = flags & COPY_FILE_SPLICE; if (flags & ~COPY_FILE_SPLICE) return -EINVAL; ret = generic_copy_file_checks(file_in, pos_in, file_out, pos_out, &len, flags); if (unlikely(ret)) return ret; ret = rw_verify_area(READ, file_in, &pos_in, len); if (unlikely(ret)) return ret; ret = rw_verify_area(WRITE, file_out, &pos_out, len); if (unlikely(ret)) return ret; if (len == 0) return 0; file_start_write(file_out); /* * Cloning is supported by more file systems, so we implement copy on * same sb using clone, but for filesystems where both clone and copy * are supported (e.g. nfs,cifs), we only call the copy method. */ if (!splice && file_out->f_op->copy_file_range) { ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out, pos_out, len, flags); goto done; } if (!splice && file_in->f_op->remap_file_range && file_inode(file_in)->i_sb == file_inode(file_out)->i_sb) { ret = file_in->f_op->remap_file_range(file_in, pos_in, file_out, pos_out, min_t(loff_t, MAX_RW_COUNT, len), REMAP_FILE_CAN_SHORTEN); if (ret > 0) goto done; } /* * We can get here for same sb copy of filesystems that do not implement * ->copy_file_range() in case filesystem does not support clone or in * case filesystem supports clone but rejected the clone request (e.g. * because it was not block aligned). * * In both cases, fall back to kernel copy so we are able to maintain a * consistent story about which filesystems support copy_file_range() * and which filesystems do not, that will allow userspace tools to * make consistent desicions w.r.t using copy_file_range(). * * We also get here if caller (e.g. nfsd) requested COPY_FILE_SPLICE. */ ret = generic_copy_file_range(file_in, pos_in, file_out, pos_out, len, flags); done: if (ret > 0) { fsnotify_access(file_in); add_rchar(current, ret); fsnotify_modify(file_out); add_wchar(current, ret); } inc_syscr(current); inc_syscw(current); file_end_write(file_out); return ret; } EXPORT_SYMBOL(vfs_copy_file_range); SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags) { loff_t pos_in; loff_t pos_out; struct fd f_in; struct fd f_out; ssize_t ret = -EBADF; f_in = fdget(fd_in); if (!f_in.file) goto out2; f_out = fdget(fd_out); if (!f_out.file) goto out1; ret = -EFAULT; if (off_in) { if (copy_from_user(&pos_in, off_in, sizeof(loff_t))) goto out; } else { pos_in = f_in.file->f_pos; } if (off_out) { if (copy_from_user(&pos_out, off_out, sizeof(loff_t))) goto out; } else { pos_out = f_out.file->f_pos; } ret = -EINVAL; if (flags != 0) goto out; ret = vfs_copy_file_range(f_in.file, pos_in, f_out.file, pos_out, len, flags); if (ret > 0) { pos_in += ret; pos_out += ret; if (off_in) { if (copy_to_user(off_in, &pos_in, sizeof(loff_t))) ret = -EFAULT; } else { f_in.file->f_pos = pos_in; } if (off_out) { if (copy_to_user(off_out, &pos_out, sizeof(loff_t))) ret = -EFAULT; } else { f_out.file->f_pos = pos_out; } } out: fdput(f_out); out1: fdput(f_in); out2: return ret; } /* * Don't operate on ranges the page cache doesn't support, and don't exceed the * LFS limits. If pos is under the limit it becomes a short access. If it * exceeds the limit we return -EFBIG. */ int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count) { struct inode *inode = file->f_mapping->host; loff_t max_size = inode->i_sb->s_maxbytes; loff_t limit = rlimit(RLIMIT_FSIZE); if (limit != RLIM_INFINITY) { if (pos >= limit) { send_sig(SIGXFSZ, current, 0); return -EFBIG; } *count = min(*count, limit - pos); } if (!(file->f_flags & O_LARGEFILE)) max_size = MAX_NON_LFS; if (unlikely(pos >= max_size)) return -EFBIG; *count = min(*count, max_size - pos); return 0; } /* Like generic_write_checks(), but takes size of write instead of iter. */ int generic_write_checks_count(struct kiocb *iocb, loff_t *count) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; if (IS_SWAPFILE(inode)) return -ETXTBSY; if (!*count) return 0; if (iocb->ki_flags & IOCB_APPEND) iocb->ki_pos = i_size_read(inode); if ((iocb->ki_flags & IOCB_NOWAIT) && !((iocb->ki_flags & IOCB_DIRECT) || (file->f_mode & FMODE_BUF_WASYNC))) return -EINVAL; return generic_write_check_limits(iocb->ki_filp, iocb->ki_pos, count); } EXPORT_SYMBOL(generic_write_checks_count); /* * Performs necessary checks before doing a write * * Can adjust writing position or amount of bytes to write. * Returns appropriate error code that caller should return or * zero in case that write should be allowed. */ ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from) { loff_t count = iov_iter_count(from); int ret; ret = generic_write_checks_count(iocb, &count); if (ret) return ret; iov_iter_truncate(from, count); return iov_iter_count(from); } EXPORT_SYMBOL(generic_write_checks); /* * Performs common checks before doing a file copy/clone * from @file_in to @file_out. */ int generic_file_rw_checks(struct file *file_in, struct file *file_out) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); /* Don't copy dirs, pipes, sockets... */ if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) return -EISDIR; if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) return -EINVAL; if (!(file_in->f_mode & FMODE_READ) || !(file_out->f_mode & FMODE_WRITE) || (file_out->f_flags & O_APPEND)) return -EBADF; return 0; } |
| 1005 2568 639 3 1520 2267 774 5 561 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Operations on the network namespace */ #ifndef __NET_NET_NAMESPACE_H #define __NET_NET_NAMESPACE_H #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/workqueue.h> #include <linux/list.h> #include <linux/sysctl.h> #include <linux/uidgid.h> #include <net/flow.h> #include <net/netns/core.h> #include <net/netns/mib.h> #include <net/netns/unix.h> #include <net/netns/packet.h> #include <net/netns/ipv4.h> #include <net/netns/ipv6.h> #include <net/netns/nexthop.h> #include <net/netns/ieee802154_6lowpan.h> #include <net/netns/sctp.h> #include <net/netns/netfilter.h> #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) #include <net/netns/conntrack.h> #endif #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) #include <net/netns/flow_table.h> #endif #include <net/netns/nftables.h> #include <net/netns/xfrm.h> #include <net/netns/mpls.h> #include <net/netns/can.h> #include <net/netns/xdp.h> #include <net/netns/smc.h> #include <net/netns/bpf.h> #include <net/netns/mctp.h> #include <net/net_trackers.h> #include <linux/ns_common.h> #include <linux/idr.h> #include <linux/skbuff.h> #include <linux/notifier.h> struct user_namespace; struct proc_dir_entry; struct net_device; struct sock; struct ctl_table_header; struct net_generic; struct uevent_sock; struct netns_ipvs; struct bpf_prog; #define NETDEV_HASHBITS 8 #define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS) struct net { /* First cache line can be often dirtied. * Do not place here read-mostly fields. */ refcount_t passive; /* To decide when the network * namespace should be freed. */ spinlock_t rules_mod_lock; atomic_t dev_unreg_count; unsigned int dev_base_seq; /* protected by rtnl_mutex */ int ifindex; spinlock_t nsid_lock; atomic_t fnhe_genid; struct list_head list; /* list of network namespaces */ struct list_head exit_list; /* To linked to call pernet exit * methods on dead net ( * pernet_ops_rwsem read locked), * or to unregister pernet ops * (pernet_ops_rwsem write locked). */ struct llist_node cleanup_list; /* namespaces on death row */ #ifdef CONFIG_KEYS struct key_tag *key_domain; /* Key domain of operation tag */ #endif struct user_namespace *user_ns; /* Owning user namespace */ struct ucounts *ucounts; struct idr netns_ids; struct ns_common ns; struct ref_tracker_dir refcnt_tracker; struct list_head dev_base_head; struct proc_dir_entry *proc_net; struct proc_dir_entry *proc_net_stat; #ifdef CONFIG_SYSCTL struct ctl_table_set sysctls; #endif struct sock *rtnl; /* rtnetlink socket */ struct sock *genl_sock; struct uevent_sock *uevent_sock; /* uevent socket */ struct hlist_head *dev_name_head; struct hlist_head *dev_index_head; struct raw_notifier_head netdev_chain; /* Note that @hash_mix can be read millions times per second, * it is critical that it is on a read_mostly cache line. */ u32 hash_mix; struct net_device *loopback_dev; /* The loopback */ /* core fib_rules */ struct list_head rules_ops; struct netns_core core; struct netns_mib mib; struct netns_packet packet; #if IS_ENABLED(CONFIG_UNIX) struct netns_unix unx; #endif struct netns_nexthop nexthop; struct netns_ipv4 ipv4; #if IS_ENABLED(CONFIG_IPV6) struct netns_ipv6 ipv6; #endif #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) struct netns_ieee802154_lowpan ieee802154_lowpan; #endif #if defined(CONFIG_IP_SCTP) || defined(CONFIG_IP_SCTP_MODULE) struct netns_sctp sctp; #endif #ifdef CONFIG_NETFILTER struct netns_nf nf; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) struct netns_ct ct; #endif #if defined(CONFIG_NF_TABLES) || defined(CONFIG_NF_TABLES_MODULE) struct netns_nftables nft; #endif #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) struct netns_ft ft; #endif #endif #ifdef CONFIG_WEXT_CORE struct sk_buff_head wext_nlevents; #endif struct net_generic __rcu *gen; /* Used to store attached BPF programs */ struct netns_bpf bpf; /* Note : following structs are cache line aligned */ #ifdef CONFIG_XFRM struct netns_xfrm xfrm; #endif u64 net_cookie; /* written once */ #if IS_ENABLED(CONFIG_IP_VS) struct netns_ipvs *ipvs; #endif #if IS_ENABLED(CONFIG_MPLS) struct netns_mpls mpls; #endif #if IS_ENABLED(CONFIG_CAN) struct netns_can can; #endif #ifdef CONFIG_XDP_SOCKETS struct netns_xdp xdp; #endif #if IS_ENABLED(CONFIG_MCTP) struct netns_mctp mctp; #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) struct sock *crypto_nlsk; #endif struct sock *diag_nlsk; #if IS_ENABLED(CONFIG_SMC) struct netns_smc smc; #endif } __randomize_layout; /* * To work around a KMI issue, hooks_bridge[] could not be * added to struct netns_nf. Since the only use of netns_nf * is embedded in struct net, struct ext_net is added to * contain struct net plus the new field. Users of the new * field must use get_nf_hooks_bridge() to access the field. */ struct ext_net { struct net net; #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE struct nf_hook_entries __rcu *hooks_bridge[NF_INET_NUMHOOKS]; #endif ANDROID_VENDOR_DATA(1); }; #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE extern struct net init_net; extern struct nf_hook_entries **init_nf_hooks_bridgep; static inline struct nf_hook_entries __rcu **get_nf_hooks_bridge(const struct net *net) { struct ext_net *ext_net; if (net == &init_net) return init_nf_hooks_bridgep; ext_net = container_of(net, struct ext_net, net); return ext_net->hooks_bridge; } #endif #include <linux/seq_file_net.h> /* Init's network namespace */ extern struct net init_net; #ifdef CONFIG_NET_NS struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns, struct net *old_net); void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid); void net_ns_barrier(void); struct ns_common *get_net_ns(struct ns_common *ns); struct net *get_net_ns_by_fd(int fd); #else /* CONFIG_NET_NS */ #include <linux/sched.h> #include <linux/nsproxy.h> static inline struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns, struct net *old_net) { if (flags & CLONE_NEWNET) return ERR_PTR(-EINVAL); return old_net; } static inline void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid) { *uid = GLOBAL_ROOT_UID; *gid = GLOBAL_ROOT_GID; } static inline void net_ns_barrier(void) {} static inline struct ns_common *get_net_ns(struct ns_common *ns) { return ERR_PTR(-EINVAL); } static inline struct net *get_net_ns_by_fd(int fd) { return ERR_PTR(-EINVAL); } #endif /* CONFIG_NET_NS */ extern struct list_head net_namespace_list; struct net *get_net_ns_by_pid(pid_t pid); #ifdef CONFIG_SYSCTL void ipx_register_sysctl(void); void ipx_unregister_sysctl(void); #else #define ipx_register_sysctl() #define ipx_unregister_sysctl() #endif #ifdef CONFIG_NET_NS void __put_net(struct net *net); /* Try using get_net_track() instead */ static inline struct net *get_net(struct net *net) { refcount_inc(&net->ns.count); return net; } static inline struct net *maybe_get_net(struct net *net) { /* Used when we know struct net exists but we * aren't guaranteed a previous reference count * exists. If the reference count is zero this * function fails and returns NULL. */ if (!refcount_inc_not_zero(&net->ns.count)) net = NULL; return net; } /* Try using put_net_track() instead */ static inline void put_net(struct net *net) { if (refcount_dec_and_test(&net->ns.count)) __put_net(net); } static inline int net_eq(const struct net *net1, const struct net *net2) { return net1 == net2; } static inline int check_net(const struct net *net) { return refcount_read(&net->ns.count) != 0; } void net_drop_ns(void *); #else static inline struct net *get_net(struct net *net) { return net; } static inline void put_net(struct net *net) { } static inline struct net *maybe_get_net(struct net *net) { return net; } static inline int net_eq(const struct net *net1, const struct net *net2) { return 1; } static inline int check_net(const struct net *net) { return 1; } #define net_drop_ns NULL #endif static inline void netns_tracker_alloc(struct net *net, netns_tracker *tracker, gfp_t gfp) { #ifdef CONFIG_NET_NS_REFCNT_TRACKER ref_tracker_alloc(&net->refcnt_tracker, tracker, gfp); #endif } static inline void netns_tracker_free(struct net *net, netns_tracker *tracker) { #ifdef CONFIG_NET_NS_REFCNT_TRACKER ref_tracker_free(&net->refcnt_tracker, tracker); #endif } static inline struct net *get_net_track(struct net *net, netns_tracker *tracker, gfp_t gfp) { get_net(net); netns_tracker_alloc(net, tracker, gfp); return net; } static inline void put_net_track(struct net *net, netns_tracker *tracker) { netns_tracker_free(net, tracker); put_net(net); } typedef struct { #ifdef CONFIG_NET_NS struct net __rcu *net; #endif } possible_net_t; static inline void write_pnet(possible_net_t *pnet, struct net *net) { #ifdef CONFIG_NET_NS rcu_assign_pointer(pnet->net, net); #endif } static inline struct net *read_pnet(const possible_net_t *pnet) { #ifdef CONFIG_NET_NS return rcu_dereference_protected(pnet->net, true); #else return &init_net; #endif } static inline struct net *read_pnet_rcu(const possible_net_t *pnet) { #ifdef CONFIG_NET_NS return rcu_dereference(pnet->net); #else return &init_net; #endif } /* Protected by net_rwsem */ #define for_each_net(VAR) \ list_for_each_entry(VAR, &net_namespace_list, list) #define for_each_net_continue_reverse(VAR) \ list_for_each_entry_continue_reverse(VAR, &net_namespace_list, list) #define for_each_net_rcu(VAR) \ list_for_each_entry_rcu(VAR, &net_namespace_list, list) #ifdef CONFIG_NET_NS #define __net_init #define __net_exit #define __net_initdata #define __net_initconst #else #define __net_init __init #define __net_exit __ref #define __net_initdata __initdata #define __net_initconst __initconst #endif int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp); int peernet2id(const struct net *net, struct net *peer); bool peernet_has_id(const struct net *net, struct net *peer); struct net *get_net_ns_by_id(const struct net *net, int id); struct pernet_operations { struct list_head list; /* * Below methods are called without any exclusive locks. * More than one net may be constructed and destructed * in parallel on several cpus. Every pernet_operations * have to keep in mind all other pernet_operations and * to introduce a locking, if they share common resources. * * The only time they are called with exclusive lock is * from register_pernet_subsys(), unregister_pernet_subsys() * register_pernet_device() and unregister_pernet_device(). * * Exit methods using blocking RCU primitives, such as * synchronize_rcu(), should be implemented via exit_batch. * Then, destruction of a group of net requires single * synchronize_rcu() related to these pernet_operations, * instead of separate synchronize_rcu() for every net. * Please, avoid synchronize_rcu() at all, where it's possible. * * Note that a combination of pre_exit() and exit() can * be used, since a synchronize_rcu() is guaranteed between * the calls. */ int (*init)(struct net *net); void (*pre_exit)(struct net *net); void (*exit)(struct net *net); void (*exit_batch)(struct list_head *net_exit_list); unsigned int *id; size_t size; }; /* * Use these carefully. If you implement a network device and it * needs per network namespace operations use device pernet operations, * otherwise use pernet subsys operations. * * Network interfaces need to be removed from a dying netns _before_ * subsys notifiers can be called, as most of the network code cleanup * (which is done from subsys notifiers) runs with the assumption that * dev_remove_pack has been called so no new packets will arrive during * and after the cleanup functions have been called. dev_remove_pack * is not per namespace so instead the guarantee of no more packets * arriving in a network namespace is provided by ensuring that all * network devices and all sockets have left the network namespace * before the cleanup methods are called. * * For the longest time the ipv4 icmp code was registered as a pernet * device which caused kernel oops, and panics during network * namespace cleanup. So please don't get this wrong. */ int register_pernet_subsys(struct pernet_operations *); void unregister_pernet_subsys(struct pernet_operations *); int register_pernet_device(struct pernet_operations *); void unregister_pernet_device(struct pernet_operations *); struct ctl_table; #ifdef CONFIG_SYSCTL int net_sysctl_init(void); struct ctl_table_header *register_net_sysctl(struct net *net, const char *path, struct ctl_table *table); void unregister_net_sysctl_table(struct ctl_table_header *header); #else static inline int net_sysctl_init(void) { return 0; } static inline struct ctl_table_header *register_net_sysctl(struct net *net, const char *path, struct ctl_table *table) { return NULL; } static inline void unregister_net_sysctl_table(struct ctl_table_header *header) { } #endif static inline int rt_genid_ipv4(const struct net *net) { return atomic_read(&net->ipv4.rt_genid); } #if IS_ENABLED(CONFIG_IPV6) static inline int rt_genid_ipv6(const struct net *net) { return atomic_read(&net->ipv6.fib6_sernum); } #endif static inline void rt_genid_bump_ipv4(struct net *net) { atomic_inc(&net->ipv4.rt_genid); } extern void (*__fib6_flush_trees)(struct net *net); static inline void rt_genid_bump_ipv6(struct net *net) { if (__fib6_flush_trees) __fib6_flush_trees(net); } #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) static inline struct netns_ieee802154_lowpan * net_ieee802154_lowpan(struct net *net) { return &net->ieee802154_lowpan; } #endif /* For callers who don't really care about whether it's IPv4 or IPv6 */ static inline void rt_genid_bump_all(struct net *net) { rt_genid_bump_ipv4(net); rt_genid_bump_ipv6(net); } static inline int fnhe_genid(const struct net *net) { return atomic_read(&net->fnhe_genid); } static inline void fnhe_genid_bump(struct net *net) { atomic_inc(&net->fnhe_genid); } #ifdef CONFIG_NET void net_ns_init(void); #else static inline void net_ns_init(void) {} #endif #endif /* __NET_NET_NAMESPACE_H */ |
| 591 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 | /* 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 */ |
| 583 583 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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); |
| 999 587 547 2944 2943 1040 2241 49 13 546 46 1 554 2945 2942 2945 2927 554 6001 1041 5996 5995 6001 5996 1041 1041 8 1041 3343 3261 936 866 1042 3344 3341 2943 2926 1905 511 3340 3341 3342 2944 2944 29 8 8 8 2945 2943 2906 971 2945 7 2206 31 1191 1191 1673 863 1504 81 1086 81 1086 1086 1086 1965 1961 25 24 23 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 | // SPDX-License-Identifier: GPL-2.0 /* * Kernel internal timers * * Copyright (C) 1991, 1992 Linus Torvalds * * 1997-01-28 Modified by Finn Arne Gangstad to make timers scale better. * * 1997-09-10 Updated NTP code according to technical memorandum Jan '96 * "A Kernel Model for Precision Timekeeping" by Dave Mills * 1998-12-24 Fixed a xtime SMP race (we need the xtime_lock rw spinlock to * serialize accesses to xtime/lost_ticks). * Copyright (C) 1998 Andrea Arcangeli * 1999-03-10 Improved NTP compatibility by Ulrich Windl * 2002-05-31 Move sys_sysinfo here and make its locking sane, Robert Love * 2000-10-05 Implemented scalable SMP per-CPU timer handling. * Copyright (C) 2000, 2001, 2002 Ingo Molnar * Designed by David S. Miller, Alexey Kuznetsov and Ingo Molnar */ #include <linux/kernel_stat.h> #include <linux/export.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/pid_namespace.h> #include <linux/notifier.h> #include <linux/thread_info.h> #include <linux/time.h> #include <linux/jiffies.h> #include <linux/posix-timers.h> #include <linux/cpu.h> #include <linux/syscalls.h> #include <linux/delay.h> #include <linux/tick.h> #include <linux/kallsyms.h> #include <linux/irq_work.h> #include <linux/sched/signal.h> #include <linux/sched/sysctl.h> #include <linux/sched/nohz.h> #include <linux/sched/debug.h> #include <linux/slab.h> #include <linux/compat.h> #include <linux/random.h> #include <linux/sysctl.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <asm/div64.h> #include <asm/timex.h> #include <asm/io.h> #include "tick-internal.h" #define CREATE_TRACE_POINTS #include <trace/events/timer.h> #undef CREATE_TRACE_POINTS #include <trace/hooks/timer.h> EXPORT_TRACEPOINT_SYMBOL_GPL(hrtimer_expire_entry); EXPORT_TRACEPOINT_SYMBOL_GPL(hrtimer_expire_exit); __visible u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES; EXPORT_SYMBOL(jiffies_64); /* * The timer wheel has LVL_DEPTH array levels. Each level provides an array of * LVL_SIZE buckets. Each level is driven by its own clock and therefor each * level has a different granularity. * * The level granularity is: LVL_CLK_DIV ^ lvl * The level clock frequency is: HZ / (LVL_CLK_DIV ^ level) * * The array level of a newly armed timer depends on the relative expiry * time. The farther the expiry time is away the higher the array level and * therefor the granularity becomes. * * Contrary to the original timer wheel implementation, which aims for 'exact' * expiry of the timers, this implementation removes the need for recascading * the timers into the lower array levels. The previous 'classic' timer wheel * implementation of the kernel already violated the 'exact' expiry by adding * slack to the expiry time to provide batched expiration. The granularity * levels provide implicit batching. * * This is an optimization of the original timer wheel implementation for the * majority of the timer wheel use cases: timeouts. The vast majority of * timeout timers (networking, disk I/O ...) are canceled before expiry. If * the timeout expires it indicates that normal operation is disturbed, so it * does not matter much whether the timeout comes with a slight delay. * * The only exception to this are networking timers with a small expiry * time. They rely on the granularity. Those fit into the first wheel level, * which has HZ granularity. * * We don't have cascading anymore. timers with a expiry time above the * capacity of the last wheel level are force expired at the maximum timeout * value of the last wheel level. From data sampling we know that the maximum * value observed is 5 days (network connection tracking), so this should not * be an issue. * * The currently chosen array constants values are a good compromise between * array size and granularity. * * This results in the following granularity and range levels: * * HZ 1000 steps * Level Offset Granularity Range * 0 0 1 ms 0 ms - 63 ms * 1 64 8 ms 64 ms - 511 ms * 2 128 64 ms 512 ms - 4095 ms (512ms - ~4s) * 3 192 512 ms 4096 ms - 32767 ms (~4s - ~32s) * 4 256 4096 ms (~4s) 32768 ms - 262143 ms (~32s - ~4m) * 5 320 32768 ms (~32s) 262144 ms - 2097151 ms (~4m - ~34m) * 6 384 262144 ms (~4m) 2097152 ms - 16777215 ms (~34m - ~4h) * 7 448 2097152 ms (~34m) 16777216 ms - 134217727 ms (~4h - ~1d) * 8 512 16777216 ms (~4h) 134217728 ms - 1073741822 ms (~1d - ~12d) * * HZ 300 * Level Offset Granularity Range * 0 0 3 ms 0 ms - 210 ms * 1 64 26 ms 213 ms - 1703 ms (213ms - ~1s) * 2 128 213 ms 1706 ms - 13650 ms (~1s - ~13s) * 3 192 1706 ms (~1s) 13653 ms - 109223 ms (~13s - ~1m) * 4 256 13653 ms (~13s) 109226 ms - 873810 ms (~1m - ~14m) * 5 320 109226 ms (~1m) 873813 ms - 6990503 ms (~14m - ~1h) * 6 384 873813 ms (~14m) 6990506 ms - 55924050 ms (~1h - ~15h) * 7 448 6990506 ms (~1h) 55924053 ms - 447392423 ms (~15h - ~5d) * 8 512 55924053 ms (~15h) 447392426 ms - 3579139406 ms (~5d - ~41d) * * HZ 250 * Level Offset Granularity Range * 0 0 4 ms 0 ms - 255 ms * 1 64 32 ms 256 ms - 2047 ms (256ms - ~2s) * 2 128 256 ms 2048 ms - 16383 ms (~2s - ~16s) * 3 192 2048 ms (~2s) 16384 ms - 131071 ms (~16s - ~2m) * 4 256 16384 ms (~16s) 131072 ms - 1048575 ms (~2m - ~17m) * 5 320 131072 ms (~2m) 1048576 ms - 8388607 ms (~17m - ~2h) * 6 384 1048576 ms (~17m) 8388608 ms - 67108863 ms (~2h - ~18h) * 7 448 8388608 ms (~2h) 67108864 ms - 536870911 ms (~18h - ~6d) * 8 512 67108864 ms (~18h) 536870912 ms - 4294967288 ms (~6d - ~49d) * * HZ 100 * Level Offset Granularity Range * 0 0 10 ms 0 ms - 630 ms * 1 64 80 ms 640 ms - 5110 ms (640ms - ~5s) * 2 128 640 ms 5120 ms - 40950 ms (~5s - ~40s) * 3 192 5120 ms (~5s) 40960 ms - 327670 ms (~40s - ~5m) * 4 256 40960 ms (~40s) 327680 ms - 2621430 ms (~5m - ~43m) * 5 320 327680 ms (~5m) 2621440 ms - 20971510 ms (~43m - ~5h) * 6 384 2621440 ms (~43m) 20971520 ms - 167772150 ms (~5h - ~1d) * 7 448 20971520 ms (~5h) 167772160 ms - 1342177270 ms (~1d - ~15d) */ /* Clock divisor for the next level */ #define LVL_CLK_SHIFT 3 #define LVL_CLK_DIV (1UL << LVL_CLK_SHIFT) #define LVL_CLK_MASK (LVL_CLK_DIV - 1) #define LVL_SHIFT(n) ((n) * LVL_CLK_SHIFT) #define LVL_GRAN(n) (1UL << LVL_SHIFT(n)) /* * The time start value for each level to select the bucket at enqueue * time. We start from the last possible delta of the previous level * so that we can later add an extra LVL_GRAN(n) to n (see calc_index()). */ #define LVL_START(n) ((LVL_SIZE - 1) << (((n) - 1) * LVL_CLK_SHIFT)) /* Size of each clock level */ #define LVL_BITS 6 #define LVL_SIZE (1UL << LVL_BITS) #define LVL_MASK (LVL_SIZE - 1) #define LVL_OFFS(n) ((n) * LVL_SIZE) /* Level depth */ #if HZ > 100 # define LVL_DEPTH 9 # else # define LVL_DEPTH 8 #endif /* The cutoff (max. capacity of the wheel) */ #define WHEEL_TIMEOUT_CUTOFF (LVL_START(LVL_DEPTH)) #define WHEEL_TIMEOUT_MAX (WHEEL_TIMEOUT_CUTOFF - LVL_GRAN(LVL_DEPTH - 1)) /* * The resulting wheel size. If NOHZ is configured we allocate two * wheels so we have a separate storage for the deferrable timers. */ #define WHEEL_SIZE (LVL_SIZE * LVL_DEPTH) #ifdef CONFIG_NO_HZ_COMMON # define NR_BASES 2 # define BASE_STD 0 # define BASE_DEF 1 #else # define NR_BASES 1 # define BASE_STD 0 # define BASE_DEF 0 #endif struct timer_base { raw_spinlock_t lock; struct timer_list *running_timer; #ifdef CONFIG_PREEMPT_RT spinlock_t expiry_lock; atomic_t timer_waiters; #endif unsigned long clk; unsigned long next_expiry; unsigned int cpu; bool next_expiry_recalc; bool is_idle; bool timers_pending; DECLARE_BITMAP(pending_map, WHEEL_SIZE); struct hlist_head vectors[WHEEL_SIZE]; } ____cacheline_aligned; static DEFINE_PER_CPU(struct timer_base, timer_bases[NR_BASES]); #ifdef CONFIG_NO_HZ_COMMON static DEFINE_STATIC_KEY_FALSE(timers_nohz_active); static DEFINE_MUTEX(timer_keys_mutex); static void timer_update_keys(struct work_struct *work); static DECLARE_WORK(timer_update_work, timer_update_keys); #ifdef CONFIG_SMP static unsigned int sysctl_timer_migration = 1; DEFINE_STATIC_KEY_FALSE(timers_migration_enabled); static void timers_update_migration(void) { if (sysctl_timer_migration && tick_nohz_active) static_branch_enable(&timers_migration_enabled); else static_branch_disable(&timers_migration_enabled); } #ifdef CONFIG_SYSCTL static int timer_migration_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; mutex_lock(&timer_keys_mutex); ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (!ret && write) timers_update_migration(); mutex_unlock(&timer_keys_mutex); return ret; } static struct ctl_table timer_sysctl[] = { { .procname = "timer_migration", .data = &sysctl_timer_migration, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = timer_migration_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, {} }; static int __init timer_sysctl_init(void) { register_sysctl("kernel", timer_sysctl); return 0; } device_initcall(timer_sysctl_init); #endif /* CONFIG_SYSCTL */ #else /* CONFIG_SMP */ static inline void timers_update_migration(void) { } #endif /* !CONFIG_SMP */ static void timer_update_keys(struct work_struct *work) { mutex_lock(&timer_keys_mutex); timers_update_migration(); static_branch_enable(&timers_nohz_active); mutex_unlock(&timer_keys_mutex); } void timers_update_nohz(void) { schedule_work(&timer_update_work); } static inline bool is_timers_nohz_active(void) { return static_branch_unlikely(&timers_nohz_active); } #else static inline bool is_timers_nohz_active(void) { return false; } #endif /* NO_HZ_COMMON */ static unsigned long round_jiffies_common(unsigned long j, int cpu, bool force_up) { int rem; unsigned long original = j; /* * We don't want all cpus firing their timers at once hitting the * same lock or cachelines, so we skew each extra cpu with an extra * 3 jiffies. This 3 jiffies came originally from the mm/ code which * already did this. * The skew is done by adding 3*cpunr, then round, then subtract this * extra offset again. */ j += cpu * 3; rem = j % HZ; /* * If the target jiffie is just after a whole second (which can happen * due to delays of the timer irq, long irq off times etc etc) then * we should round down to the whole second, not up. Use 1/4th second * as cutoff for this rounding as an extreme upper bound for this. * But never round down if @force_up is set. */ if (rem < HZ/4 && !force_up) /* round down */ j = j - rem; else /* round up */ j = j - rem + HZ; /* now that we have rounded, subtract the extra skew again */ j -= cpu * 3; /* * Make sure j is still in the future. Otherwise return the * unmodified value. */ return time_is_after_jiffies(j) ? j : original; } /** * __round_jiffies - function to round jiffies to a full second * @j: the time in (absolute) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * __round_jiffies() rounds an absolute time in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The exact rounding is skewed for each processor to avoid all * processors firing at the exact same time, which could lead * to lock contention or spurious cache line bouncing. * * The return value is the rounded version of the @j parameter. */ unsigned long __round_jiffies(unsigned long j, int cpu) { return round_jiffies_common(j, cpu, false); } EXPORT_SYMBOL_GPL(__round_jiffies); /** * __round_jiffies_relative - function to round jiffies to a full second * @j: the time in (relative) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * __round_jiffies_relative() rounds a time delta in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The exact rounding is skewed for each processor to avoid all * processors firing at the exact same time, which could lead * to lock contention or spurious cache line bouncing. * * The return value is the rounded version of the @j parameter. */ unsigned long __round_jiffies_relative(unsigned long j, int cpu) { unsigned long j0 = jiffies; /* Use j0 because jiffies might change while we run */ return round_jiffies_common(j + j0, cpu, false) - j0; } EXPORT_SYMBOL_GPL(__round_jiffies_relative); /** * round_jiffies - function to round jiffies to a full second * @j: the time in (absolute) jiffies that should be rounded * * round_jiffies() rounds an absolute time in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The return value is the rounded version of the @j parameter. */ unsigned long round_jiffies(unsigned long j) { return round_jiffies_common(j, raw_smp_processor_id(), false); } EXPORT_SYMBOL_GPL(round_jiffies); /** * round_jiffies_relative - function to round jiffies to a full second * @j: the time in (relative) jiffies that should be rounded * * round_jiffies_relative() rounds a time delta in the future (in jiffies) * up or down to (approximately) full seconds. This is useful for timers * for which the exact time they fire does not matter too much, as long as * they fire approximately every X seconds. * * By rounding these timers to whole seconds, all such timers will fire * at the same time, rather than at various times spread out. The goal * of this is to have the CPU wake up less, which saves power. * * The return value is the rounded version of the @j parameter. */ unsigned long round_jiffies_relative(unsigned long j) { return __round_jiffies_relative(j, raw_smp_processor_id()); } EXPORT_SYMBOL_GPL(round_jiffies_relative); /** * __round_jiffies_up - function to round jiffies up to a full second * @j: the time in (absolute) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * This is the same as __round_jiffies() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long __round_jiffies_up(unsigned long j, int cpu) { return round_jiffies_common(j, cpu, true); } EXPORT_SYMBOL_GPL(__round_jiffies_up); /** * __round_jiffies_up_relative - function to round jiffies up to a full second * @j: the time in (relative) jiffies that should be rounded * @cpu: the processor number on which the timeout will happen * * This is the same as __round_jiffies_relative() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long __round_jiffies_up_relative(unsigned long j, int cpu) { unsigned long j0 = jiffies; /* Use j0 because jiffies might change while we run */ return round_jiffies_common(j + j0, cpu, true) - j0; } EXPORT_SYMBOL_GPL(__round_jiffies_up_relative); /** * round_jiffies_up - function to round jiffies up to a full second * @j: the time in (absolute) jiffies that should be rounded * * This is the same as round_jiffies() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long round_jiffies_up(unsigned long j) { return round_jiffies_common(j, raw_smp_processor_id(), true); } EXPORT_SYMBOL_GPL(round_jiffies_up); /** * round_jiffies_up_relative - function to round jiffies up to a full second * @j: the time in (relative) jiffies that should be rounded * * This is the same as round_jiffies_relative() except that it will never * round down. This is useful for timeouts for which the exact time * of firing does not matter too much, as long as they don't fire too * early. */ unsigned long round_jiffies_up_relative(unsigned long j) { return __round_jiffies_up_relative(j, raw_smp_processor_id()); } EXPORT_SYMBOL_GPL(round_jiffies_up_relative); static inline unsigned int timer_get_idx(struct timer_list *timer) { return (timer->flags & TIMER_ARRAYMASK) >> TIMER_ARRAYSHIFT; } static inline void timer_set_idx(struct timer_list *timer, unsigned int idx) { timer->flags = (timer->flags & ~TIMER_ARRAYMASK) | idx << TIMER_ARRAYSHIFT; } /* * Helper function to calculate the array index for a given expiry * time. */ static inline unsigned calc_index(unsigned long expires, unsigned lvl, unsigned long *bucket_expiry) { /* * The timer wheel has to guarantee that a timer does not fire * early. Early expiry can happen due to: * - Timer is armed at the edge of a tick * - Truncation of the expiry time in the outer wheel levels * * Round up with level granularity to prevent this. */ trace_android_vh_timer_calc_index(lvl, &expires); expires = (expires >> LVL_SHIFT(lvl)) + 1; *bucket_expiry = expires << LVL_SHIFT(lvl); return LVL_OFFS(lvl) + (expires & LVL_MASK); } static int calc_wheel_index(unsigned long expires, unsigned long clk, unsigned long *bucket_expiry) { unsigned long delta = expires - clk; unsigned int idx; if (delta < LVL_START(1)) { idx = calc_index(expires, 0, bucket_expiry); } else if (delta < LVL_START(2)) { idx = calc_index(expires, 1, bucket_expiry); } else if (delta < LVL_START(3)) { idx = calc_index(expires, 2, bucket_expiry); } else if (delta < LVL_START(4)) { idx = calc_index(expires, 3, bucket_expiry); } else if (delta < LVL_START(5)) { idx = calc_index(expires, 4, bucket_expiry); } else if (delta < LVL_START(6)) { idx = calc_index(expires, 5, bucket_expiry); } else if (delta < LVL_START(7)) { idx = calc_index(expires, 6, bucket_expiry); } else if (LVL_DEPTH > 8 && delta < LVL_START(8)) { idx = calc_index(expires, 7, bucket_expiry); } else if ((long) delta < 0) { idx = clk & LVL_MASK; *bucket_expiry = clk; } else { /* * Force expire obscene large timeouts to expire at the * capacity limit of the wheel. */ if (delta >= WHEEL_TIMEOUT_CUTOFF) expires = clk + WHEEL_TIMEOUT_MAX; idx = calc_index(expires, LVL_DEPTH - 1, bucket_expiry); } return idx; } static void trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer) { if (!is_timers_nohz_active()) return; /* * TODO: This wants some optimizing similar to the code below, but we * will do that when we switch from push to pull for deferrable timers. */ if (timer->flags & TIMER_DEFERRABLE) { if (tick_nohz_full_cpu(base->cpu)) wake_up_nohz_cpu(base->cpu); return; } /* * We might have to IPI the remote CPU if the base is idle and the * timer is not deferrable. If the other CPU is on the way to idle * then it can't set base->is_idle as we hold the base lock: */ if (base->is_idle) wake_up_nohz_cpu(base->cpu); } /* * Enqueue the timer into the hash bucket, mark it pending in * the bitmap, store the index in the timer flags then wake up * the target CPU if needed. */ static void enqueue_timer(struct timer_base *base, struct timer_list *timer, unsigned int idx, unsigned long bucket_expiry) { hlist_add_head(&timer->entry, base->vectors + idx); __set_bit(idx, base->pending_map); timer_set_idx(timer, idx); trace_timer_start(timer, timer->expires, timer->flags); /* * Check whether this is the new first expiring timer. The * effective expiry time of the timer is required here * (bucket_expiry) instead of timer->expires. */ if (time_before(bucket_expiry, base->next_expiry)) { /* * Set the next expiry time and kick the CPU so it * can reevaluate the wheel: */ base->next_expiry = bucket_expiry; base->timers_pending = true; base->next_expiry_recalc = false; trigger_dyntick_cpu(base, timer); } } static void internal_add_timer(struct timer_base *base, struct timer_list *timer) { unsigned long bucket_expiry; unsigned int idx; idx = calc_wheel_index(timer->expires, base->clk, &bucket_expiry); enqueue_timer(base, timer, idx, bucket_expiry); } #ifdef CONFIG_DEBUG_OBJECTS_TIMERS static const struct debug_obj_descr timer_debug_descr; struct timer_hint { void (*function)(struct timer_list *t); long offset; }; #define TIMER_HINT(fn, container, timr, hintfn) \ { \ .function = fn, \ .offset = offsetof(container, hintfn) - \ offsetof(container, timr) \ } static const struct timer_hint timer_hints[] = { TIMER_HINT(delayed_work_timer_fn, struct delayed_work, timer, work.func), TIMER_HINT(kthread_delayed_work_timer_fn, struct kthread_delayed_work, timer, work.func), }; static void *timer_debug_hint(void *addr) { struct timer_list *timer = addr; int i; for (i = 0; i < ARRAY_SIZE(timer_hints); i++) { if (timer_hints[i].function == timer->function) { void (**fn)(void) = addr + timer_hints[i].offset; return *fn; } } return timer->function; } static bool timer_is_static_object(void *addr) { struct timer_list *timer = addr; return (timer->entry.pprev == NULL && timer->entry.next == TIMER_ENTRY_STATIC); } /* * fixup_init is called when: * - an active object is initialized */ static bool timer_fixup_init(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: del_timer_sync(timer); debug_object_init(timer, &timer_debug_descr); return true; default: return false; } } /* Stub timer callback for improperly used timers. */ static void stub_timer(struct timer_list *unused) { WARN_ON(1); } /* * fixup_activate is called when: * - an active object is activated * - an unknown non-static object is activated */ static bool timer_fixup_activate(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_NOTAVAILABLE: timer_setup(timer, stub_timer, 0); return true; case ODEBUG_STATE_ACTIVE: WARN_ON(1); fallthrough; default: return false; } } /* * fixup_free is called when: * - an active object is freed */ static bool timer_fixup_free(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: del_timer_sync(timer); debug_object_free(timer, &timer_debug_descr); return true; default: return false; } } /* * fixup_assert_init is called when: * - an untracked/uninit-ed object is found */ static bool timer_fixup_assert_init(void *addr, enum debug_obj_state state) { struct timer_list *timer = addr; switch (state) { case ODEBUG_STATE_NOTAVAILABLE: timer_setup(timer, stub_timer, 0); return true; default: return false; } } static const struct debug_obj_descr timer_debug_descr = { .name = "timer_list", .debug_hint = timer_debug_hint, .is_static_object = timer_is_static_object, .fixup_init = timer_fixup_init, .fixup_activate = timer_fixup_activate, .fixup_free = timer_fixup_free, .fixup_assert_init = timer_fixup_assert_init, }; static inline void debug_timer_init(struct timer_list *timer) { debug_object_init(timer, &timer_debug_descr); } static inline void debug_timer_activate(struct timer_list *timer) { debug_object_activate(timer, &timer_debug_descr); } static inline void debug_timer_deactivate(struct timer_list *timer) { debug_object_deactivate(timer, &timer_debug_descr); } static inline void debug_timer_assert_init(struct timer_list *timer) { debug_object_assert_init(timer, &timer_debug_descr); } static void do_init_timer(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key); void init_timer_on_stack_key(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { debug_object_init_on_stack(timer, &timer_debug_descr); do_init_timer(timer, func, flags, name, key); } EXPORT_SYMBOL_GPL(init_timer_on_stack_key); void destroy_timer_on_stack(struct timer_list *timer) { debug_object_free(timer, &timer_debug_descr); } EXPORT_SYMBOL_GPL(destroy_timer_on_stack); #else static inline void debug_timer_init(struct timer_list *timer) { } static inline void debug_timer_activate(struct timer_list *timer) { } static inline void debug_timer_deactivate(struct timer_list *timer) { } static inline void debug_timer_assert_init(struct timer_list *timer) { } #endif static inline void debug_init(struct timer_list *timer) { debug_timer_init(timer); trace_timer_init(timer); } static inline void debug_deactivate(struct timer_list *timer) { debug_timer_deactivate(timer); trace_timer_cancel(timer); } static inline void debug_assert_init(struct timer_list *timer) { debug_timer_assert_init(timer); } static void do_init_timer(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { timer->entry.pprev = NULL; timer->function = func; if (WARN_ON_ONCE(flags & ~TIMER_INIT_FLAGS)) flags &= TIMER_INIT_FLAGS; timer->flags = flags | raw_smp_processor_id(); lockdep_init_map(&timer->lockdep_map, name, key, 0); } /** * init_timer_key - initialize a timer * @timer: the timer to be initialized * @func: timer callback function * @flags: timer flags * @name: name of the timer * @key: lockdep class key of the fake lock used for tracking timer * sync lock dependencies * * init_timer_key() must be done to a timer prior calling *any* of the * other timer functions. */ void init_timer_key(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { debug_init(timer); do_init_timer(timer, func, flags, name, key); } EXPORT_SYMBOL(init_timer_key); static inline void detach_timer(struct timer_list *timer, bool clear_pending) { struct hlist_node *entry = &timer->entry; debug_deactivate(timer); __hlist_del(entry); if (clear_pending) entry->pprev = NULL; entry->next = LIST_POISON2; } static int detach_if_pending(struct timer_list *timer, struct timer_base *base, bool clear_pending) { unsigned idx = timer_get_idx(timer); if (!timer_pending(timer)) return 0; if (hlist_is_singular_node(&timer->entry, base->vectors + idx)) { __clear_bit(idx, base->pending_map); base->next_expiry_recalc = true; } detach_timer(timer, clear_pending); return 1; } static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu) { struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_STD], cpu); /* * If the timer is deferrable and NO_HZ_COMMON is set then we need * to use the deferrable base. */ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE)) base = per_cpu_ptr(&timer_bases[BASE_DEF], cpu); return base; } static inline struct timer_base *get_timer_this_cpu_base(u32 tflags) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); /* * If the timer is deferrable and NO_HZ_COMMON is set then we need * to use the deferrable base. */ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE)) base = this_cpu_ptr(&timer_bases[BASE_DEF]); return base; } static inline struct timer_base *get_timer_base(u32 tflags) { return get_timer_cpu_base(tflags, tflags & TIMER_CPUMASK); } static inline struct timer_base * get_target_base(struct timer_base *base, unsigned tflags) { #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) if (static_branch_likely(&timers_migration_enabled) && !(tflags & TIMER_PINNED)) return get_timer_cpu_base(tflags, get_nohz_timer_target()); #endif return get_timer_this_cpu_base(tflags); } static inline void forward_timer_base(struct timer_base *base) { unsigned long jnow = READ_ONCE(jiffies); /* * No need to forward if we are close enough below jiffies. * Also while executing timers, base->clk is 1 offset ahead * of jiffies to avoid endless requeuing to current jiffies. */ if ((long)(jnow - base->clk) < 1) return; /* * If the next expiry value is > jiffies, then we fast forward to * jiffies otherwise we forward to the next expiry value. */ if (time_after(base->next_expiry, jnow)) { base->clk = jnow; } else { if (WARN_ON_ONCE(time_before(base->next_expiry, base->clk))) return; base->clk = base->next_expiry; } } /* * We are using hashed locking: Holding per_cpu(timer_bases[x]).lock means * that all timers which are tied to this base are locked, and the base itself * is locked too. * * So __run_timers/migrate_timers can safely modify all timers which could * be found in the base->vectors array. * * When a timer is migrating then the TIMER_MIGRATING flag is set and we need * to wait until the migration is done. */ static struct timer_base *lock_timer_base(struct timer_list *timer, unsigned long *flags) __acquires(timer->base->lock) { for (;;) { struct timer_base *base; u32 tf; /* * We need to use READ_ONCE() here, otherwise the compiler * might re-read @tf between the check for TIMER_MIGRATING * and spin_lock(). */ tf = READ_ONCE(timer->flags); if (!(tf & TIMER_MIGRATING)) { base = get_timer_base(tf); raw_spin_lock_irqsave(&base->lock, *flags); if (timer->flags == tf) return base; raw_spin_unlock_irqrestore(&base->lock, *flags); } cpu_relax(); } } #define MOD_TIMER_PENDING_ONLY 0x01 #define MOD_TIMER_REDUCE 0x02 #define MOD_TIMER_NOTPENDING 0x04 static inline int __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int options) { unsigned long clk = 0, flags, bucket_expiry; struct timer_base *base, *new_base; unsigned int idx = UINT_MAX; int ret = 0; BUG_ON(!timer->function); /* * This is a common optimization triggered by the networking code - if * the timer is re-modified to have the same timeout or ends up in the * same array bucket then just return: */ if (!(options & MOD_TIMER_NOTPENDING) && timer_pending(timer)) { /* * The downside of this optimization is that it can result in * larger granularity than you would get from adding a new * timer with this expiry. */ long diff = timer->expires - expires; if (!diff) return 1; if (options & MOD_TIMER_REDUCE && diff <= 0) return 1; /* * We lock timer base and calculate the bucket index right * here. If the timer ends up in the same bucket, then we * just update the expiry time and avoid the whole * dequeue/enqueue dance. */ base = lock_timer_base(timer, &flags); forward_timer_base(base); if (timer_pending(timer) && (options & MOD_TIMER_REDUCE) && time_before_eq(timer->expires, expires)) { ret = 1; goto out_unlock; } clk = base->clk; idx = calc_wheel_index(expires, clk, &bucket_expiry); /* * Retrieve and compare the array index of the pending * timer. If it matches set the expiry to the new value so a * subsequent call will exit in the expires check above. */ if (idx == timer_get_idx(timer)) { if (!(options & MOD_TIMER_REDUCE)) timer->expires = expires; else if (time_after(timer->expires, expires)) timer->expires = expires; ret = 1; goto out_unlock; } } else { base = lock_timer_base(timer, &flags); forward_timer_base(base); } ret = detach_if_pending(timer, base, false); if (!ret && (options & MOD_TIMER_PENDING_ONLY)) goto out_unlock; new_base = get_target_base(base, timer->flags); if (base != new_base) { /* * We are trying to schedule the timer on the new base. * However we can't change timer's base while it is running, * otherwise del_timer_sync() can't detect that the timer's * handler yet has not finished. This also guarantees that the * timer is serialized wrt itself. */ if (likely(base->running_timer != timer)) { /* See the comment in lock_timer_base() */ timer->flags |= TIMER_MIGRATING; raw_spin_unlock(&base->lock); base = new_base; raw_spin_lock(&base->lock); WRITE_ONCE(timer->flags, (timer->flags & ~TIMER_BASEMASK) | base->cpu); forward_timer_base(base); } } debug_timer_activate(timer); timer->expires = expires; /* * If 'idx' was calculated above and the base time did not advance * between calculating 'idx' and possibly switching the base, only * enqueue_timer() is required. Otherwise we need to (re)calculate * the wheel index via internal_add_timer(). */ if (idx != UINT_MAX && clk == base->clk) enqueue_timer(base, timer, idx, bucket_expiry); else internal_add_timer(base, timer); out_unlock: raw_spin_unlock_irqrestore(&base->lock, flags); return ret; } /** * mod_timer_pending - Modify a pending timer's timeout * @timer: The pending timer to be modified * @expires: New absolute timeout in jiffies * * mod_timer_pending() is the same for pending timers as mod_timer(), but * will not activate inactive timers. * * Return: * * %0 - The timer was inactive and not modified * * %1 - The timer was active and requeued to expire at @expires */ int mod_timer_pending(struct timer_list *timer, unsigned long expires) { return __mod_timer(timer, expires, MOD_TIMER_PENDING_ONLY); } EXPORT_SYMBOL(mod_timer_pending); /** * mod_timer - Modify a timer's timeout * @timer: The timer to be modified * @expires: New absolute timeout in jiffies * * mod_timer(timer, expires) is equivalent to: * * del_timer(timer); timer->expires = expires; add_timer(timer); * * mod_timer() is more efficient than the above open coded sequence. In * case that the timer is inactive, the del_timer() part is a NOP. The * timer is in any case activated with the new expiry time @expires. * * Note that if there are multiple unserialized concurrent users of the * same timer, then mod_timer() is the only safe way to modify the timeout, * since add_timer() cannot modify an already running timer. * * Return: * * %0 - The timer was inactive and started * * %1 - The timer was active and requeued to expire at @expires or * the timer was active and not modified because @expires did * not change the effective expiry time */ int mod_timer(struct timer_list *timer, unsigned long expires) { return __mod_timer(timer, expires, 0); } EXPORT_SYMBOL(mod_timer); /** * timer_reduce - Modify a timer's timeout if it would reduce the timeout * @timer: The timer to be modified * @expires: New absolute timeout in jiffies * * timer_reduce() is very similar to mod_timer(), except that it will only * modify an enqueued timer if that would reduce the expiration time. If * @timer is not enqueued it starts the timer. * * Return: * * %0 - The timer was inactive and started * * %1 - The timer was active and requeued to expire at @expires or * the timer was active and not modified because @expires * did not change the effective expiry time such that the * timer would expire earlier than already scheduled */ int timer_reduce(struct timer_list *timer, unsigned long expires) { return __mod_timer(timer, expires, MOD_TIMER_REDUCE); } EXPORT_SYMBOL(timer_reduce); /** * add_timer - Start a timer * @timer: The timer to be started * * Start @timer to expire at @timer->expires in the future. @timer->expires * is the absolute expiry time measured in 'jiffies'. When the timer expires * timer->function(timer) will be invoked from soft interrupt context. * * The @timer->expires and @timer->function fields must be set prior * to calling this function. * * If @timer->expires is already in the past @timer will be queued to * expire at the next timer tick. * * This can only operate on an inactive timer. Attempts to invoke this on * an active timer are rejected with a warning. */ void add_timer(struct timer_list *timer) { BUG_ON(timer_pending(timer)); __mod_timer(timer, timer->expires, MOD_TIMER_NOTPENDING); } EXPORT_SYMBOL(add_timer); /** * add_timer_on - Start a timer on a particular CPU * @timer: The timer to be started * @cpu: The CPU to start it on * * Same as add_timer() except that it starts the timer on the given CPU. * * See add_timer() for further details. */ void add_timer_on(struct timer_list *timer, int cpu) { struct timer_base *new_base, *base; unsigned long flags; BUG_ON(timer_pending(timer) || !timer->function); new_base = get_timer_cpu_base(timer->flags, cpu); /* * If @timer was on a different CPU, it should be migrated with the * old base locked to prevent other operations proceeding with the * wrong base locked. See lock_timer_base(). */ base = lock_timer_base(timer, &flags); if (base != new_base) { timer->flags |= TIMER_MIGRATING; raw_spin_unlock(&base->lock); base = new_base; raw_spin_lock(&base->lock); WRITE_ONCE(timer->flags, (timer->flags & ~TIMER_BASEMASK) | cpu); } forward_timer_base(base); debug_timer_activate(timer); internal_add_timer(base, timer); raw_spin_unlock_irqrestore(&base->lock, flags); } EXPORT_SYMBOL_GPL(add_timer_on); /** * del_timer - Deactivate a timer. * @timer: The timer to be deactivated * * The function only deactivates a pending timer, but contrary to * del_timer_sync() it does not take into account whether the timer's * callback function is concurrently executed on a different CPU or not. * It neither prevents rearming of the timer. If @timer can be rearmed * concurrently then the return value of this function is meaningless. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated */ int del_timer(struct timer_list *timer) { struct timer_base *base; unsigned long flags; int ret = 0; debug_assert_init(timer); if (timer_pending(timer)) { base = lock_timer_base(timer, &flags); ret = detach_if_pending(timer, base, true); raw_spin_unlock_irqrestore(&base->lock, flags); } return ret; } EXPORT_SYMBOL(del_timer); /** * try_to_del_timer_sync - Try to deactivate a timer * @timer: Timer to deactivate * * This function tries to deactivate a timer. On success the timer is not * queued and the timer callback function is not running on any CPU. * * This function does not guarantee that the timer cannot be rearmed right * after dropping the base lock. That needs to be prevented by the calling * code if necessary. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated * * %-1 - The timer callback function is running on a different CPU */ int try_to_del_timer_sync(struct timer_list *timer) { struct timer_base *base; unsigned long flags; int ret = -1; debug_assert_init(timer); base = lock_timer_base(timer, &flags); if (base->running_timer != timer) ret = detach_if_pending(timer, base, true); raw_spin_unlock_irqrestore(&base->lock, flags); return ret; } EXPORT_SYMBOL(try_to_del_timer_sync); #ifdef CONFIG_PREEMPT_RT static __init void timer_base_init_expiry_lock(struct timer_base *base) { spin_lock_init(&base->expiry_lock); } static inline void timer_base_lock_expiry(struct timer_base *base) { spin_lock(&base->expiry_lock); } static inline void timer_base_unlock_expiry(struct timer_base *base) { spin_unlock(&base->expiry_lock); } /* * The counterpart to del_timer_wait_running(). * * If there is a waiter for base->expiry_lock, then it was waiting for the * timer callback to finish. Drop expiry_lock and reacquire it. That allows * the waiter to acquire the lock and make progress. */ static void timer_sync_wait_running(struct timer_base *base) { if (atomic_read(&base->timer_waiters)) { raw_spin_unlock_irq(&base->lock); spin_unlock(&base->expiry_lock); spin_lock(&base->expiry_lock); raw_spin_lock_irq(&base->lock); } } /* * This function is called on PREEMPT_RT kernels when the fast path * deletion of a timer failed because the timer callback function was * running. * * This prevents priority inversion, if the softirq thread on a remote CPU * got preempted, and it prevents a life lock when the task which tries to * delete a timer preempted the softirq thread running the timer callback * function. */ static void del_timer_wait_running(struct timer_list *timer) { u32 tf; tf = READ_ONCE(timer->flags); if (!(tf & (TIMER_MIGRATING | TIMER_IRQSAFE))) { struct timer_base *base = get_timer_base(tf); /* * Mark the base as contended and grab the expiry lock, * which is held by the softirq across the timer * callback. Drop the lock immediately so the softirq can * expire the next timer. In theory the timer could already * be running again, but that's more than unlikely and just * causes another wait loop. */ atomic_inc(&base->timer_waiters); spin_lock_bh(&base->expiry_lock); atomic_dec(&base->timer_waiters); spin_unlock_bh(&base->expiry_lock); } } #else static inline void timer_base_init_expiry_lock(struct timer_base *base) { } static inline void timer_base_lock_expiry(struct timer_base *base) { } static inline void timer_base_unlock_expiry(struct timer_base *base) { } static inline void timer_sync_wait_running(struct timer_base *base) { } static inline void del_timer_wait_running(struct timer_list *timer) { } #endif /** * del_timer_sync - Deactivate a timer and wait for the handler to finish. * @timer: The timer to be deactivated * * Synchronization rules: Callers must prevent restarting of the timer, * otherwise this function is meaningless. It must not be called from * interrupt contexts unless the timer is an irqsafe one. The caller must * not hold locks which would prevent completion of the timer's callback * function. The timer's handler must not call add_timer_on(). Upon exit * the timer is not queued and the handler is not running on any CPU. * * For !irqsafe timers, the caller must not hold locks that are held in * interrupt context. Even if the lock has nothing to do with the timer in * question. Here's why:: * * CPU0 CPU1 * ---- ---- * <SOFTIRQ> * call_timer_fn(); * base->running_timer = mytimer; * spin_lock_irq(somelock); * <IRQ> * spin_lock(somelock); * del_timer_sync(mytimer); * while (base->running_timer == mytimer); * * Now del_timer_sync() will never return and never release somelock. * The interrupt on the other CPU is waiting to grab somelock but it has * interrupted the softirq that CPU0 is waiting to finish. * * This function cannot guarantee that the timer is not rearmed again by * some concurrent or preempting code, right after it dropped the base * lock. If there is the possibility of a concurrent rearm then the return * value of the function is meaningless. * * Return: * * %0 - The timer was not pending * * %1 - The timer was pending and deactivated */ int del_timer_sync(struct timer_list *timer) { int ret; #ifdef CONFIG_LOCKDEP unsigned long flags; /* * If lockdep gives a backtrace here, please reference * the synchronization rules above. */ local_irq_save(flags); lock_map_acquire(&timer->lockdep_map); lock_map_release(&timer->lockdep_map); local_irq_restore(flags); #endif /* * don't use it in hardirq context, because it * could lead to deadlock. */ WARN_ON(in_irq() && !(timer->flags & TIMER_IRQSAFE)); /* * Must be able to sleep on PREEMPT_RT because of the slowpath in * del_timer_wait_running(). */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(timer->flags & TIMER_IRQSAFE)) lockdep_assert_preemption_enabled(); do { ret = try_to_del_timer_sync(timer); if (unlikely(ret < 0)) { del_timer_wait_running(timer); cpu_relax(); } } while (ret < 0); return ret; } EXPORT_SYMBOL(del_timer_sync); static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list *), unsigned long baseclk) { int count = preempt_count(); #ifdef CONFIG_LOCKDEP /* * It is permissible to free the timer from inside the * function that is called from it, this we need to take into * account for lockdep too. To avoid bogus "held lock freed" * warnings as well as problems when looking into * timer->lockdep_map, make a copy and use that here. */ struct lockdep_map lockdep_map; lockdep_copy_map(&lockdep_map, &timer->lockdep_map); #endif /* * Couple the lock chain with the lock chain at * del_timer_sync() by acquiring the lock_map around the fn() * call here and in del_timer_sync(). */ lock_map_acquire(&lockdep_map); trace_timer_expire_entry(timer, baseclk); fn(timer); trace_timer_expire_exit(timer); lock_map_release(&lockdep_map); if (count != preempt_count()) { WARN_ONCE(1, "timer: %pS preempt leak: %08x -> %08x\n", fn, count, preempt_count()); /* * Restore the preempt count. That gives us a decent * chance to survive and extract information. If the * callback kept a lock held, bad luck, but not worse * than the BUG() we had. */ preempt_count_set(count); } } static void expire_timers(struct timer_base *base, struct hlist_head *head) { /* * This value is required only for tracing. base->clk was * incremented directly before expire_timers was called. But expiry * is related to the old base->clk value. */ unsigned long baseclk = base->clk - 1; while (!hlist_empty(head)) { struct timer_list *timer; void (*fn)(struct timer_list *); timer = hlist_entry(head->first, struct timer_list, entry); base->running_timer = timer; detach_timer(timer, true); fn = timer->function; if (timer->flags & TIMER_IRQSAFE) { raw_spin_unlock(&base->lock); call_timer_fn(timer, fn, baseclk); raw_spin_lock(&base->lock); base->running_timer = NULL; } else { raw_spin_unlock_irq(&base->lock); call_timer_fn(timer, fn, baseclk); raw_spin_lock_irq(&base->lock); base->running_timer = NULL; timer_sync_wait_running(base); } } } static int collect_expired_timers(struct timer_base *base, struct hlist_head *heads) { unsigned long clk = base->clk = base->next_expiry; struct hlist_head *vec; int i, levels = 0; unsigned int idx; for (i = 0; i < LVL_DEPTH; i++) { idx = (clk & LVL_MASK) + i * LVL_SIZE; if (__test_and_clear_bit(idx, base->pending_map)) { vec = base->vectors + idx; hlist_move_list(vec, heads++); levels++; } /* Is it time to look at the next level? */ if (clk & LVL_CLK_MASK) break; /* Shift clock for the next level granularity */ clk >>= LVL_CLK_SHIFT; } return levels; } /* * Find the next pending bucket of a level. Search from level start (@offset) * + @clk upwards and if nothing there, search from start of the level * (@offset) up to @offset + clk. */ static int next_pending_bucket(struct timer_base *base, unsigned offset, unsigned clk) { unsigned pos, start = offset + clk; unsigned end = offset + LVL_SIZE; pos = find_next_bit(base->pending_map, end, start); if (pos < end) return pos - start; pos = find_next_bit(base->pending_map, start, offset); return pos < start ? pos + LVL_SIZE - start : -1; } /* * Search the first expiring timer in the various clock levels. Caller must * hold base->lock. */ static unsigned long __next_timer_interrupt(struct timer_base *base) { unsigned long clk, next, adj; unsigned lvl, offset = 0; next = base->clk + NEXT_TIMER_MAX_DELTA; clk = base->clk; for (lvl = 0; lvl < LVL_DEPTH; lvl++, offset += LVL_SIZE) { int pos = next_pending_bucket(base, offset, clk & LVL_MASK); unsigned long lvl_clk = clk & LVL_CLK_MASK; if (pos >= 0) { unsigned long tmp = clk + (unsigned long) pos; tmp <<= LVL_SHIFT(lvl); if (time_before(tmp, next)) next = tmp; /* * If the next expiration happens before we reach * the next level, no need to check further. */ if (pos <= ((LVL_CLK_DIV - lvl_clk) & LVL_CLK_MASK)) break; } /* * Clock for the next level. If the current level clock lower * bits are zero, we look at the next level as is. If not we * need to advance it by one because that's going to be the * next expiring bucket in that level. base->clk is the next * expiring jiffie. So in case of: * * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 * 0 0 0 0 0 0 * * we have to look at all levels @index 0. With * * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 * 0 0 0 0 0 2 * * LVL0 has the next expiring bucket @index 2. The upper * levels have the next expiring bucket @index 1. * * In case that the propagation wraps the next level the same * rules apply: * * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 * 0 0 0 0 F 2 * * So after looking at LVL0 we get: * * LVL5 LVL4 LVL3 LVL2 LVL1 * 0 0 0 1 0 * * So no propagation from LVL1 to LVL2 because that happened * with the add already, but then we need to propagate further * from LVL2 to LVL3. * * So the simple check whether the lower bits of the current * level are 0 or not is sufficient for all cases. */ adj = lvl_clk ? 1 : 0; clk >>= LVL_CLK_SHIFT; clk += adj; } base->next_expiry_recalc = false; base->timers_pending = !(next == base->clk + NEXT_TIMER_MAX_DELTA); return next; } #ifdef CONFIG_NO_HZ_COMMON /* * Check, if the next hrtimer event is before the next timer wheel * event: */ static u64 cmp_next_hrtimer_event(u64 basem, u64 expires) { u64 nextevt = hrtimer_get_next_event(); /* * If high resolution timers are enabled * hrtimer_get_next_event() returns KTIME_MAX. */ if (expires <= nextevt) return expires; /* * If the next timer is already expired, return the tick base * time so the tick is fired immediately. */ if (nextevt <= basem) return basem; /* * Round up to the next jiffie. High resolution timers are * off, so the hrtimers are expired in the tick and we need to * make sure that this tick really expires the timer to avoid * a ping pong of the nohz stop code. * * Use DIV_ROUND_UP_ULL to prevent gcc calling __divdi3 */ return DIV_ROUND_UP_ULL(nextevt, TICK_NSEC) * TICK_NSEC; } /** * get_next_timer_interrupt - return the time (clock mono) of the next timer * @basej: base time jiffies * @basem: base time clock monotonic * * Returns the tick aligned clock monotonic time of the next pending * timer or KTIME_MAX if no timer is pending. */ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); u64 expires = KTIME_MAX; unsigned long nextevt; /* * Pretend that there is no timer pending if the cpu is offline. * Possible pending timers will be migrated later to an active cpu. */ if (cpu_is_offline(smp_processor_id())) return expires; raw_spin_lock(&base->lock); if (base->next_expiry_recalc) base->next_expiry = __next_timer_interrupt(base); nextevt = base->next_expiry; /* * We have a fresh next event. Check whether we can forward the * base. We can only do that when @basej is past base->clk * otherwise we might rewind base->clk. */ if (time_after(basej, base->clk)) { if (time_after(nextevt, basej)) base->clk = basej; else if (time_after(nextevt, base->clk)) base->clk = nextevt; } if (time_before_eq(nextevt, basej)) { expires = basem; base->is_idle = false; } else { if (base->timers_pending) expires = basem + (u64)(nextevt - basej) * TICK_NSEC; /* * If we expect to sleep more than a tick, mark the base idle. * Also the tick is stopped so any added timer must forward * the base clk itself to keep granularity small. This idle * logic is only maintained for the BASE_STD base, deferrable * timers may still see large granularity skew (by design). */ if ((expires - basem) > TICK_NSEC) base->is_idle = true; } raw_spin_unlock(&base->lock); return cmp_next_hrtimer_event(basem, expires); } /** * timer_clear_idle - Clear the idle state of the timer base * * Called with interrupts disabled */ void timer_clear_idle(void) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); /* * We do this unlocked. The worst outcome is a remote enqueue sending * a pointless IPI, but taking the lock would just make the window for * sending the IPI a few instructions smaller for the cost of taking * the lock in the exit from idle path. */ base->is_idle = false; } #endif /** * __run_timers - run all expired timers (if any) on this CPU. * @base: the timer vector to be processed. */ static inline void __run_timers(struct timer_base *base) { struct hlist_head heads[LVL_DEPTH]; int levels; if (time_before(jiffies, base->next_expiry)) return; timer_base_lock_expiry(base); raw_spin_lock_irq(&base->lock); while (time_after_eq(jiffies, base->clk) && time_after_eq(jiffies, base->next_expiry)) { levels = collect_expired_timers(base, heads); /* * The two possible reasons for not finding any expired * timer at this clk are that all matching timers have been * dequeued or no timer has been queued since * base::next_expiry was set to base::clk + * NEXT_TIMER_MAX_DELTA. */ WARN_ON_ONCE(!levels && !base->next_expiry_recalc && base->timers_pending); base->clk++; base->next_expiry = __next_timer_interrupt(base); while (levels--) expire_timers(base, heads + levels); } raw_spin_unlock_irq(&base->lock); timer_base_unlock_expiry(base); } /* * This function runs timers and the timer-tq in bottom half context. */ static __latent_entropy void run_timer_softirq(struct softirq_action *h) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); __run_timers(base); if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) __run_timers(this_cpu_ptr(&timer_bases[BASE_DEF])); } /* * Called by the local, per-CPU timer interrupt on SMP. */ static void run_local_timers(void) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); hrtimer_run_queues(); /* Raise the softirq only if required. */ if (time_before(jiffies, base->next_expiry)) { if (!IS_ENABLED(CONFIG_NO_HZ_COMMON)) return; /* CPU is awake, so check the deferrable base. */ base++; if (time_before(jiffies, base->next_expiry)) return; } raise_softirq(TIMER_SOFTIRQ); } /* * Called from the timer interrupt handler to charge one tick to the current * process. user_tick is 1 if the tick is user time, 0 for system. */ void update_process_times(int user_tick) { struct task_struct *p = current; /* Note: this timer irq context must be accounted for as well. */ account_process_tick(p, user_tick); run_local_timers(); rcu_sched_clock_irq(user_tick); #ifdef CONFIG_IRQ_WORK if (in_irq()) irq_work_tick(); #endif scheduler_tick(); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) run_posix_cpu_timers(); } /* * Since schedule_timeout()'s timer is defined on the stack, it must store * the target task on the stack as well. */ struct process_timer { struct timer_list timer; struct task_struct *task; }; static void process_timeout(struct timer_list *t) { struct process_timer *timeout = from_timer(timeout, t, timer); wake_up_process(timeout->task); } /** * schedule_timeout - sleep until timeout * @timeout: timeout value in jiffies * * Make the current task sleep until @timeout jiffies have elapsed. * The function behavior depends on the current task state * (see also set_current_state() description): * * %TASK_RUNNING - the scheduler is called, but the task does not sleep * at all. That happens because sched_submit_work() does nothing for * tasks in %TASK_RUNNING state. * * %TASK_UNINTERRUPTIBLE - at least @timeout jiffies are guaranteed to * pass before the routine returns unless the current task is explicitly * woken up, (e.g. by wake_up_process()). * * %TASK_INTERRUPTIBLE - the routine may return early if a signal is * delivered to the current task or the current task is explicitly woken * up. * * The current task state is guaranteed to be %TASK_RUNNING when this * routine returns. * * Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule * the CPU away without a bound on the timeout. In this case the return * value will be %MAX_SCHEDULE_TIMEOUT. * * Returns 0 when the timer has expired otherwise the remaining time in * jiffies will be returned. In all cases the return value is guaranteed * to be non-negative. */ signed long __sched schedule_timeout(signed long timeout) { struct process_timer timer; unsigned long expire; switch (timeout) { case MAX_SCHEDULE_TIMEOUT: /* * These two special cases are useful to be comfortable * in the caller. Nothing more. We could take * MAX_SCHEDULE_TIMEOUT from one of the negative value * but I' d like to return a valid offset (>=0) to allow * the caller to do everything it want with the retval. */ schedule(); goto out; default: /* * Another bit of PARANOID. Note that the retval will be * 0 since no piece of kernel is supposed to do a check * for a negative retval of schedule_timeout() (since it * should never happens anyway). You just have the printk() * that will tell you if something is gone wrong and where. */ if (timeout < 0) { printk(KERN_ERR "schedule_timeout: wrong timeout " "value %lx\n", timeout); dump_stack(); __set_current_state(TASK_RUNNING); goto out; } } expire = timeout + jiffies; timer.task = current; timer_setup_on_stack(&timer.timer, process_timeout, 0); __mod_timer(&timer.timer, expire, MOD_TIMER_NOTPENDING); schedule(); del_timer_sync(&timer.timer); /* Remove the timer from the object tracker */ destroy_timer_on_stack(&timer.timer); timeout = expire - jiffies; out: return timeout < 0 ? 0 : timeout; } EXPORT_SYMBOL(schedule_timeout); /* * We can use __set_current_state() here because schedule_timeout() calls * schedule() unconditionally. */ signed long __sched schedule_timeout_interruptible(signed long timeout) { __set_current_state(TASK_INTERRUPTIBLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_interruptible); signed long __sched schedule_timeout_killable(signed long timeout) { __set_current_state(TASK_KILLABLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_killable); signed long __sched schedule_timeout_uninterruptible(signed long timeout) { __set_current_state(TASK_UNINTERRUPTIBLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_uninterruptible); /* * Like schedule_timeout_uninterruptible(), except this task will not contribute * to load average. */ signed long __sched schedule_timeout_idle(signed long timeout) { __set_current_state(TASK_IDLE); return schedule_timeout(timeout); } EXPORT_SYMBOL(schedule_timeout_idle); #ifdef CONFIG_HOTPLUG_CPU static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *head) { struct timer_list *timer; int cpu = new_base->cpu; while (!hlist_empty(head)) { timer = hlist_entry(head->first, struct timer_list, entry); detach_timer(timer, false); timer->flags = (timer->flags & ~TIMER_BASEMASK) | cpu; internal_add_timer(new_base, timer); } } int timers_prepare_cpu(unsigned int cpu) { struct timer_base *base; int b; for (b = 0; b < NR_BASES; b++) { base = per_cpu_ptr(&timer_bases[b], cpu); base->clk = jiffies; base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA; base->next_expiry_recalc = false; base->timers_pending = false; base->is_idle = false; } return 0; } int timers_dead_cpu(unsigned int cpu) { struct timer_base *old_base; struct timer_base *new_base; int b, i; BUG_ON(cpu_online(cpu)); for (b = 0; b < NR_BASES; b++) { old_base = per_cpu_ptr(&timer_bases[b], cpu); new_base = get_cpu_ptr(&timer_bases[b]); /* * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. */ raw_spin_lock_irq(&new_base->lock); raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); /* * The current CPUs base clock might be stale. Update it * before moving the timers over. */ forward_timer_base(new_base); BUG_ON(old_base->running_timer); for (i = 0; i < WHEEL_SIZE; i++) migrate_timer_list(new_base, old_base->vectors + i); raw_spin_unlock(&old_base->lock); raw_spin_unlock_irq(&new_base->lock); put_cpu_ptr(&timer_bases); } return 0; } #endif /* CONFIG_HOTPLUG_CPU */ static void __init init_timer_cpu(int cpu) { struct timer_base *base; int i; for (i = 0; i < NR_BASES; i++) { base = per_cpu_ptr(&timer_bases[i], cpu); base->cpu = cpu; raw_spin_lock_init(&base->lock); base->clk = jiffies; base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA; timer_base_init_expiry_lock(base); } } static void __init init_timer_cpus(void) { int cpu; for_each_possible_cpu(cpu) init_timer_cpu(cpu); } void __init init_timers(void) { init_timer_cpus(); posix_cputimers_init_work(); open_softirq(TIMER_SOFTIRQ, run_timer_softirq); } /** * msleep - sleep safely even with waitqueue interruptions * @msecs: Time in milliseconds to sleep for */ void msleep(unsigned int msecs) { unsigned long timeout = msecs_to_jiffies(msecs) + 1; while (timeout) timeout = schedule_timeout_uninterruptible(timeout); } EXPORT_SYMBOL(msleep); /** * msleep_interruptible - sleep waiting for signals * @msecs: Time in milliseconds to sleep for */ unsigned long msleep_interruptible(unsigned int msecs) { unsigned long timeout = msecs_to_jiffies(msecs) + 1; while (timeout && !signal_pending(current)) timeout = schedule_timeout_interruptible(timeout); return jiffies_to_msecs(timeout); } EXPORT_SYMBOL(msleep_interruptible); /** * usleep_range_state - Sleep for an approximate time in a given state * @min: Minimum time in usecs to sleep * @max: Maximum time in usecs to sleep * @state: State of the current task that will be while sleeping * * In non-atomic context where the exact wakeup time is flexible, use * usleep_range_state() instead of udelay(). The sleep improves responsiveness * by avoiding the CPU-hogging busy-wait of udelay(), and the range reduces * power usage by allowing hrtimers to take advantage of an already- * scheduled interrupt instead of scheduling a new one just for this sleep. */ void __sched usleep_range_state(unsigned long min, unsigned long max, unsigned int state) { ktime_t exp = ktime_add_us(ktime_get(), min); u64 delta = (u64)(max - min) * NSEC_PER_USEC; for (;;) { __set_current_state(state); /* Do not return before the requested sleep time has elapsed */ if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS)) break; } } EXPORT_SYMBOL(usleep_range_state); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Hash: Hash algorithms under the crypto API * * Copyright (c) 2008 Herbert Xu <herbert@gondor.apana.org.au> */ #ifndef _CRYPTO_HASH_H #define _CRYPTO_HASH_H #include <linux/crypto.h> #include <linux/string.h> struct crypto_ahash; /** * DOC: Message Digest Algorithm Definitions * * These data structures define modular message digest algorithm * implementations, managed via crypto_register_ahash(), * crypto_register_shash(), crypto_unregister_ahash() and * crypto_unregister_shash(). */ /** * struct hash_alg_common - define properties of message digest * @digestsize: Size of the result of the transformation. A buffer of this size * must be available to the @final and @finup calls, so they can * store the resulting hash into it. For various predefined sizes, * search include/crypto/ using * git grep _DIGEST_SIZE include/crypto. * @statesize: Size of the block for partial state of the transformation. A * buffer of this size must be passed to the @export function as it * will save the partial state of the transformation into it. On the * other side, the @import function will load the state from a * buffer of this size as well. * @base: Start of data structure of cipher algorithm. The common data * structure of crypto_alg contains information common to all ciphers. * The hash_alg_common data structure now adds the hash-specific * information. */ struct hash_alg_common { unsigned int digestsize; unsigned int statesize; struct crypto_alg base; }; struct ahash_request { struct crypto_async_request base; unsigned int nbytes; struct scatterlist *src; u8 *result; /* This field may only be used by the ahash API code. */ void *priv; void *__ctx[] CRYPTO_MINALIGN_ATTR; }; /** * struct ahash_alg - asynchronous message digest definition * @init: **[mandatory]** Initialize the transformation context. Intended only to initialize the * state of the HASH transformation at the beginning. This shall fill in * the internal structures used during the entire duration of the whole * transformation. No data processing happens at this point. Driver code * implementation must not use req->result. * @update: **[mandatory]** Push a chunk of data into the driver for transformation. This * function actually pushes blocks of data from upper layers into the * driver, which then passes those to the hardware as seen fit. This * function must not finalize the HASH transformation by calculating the * final message digest as this only adds more data into the * transformation. This function shall not modify the transformation * context, as this function may be called in parallel with the same * transformation object. Data processing can happen synchronously * [SHASH] or asynchronously [AHASH] at this point. Driver must not use * req->result. * @final: **[mandatory]** Retrieve result from the driver. This function finalizes the * transformation and retrieves the resulting hash from the driver and * pushes it back to upper layers. No data processing happens at this * point unless hardware requires it to finish the transformation * (then the data buffered by the device driver is processed). * @finup: **[optional]** Combination of @update and @final. This function is effectively a * combination of @update and @final calls issued in sequence. As some * hardware cannot do @update and @final separately, this callback was * added to allow such hardware to be used at least by IPsec. Data * processing can happen synchronously [SHASH] or asynchronously [AHASH] * at this point. * @digest: Combination of @init and @update and @final. This function * effectively behaves as the entire chain of operations, @init, * @update and @final issued in sequence. Just like @finup, this was * added for hardware which cannot do even the @finup, but can only do * the whole transformation in one run. Data processing can happen * synchronously [SHASH] or asynchronously [AHASH] at this point. * @setkey: Set optional key used by the hashing algorithm. Intended to push * optional key used by the hashing algorithm from upper layers into * the driver. This function can store the key in the transformation * context or can outright program it into the hardware. In the former * case, one must be careful to program the key into the hardware at * appropriate time and one must be careful that .setkey() can be * called multiple times during the existence of the transformation * object. Not all hashing algorithms do implement this function as it * is only needed for keyed message digests. SHAx/MDx/CRCx do NOT * implement this function. HMAC(MDx)/HMAC(SHAx)/CMAC(AES) do implement * this function. This function must be called before any other of the * @init, @update, @final, @finup, @digest is called. No data * processing happens at this point. * @export: Export partial state of the transformation. This function dumps the * entire state of the ongoing transformation into a provided block of * data so it can be @import 'ed back later on. This is useful in case * you want to save partial result of the transformation after * processing certain amount of data and reload this partial result * multiple times later on for multiple re-use. No data processing * happens at this point. Driver must not use req->result. * @import: Import partial state of the transformation. This function loads the * entire state of the ongoing transformation from a provided block of * data so the transformation can continue from this point onward. No * data processing happens at this point. Driver must not use * req->result. * @init_tfm: Initialize the cryptographic transformation object. * This function is called only once at the instantiation * time, right after the transformation context was * allocated. In case the cryptographic hardware has * some special requirements which need to be handled * by software, this function shall check for the precise * requirement of the transformation and put any software * fallbacks in place. * @exit_tfm: Deinitialize the cryptographic transformation object. * This is a counterpart to @init_tfm, used to remove * various changes set in @init_tfm. * @halg: see struct hash_alg_common */ struct ahash_alg { int (*init)(struct ahash_request *req); int (*update)(struct ahash_request *req); int (*final)(struct ahash_request *req); int (*finup)(struct ahash_request *req); int (*digest)(struct ahash_request *req); int (*export)(struct ahash_request *req, void *out); int (*import)(struct ahash_request *req, const void *in); int (*setkey)(struct crypto_ahash *tfm, const u8 *key, unsigned int keylen); int (*init_tfm)(struct crypto_ahash *tfm); void (*exit_tfm)(struct crypto_ahash *tfm); struct hash_alg_common halg; }; struct shash_desc { struct crypto_shash *tfm; void *__ctx[] __aligned(ARCH_SLAB_MINALIGN); }; #define HASH_MAX_DIGESTSIZE 64 /* * Worst case is hmac(sha3-224-generic). Its context is a nested 'shash_desc' * containing a 'struct sha3_state'. */ #define HASH_MAX_DESCSIZE (sizeof(struct shash_desc) + 360) #define HASH_MAX_STATESIZE 512 #define SHASH_DESC_ON_STACK(shash, ctx) \ char __##shash##_desc[sizeof(struct shash_desc) + HASH_MAX_DESCSIZE] \ __aligned(__alignof__(struct shash_desc)); \ struct shash_desc *shash = (struct shash_desc *)__##shash##_desc /** * struct shash_alg - synchronous message digest definition * @init: see struct ahash_alg * @update: see struct ahash_alg * @final: see struct ahash_alg * @finup: see struct ahash_alg * @digest: see struct ahash_alg * @export: see struct ahash_alg * @import: see struct ahash_alg * @setkey: see struct ahash_alg * @init_tfm: Initialize the cryptographic transformation object. * This function is called only once at the instantiation * time, right after the transformation context was * allocated. In case the cryptographic hardware has * some special requirements which need to be handled * by software, this function shall check for the precise * requirement of the transformation and put any software * fallbacks in place. * @exit_tfm: Deinitialize the cryptographic transformation object. * This is a counterpart to @init_tfm, used to remove * various changes set in @init_tfm. * @digestsize: see struct ahash_alg * @statesize: see struct ahash_alg * @descsize: Size of the operational state for the message digest. This state * size is the memory size that needs to be allocated for * shash_desc.__ctx * @base: internally used */ struct shash_alg { int (*init)(struct shash_desc *desc); int (*update)(struct shash_desc *desc, const u8 *data, unsigned int len); int (*final)(struct shash_desc *desc, u8 *out); int (*finup)(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out); int (*digest)(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out); int (*export)(struct shash_desc *desc, void *out); int (*import)(struct shash_desc *desc, const void *in); int (*setkey)(struct crypto_shash *tfm, const u8 *key, unsigned int keylen); int (*init_tfm)(struct crypto_shash *tfm); void (*exit_tfm)(struct crypto_shash *tfm); unsigned int descsize; /* These fields must match hash_alg_common. */ unsigned int digestsize __attribute__ ((aligned(__alignof__(struct hash_alg_common)))); unsigned int statesize; struct crypto_alg base; }; struct crypto_ahash { int (*init)(struct ahash_request *req); int (*update)(struct ahash_request *req); int (*final)(struct ahash_request *req); int (*finup)(struct ahash_request *req); int (*digest)(struct ahash_request *req); int (*export)(struct ahash_request *req, void *out); int (*import)(struct ahash_request *req, const void *in); int (*setkey)(struct crypto_ahash *tfm, const u8 *key, unsigned int keylen); unsigned int reqsize; struct crypto_tfm base; }; struct crypto_shash { unsigned int descsize; struct crypto_tfm base; }; /** * DOC: Asynchronous Message Digest API * * The asynchronous message digest API is used with the ciphers of type * CRYPTO_ALG_TYPE_AHASH (listed as type "ahash" in /proc/crypto) * * The asynchronous cipher operation discussion provided for the * CRYPTO_ALG_TYPE_SKCIPHER API applies here as well. */ static inline struct crypto_ahash *__crypto_ahash_cast(struct crypto_tfm *tfm) { return container_of(tfm, struct crypto_ahash, base); } /** * crypto_alloc_ahash() - allocate ahash cipher handle * @alg_name: is the cra_name / name or cra_driver_name / driver name of the * ahash cipher * @type: specifies the type of the cipher * @mask: specifies the mask for the cipher * * Allocate a cipher handle for an ahash. The returned struct * crypto_ahash is the cipher handle that is required for any subsequent * API invocation for that ahash. * * Return: allocated cipher handle in case of success; IS_ERR() is true in case * of an error, PTR_ERR() returns the error code. */ struct crypto_ahash *crypto_alloc_ahash(const char *alg_name, u32 type, u32 mask); static inline struct crypto_tfm *crypto_ahash_tfm(struct crypto_ahash *tfm) { return &tfm->base; } /** * crypto_free_ahash() - zeroize and free the ahash handle * @tfm: cipher handle to be freed * * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_ahash(struct crypto_ahash *tfm) { crypto_destroy_tfm(tfm, crypto_ahash_tfm(tfm)); } /** * crypto_has_ahash() - Search for the availability of an ahash. * @alg_name: is the cra_name / name or cra_driver_name / driver name of the * ahash * @type: specifies the type of the ahash * @mask: specifies the mask for the ahash * * Return: true when the ahash is known to the kernel crypto API; false * otherwise */ int crypto_has_ahash(const char *alg_name, u32 type, u32 mask); static inline const char *crypto_ahash_alg_name(struct crypto_ahash *tfm) { return crypto_tfm_alg_name(crypto_ahash_tfm(tfm)); } static inline const char *crypto_ahash_driver_name(struct crypto_ahash *tfm) { return crypto_tfm_alg_driver_name(crypto_ahash_tfm(tfm)); } static inline unsigned int crypto_ahash_alignmask( struct crypto_ahash *tfm) { return crypto_tfm_alg_alignmask(crypto_ahash_tfm(tfm)); } /** * crypto_ahash_blocksize() - obtain block size for cipher * @tfm: cipher handle * * The block size for the message digest cipher referenced with the cipher * handle is returned. * * Return: block size of cipher */ static inline unsigned int crypto_ahash_blocksize(struct crypto_ahash *tfm) { return crypto_tfm_alg_blocksize(crypto_ahash_tfm(tfm)); } static inline struct hash_alg_common *__crypto_hash_alg_common( struct crypto_alg *alg) { return container_of(alg, struct hash_alg_common, base); } static inline struct hash_alg_common *crypto_hash_alg_common( struct crypto_ahash *tfm) { return __crypto_hash_alg_common(crypto_ahash_tfm(tfm)->__crt_alg); } /** * crypto_ahash_digestsize() - obtain message digest size * @tfm: cipher handle * * The size for the message digest created by the message digest cipher * referenced with the cipher handle is returned. * * * Return: message digest size of cipher */ static inline unsigned int crypto_ahash_digestsize(struct crypto_ahash *tfm) { return crypto_hash_alg_common(tfm)->digestsize; } /** * crypto_ahash_statesize() - obtain size of the ahash state * @tfm: cipher handle * * Return the size of the ahash state. With the crypto_ahash_export() * function, the caller can export the state into a buffer whose size is * defined with this function. * * Return: size of the ahash state */ static inline unsigned int crypto_ahash_statesize(struct crypto_ahash *tfm) { return crypto_hash_alg_common(tfm)->statesize; } static inline u32 crypto_ahash_get_flags(struct crypto_ahash *tfm) { return crypto_tfm_get_flags(crypto_ahash_tfm(tfm)); } static inline void crypto_ahash_set_flags(struct crypto_ahash *tfm, u32 flags) { crypto_tfm_set_flags(crypto_ahash_tfm(tfm), flags); } static inline void crypto_ahash_clear_flags(struct crypto_ahash *tfm, u32 flags) { crypto_tfm_clear_flags(crypto_ahash_tfm(tfm), flags); } /** * crypto_ahash_reqtfm() - obtain cipher handle from request * @req: asynchronous request handle that contains the reference to the ahash * cipher handle * * Return the ahash cipher handle that is registered with the asynchronous * request handle ahash_request. * * Return: ahash cipher handle */ static inline struct crypto_ahash *crypto_ahash_reqtfm( struct ahash_request *req) { return __crypto_ahash_cast(req->base.tfm); } /** * crypto_ahash_reqsize() - obtain size of the request data structure * @tfm: cipher handle * * Return: size of the request data */ static inline unsigned int crypto_ahash_reqsize(struct crypto_ahash *tfm) { return tfm->reqsize; } static inline void *ahash_request_ctx(struct ahash_request *req) { return req->__ctx; } /** * crypto_ahash_setkey - set key for cipher handle * @tfm: cipher handle * @key: buffer holding the key * @keylen: length of the key in bytes * * The caller provided key is set for the ahash cipher. The cipher * handle must point to a keyed hash in order for this function to succeed. * * Return: 0 if the setting of the key was successful; < 0 if an error occurred */ int crypto_ahash_setkey(struct crypto_ahash *tfm, const u8 *key, unsigned int keylen); /** * crypto_ahash_finup() - update and finalize message digest * @req: reference to the ahash_request handle that holds all information * needed to perform the cipher operation * * This function is a "short-hand" for the function calls of * crypto_ahash_update and crypto_ahash_final. The parameters have the same * meaning as discussed for those separate functions. * * Return: see crypto_ahash_final() */ int crypto_ahash_finup(struct ahash_request *req); /** * crypto_ahash_final() - calculate message digest * @req: reference to the ahash_request handle that holds all information * needed to perform the cipher operation * * Finalize the message digest operation and create the message digest * based on all data added to the cipher handle. The message digest is placed * into the output buffer registered with the ahash_request handle. * * Return: * 0 if the message digest was successfully calculated; * -EINPROGRESS if data is fed into hardware (DMA) or queued for later; * -EBUSY if queue is full and request should be resubmitted later; * other < 0 if an error occurred */ int crypto_ahash_final(struct ahash_request *req); /** * crypto_ahash_digest() - calculate message digest for a buffer * @req: reference to the ahash_request handle that holds all information * needed to perform the cipher operation * * This function is a "short-hand" for the function calls of crypto_ahash_init, * crypto_ahash_update and crypto_ahash_final. The parameters have the same * meaning as discussed for those separate three functions. * * Return: see crypto_ahash_final() */ int crypto_ahash_digest(struct ahash_request *req); /** * crypto_ahash_export() - extract current message digest state * @req: reference to the ahash_request handle whose state is exported * @out: output buffer of sufficient size that can hold the hash state * * This function exports the hash state of the ahash_request handle into the * caller-allocated output buffer out which must have sufficient size (e.g. by * calling crypto_ahash_statesize()). * * Return: 0 if the export was successful; < 0 if an error occurred */ static inline int crypto_ahash_export(struct ahash_request *req, void *out) { return crypto_ahash_reqtfm(req)->export(req, out); } /** * crypto_ahash_import() - import message digest state * @req: reference to ahash_request handle the state is imported into * @in: buffer holding the state * * This function imports the hash state into the ahash_request handle from the * input buffer. That buffer should have been generated with the * crypto_ahash_export function. * * Return: 0 if the import was successful; < 0 if an error occurred */ static inline int crypto_ahash_import(struct ahash_request *req, const void *in) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; return tfm->import(req, in); } /** * crypto_ahash_init() - (re)initialize message digest handle * @req: ahash_request handle that already is initialized with all necessary * data using the ahash_request_* API functions * * The call (re-)initializes the message digest referenced by the ahash_request * handle. Any potentially existing state created by previous operations is * discarded. * * Return: see crypto_ahash_final() */ static inline int crypto_ahash_init(struct ahash_request *req) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; return tfm->init(req); } /** * crypto_ahash_update() - add data to message digest for processing * @req: ahash_request handle that was previously initialized with the * crypto_ahash_init call. * * Updates the message digest state of the &ahash_request handle. The input data * is pointed to by the scatter/gather list registered in the &ahash_request * handle * * Return: see crypto_ahash_final() */ static inline int crypto_ahash_update(struct ahash_request *req) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); struct crypto_alg *alg = tfm->base.__crt_alg; unsigned int nbytes = req->nbytes; int ret; crypto_stats_get(alg); ret = crypto_ahash_reqtfm(req)->update(req); crypto_stats_ahash_update(nbytes, ret, alg); return ret; } /** * DOC: Asynchronous Hash Request Handle * * The &ahash_request data structure contains all pointers to data * required for the asynchronous cipher operation. This includes the cipher * handle (which can be used by multiple &ahash_request instances), pointer * to plaintext and the message digest output buffer, asynchronous callback * function, etc. It acts as a handle to the ahash_request_* API calls in a * similar way as ahash handle to the crypto_ahash_* API calls. */ /** * ahash_request_set_tfm() - update cipher handle reference in request * @req: request handle to be modified * @tfm: cipher handle that shall be added to the request handle * * Allow the caller to replace the existing ahash handle in the request * data structure with a different one. */ static inline void ahash_request_set_tfm(struct ahash_request *req, struct crypto_ahash *tfm) { req->base.tfm = crypto_ahash_tfm(tfm); } /** * ahash_request_alloc() - allocate request data structure * @tfm: cipher handle to be registered with the request * @gfp: memory allocation flag that is handed to kmalloc by the API call. * * Allocate the request data structure that must be used with the ahash * message digest API calls. During * the allocation, the provided ahash handle * is registered in the request data structure. * * Return: allocated request handle in case of success, or NULL if out of memory */ static inline struct ahash_request *ahash_request_alloc( struct crypto_ahash *tfm, gfp_t gfp) { struct ahash_request *req; req = kmalloc(sizeof(struct ahash_request) + crypto_ahash_reqsize(tfm), gfp); if (likely(req)) ahash_request_set_tfm(req, tfm); return req; } /** * ahash_request_free() - zeroize and free the request data structure * @req: request data structure cipher handle to be freed */ static inline void ahash_request_free(struct ahash_request *req) { kfree_sensitive(req); } static inline void ahash_request_zero(struct ahash_request *req) { memzero_explicit(req, sizeof(*req) + crypto_ahash_reqsize(crypto_ahash_reqtfm(req))); } static inline struct ahash_request *ahash_request_cast( struct crypto_async_request *req) { return container_of(req, struct ahash_request, base); } /** * ahash_request_set_callback() - set asynchronous callback function * @req: request handle * @flags: specify zero or an ORing of the flags * CRYPTO_TFM_REQ_MAY_BACKLOG the request queue may back log and * increase the wait queue beyond the initial maximum size; * CRYPTO_TFM_REQ_MAY_SLEEP the request processing may sleep * @compl: callback function pointer to be registered with the request handle * @data: The data pointer refers to memory that is not used by the kernel * crypto API, but provided to the callback function for it to use. Here, * the caller can provide a reference to memory the callback function can * operate on. As the callback function is invoked asynchronously to the * related functionality, it may need to access data structures of the * related functionality which can be referenced using this pointer. The * callback function can access the memory via the "data" field in the * &crypto_async_request data structure provided to the callback function. * * This function allows setting the callback function that is triggered once * the cipher operation completes. * * The callback function is registered with the &ahash_request handle and * must comply with the following template:: * * void callback_function(struct crypto_async_request *req, int error) */ static inline void ahash_request_set_callback(struct ahash_request *req, u32 flags, crypto_completion_t compl, void *data) { req->base.complete = compl; req->base.data = data; req->base.flags = flags; } /** * ahash_request_set_crypt() - set data buffers * @req: ahash_request handle to be updated * @src: source scatter/gather list * @result: buffer that is filled with the message digest -- the caller must * ensure that the buffer has sufficient space by, for example, calling * crypto_ahash_digestsize() * @nbytes: number of bytes to process from the source scatter/gather list * * By using this call, the caller references the source scatter/gather list. * The source scatter/gather list points to the data the message digest is to * be calculated for. */ static inline void ahash_request_set_crypt(struct ahash_request *req, struct scatterlist *src, u8 *result, unsigned int nbytes) { req->src = src; req->nbytes = nbytes; req->result = result; } /** * DOC: Synchronous Message Digest API * * The synchronous message digest API is used with the ciphers of type * CRYPTO_ALG_TYPE_SHASH (listed as type "shash" in /proc/crypto) * * The message digest API is able to maintain state information for the * caller. * * The synchronous message digest API can store user-related context in its * shash_desc request data structure. */ /** * crypto_alloc_shash() - allocate message digest handle * @alg_name: is the cra_name / name or cra_driver_name / driver name of the * message digest cipher * @type: specifies the type of the cipher * @mask: specifies the mask for the cipher * * Allocate a cipher handle for a message digest. The returned &struct * crypto_shash is the cipher handle that is required for any subsequent * API invocation for that message digest. * * Return: allocated cipher handle in case of success; IS_ERR() is true in case * of an error, PTR_ERR() returns the error code. */ struct crypto_shash *crypto_alloc_shash(const char *alg_name, u32 type, u32 mask); int crypto_has_shash(const char *alg_name, u32 type, u32 mask); static inline struct crypto_tfm *crypto_shash_tfm(struct crypto_shash *tfm) { return &tfm->base; } /** * crypto_free_shash() - zeroize and free the message digest handle * @tfm: cipher handle to be freed * * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_shash(struct crypto_shash *tfm) { crypto_destroy_tfm(tfm, crypto_shash_tfm(tfm)); } static inline const char *crypto_shash_alg_name(struct crypto_shash *tfm) { return crypto_tfm_alg_name(crypto_shash_tfm(tfm)); } static inline const char *crypto_shash_driver_name(struct crypto_shash *tfm) { return crypto_tfm_alg_driver_name(crypto_shash_tfm(tfm)); } static inline unsigned int crypto_shash_alignmask( struct crypto_shash *tfm) { return crypto_tfm_alg_alignmask(crypto_shash_tfm(tfm)); } /** * crypto_shash_blocksize() - obtain block size for cipher * @tfm: cipher handle * * The block size for the message digest cipher referenced with the cipher * handle is returned. * * Return: block size of cipher */ static inline unsigned int crypto_shash_blocksize(struct crypto_shash *tfm) { return crypto_tfm_alg_blocksize(crypto_shash_tfm(tfm)); } static inline struct shash_alg *__crypto_shash_alg(struct crypto_alg *alg) { return container_of(alg, struct shash_alg, base); } static inline struct shash_alg *crypto_shash_alg(struct crypto_shash *tfm) { return __crypto_shash_alg(crypto_shash_tfm(tfm)->__crt_alg); } /** * crypto_shash_digestsize() - obtain message digest size * @tfm: cipher handle * * The size for the message digest created by the message digest cipher * referenced with the cipher handle is returned. * * Return: digest size of cipher */ static inline unsigned int crypto_shash_digestsize(struct crypto_shash *tfm) { return crypto_shash_alg(tfm)->digestsize; } static inline unsigned int crypto_shash_statesize(struct crypto_shash *tfm) { return crypto_shash_alg(tfm)->statesize; } static inline u32 crypto_shash_get_flags(struct crypto_shash *tfm) { return crypto_tfm_get_flags(crypto_shash_tfm(tfm)); } static inline void crypto_shash_set_flags(struct crypto_shash *tfm, u32 flags) { crypto_tfm_set_flags(crypto_shash_tfm(tfm), flags); } static inline void crypto_shash_clear_flags(struct crypto_shash *tfm, u32 flags) { crypto_tfm_clear_flags(crypto_shash_tfm(tfm), flags); } /** * crypto_shash_descsize() - obtain the operational state size * @tfm: cipher handle * * The size of the operational state the cipher needs during operation is * returned for the hash referenced with the cipher handle. This size is * required to calculate the memory requirements to allow the caller allocating * sufficient memory for operational state. * * The operational state is defined with struct shash_desc where the size of * that data structure is to be calculated as * sizeof(struct shash_desc) + crypto_shash_descsize(alg) * * Return: size of the operational state */ static inline unsigned int crypto_shash_descsize(struct crypto_shash *tfm) { return tfm->descsize; } static inline void *shash_desc_ctx(struct shash_desc *desc) { return desc->__ctx; } /** * crypto_shash_setkey() - set key for message digest * @tfm: cipher handle * @key: buffer holding the key * @keylen: length of the key in bytes * * The caller provided key is set for the keyed message digest cipher. The * cipher handle must point to a keyed message digest cipher in order for this * function to succeed. * * Context: Any context. * Return: 0 if the setting of the key was successful; < 0 if an error occurred */ int crypto_shash_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen); /** * crypto_shash_digest() - calculate message digest for buffer * @desc: see crypto_shash_final() * @data: see crypto_shash_update() * @len: see crypto_shash_update() * @out: see crypto_shash_final() * * This function is a "short-hand" for the function calls of crypto_shash_init, * crypto_shash_update and crypto_shash_final. The parameters have the same * meaning as discussed for those separate three functions. * * Context: Any context. * Return: 0 if the message digest creation was successful; < 0 if an error * occurred */ int crypto_shash_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out); /** * crypto_shash_tfm_digest() - calculate message digest for buffer * @tfm: hash transformation object * @data: see crypto_shash_update() * @len: see crypto_shash_update() * @out: see crypto_shash_final() * * This is a simplified version of crypto_shash_digest() for users who don't * want to allocate their own hash descriptor (shash_desc). Instead, * crypto_shash_tfm_digest() takes a hash transformation object (crypto_shash) * directly, and it allocates a hash descriptor on the stack internally. * Note that this stack allocation may be fairly large. * * Context: Any context. * Return: 0 on success; < 0 if an error occurred. */ int crypto_shash_tfm_digest(struct crypto_shash *tfm, const u8 *data, unsigned int len, u8 *out); /** * crypto_shash_export() - extract operational state for message digest * @desc: reference to the operational state handle whose state is exported * @out: output buffer of sufficient size that can hold the hash state * * This function exports the hash state of the operational state handle into the * caller-allocated output buffer out which must have sufficient size (e.g. by * calling crypto_shash_descsize). * * Context: Any context. * Return: 0 if the export creation was successful; < 0 if an error occurred */ static inline int crypto_shash_export(struct shash_desc *desc, void *out) { return crypto_shash_alg(desc->tfm)->export(desc, out); } /** * crypto_shash_import() - import operational state * @desc: reference to the operational state handle the state imported into * @in: buffer holding the state * * This function imports the hash state into the operational state handle from * the input buffer. That buffer should have been generated with the * crypto_ahash_export function. * * Context: Any context. * Return: 0 if the import was successful; < 0 if an error occurred */ static inline int crypto_shash_import(struct shash_desc *desc, const void *in) { struct crypto_shash *tfm = desc->tfm; if (crypto_shash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; return crypto_shash_alg(tfm)->import(desc, in); } /** * crypto_shash_init() - (re)initialize message digest * @desc: operational state handle that is already filled * * The call (re-)initializes the message digest referenced by the * operational state handle. Any potentially existing state created by * previous operations is discarded. * * Context: Any context. * Return: 0 if the message digest initialization was successful; < 0 if an * error occurred */ static inline int crypto_shash_init(struct shash_desc *desc) { struct crypto_shash *tfm = desc->tfm; if (crypto_shash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; return crypto_shash_alg(tfm)->init(desc); } /** * crypto_shash_update() - add data to message digest for processing * @desc: operational state handle that is already initialized * @data: input data to be added to the message digest * @len: length of the input data * * Updates the message digest state of the operational state handle. * * Context: Any context. * Return: 0 if the message digest update was successful; < 0 if an error * occurred */ int crypto_shash_update(struct shash_desc *desc, const u8 *data, unsigned int len); /** * crypto_shash_final() - calculate message digest * @desc: operational state handle that is already filled with data * @out: output buffer filled with the message digest * * Finalize the message digest operation and create the message digest * based on all data added to the cipher handle. The message digest is placed * into the output buffer. The caller must ensure that the output buffer is * large enough by using crypto_shash_digestsize. * * Context: Any context. * Return: 0 if the message digest creation was successful; < 0 if an error * occurred */ int crypto_shash_final(struct shash_desc *desc, u8 *out); /** * crypto_shash_finup() - calculate message digest of buffer * @desc: see crypto_shash_final() * @data: see crypto_shash_update() * @len: see crypto_shash_update() * @out: see crypto_shash_final() * * This function is a "short-hand" for the function calls of * crypto_shash_update and crypto_shash_final. The parameters have the same * meaning as discussed for those separate functions. * * Context: Any context. * Return: 0 if the message digest creation was successful; < 0 if an error * occurred */ int crypto_shash_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out); static inline void shash_desc_zero(struct shash_desc *desc) { memzero_explicit(desc, sizeof(*desc) + crypto_shash_descsize(desc->tfm)); } #endif /* _CRYPTO_HASH_H */ |
| 47 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 | // SPDX-License-Identifier: GPL-2.0-only /* * 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. * * Implementation of the Transmission Control Protocol(TCP). * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * Corey Minyard <wf-rch!minyard@relay.EU.net> * Florian La Roche, <flla@stud.uni-sb.de> * Charles Hedrick, <hedrick@klinzhai.rutgers.edu> * Linus Torvalds, <torvalds@cs.helsinki.fi> * Alan Cox, <gw4pts@gw4pts.ampr.org> * Matthew Dillon, <dillon@apollo.west.oic.com> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Jorge Cwik, <jorge@laser.satlink.net> */ #include <linux/module.h> #include <linux/gfp.h> #include <net/tcp.h> static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); u32 elapsed, start_ts; s32 remaining; start_ts = tcp_sk(sk)->retrans_stamp; if (!icsk->icsk_user_timeout) return icsk->icsk_rto; elapsed = tcp_time_stamp(tcp_sk(sk)) - start_ts; remaining = icsk->icsk_user_timeout - elapsed; if (remaining <= 0) return 1; /* user timeout has passed; fire ASAP */ return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(remaining)); } u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when) { struct inet_connection_sock *icsk = inet_csk(sk); u32 remaining; s32 elapsed; if (!icsk->icsk_user_timeout || !icsk->icsk_probes_tstamp) return when; elapsed = tcp_jiffies32 - icsk->icsk_probes_tstamp; if (unlikely(elapsed < 0)) elapsed = 0; remaining = msecs_to_jiffies(icsk->icsk_user_timeout) - elapsed; remaining = max_t(u32, remaining, TCP_TIMEOUT_MIN); return min_t(u32, remaining, when); } /** * tcp_write_err() - close socket and save error info * @sk: The socket the error has appeared on. * * Returns: Nothing (void) */ static void tcp_write_err(struct sock *sk) { tcp_done_with_error(sk, READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT); } /** * tcp_out_of_resources() - Close socket if out of resources * @sk: pointer to current socket * @do_reset: send a last packet with reset flag * * Do not allow orphaned sockets to eat all our resources. * This is direct violation of TCP specs, but it is required * to prevent DoS attacks. It is called when a retransmission timeout * or zero probe timeout occurs on orphaned socket. * * Also close if our net namespace is exiting; in that case there is no * hope of ever communicating again since all netns interfaces are already * down (or about to be down), and we need to release our dst references, * which have been moved to the netns loopback interface, so the namespace * can finish exiting. This condition is only possible if we are a kernel * socket, as those do not hold references to the namespace. * * Criteria is still not confirmed experimentally and may change. * We kill the socket, if: * 1. If number of orphaned sockets exceeds an administratively configured * limit. * 2. If we have strong memory pressure. * 3. If our net namespace is exiting. */ static int tcp_out_of_resources(struct sock *sk, bool do_reset) { struct tcp_sock *tp = tcp_sk(sk); int shift = 0; /* If peer does not open window for long time, or did not transmit * anything for long time, penalize it. */ if ((s32)(tcp_jiffies32 - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset) shift++; /* If some dubious ICMP arrived, penalize even more. */ if (READ_ONCE(sk->sk_err_soft)) shift++; if (tcp_check_oom(sk, shift)) { /* Catch exceptional cases, when connection requires reset. * 1. Last segment was sent recently. */ if ((s32)(tcp_jiffies32 - tp->lsndtime) <= TCP_TIMEWAIT_LEN || /* 2. Window is closed. */ (!tp->snd_wnd && !tp->packets_out)) do_reset = true; if (do_reset) tcp_send_active_reset(sk, GFP_ATOMIC); tcp_done(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); return 1; } if (!check_net(sock_net(sk))) { /* Not possible to send reset; just close */ tcp_done(sk); return 1; } return 0; } /** * tcp_orphan_retries() - Returns maximal number of retries on an orphaned socket * @sk: Pointer to the current socket. * @alive: bool, socket alive state */ static int tcp_orphan_retries(struct sock *sk, bool alive) { int retries = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_orphan_retries); /* May be zero. */ /* We know from an ICMP that something is wrong. */ if (READ_ONCE(sk->sk_err_soft) && !alive) retries = 0; /* However, if socket sent something recently, select some safe * number of retries. 8 corresponds to >100 seconds with minimal * RTO of 200msec. */ if (retries == 0 && alive) retries = 8; return retries; } static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) { const struct net *net = sock_net(sk); int mss; /* Black hole detection */ if (!READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing)) return; if (!icsk->icsk_mtup.enabled) { icsk->icsk_mtup.enabled = 1; icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; } else { mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1; mss = min(READ_ONCE(net->ipv4.sysctl_tcp_base_mss), mss); mss = max(mss, READ_ONCE(net->ipv4.sysctl_tcp_mtu_probe_floor)); mss = max(mss, READ_ONCE(net->ipv4.sysctl_tcp_min_snd_mss)); icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); } tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); } static unsigned int tcp_model_timeout(struct sock *sk, unsigned int boundary, unsigned int rto_base) { unsigned int linear_backoff_thresh, timeout; linear_backoff_thresh = ilog2(TCP_RTO_MAX / rto_base); if (boundary <= linear_backoff_thresh) timeout = ((2 << boundary) - 1) * rto_base; else timeout = ((2 << linear_backoff_thresh) - 1) * rto_base + (boundary - linear_backoff_thresh) * TCP_RTO_MAX; return jiffies_to_msecs(timeout); } /** * retransmits_timed_out() - returns true if this connection has timed out * @sk: The current socket * @boundary: max number of retransmissions * @timeout: A custom timeout value. * If set to 0 the default timeout is calculated and used. * Using TCP_RTO_MIN and the number of unsuccessful retransmits. * * The default "timeout" value this function can calculate and use * is equivalent to the timeout of a TCP Connection * after "boundary" unsuccessful, exponentially backed-off * retransmissions with an initial RTO of TCP_RTO_MIN. */ static bool retransmits_timed_out(struct sock *sk, unsigned int boundary, unsigned int timeout) { unsigned int start_ts; if (!inet_csk(sk)->icsk_retransmits) return false; start_ts = tcp_sk(sk)->retrans_stamp; if (likely(timeout == 0)) { unsigned int rto_base = TCP_RTO_MIN; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) rto_base = tcp_timeout_init(sk); timeout = tcp_model_timeout(sk, boundary, rto_base); } return (s32)(tcp_time_stamp(tcp_sk(sk)) - start_ts - timeout) >= 0; } /* A write timeout has occurred. Process the after effects. */ static int tcp_write_timeout(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); bool expired = false, do_reset; int retry_until; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) __dst_negative_advice(sk); retry_until = icsk->icsk_syn_retries ? : READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); expired = icsk->icsk_retransmits >= retry_until; } else { if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1), 0)) { /* Black hole detection */ tcp_mtu_probing(icsk, sk); __dst_negative_advice(sk); } retry_until = READ_ONCE(net->ipv4.sysctl_tcp_retries2); if (sock_flag(sk, SOCK_DEAD)) { const bool alive = icsk->icsk_rto < TCP_RTO_MAX; retry_until = tcp_orphan_retries(sk, alive); do_reset = alive || !retransmits_timed_out(sk, retry_until, 0); if (tcp_out_of_resources(sk, do_reset)) return 1; } } if (!expired) expired = retransmits_timed_out(sk, retry_until, icsk->icsk_user_timeout); tcp_fastopen_active_detect_blackhole(sk, expired); if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTO_CB_FLAG)) tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RTO_CB, icsk->icsk_retransmits, icsk->icsk_rto, (int)expired); if (expired) { /* Has it gone just too far? */ tcp_write_err(sk); return 1; } if (sk_rethink_txhash(sk)) { tp->timeout_rehash++; __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTREHASH); } return 0; } /* Called with BH disabled */ void tcp_delack_timer_handler(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) return; /* Handling the sack compression case */ if (tp->compressed_ack) { tcp_mstamp_refresh(tp); tcp_sack_compress_send_ack(sk); return; } if (!(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) return; if (time_after(icsk->icsk_ack.timeout, jiffies)) { sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout); return; } icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER; if (inet_csk_ack_scheduled(sk)) { if (!inet_csk_in_pingpong_mode(sk)) { /* Delayed ACK missed: inflate ATO. */ icsk->icsk_ack.ato = min(icsk->icsk_ack.ato << 1, icsk->icsk_rto); } else { /* Delayed ACK missed: leave pingpong mode and * deflate ATO. */ inet_csk_exit_pingpong_mode(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; } tcp_mstamp_refresh(tp); tcp_send_ack(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS); } } /** * tcp_delack_timer() - The TCP delayed ACK timeout handler * @t: Pointer to the timer. (gets casted to struct sock *) * * This function gets (indirectly) called when the kernel timer for a TCP packet * of this socket expires. Calls tcp_delack_timer_handler() to do the actual work. * * Returns: Nothing (void) */ static void tcp_delack_timer(struct timer_list *t) { struct inet_connection_sock *icsk = from_timer(icsk, t, icsk_delack_timer); struct sock *sk = &icsk->icsk_inet.sk; bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { tcp_delack_timer_handler(sk); } else { __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED); /* deleguate our work to tcp_release_cb() */ if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); } bh_unlock_sock(sk); sock_put(sk); } static void tcp_probe_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct sk_buff *skb = tcp_send_head(sk); struct tcp_sock *tp = tcp_sk(sk); int max_probes; if (tp->packets_out || !skb) { icsk->icsk_probes_out = 0; icsk->icsk_probes_tstamp = 0; return; } /* RFC 1122 4.2.2.17 requires the sender to stay open indefinitely as * long as the receiver continues to respond probes. We support this by * default and reset icsk_probes_out with incoming ACKs. But if the * socket is orphaned or the user specifies TCP_USER_TIMEOUT, we * kill the socket when the retry count and the time exceeds the * corresponding system limit. We also implement similar policy when * we use RTO to probe window in tcp_retransmit_timer(). */ if (!icsk->icsk_probes_tstamp) icsk->icsk_probes_tstamp = tcp_jiffies32; else if (icsk->icsk_user_timeout && (s32)(tcp_jiffies32 - icsk->icsk_probes_tstamp) >= msecs_to_jiffies(icsk->icsk_user_timeout)) goto abort; max_probes = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retries2); if (sock_flag(sk, SOCK_DEAD)) { const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX; max_probes = tcp_orphan_retries(sk, alive); if (!alive && icsk->icsk_backoff >= max_probes) goto abort; if (tcp_out_of_resources(sk, true)) return; } if (icsk->icsk_probes_out >= max_probes) { abort: tcp_write_err(sk); } else { /* Only send another probe if we didn't close things up. */ tcp_send_probe0(sk); } } /* * Timer for Fast Open socket to retransmit SYNACK. Note that the * sk here is the child socket, not the parent (listener) socket. */ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int max_retries; req->rsk_ops->syn_ack_timeout(req); /* add one more retry for fastopen */ max_retries = icsk->icsk_syn_retries ? : READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_synack_retries) + 1; if (req->num_timeout >= max_retries) { tcp_write_err(sk); return; } /* Lower cwnd after certain SYNACK timeout like tcp_init_transfer() */ if (icsk->icsk_retransmits == 1) tcp_enter_loss(sk); /* XXX (TFO) - Unlike regular SYN-ACK retransmit, we ignore error * returned from rtx_syn_ack() to make it more persistent like * regular retransmit because if the child socket has been accepted * it's not good to give up too easily. */ inet_rtx_syn_ack(sk, req); req->num_timeout++; icsk->icsk_retransmits++; if (!tp->retrans_stamp) tp->retrans_stamp = tcp_time_stamp(tp); inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, req->timeout << req->num_timeout, TCP_RTO_MAX); } static bool tcp_rtx_probe0_timed_out(const struct sock *sk, const struct sk_buff *skb) { const struct inet_connection_sock *icsk = inet_csk(sk); u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout); const struct tcp_sock *tp = tcp_sk(sk); int timeout = TCP_RTO_MAX * 2; u32 rtx_delta; s32 rcv_delta; rtx_delta = (u32)msecs_to_jiffies(tcp_time_stamp(tp) - (tp->retrans_stamp ?: tcp_skb_timestamp(skb))); if (user_timeout) { /* If user application specified a TCP_USER_TIMEOUT, * it does not want win 0 packets to 'reset the timer' * while retransmits are not making progress. */ if (rtx_delta > user_timeout) return true; timeout = min_t(u32, timeout, msecs_to_jiffies(user_timeout)); } /* Note: timer interrupt might have been delayed by at least one jiffy, * and tp->rcv_tstamp might very well have been written recently. * rcv_delta can thus be negative. */ rcv_delta = icsk->icsk_timeout - tp->rcv_tstamp; if (rcv_delta <= timeout) return false; return rtx_delta > timeout; } /** * tcp_retransmit_timer() - The TCP retransmit timeout handler * @sk: Pointer to the current socket. * * This function gets called when the kernel timer for a TCP packet * of this socket expires. * * It handles retransmission, timer adjustment and other necessary measures. * * Returns: Nothing (void) */ void tcp_retransmit_timer(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct inet_connection_sock *icsk = inet_csk(sk); struct request_sock *req; struct sk_buff *skb; req = rcu_dereference_protected(tp->fastopen_rsk, lockdep_sock_is_held(sk)); if (req) { WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); tcp_fastopen_synack_timer(sk, req); /* Before we receive ACK to our SYN-ACK don't retransmit * anything else (e.g., data or FIN segments). */ return; } if (!tp->packets_out) return; skb = tcp_rtx_queue_head(sk); if (WARN_ON_ONCE(!skb)) return; if (!tp->snd_wnd && !sock_flag(sk, SOCK_DEAD) && !((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))) { /* Receiver dastardly shrinks window. Our retransmits * become zero probes, but we should not timeout this * connection. If the socket is an orphan, time it out, * we cannot allow such beasts to hang infinitely. */ struct inet_sock *inet = inet_sk(sk); if (sk->sk_family == AF_INET) { net_dbg_ratelimited("Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n", &inet->inet_daddr, ntohs(inet->inet_dport), inet->inet_num, tp->snd_una, tp->snd_nxt); } #if IS_ENABLED(CONFIG_IPV6) else if (sk->sk_family == AF_INET6) { net_dbg_ratelimited("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n", &sk->sk_v6_daddr, ntohs(inet->inet_dport), inet->inet_num, tp->snd_una, tp->snd_nxt); } #endif if (tcp_rtx_probe0_timed_out(sk, skb)) { tcp_write_err(sk); goto out; } tcp_enter_loss(sk); tcp_retransmit_skb(sk, skb, 1); __sk_dst_reset(sk); goto out_reset_timer; } __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTS); if (tcp_write_timeout(sk)) goto out; if (icsk->icsk_retransmits == 0) { int mib_idx = 0; if (icsk->icsk_ca_state == TCP_CA_Recovery) { if (tcp_is_sack(tp)) mib_idx = LINUX_MIB_TCPSACKRECOVERYFAIL; else mib_idx = LINUX_MIB_TCPRENORECOVERYFAIL; } else if (icsk->icsk_ca_state == TCP_CA_Loss) { mib_idx = LINUX_MIB_TCPLOSSFAILURES; } else if ((icsk->icsk_ca_state == TCP_CA_Disorder) || tp->sacked_out) { if (tcp_is_sack(tp)) mib_idx = LINUX_MIB_TCPSACKFAILURES; else mib_idx = LINUX_MIB_TCPRENOFAILURES; } if (mib_idx) __NET_INC_STATS(sock_net(sk), mib_idx); } tcp_enter_loss(sk); icsk->icsk_retransmits++; if (tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1) > 0) { /* Retransmission failed because of local congestion, * Let senders fight for local resources conservatively. */ inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, TCP_RESOURCE_PROBE_INTERVAL, TCP_RTO_MAX); goto out; } /* Increase the timeout each time we retransmit. Note that * we do not increase the rtt estimate. rto is initialized * from rtt, but increases here. Jacobson (SIGCOMM 88) suggests * that doubling rto each time is the least we can get away with. * In KA9Q, Karn uses this for the first few times, and then * goes to quadratic. netBSD doubles, but only goes up to *64, * and clamps at 1 to 64 sec afterwards. Note that 120 sec is * defined in the protocol as the maximum possible RTT. I guess * we'll have to use something other than TCP to talk to the * University of Mars. * * PAWS allows us longer timeouts and large windows, so once * implemented ftp to mars will work nicely. We will have to fix * the 120 second clamps though! */ icsk->icsk_backoff++; out_reset_timer: /* If stream is thin, use linear timeouts. Since 'icsk_backoff' is * used to reset timer, set to 0. Recalculate 'icsk_rto' as this * might be increased if the stream oscillates between thin and thick, * thus the old value might already be too high compared to the value * set by 'tcp_set_rto' in tcp_input.c which resets the rto without * backoff. Limit to TCP_THIN_LINEAR_RETRIES before initiating * exponential backoff behaviour to avoid continue hammering * linear-timeout retransmissions into a black hole */ if (sk->sk_state == TCP_ESTABLISHED && (tp->thin_lto || READ_ONCE(net->ipv4.sysctl_tcp_thin_linear_timeouts)) && tcp_stream_is_thin(tp) && icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) { icsk->icsk_backoff = 0; icsk->icsk_rto = clamp(__tcp_set_rto(tp), tcp_rto_min(sk), TCP_RTO_MAX); } else { /* Use normal (exponential) backoff */ icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX); } inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, tcp_clamp_rto_to_user_timeout(sk), TCP_RTO_MAX); if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1) + 1, 0)) __sk_dst_reset(sk); out:; } /* Called with bottom-half processing disabled. Called by tcp_write_timer() */ void tcp_write_timer_handler(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); int event; if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || !icsk->icsk_pending) return; if (time_after(icsk->icsk_timeout, jiffies)) { sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout); return; } tcp_mstamp_refresh(tcp_sk(sk)); event = icsk->icsk_pending; switch (event) { case ICSK_TIME_REO_TIMEOUT: tcp_rack_reo_timeout(sk); break; case ICSK_TIME_LOSS_PROBE: tcp_send_loss_probe(sk); break; case ICSK_TIME_RETRANS: icsk->icsk_pending = 0; tcp_retransmit_timer(sk); break; case ICSK_TIME_PROBE0: icsk->icsk_pending = 0; tcp_probe_timer(sk); break; } } static void tcp_write_timer(struct timer_list *t) { struct inet_connection_sock *icsk = from_timer(icsk, t, icsk_retransmit_timer); struct sock *sk = &icsk->icsk_inet.sk; bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { tcp_write_timer_handler(sk); } else { /* delegate our work to tcp_release_cb() */ if (!test_and_set_bit(TCP_WRITE_TIMER_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); } bh_unlock_sock(sk); sock_put(sk); } void tcp_syn_ack_timeout(const struct request_sock *req) { struct net *net = read_pnet(&inet_rsk(req)->ireq_net); __NET_INC_STATS(net, LINUX_MIB_TCPTIMEOUTS); } EXPORT_SYMBOL(tcp_syn_ack_timeout); void tcp_set_keepalive(struct sock *sk, int val) { if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) return; if (val && !sock_flag(sk, SOCK_KEEPOPEN)) inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tcp_sk(sk))); else if (!val) inet_csk_delete_keepalive_timer(sk); } EXPORT_SYMBOL_GPL(tcp_set_keepalive); static void tcp_keepalive_timer (struct timer_list *t) { struct sock *sk = from_timer(sk, t, sk_timer); struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); u32 elapsed; /* Only process if socket is not in use. */ bh_lock_sock(sk); if (sock_owned_by_user(sk)) { /* Try again later. */ inet_csk_reset_keepalive_timer (sk, HZ/20); goto out; } if (sk->sk_state == TCP_LISTEN) { pr_err("Hmm... keepalive on a LISTEN ???\n"); goto out; } tcp_mstamp_refresh(tp); if (sk->sk_state == TCP_FIN_WAIT2 && sock_flag(sk, SOCK_DEAD)) { if (tp->linger2 >= 0) { const int tmo = tcp_fin_time(sk) - TCP_TIMEWAIT_LEN; if (tmo > 0) { tcp_time_wait(sk, TCP_FIN_WAIT2, tmo); goto out; } } tcp_send_active_reset(sk, GFP_ATOMIC); goto death; } if (!sock_flag(sk, SOCK_KEEPOPEN) || ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT))) goto out; elapsed = keepalive_time_when(tp); /* It is alive without keepalive 8) */ if (tp->packets_out || !tcp_write_queue_empty(sk)) goto resched; elapsed = keepalive_time_elapsed(tp); if (elapsed >= keepalive_time_when(tp)) { /* If the TCP_USER_TIMEOUT option is enabled, use that * to determine when to timeout instead. */ if ((icsk->icsk_user_timeout != 0 && elapsed >= msecs_to_jiffies(icsk->icsk_user_timeout) && icsk->icsk_probes_out > 0) || (icsk->icsk_user_timeout == 0 && icsk->icsk_probes_out >= keepalive_probes(tp))) { tcp_send_active_reset(sk, GFP_ATOMIC); tcp_write_err(sk); goto out; } if (tcp_write_wakeup(sk, LINUX_MIB_TCPKEEPALIVE) <= 0) { icsk->icsk_probes_out++; elapsed = keepalive_intvl_when(tp); } else { /* If keepalive was lost due to local congestion, * try harder. */ elapsed = TCP_RESOURCE_PROBE_INTERVAL; } } else { /* It is tp->rcv_tstamp + keepalive_time_when(tp) */ elapsed = keepalive_time_when(tp) - elapsed; } resched: inet_csk_reset_keepalive_timer (sk, elapsed); goto out; death: tcp_done(sk); out: bh_unlock_sock(sk); sock_put(sk); } static enum hrtimer_restart tcp_compressed_ack_kick(struct hrtimer *timer) { struct tcp_sock *tp = container_of(timer, struct tcp_sock, compressed_ack_timer); struct sock *sk = (struct sock *)tp; bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { if (tp->compressed_ack) { /* Since we have to send one ack finally, * subtract one from tp->compressed_ack to keep * LINUX_MIB_TCPACKCOMPRESSED accurate. */ tp->compressed_ack--; tcp_send_ack(sk); } } else { if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); } bh_unlock_sock(sk); sock_put(sk); return HRTIMER_NORESTART; } void tcp_init_xmit_timers(struct sock *sk) { inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer, &tcp_keepalive_timer); hrtimer_init(&tcp_sk(sk)->pacing_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_SOFT); tcp_sk(sk)->pacing_timer.function = tcp_pace_kick; hrtimer_init(&tcp_sk(sk)->compressed_ack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED_SOFT); tcp_sk(sk)->compressed_ack_timer.function = tcp_compressed_ack_kick; } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <linux/init.h> #include <linux/types.h> #include <linux/bpf_verifier.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <linux/filter.h> #include <net/tcp.h> #include <net/bpf_sk_storage.h> /* "extern" is to avoid sparse warning. It is only used in bpf_struct_ops.c. */ extern struct bpf_struct_ops bpf_tcp_congestion_ops; static u32 unsupported_ops[] = { offsetof(struct tcp_congestion_ops, get_info), }; static const struct btf_type *tcp_sock_type; static u32 tcp_sock_id, sock_id; static int bpf_tcp_ca_init(struct btf *btf) { s32 type_id; type_id = btf_find_by_name_kind(btf, "sock", BTF_KIND_STRUCT); if (type_id < 0) return -EINVAL; sock_id = type_id; type_id = btf_find_by_name_kind(btf, "tcp_sock", BTF_KIND_STRUCT); if (type_id < 0) return -EINVAL; tcp_sock_id = type_id; tcp_sock_type = btf_type_by_id(btf, tcp_sock_id); return 0; } static bool is_unsupported(u32 member_offset) { unsigned int i; for (i = 0; i < ARRAY_SIZE(unsupported_ops); i++) { if (member_offset == unsupported_ops[i]) return true; } return false; } extern struct btf *btf_vmlinux; static bool bpf_tcp_ca_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (!bpf_tracing_btf_ctx_access(off, size, type, prog, info)) return false; if (info->reg_type == PTR_TO_BTF_ID && info->btf_id == sock_id) /* promote it to tcp_sock */ info->btf_id = tcp_sock_id; return true; } static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id, enum bpf_type_flag *flag) { size_t end; if (atype == BPF_READ) return btf_struct_access(log, btf, t, off, size, atype, next_btf_id, flag); if (t != tcp_sock_type) { bpf_log(log, "only read is supported\n"); return -EACCES; } switch (off) { case offsetof(struct sock, sk_pacing_rate): end = offsetofend(struct sock, sk_pacing_rate); break; case offsetof(struct sock, sk_pacing_status): end = offsetofend(struct sock, sk_pacing_status); break; case bpf_ctx_range(struct inet_connection_sock, icsk_ca_priv): end = offsetofend(struct inet_connection_sock, icsk_ca_priv); break; case offsetof(struct inet_connection_sock, icsk_ack.pending): end = offsetofend(struct inet_connection_sock, icsk_ack.pending); break; case offsetof(struct tcp_sock, snd_cwnd): end = offsetofend(struct tcp_sock, snd_cwnd); break; case offsetof(struct tcp_sock, snd_cwnd_cnt): end = offsetofend(struct tcp_sock, snd_cwnd_cnt); break; case offsetof(struct tcp_sock, snd_ssthresh): end = offsetofend(struct tcp_sock, snd_ssthresh); break; case offsetof(struct tcp_sock, ecn_flags): end = offsetofend(struct tcp_sock, ecn_flags); break; default: bpf_log(log, "no write support to tcp_sock at off %d\n", off); return -EACCES; } if (off + size > end) { bpf_log(log, "write access at off %d with size %d beyond the member of tcp_sock ended at %zu\n", off, size, end); return -EACCES; } return 0; } BPF_CALL_2(bpf_tcp_send_ack, struct tcp_sock *, tp, u32, rcv_nxt) { /* bpf_tcp_ca prog cannot have NULL tp */ __tcp_send_ack((struct sock *)tp, rcv_nxt); return 0; } static const struct bpf_func_proto bpf_tcp_send_ack_proto = { .func = bpf_tcp_send_ack, .gpl_only = false, /* In case we want to report error later */ .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &tcp_sock_id, .arg2_type = ARG_ANYTHING, }; static u32 prog_ops_moff(const struct bpf_prog *prog) { const struct btf_member *m; const struct btf_type *t; u32 midx; midx = prog->expected_attach_type; t = bpf_tcp_congestion_ops.type; m = &btf_type_member(t)[midx]; return __btf_member_bit_offset(t, m) / 8; } static const struct bpf_func_proto * bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_tcp_send_ack: return &bpf_tcp_send_ack_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; case BPF_FUNC_setsockopt: /* Does not allow release() to call setsockopt. * release() is called when the current bpf-tcp-cc * is retiring. It is not allowed to call * setsockopt() to make further changes which * may potentially allocate new resources. */ if (prog_ops_moff(prog) != offsetof(struct tcp_congestion_ops, release)) return &bpf_sk_setsockopt_proto; return NULL; case BPF_FUNC_getsockopt: /* Since get/setsockopt is usually expected to * be available together, disable getsockopt for * release also to avoid usage surprise. * The bpf-tcp-cc already has a more powerful way * to read tcp_sock from the PTR_TO_BTF_ID. */ if (prog_ops_moff(prog) != offsetof(struct tcp_congestion_ops, release)) return &bpf_sk_getsockopt_proto; return NULL; case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id); } } BTF_SET8_START(bpf_tcp_ca_check_kfunc_ids) BTF_ID_FLAGS(func, tcp_reno_ssthresh) BTF_ID_FLAGS(func, tcp_reno_cong_avoid) BTF_ID_FLAGS(func, tcp_reno_undo_cwnd) BTF_ID_FLAGS(func, tcp_slow_start) BTF_ID_FLAGS(func, tcp_cong_avoid_ai) BTF_SET8_END(bpf_tcp_ca_check_kfunc_ids) static const struct btf_kfunc_id_set bpf_tcp_ca_kfunc_set = { .owner = THIS_MODULE, .set = &bpf_tcp_ca_check_kfunc_ids, }; static const struct bpf_verifier_ops bpf_tcp_ca_verifier_ops = { .get_func_proto = bpf_tcp_ca_get_func_proto, .is_valid_access = bpf_tcp_ca_is_valid_access, .btf_struct_access = bpf_tcp_ca_btf_struct_access, }; static int bpf_tcp_ca_init_member(const struct btf_type *t, const struct btf_member *member, void *kdata, const void *udata) { const struct tcp_congestion_ops *utcp_ca; struct tcp_congestion_ops *tcp_ca; u32 moff; utcp_ca = (const struct tcp_congestion_ops *)udata; tcp_ca = (struct tcp_congestion_ops *)kdata; moff = __btf_member_bit_offset(t, member) / 8; switch (moff) { case offsetof(struct tcp_congestion_ops, flags): if (utcp_ca->flags & ~TCP_CONG_MASK) return -EINVAL; tcp_ca->flags = utcp_ca->flags; return 1; case offsetof(struct tcp_congestion_ops, name): if (bpf_obj_name_cpy(tcp_ca->name, utcp_ca->name, sizeof(tcp_ca->name)) <= 0) return -EINVAL; if (tcp_ca_find(utcp_ca->name)) return -EEXIST; return 1; } return 0; } static int bpf_tcp_ca_check_member(const struct btf_type *t, const struct btf_member *member) { if (is_unsupported(__btf_member_bit_offset(t, member) / 8)) return -ENOTSUPP; return 0; } static int bpf_tcp_ca_reg(void *kdata) { return tcp_register_congestion_control(kdata); } static void bpf_tcp_ca_unreg(void *kdata) { tcp_unregister_congestion_control(kdata); } struct bpf_struct_ops bpf_tcp_congestion_ops = { .verifier_ops = &bpf_tcp_ca_verifier_ops, .reg = bpf_tcp_ca_reg, .unreg = bpf_tcp_ca_unreg, .check_member = bpf_tcp_ca_check_member, .init_member = bpf_tcp_ca_init_member, .init = bpf_tcp_ca_init, .name = "tcp_congestion_ops", }; static int __init bpf_tcp_ca_kfunc_init(void) { return register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set); } late_initcall(bpf_tcp_ca_kfunc_init); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MEMREMAP_H_ #define _LINUX_MEMREMAP_H_ #include <linux/mmzone.h> #include <linux/range.h> #include <linux/ioport.h> #include <linux/percpu-refcount.h> struct resource; struct device; /** * struct vmem_altmap - pre-allocated storage for vmemmap_populate * @base_pfn: base of the entire dev_pagemap mapping * @reserve: pages mapped, but reserved for driver use (relative to @base) * @free: free pages set aside in the mapping for memmap storage * @align: pages reserved to meet allocation alignments * @alloc: track pages consumed, private to vmemmap_populate() */ struct vmem_altmap { unsigned long base_pfn; const unsigned long end_pfn; const unsigned long reserve; unsigned long free; unsigned long align; unsigned long alloc; }; /* * Specialize ZONE_DEVICE memory into multiple types each has a different * usage. * * MEMORY_DEVICE_PRIVATE: * Device memory that is not directly addressable by the CPU: CPU can neither * read nor write private memory. In this case, we do still have struct pages * backing the device memory. Doing so simplifies the implementation, but it is * important to remember that there are certain points at which the struct page * must be treated as an opaque object, rather than a "normal" struct page. * * A more complete discussion of unaddressable memory may be found in * include/linux/hmm.h and Documentation/mm/hmm.rst. * * MEMORY_DEVICE_COHERENT: * Device memory that is cache coherent from device and CPU point of view. This * is used on platforms that have an advanced system bus (like CAPI or CXL). A * driver can hotplug the device memory using ZONE_DEVICE and with that memory * type. Any page of a process can be migrated to such memory. However no one * should be allowed to pin such memory so that it can always be evicted. * * MEMORY_DEVICE_FS_DAX: * Host memory that has similar access semantics as System RAM i.e. DMA * coherent and supports page pinning. In support of coordinating page * pinning vs other operations MEMORY_DEVICE_FS_DAX arranges for a * wakeup event whenever a page is unpinned and becomes idle. This * wakeup is used to coordinate physical address space management (ex: * fs truncate/hole punch) vs pinned pages (ex: device dma). * * MEMORY_DEVICE_GENERIC: * Host memory that has similar access semantics as System RAM i.e. DMA * coherent and supports page pinning. This is for example used by DAX devices * that expose memory using a character device. * * MEMORY_DEVICE_PCI_P2PDMA: * Device memory residing in a PCI BAR intended for use with Peer-to-Peer * transactions. */ enum memory_type { /* 0 is reserved to catch uninitialized type fields */ MEMORY_DEVICE_PRIVATE = 1, MEMORY_DEVICE_COHERENT, MEMORY_DEVICE_FS_DAX, MEMORY_DEVICE_GENERIC, MEMORY_DEVICE_PCI_P2PDMA, }; struct dev_pagemap_ops { /* * Called once the page refcount reaches 0. The reference count will be * reset to one by the core code after the method is called to prepare * for handing out the page again. */ void (*page_free)(struct page *page); /* * Used for private (un-addressable) device memory only. Must migrate * the page back to a CPU accessible page. */ vm_fault_t (*migrate_to_ram)(struct vm_fault *vmf); /* * Handle the memory failure happens on a range of pfns. Notify the * processes who are using these pfns, and try to recover the data on * them if necessary. The mf_flags is finally passed to the recover * function through the whole notify routine. * * When this is not implemented, or it returns -EOPNOTSUPP, the caller * will fall back to a common handler called mf_generic_kill_procs(). */ int (*memory_failure)(struct dev_pagemap *pgmap, unsigned long pfn, unsigned long nr_pages, int mf_flags); }; #define PGMAP_ALTMAP_VALID (1 << 0) /** * struct dev_pagemap - metadata for ZONE_DEVICE mappings * @altmap: pre-allocated/reserved memory for vmemmap allocations * @ref: reference count that pins the devm_memremap_pages() mapping * @done: completion for @ref * @type: memory type: see MEMORY_* in memory_hotplug.h * @flags: PGMAP_* flags to specify defailed behavior * @vmemmap_shift: structural definition of how the vmemmap page metadata * is populated, specifically the metadata page order. * A zero value (default) uses base pages as the vmemmap metadata * representation. A bigger value will set up compound struct pages * of the requested order value. * @ops: method table * @owner: an opaque pointer identifying the entity that manages this * instance. Used by various helpers to make sure that no * foreign ZONE_DEVICE memory is accessed. * @nr_range: number of ranges to be mapped * @range: range to be mapped when nr_range == 1 * @ranges: array of ranges to be mapped when nr_range > 1 */ struct dev_pagemap { struct vmem_altmap altmap; struct percpu_ref ref; struct completion done; enum memory_type type; unsigned int flags; unsigned long vmemmap_shift; const struct dev_pagemap_ops *ops; void *owner; int nr_range; union { struct range range; struct range ranges[0]; }; }; static inline bool pgmap_has_memory_failure(struct dev_pagemap *pgmap) { return pgmap->ops && pgmap->ops->memory_failure; } static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap) { if (pgmap->flags & PGMAP_ALTMAP_VALID) return &pgmap->altmap; return NULL; } static inline unsigned long pgmap_vmemmap_nr(struct dev_pagemap *pgmap) { return 1 << pgmap->vmemmap_shift; } static inline bool is_device_private_page(const struct page *page) { return IS_ENABLED(CONFIG_DEVICE_PRIVATE) && is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_PRIVATE; } static inline bool folio_is_device_private(const struct folio *folio) { return is_device_private_page(&folio->page); } static inline bool is_pci_p2pdma_page(const struct page *page) { return IS_ENABLED(CONFIG_PCI_P2PDMA) && is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; } static inline bool is_device_coherent_page(const struct page *page) { return is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_COHERENT; } static inline bool folio_is_device_coherent(const struct folio *folio) { return is_device_coherent_page(&folio->page); } #ifdef CONFIG_ZONE_DEVICE void zone_device_page_init(struct page *page); void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap); struct dev_pagemap *get_dev_pagemap(unsigned long pfn, struct dev_pagemap *pgmap); bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn); unsigned long vmem_altmap_offset(struct vmem_altmap *altmap); void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns); unsigned long memremap_compat_align(void); #else static inline void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) { /* * Fail attempts to call devm_memremap_pages() without * ZONE_DEVICE support enabled, this requires callers to fall * back to plain devm_memremap() based on config */ WARN_ON_ONCE(1); return ERR_PTR(-ENXIO); } static inline void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap) { } static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn, struct dev_pagemap *pgmap) { return NULL; } static inline bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn) { return false; } static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) { return 0; } static inline void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns) { } /* when memremap_pages() is disabled all archs can remap a single page */ static inline unsigned long memremap_compat_align(void) { return PAGE_SIZE; } #endif /* CONFIG_ZONE_DEVICE */ static inline void put_dev_pagemap(struct dev_pagemap *pgmap) { if (pgmap) percpu_ref_put(&pgmap->ref); } #endif /* _LINUX_MEMREMAP_H_ */ |
| 1905 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM pagemap #if !defined(_TRACE_PAGEMAP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PAGEMAP_H #include <linux/tracepoint.h> #include <linux/mm.h> #define PAGEMAP_MAPPED 0x0001u #define PAGEMAP_ANONYMOUS 0x0002u #define PAGEMAP_FILE 0x0004u #define PAGEMAP_SWAPCACHE 0x0008u #define PAGEMAP_SWAPBACKED 0x0010u #define PAGEMAP_MAPPEDDISK 0x0020u #define PAGEMAP_BUFFERS 0x0040u #define trace_pagemap_flags(folio) ( \ (folio_test_anon(folio) ? PAGEMAP_ANONYMOUS : PAGEMAP_FILE) | \ (folio_mapped(folio) ? PAGEMAP_MAPPED : 0) | \ (folio_test_swapcache(folio) ? PAGEMAP_SWAPCACHE : 0) | \ (folio_test_swapbacked(folio) ? PAGEMAP_SWAPBACKED : 0) | \ (folio_test_mappedtodisk(folio) ? PAGEMAP_MAPPEDDISK : 0) | \ (folio_test_private(folio) ? PAGEMAP_BUFFERS : 0) \ ) TRACE_EVENT(mm_lru_insertion, TP_PROTO(struct folio *folio), TP_ARGS(folio), TP_STRUCT__entry( __field(struct folio *, folio ) __field(unsigned long, pfn ) __field(enum lru_list, lru ) __field(unsigned long, flags ) ), TP_fast_assign( __entry->folio = folio; __entry->pfn = folio_pfn(folio); __entry->lru = folio_lru_list(folio); __entry->flags = trace_pagemap_flags(folio); ), /* Flag format is based on page-types.c formatting for pagemap */ TP_printk("folio=%p pfn=0x%lx lru=%d flags=%s%s%s%s%s%s", __entry->folio, __entry->pfn, __entry->lru, __entry->flags & PAGEMAP_MAPPED ? "M" : " ", __entry->flags & PAGEMAP_ANONYMOUS ? "a" : "f", __entry->flags & PAGEMAP_SWAPCACHE ? "s" : " ", __entry->flags & PAGEMAP_SWAPBACKED ? "b" : " ", __entry->flags & PAGEMAP_MAPPEDDISK ? "d" : " ", __entry->flags & PAGEMAP_BUFFERS ? "B" : " ") ); TRACE_EVENT(mm_lru_activate, TP_PROTO(struct folio *folio), TP_ARGS(folio), TP_STRUCT__entry( __field(struct folio *, folio ) __field(unsigned long, pfn ) ), TP_fast_assign( __entry->folio = folio; __entry->pfn = folio_pfn(folio); ), TP_printk("folio=%p pfn=0x%lx", __entry->folio, __entry->pfn) ); #endif /* _TRACE_PAGEMAP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 73 73 73 73 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 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-only #include <linux/module.h> #include <linux/errno.h> #include <linux/socket.h> #include <linux/udp.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/in6.h> #include <net/udp.h> #include <net/udp_tunnel.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/ip6_tunnel.h> #include <net/ip6_checksum.h> int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { struct sockaddr_in6 udp6_addr = {}; int err; struct socket *sock = NULL; err = sock_create_kern(net, AF_INET6, SOCK_DGRAM, 0, &sock); if (err < 0) goto error; if (cfg->ipv6_v6only) { err = ip6_sock_set_v6only(sock->sk); if (err < 0) goto error; } if (cfg->bind_ifindex) { err = sock_bindtoindex(sock->sk, cfg->bind_ifindex, true); if (err < 0) goto error; } udp6_addr.sin6_family = AF_INET6; memcpy(&udp6_addr.sin6_addr, &cfg->local_ip6, sizeof(udp6_addr.sin6_addr)); udp6_addr.sin6_port = cfg->local_udp_port; err = kernel_bind(sock, (struct sockaddr *)&udp6_addr, sizeof(udp6_addr)); if (err < 0) goto error; if (cfg->peer_udp_port) { memset(&udp6_addr, 0, sizeof(udp6_addr)); udp6_addr.sin6_family = AF_INET6; memcpy(&udp6_addr.sin6_addr, &cfg->peer_ip6, sizeof(udp6_addr.sin6_addr)); udp6_addr.sin6_port = cfg->peer_udp_port; err = kernel_connect(sock, (struct sockaddr *)&udp6_addr, sizeof(udp6_addr), 0); } if (err < 0) goto error; udp_set_no_check6_tx(sock->sk, !cfg->use_udp6_tx_checksums); udp_set_no_check6_rx(sock->sk, !cfg->use_udp6_rx_checksums); *sockp = sock; return 0; error: if (sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); } *sockp = NULL; return err; } EXPORT_SYMBOL_GPL(udp_sock_create6); int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, struct net_device *dev, struct in6_addr *saddr, struct in6_addr *daddr, __u8 prio, __u8 ttl, __be32 label, __be16 src_port, __be16 dst_port, bool nocheck) { struct udphdr *uh; struct ipv6hdr *ip6h; __skb_push(skb, sizeof(*uh)); skb_reset_transport_header(skb); uh = udp_hdr(skb); uh->dest = dst_port; uh->source = src_port; uh->len = htons(skb->len); skb_dst_set(skb, dst); udp6_set_csum(nocheck, skb, saddr, daddr, skb->len); __skb_push(skb, sizeof(*ip6h)); skb_reset_network_header(skb); ip6h = ipv6_hdr(skb); ip6_flow_hdr(ip6h, prio, label); ip6h->payload_len = htons(skb->len); ip6h->nexthdr = IPPROTO_UDP; ip6h->hop_limit = ttl; ip6h->daddr = *daddr; ip6h->saddr = *saddr; ip6tunnel_xmit(sk, skb, dev); return 0; } EXPORT_SYMBOL_GPL(udp_tunnel6_xmit_skb); MODULE_LICENSE("GPL"); |
| 651 1532 2040 1580 1534 1876 2498 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMU_NOTIFIER_H #define _LINUX_MMU_NOTIFIER_H #include <linux/list.h> #include <linux/spinlock.h> #include <linux/mm_types.h> #include <linux/mmap_lock.h> #include <linux/srcu.h> #include <linux/interval_tree.h> #include <linux/android_kabi.h> struct mmu_notifier_subscriptions; struct mmu_notifier; struct mmu_notifier_range; struct mmu_interval_notifier; /** * enum mmu_notifier_event - reason for the mmu notifier callback * @MMU_NOTIFY_UNMAP: either munmap() that unmap the range or a mremap() that * move the range * * @MMU_NOTIFY_CLEAR: clear page table entry (many reasons for this like * madvise() or replacing a page by another one, ...). * * @MMU_NOTIFY_PROTECTION_VMA: update is due to protection change for the range * ie using the vma access permission (vm_page_prot) to update the whole range * is enough no need to inspect changes to the CPU page table (mprotect() * syscall) * * @MMU_NOTIFY_PROTECTION_PAGE: update is due to change in read/write flag for * pages in the range so to mirror those changes the user must inspect the CPU * page table (from the end callback). * * @MMU_NOTIFY_SOFT_DIRTY: soft dirty accounting (still same page and same * access flags). User should soft dirty the page in the end callback to make * sure that anyone relying on soft dirtiness catch pages that might be written * through non CPU mappings. * * @MMU_NOTIFY_RELEASE: used during mmu_interval_notifier invalidate to signal * that the mm refcount is zero and the range is no longer accessible. * * @MMU_NOTIFY_MIGRATE: used during migrate_vma_collect() invalidate to signal * a device driver to possibly ignore the invalidation if the * owner field matches the driver's device private pgmap owner. * * @MMU_NOTIFY_EXCLUSIVE: to signal a device driver that the device will no * longer have exclusive access to the page. When sent during creation of an * exclusive range the owner will be initialised to the value provided by the * caller of make_device_exclusive_range(), otherwise the owner will be NULL. */ enum mmu_notifier_event { MMU_NOTIFY_UNMAP = 0, MMU_NOTIFY_CLEAR, MMU_NOTIFY_PROTECTION_VMA, MMU_NOTIFY_PROTECTION_PAGE, MMU_NOTIFY_SOFT_DIRTY, MMU_NOTIFY_RELEASE, MMU_NOTIFY_MIGRATE, MMU_NOTIFY_EXCLUSIVE, }; #define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0) struct mmu_notifier_ops { /* * Called either by mmu_notifier_unregister or when the mm is * being destroyed by exit_mmap, always before all pages are * freed. This can run concurrently with other mmu notifier * methods (the ones invoked outside the mm context) and it * should tear down all secondary mmu mappings and freeze the * secondary mmu. If this method isn't implemented you've to * be sure that nothing could possibly write to the pages * through the secondary mmu by the time the last thread with * tsk->mm == mm exits. * * As side note: the pages freed after ->release returns could * be immediately reallocated by the gart at an alias physical * address with a different cache model, so if ->release isn't * implemented because all _software_ driven memory accesses * through the secondary mmu are terminated by the time the * last thread of this mm quits, you've also to be sure that * speculative _hardware_ operations can't allocate dirty * cachelines in the cpu that could not be snooped and made * coherent with the other read and write operations happening * through the gart alias address, so leading to memory * corruption. */ void (*release)(struct mmu_notifier *subscription, struct mm_struct *mm); /* * clear_flush_young is called after the VM is * test-and-clearing the young/accessed bitflag in the * pte. This way the VM will provide proper aging to the * accesses to the page through the secondary MMUs and not * only to the ones through the Linux pte. * Start-end is necessary in case the secondary MMU is mapping the page * at a smaller granularity than the primary MMU. */ int (*clear_flush_young)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long start, unsigned long end); /* * clear_young is a lightweight version of clear_flush_young. Like the * latter, it is supposed to test-and-clear the young/accessed bitflag * in the secondary pte, but it may omit flushing the secondary tlb. */ int (*clear_young)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long start, unsigned long end); /* * test_young is called to check the young/accessed bitflag in * the secondary pte. This is used to know if the page is * frequently used without actually clearing the flag or tearing * down the secondary mapping on the page. */ int (*test_young)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long address); /* * change_pte is called in cases that pte mapping to page is changed: * for example, when ksm remaps pte to point to a new shared page. */ void (*change_pte)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long address, pte_t pte); /* * invalidate_range_start() and invalidate_range_end() must be * paired and are called only when the mmap_lock and/or the * locks protecting the reverse maps are held. If the subsystem * can't guarantee that no additional references are taken to * the pages in the range, it has to implement the * invalidate_range() notifier to remove any references taken * after invalidate_range_start(). * * Invalidation of multiple concurrent ranges may be * optionally permitted by the driver. Either way the * establishment of sptes is forbidden in the range passed to * invalidate_range_begin/end for the whole duration of the * invalidate_range_begin/end critical section. * * invalidate_range_start() is called when all pages in the * range are still mapped and have at least a refcount of one. * * invalidate_range_end() is called when all pages in the * range have been unmapped and the pages have been freed by * the VM. * * The VM will remove the page table entries and potentially * the page between invalidate_range_start() and * invalidate_range_end(). If the page must not be freed * because of pending I/O or other circumstances then the * invalidate_range_start() callback (or the initial mapping * by the driver) must make sure that the refcount is kept * elevated. * * If the driver increases the refcount when the pages are * initially mapped into an address space then either * invalidate_range_start() or invalidate_range_end() may * decrease the refcount. If the refcount is decreased on * invalidate_range_start() then the VM can free pages as page * table entries are removed. If the refcount is only * dropped on invalidate_range_end() then the driver itself * will drop the last refcount but it must take care to flush * any secondary tlb before doing the final free on the * page. Pages will no longer be referenced by the linux * address space but may still be referenced by sptes until * the last refcount is dropped. * * If blockable argument is set to false then the callback cannot * sleep and has to return with -EAGAIN if sleeping would be required. * 0 should be returned otherwise. Please note that notifiers that can * fail invalidate_range_start are not allowed to implement * invalidate_range_end, as there is no mechanism for informing the * notifier that its start failed. */ int (*invalidate_range_start)(struct mmu_notifier *subscription, const struct mmu_notifier_range *range); void (*invalidate_range_end)(struct mmu_notifier *subscription, const struct mmu_notifier_range *range); /* * invalidate_range() is either called between * invalidate_range_start() and invalidate_range_end() when the * VM has to free pages that where unmapped, but before the * pages are actually freed, or outside of _start()/_end() when * a (remote) TLB is necessary. * * If invalidate_range() is used to manage a non-CPU TLB with * shared page-tables, it not necessary to implement the * invalidate_range_start()/end() notifiers, as * invalidate_range() already catches the points in time when an * external TLB range needs to be flushed. For more in depth * discussion on this see Documentation/mm/mmu_notifier.rst * * Note that this function might be called with just a sub-range * of what was passed to invalidate_range_start()/end(), if * called between those functions. */ void (*invalidate_range)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long start, unsigned long end); /* * These callbacks are used with the get/put interface to manage the * lifetime of the mmu_notifier memory. alloc_notifier() returns a new * notifier for use with the mm. * * free_notifier() is only called after the mmu_notifier has been * fully put, calls to any ops callback are prevented and no ops * callbacks are currently running. It is called from a SRCU callback * and cannot sleep. */ struct mmu_notifier *(*alloc_notifier)(struct mm_struct *mm); void (*free_notifier)(struct mmu_notifier *subscription); ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); ANDROID_KABI_RESERVE(3); ANDROID_KABI_RESERVE(4); }; /* * The notifier chains are protected by mmap_lock and/or the reverse map * semaphores. Notifier chains are only changed when all reverse maps and * the mmap_lock locks are taken. * * Therefore notifier chains can only be traversed when either * * 1. mmap_lock is held. * 2. One of the reverse map locks is held (i_mmap_rwsem or anon_vma->rwsem). * 3. No other concurrent thread can access the list (release) */ struct mmu_notifier { struct hlist_node hlist; const struct mmu_notifier_ops *ops; struct mm_struct *mm; struct rcu_head rcu; unsigned int users; ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); }; /** * struct mmu_interval_notifier_ops * @invalidate: Upon return the caller must stop using any SPTEs within this * range. This function can sleep. Return false only if sleeping * was required but mmu_notifier_range_blockable(range) is false. */ struct mmu_interval_notifier_ops { bool (*invalidate)(struct mmu_interval_notifier *interval_sub, const struct mmu_notifier_range *range, unsigned long cur_seq); }; struct mmu_interval_notifier { struct interval_tree_node interval_tree; const struct mmu_interval_notifier_ops *ops; struct mm_struct *mm; struct hlist_node deferred_item; unsigned long invalidate_seq; }; #ifdef CONFIG_MMU_NOTIFIER #ifdef CONFIG_LOCKDEP extern struct lockdep_map __mmu_notifier_invalidate_range_start_map; #endif struct mmu_notifier_range { struct vm_area_struct *vma; struct mm_struct *mm; unsigned long start; unsigned long end; unsigned flags; enum mmu_notifier_event event; void *owner; }; static inline int mm_has_notifiers(struct mm_struct *mm) { return unlikely(mm->notifier_subscriptions); } struct mmu_notifier *mmu_notifier_get_locked(const struct mmu_notifier_ops *ops, struct mm_struct *mm); static inline struct mmu_notifier * mmu_notifier_get(const struct mmu_notifier_ops *ops, struct mm_struct *mm) { struct mmu_notifier *ret; mmap_write_lock(mm); ret = mmu_notifier_get_locked(ops, mm); mmap_write_unlock(mm); return ret; } void mmu_notifier_put(struct mmu_notifier *subscription); void mmu_notifier_synchronize(void); extern int mmu_notifier_register(struct mmu_notifier *subscription, struct mm_struct *mm); extern int __mmu_notifier_register(struct mmu_notifier *subscription, struct mm_struct *mm); extern void mmu_notifier_unregister(struct mmu_notifier *subscription, struct mm_struct *mm); unsigned long mmu_interval_read_begin(struct mmu_interval_notifier *interval_sub); int mmu_interval_notifier_insert(struct mmu_interval_notifier *interval_sub, struct mm_struct *mm, unsigned long start, unsigned long length, const struct mmu_interval_notifier_ops *ops); int mmu_interval_notifier_insert_locked( struct mmu_interval_notifier *interval_sub, struct mm_struct *mm, unsigned long start, unsigned long length, const struct mmu_interval_notifier_ops *ops); void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub); /** * mmu_interval_set_seq - Save the invalidation sequence * @interval_sub - The subscription passed to invalidate * @cur_seq - The cur_seq passed to the invalidate() callback * * This must be called unconditionally from the invalidate callback of a * struct mmu_interval_notifier_ops under the same lock that is used to call * mmu_interval_read_retry(). It updates the sequence number for later use by * mmu_interval_read_retry(). The provided cur_seq will always be odd. * * If the caller does not call mmu_interval_read_begin() or * mmu_interval_read_retry() then this call is not required. */ static inline void mmu_interval_set_seq(struct mmu_interval_notifier *interval_sub, unsigned long cur_seq) { WRITE_ONCE(interval_sub->invalidate_seq, cur_seq); } /** * mmu_interval_read_retry - End a read side critical section against a VA range * interval_sub: The subscription * seq: The return of the paired mmu_interval_read_begin() * * This MUST be called under a user provided lock that is also held * unconditionally by op->invalidate() when it calls mmu_interval_set_seq(). * * Each call should be paired with a single mmu_interval_read_begin() and * should be used to conclude the read side. * * Returns true if an invalidation collided with this critical section, and * the caller should retry. */ static inline bool mmu_interval_read_retry(struct mmu_interval_notifier *interval_sub, unsigned long seq) { return interval_sub->invalidate_seq != seq; } /** * mmu_interval_check_retry - Test if a collision has occurred * interval_sub: The subscription * seq: The return of the matching mmu_interval_read_begin() * * This can be used in the critical section between mmu_interval_read_begin() * and mmu_interval_read_retry(). A return of true indicates an invalidation * has collided with this critical region and a future * mmu_interval_read_retry() will return true. * * False is not reliable and only suggests a collision may not have * occurred. It can be called many times and does not have to hold the user * provided lock. * * This call can be used as part of loops and other expensive operations to * expedite a retry. */ static inline bool mmu_interval_check_retry(struct mmu_interval_notifier *interval_sub, unsigned long seq) { /* Pairs with the WRITE_ONCE in mmu_interval_set_seq() */ return READ_ONCE(interval_sub->invalidate_seq) != seq; } extern void __mmu_notifier_subscriptions_destroy(struct mm_struct *mm); extern void __mmu_notifier_release(struct mm_struct *mm); extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, unsigned long end); extern int __mmu_notifier_clear_young(struct mm_struct *mm, unsigned long start, unsigned long end); extern int __mmu_notifier_test_young(struct mm_struct *mm, unsigned long address); extern void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte); extern int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *r); extern void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *r, bool only_end); extern void __mmu_notifier_invalidate_range(struct mm_struct *mm, unsigned long start, unsigned long end); extern bool mmu_notifier_range_update_to_read_only(const struct mmu_notifier_range *range); static inline bool mmu_notifier_range_blockable(const struct mmu_notifier_range *range) { return (range->flags & MMU_NOTIFIER_RANGE_BLOCKABLE); } static inline void mmu_notifier_release(struct mm_struct *mm) { if (mm_has_notifiers(mm)) __mmu_notifier_release(mm); } static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, unsigned long end) { if (mm_has_notifiers(mm)) return __mmu_notifier_clear_flush_young(mm, start, end); return 0; } static inline int mmu_notifier_clear_young(struct mm_struct *mm, unsigned long start, unsigned long end) { if (mm_has_notifiers(mm)) return __mmu_notifier_clear_young(mm, start, end); return 0; } static inline int mmu_notifier_test_young(struct mm_struct *mm, unsigned long address) { if (mm_has_notifiers(mm)) return __mmu_notifier_test_young(mm, address); return 0; } static inline void mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte) { if (mm_has_notifiers(mm)) __mmu_notifier_change_pte(mm, address, pte); } static inline void mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) { might_sleep(); lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); if (mm_has_notifiers(range->mm)) { range->flags |= MMU_NOTIFIER_RANGE_BLOCKABLE; __mmu_notifier_invalidate_range_start(range); } lock_map_release(&__mmu_notifier_invalidate_range_start_map); } static inline int mmu_notifier_invalidate_range_start_nonblock(struct mmu_notifier_range *range) { int ret = 0; lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); if (mm_has_notifiers(range->mm)) { range->flags &= ~MMU_NOTIFIER_RANGE_BLOCKABLE; ret = __mmu_notifier_invalidate_range_start(range); } lock_map_release(&__mmu_notifier_invalidate_range_start_map); return ret; } static inline void mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range) { if (mmu_notifier_range_blockable(range)) might_sleep(); if (mm_has_notifiers(range->mm)) __mmu_notifier_invalidate_range_end(range, false); } static inline void mmu_notifier_invalidate_range_only_end(struct mmu_notifier_range *range) { if (mm_has_notifiers(range->mm)) __mmu_notifier_invalidate_range_end(range, true); } static inline void mmu_notifier_invalidate_range(struct mm_struct *mm, unsigned long start, unsigned long end) { if (mm_has_notifiers(mm)) __mmu_notifier_invalidate_range(mm, start, end); } static inline void mmu_notifier_subscriptions_init(struct mm_struct *mm) { mm->notifier_subscriptions = NULL; } static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm) { if (mm_has_notifiers(mm)) __mmu_notifier_subscriptions_destroy(mm); } static inline void mmu_notifier_range_init(struct mmu_notifier_range *range, enum mmu_notifier_event event, unsigned flags, struct vm_area_struct *vma, struct mm_struct *mm, unsigned long start, unsigned long end) { range->vma = vma; range->event = event; range->mm = mm; range->start = start; range->end = end; range->flags = flags; } static inline void mmu_notifier_range_init_owner( struct mmu_notifier_range *range, enum mmu_notifier_event event, unsigned int flags, struct vm_area_struct *vma, struct mm_struct *mm, unsigned long start, unsigned long end, void *owner) { mmu_notifier_range_init(range, event, flags, vma, mm, start, end); range->owner = owner; } #define ptep_clear_flush_young_notify(__vma, __address, __ptep) \ ({ \ int __young; \ struct vm_area_struct *___vma = __vma; \ unsigned long ___address = __address; \ __young = ptep_clear_flush_young(___vma, ___address, __ptep); \ __young |= mmu_notifier_clear_flush_young(___vma->vm_mm, \ ___address, \ ___address + \ PAGE_SIZE); \ __young; \ }) #define pmdp_clear_flush_young_notify(__vma, __address, __pmdp) \ ({ \ int __young; \ struct vm_area_struct *___vma = __vma; \ unsigned long ___address = __address; \ __young = pmdp_clear_flush_young(___vma, ___address, __pmdp); \ __young |= mmu_notifier_clear_flush_young(___vma->vm_mm, \ ___address, \ ___address + \ PMD_SIZE); \ __young; \ }) #define ptep_clear_young_notify(__vma, __address, __ptep) \ ({ \ int __young; \ struct vm_area_struct *___vma = __vma; \ unsigned long ___address = __address; \ __young = ptep_test_and_clear_young(___vma, ___address, __ptep);\ __young |= mmu_notifier_clear_young(___vma->vm_mm, ___address, \ ___address + PAGE_SIZE); \ __young; \ }) #define pmdp_clear_young_notify(__vma, __address, __pmdp) \ ({ \ int __young; \ struct vm_area_struct *___vma = __vma; \ unsigned long ___address = __address; \ __young = pmdp_test_and_clear_young(___vma, ___address, __pmdp);\ __young |= mmu_notifier_clear_young(___vma->vm_mm, ___address, \ ___address + PMD_SIZE); \ __young; \ }) #define ptep_clear_flush_notify(__vma, __address, __ptep) \ ({ \ unsigned long ___addr = __address & PAGE_MASK; \ struct mm_struct *___mm = (__vma)->vm_mm; \ pte_t ___pte; \ \ ___pte = ptep_clear_flush(__vma, __address, __ptep); \ mmu_notifier_invalidate_range(___mm, ___addr, \ ___addr + PAGE_SIZE); \ \ ___pte; \ }) #define pmdp_huge_clear_flush_notify(__vma, __haddr, __pmd) \ ({ \ unsigned long ___haddr = __haddr & HPAGE_PMD_MASK; \ struct mm_struct *___mm = (__vma)->vm_mm; \ pmd_t ___pmd; \ \ ___pmd = pmdp_huge_clear_flush(__vma, __haddr, __pmd); \ mmu_notifier_invalidate_range(___mm, ___haddr, \ ___haddr + HPAGE_PMD_SIZE); \ \ ___pmd; \ }) #define pudp_huge_clear_flush_notify(__vma, __haddr, __pud) \ ({ \ unsigned long ___haddr = __haddr & HPAGE_PUD_MASK; \ struct mm_struct *___mm = (__vma)->vm_mm; \ pud_t ___pud; \ \ ___pud = pudp_huge_clear_flush(__vma, __haddr, __pud); \ mmu_notifier_invalidate_range(___mm, ___haddr, \ ___haddr + HPAGE_PUD_SIZE); \ \ ___pud; \ }) /* * set_pte_at_notify() sets the pte _after_ running the notifier. * This is safe to start by updating the secondary MMUs, because the primary MMU * pte invalidate must have already happened with a ptep_clear_flush() before * set_pte_at_notify() has been invoked. Updating the secondary MMUs first is * required when we change both the protection of the mapping from read-only to * read-write and the pfn (like during copy on write page faults). Otherwise the * old page would remain mapped readonly in the secondary MMUs after the new * page is already writable by some CPU through the primary MMU. */ #define set_pte_at_notify(__mm, __address, __ptep, __pte) \ ({ \ struct mm_struct *___mm = __mm; \ unsigned long ___address = __address; \ pte_t ___pte = __pte; \ \ mmu_notifier_change_pte(___mm, ___address, ___pte); \ set_pte_at(___mm, ___address, __ptep, ___pte); \ }) #else /* CONFIG_MMU_NOTIFIER */ struct mmu_notifier_range { unsigned long start; unsigned long end; }; static inline void _mmu_notifier_range_init(struct mmu_notifier_range *range, unsigned long start, unsigned long end) { range->start = start; range->end = end; } #define mmu_notifier_range_init(range,event,flags,vma,mm,start,end) \ _mmu_notifier_range_init(range, start, end) #define mmu_notifier_range_init_owner(range, event, flags, vma, mm, start, \ end, owner) \ _mmu_notifier_range_init(range, start, end) static inline bool mmu_notifier_range_blockable(const struct mmu_notifier_range *range) { return true; } static inline int mm_has_notifiers(struct mm_struct *mm) { return 0; } static inline void mmu_notifier_release(struct mm_struct *mm) { } static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, unsigned long end) { return 0; } static inline int mmu_notifier_test_young(struct mm_struct *mm, unsigned long address) { return 0; } static inline void mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte) { } static inline void mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) { } static inline int mmu_notifier_invalidate_range_start_nonblock(struct mmu_notifier_range *range) { return 0; } static inline void mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range) { } static inline void mmu_notifier_invalidate_range_only_end(struct mmu_notifier_range *range) { } static inline void mmu_notifier_invalidate_range(struct mm_struct *mm, unsigned long start, unsigned long end) { } static inline void mmu_notifier_subscriptions_init(struct mm_struct *mm) { } static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm) { } #define mmu_notifier_range_update_to_read_only(r) false #define ptep_clear_flush_young_notify ptep_clear_flush_young #define pmdp_clear_flush_young_notify pmdp_clear_flush_young #define ptep_clear_young_notify ptep_test_and_clear_young #define pmdp_clear_young_notify pmdp_test_and_clear_young #define ptep_clear_flush_notify ptep_clear_flush #define pmdp_huge_clear_flush_notify pmdp_huge_clear_flush #define pudp_huge_clear_flush_notify pudp_huge_clear_flush #define set_pte_at_notify set_pte_at static inline void mmu_notifier_synchronize(void) { } #endif /* CONFIG_MMU_NOTIFIER */ #endif /* _LINUX_MMU_NOTIFIER_H */ |
| 14041 14043 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 | /* SPDX-License-Identifier: GPL-2.0 */ /* thread_info.h: low-level thread information * * Copyright (C) 2002 David Howells (dhowells@redhat.com) * - Incorporating suggestions made by Linus Torvalds and Dave Miller */ #ifndef _ASM_X86_THREAD_INFO_H #define _ASM_X86_THREAD_INFO_H #include <linux/compiler.h> #include <asm/page.h> #include <asm/percpu.h> #include <asm/types.h> /* * TOP_OF_KERNEL_STACK_PADDING is a number of unused bytes that we * reserve at the top of the kernel stack. We do it because of a nasty * 32-bit corner case. On x86_32, the hardware stack frame is * variable-length. Except for vm86 mode, struct pt_regs assumes a * maximum-length frame. If we enter from CPL 0, the top 8 bytes of * pt_regs don't actually exist. Ordinarily this doesn't matter, but it * does in at least one case: * * If we take an NMI early enough in SYSENTER, then we can end up with * pt_regs that extends above sp0. On the way out, in the espfix code, * we can read the saved SS value, but that value will be above sp0. * Without this offset, that can result in a page fault. (We are * careful that, in this case, the value we read doesn't matter.) * * In vm86 mode, the hardware frame is much longer still, so add 16 * bytes to make room for the real-mode segments. * * x86_64 has a fixed-length stack frame. */ #ifdef CONFIG_X86_32 # ifdef CONFIG_VM86 # define TOP_OF_KERNEL_STACK_PADDING 16 # else # define TOP_OF_KERNEL_STACK_PADDING 8 # endif #else # define TOP_OF_KERNEL_STACK_PADDING 0 #endif /* * low level task data that entry.S needs immediate access to * - this struct should fit entirely inside of one cache line * - this struct shares the supervisor stack pages */ #ifndef __ASSEMBLY__ struct task_struct; #include <asm/cpufeature.h> #include <linux/atomic.h> struct thread_info { unsigned long flags; /* low level flags */ unsigned long syscall_work; /* SYSCALL_WORK_ flags */ u32 status; /* thread synchronous flags */ #ifdef CONFIG_SMP u32 cpu; /* current CPU */ #endif }; #define INIT_THREAD_INFO(tsk) \ { \ .flags = 0, \ } #else /* !__ASSEMBLY__ */ #include <asm/asm-offsets.h> #endif /* * thread information flags * - these are process state flags that various assembly files * may need to access */ #define TIF_NOTIFY_RESUME 1 /* callback before returning to user */ #define TIF_SIGPENDING 2 /* signal pending */ #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ #define TIF_SINGLESTEP 4 /* reenable singlestep on user return*/ #define TIF_SSBD 5 /* Speculative store bypass disable */ #define TIF_SPEC_IB 9 /* Indirect branch speculation mitigation */ #define TIF_SPEC_L1D_FLUSH 10 /* Flush L1D on mm switches (processes) */ #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ #define TIF_UPROBE 12 /* breakpointed or singlestepping */ #define TIF_PATCH_PENDING 13 /* pending live patching update */ #define TIF_NEED_FPU_LOAD 14 /* load FPU on return to userspace */ #define TIF_NOCPUID 15 /* CPUID is not accessible in userland */ #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_NOTIFY_SIGNAL 17 /* signal notifications exist */ #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ #define TIF_POLLING_NRFLAG 21 /* idle is polling for TIF_NEED_RESCHED */ #define TIF_IO_BITMAP 22 /* uses I/O bitmap */ #define TIF_SPEC_FORCE_UPDATE 23 /* Force speculation MSR update in context switch */ #define TIF_FORCED_TF 24 /* true if TF in eflags artificially */ #define TIF_BLOCKSTEP 25 /* set when we want DEBUGCTLMSR_BTF */ #define TIF_LAZY_MMU_UPDATES 27 /* task is updating the mmu lazily */ #define TIF_ADDR32 29 /* 32-bit address space on 64 bits */ #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) #define _TIF_SSBD (1 << TIF_SSBD) #define _TIF_SPEC_IB (1 << TIF_SPEC_IB) #define _TIF_SPEC_L1D_FLUSH (1 << TIF_SPEC_L1D_FLUSH) #define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) #define _TIF_UPROBE (1 << TIF_UPROBE) #define _TIF_PATCH_PENDING (1 << TIF_PATCH_PENDING) #define _TIF_NEED_FPU_LOAD (1 << TIF_NEED_FPU_LOAD) #define _TIF_NOCPUID (1 << TIF_NOCPUID) #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) #define _TIF_SPEC_FORCE_UPDATE (1 << TIF_SPEC_FORCE_UPDATE) #define _TIF_FORCED_TF (1 << TIF_FORCED_TF) #define _TIF_BLOCKSTEP (1 << TIF_BLOCKSTEP) #define _TIF_LAZY_MMU_UPDATES (1 << TIF_LAZY_MMU_UPDATES) #define _TIF_ADDR32 (1 << TIF_ADDR32) /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW_BASE \ (_TIF_NOCPUID | _TIF_NOTSC | _TIF_BLOCKSTEP | \ _TIF_SSBD | _TIF_SPEC_FORCE_UPDATE) /* * Avoid calls to __switch_to_xtra() on UP as STIBP is not evaluated. */ #ifdef CONFIG_SMP # define _TIF_WORK_CTXSW (_TIF_WORK_CTXSW_BASE | _TIF_SPEC_IB) #else # define _TIF_WORK_CTXSW (_TIF_WORK_CTXSW_BASE) #endif #ifdef CONFIG_X86_IOPL_IOPERM # define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW| _TIF_USER_RETURN_NOTIFY | \ _TIF_IO_BITMAP) #else # define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW| _TIF_USER_RETURN_NOTIFY) #endif #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) #define STACK_WARN (THREAD_SIZE/8) /* * macros/functions for gaining access to the thread information structure * * preempt_count needs to be 1 initially, until the scheduler is functional. */ #ifndef __ASSEMBLY__ /* * Walks up the stack frames to make sure that the specified object is * entirely contained by a single stack frame. * * Returns: * GOOD_FRAME if within a frame * BAD_STACK if placed across a frame boundary (or outside stack) * NOT_STACK unable to determine (no frame pointers, etc) */ static inline int arch_within_stack_frames(const void * const stack, const void * const stackend, const void *obj, unsigned long len) { #if defined(CONFIG_FRAME_POINTER) const void *frame = NULL; const void *oldframe; oldframe = __builtin_frame_address(1); if (oldframe) frame = __builtin_frame_address(2); /* * low ----------------------------------------------> high * [saved bp][saved ip][args][local vars][saved bp][saved ip] * ^----------------^ * allow copies only within here */ while (stack <= frame && frame < stackend) { /* * If obj + len extends past the last frame, this * check won't pass and the next frame will be 0, * causing us to bail out and correctly report * the copy as invalid. */ if (obj + len <= frame) return obj >= oldframe + 2 * sizeof(void *) ? GOOD_FRAME : BAD_STACK; oldframe = frame; frame = *(const void * const *)frame; } return BAD_STACK; #else return NOT_STACK; #endif } #endif /* !__ASSEMBLY__ */ /* * Thread-synchronous status. * * This is different from the flags in that nobody else * ever touches our thread-synchronous status, so we don't * have to worry about atomic accesses. */ #define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ #ifndef __ASSEMBLY__ #ifdef CONFIG_COMPAT #define TS_I386_REGS_POKED 0x0004 /* regs poked by 32-bit ptracer */ #define arch_set_restart_data(restart) \ do { restart->arch_data = current_thread_info()->status; } while (0) #endif #ifdef CONFIG_X86_32 #define in_ia32_syscall() true #else #define in_ia32_syscall() (IS_ENABLED(CONFIG_IA32_EMULATION) && \ current_thread_info()->status & TS_COMPAT) #endif extern void arch_task_cache_init(void); extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); extern void arch_release_task_struct(struct task_struct *tsk); extern void arch_setup_new_exec(void); #define arch_setup_new_exec arch_setup_new_exec #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_THREAD_INFO_H */ |
| 3 1161 1162 1162 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM writeback #if !defined(_TRACE_WRITEBACK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_WRITEBACK_H #include <linux/tracepoint.h> #include <linux/backing-dev.h> #include <linux/writeback.h> #define show_inode_state(state) \ __print_flags(state, "|", \ {I_DIRTY_SYNC, "I_DIRTY_SYNC"}, \ {I_DIRTY_DATASYNC, "I_DIRTY_DATASYNC"}, \ {I_DIRTY_PAGES, "I_DIRTY_PAGES"}, \ {I_NEW, "I_NEW"}, \ {I_WILL_FREE, "I_WILL_FREE"}, \ {I_FREEING, "I_FREEING"}, \ {I_CLEAR, "I_CLEAR"}, \ {I_SYNC, "I_SYNC"}, \ {I_DIRTY_TIME, "I_DIRTY_TIME"}, \ {I_REFERENCED, "I_REFERENCED"} \ ) /* enums need to be exported to user space */ #undef EM #undef EMe #define EM(a,b) TRACE_DEFINE_ENUM(a); #define EMe(a,b) TRACE_DEFINE_ENUM(a); #define WB_WORK_REASON \ EM( WB_REASON_BACKGROUND, "background") \ EM( WB_REASON_VMSCAN, "vmscan") \ EM( WB_REASON_SYNC, "sync") \ EM( WB_REASON_PERIODIC, "periodic") \ EM( WB_REASON_LAPTOP_TIMER, "laptop_timer") \ EM( WB_REASON_FS_FREE_SPACE, "fs_free_space") \ EM( WB_REASON_FORKER_THREAD, "forker_thread") \ EMe(WB_REASON_FOREIGN_FLUSH, "foreign_flush") WB_WORK_REASON /* * Now redefine the EM() and EMe() macros to map the enums to the strings * that will be printed in the output. */ #undef EM #undef EMe #define EM(a,b) { a, b }, #define EMe(a,b) { a, b } struct wb_writeback_work; DECLARE_EVENT_CLASS(writeback_folio_template, TP_PROTO(struct folio *folio, struct address_space *mapping), TP_ARGS(folio, mapping), TP_STRUCT__entry ( __array(char, name, 32) __field(ino_t, ino) __field(pgoff_t, index) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(mapping ? inode_to_bdi(mapping->host) : NULL), 32); __entry->ino = (mapping && mapping->host) ? mapping->host->i_ino : 0; __entry->index = folio->index; ), TP_printk("bdi %s: ino=%lu index=%lu", __entry->name, (unsigned long)__entry->ino, __entry->index ) ); DEFINE_EVENT(writeback_folio_template, writeback_dirty_folio, TP_PROTO(struct folio *folio, struct address_space *mapping), TP_ARGS(folio, mapping) ); DEFINE_EVENT(writeback_folio_template, folio_wait_writeback, TP_PROTO(struct folio *folio, struct address_space *mapping), TP_ARGS(folio, mapping) ); DECLARE_EVENT_CLASS(writeback_dirty_inode_template, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags), TP_STRUCT__entry ( __array(char, name, 32) __field(ino_t, ino) __field(unsigned long, state) __field(unsigned long, flags) ), TP_fast_assign( struct backing_dev_info *bdi = inode_to_bdi(inode); /* may be called for files on pseudo FSes w/ unregistered bdi */ strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->flags = flags; ), TP_printk("bdi %s: ino=%lu state=%s flags=%s", __entry->name, (unsigned long)__entry->ino, show_inode_state(__entry->state), show_inode_state(__entry->flags) ) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_mark_inode_dirty, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode_start, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); #ifdef CREATE_TRACE_POINTS #ifdef CONFIG_CGROUP_WRITEBACK static inline ino_t __trace_wb_assign_cgroup(struct bdi_writeback *wb) { return cgroup_ino(wb->memcg_css->cgroup); } static inline ino_t __trace_wbc_assign_cgroup(struct writeback_control *wbc) { if (wbc->wb) return __trace_wb_assign_cgroup(wbc->wb); else return 1; } #else /* CONFIG_CGROUP_WRITEBACK */ static inline ino_t __trace_wb_assign_cgroup(struct bdi_writeback *wb) { return 1; } static inline ino_t __trace_wbc_assign_cgroup(struct writeback_control *wbc) { return 1; } #endif /* CONFIG_CGROUP_WRITEBACK */ #endif /* CREATE_TRACE_POINTS */ #ifdef CONFIG_CGROUP_WRITEBACK TRACE_EVENT(inode_foreign_history, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned int history), TP_ARGS(inode, wbc, history), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(ino_t, cgroup_ino) __field(unsigned int, history) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); __entry->history = history; ), TP_printk("bdi %s: ino=%lu cgroup_ino=%lu history=0x%x", __entry->name, (unsigned long)__entry->ino, (unsigned long)__entry->cgroup_ino, __entry->history ) ); TRACE_EVENT(inode_switch_wbs, TP_PROTO(struct inode *inode, struct bdi_writeback *old_wb, struct bdi_writeback *new_wb), TP_ARGS(inode, old_wb, new_wb), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(ino_t, old_cgroup_ino) __field(ino_t, new_cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(old_wb->bdi), 32); __entry->ino = inode->i_ino; __entry->old_cgroup_ino = __trace_wb_assign_cgroup(old_wb); __entry->new_cgroup_ino = __trace_wb_assign_cgroup(new_wb); ), TP_printk("bdi %s: ino=%lu old_cgroup_ino=%lu new_cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, (unsigned long)__entry->old_cgroup_ino, (unsigned long)__entry->new_cgroup_ino ) ); TRACE_EVENT(track_foreign_dirty, TP_PROTO(struct folio *folio, struct bdi_writeback *wb), TP_ARGS(folio, wb), TP_STRUCT__entry( __array(char, name, 32) __field(u64, bdi_id) __field(ino_t, ino) __field(unsigned int, memcg_id) __field(ino_t, cgroup_ino) __field(ino_t, page_cgroup_ino) ), TP_fast_assign( struct address_space *mapping = folio_mapping(folio); struct inode *inode = mapping ? mapping->host : NULL; strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->bdi_id = wb->bdi->id; __entry->ino = inode ? inode->i_ino : 0; __entry->memcg_id = wb->memcg_css->id; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); __entry->page_cgroup_ino = cgroup_ino(folio_memcg(folio)->css.cgroup); ), TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%lu page_cgroup_ino=%lu", __entry->name, __entry->bdi_id, (unsigned long)__entry->ino, __entry->memcg_id, (unsigned long)__entry->cgroup_ino, (unsigned long)__entry->page_cgroup_ino ) ); TRACE_EVENT(flush_foreign, TP_PROTO(struct bdi_writeback *wb, unsigned int frn_bdi_id, unsigned int frn_memcg_id), TP_ARGS(wb, frn_bdi_id, frn_memcg_id), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, cgroup_ino) __field(unsigned int, frn_bdi_id) __field(unsigned int, frn_memcg_id) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); __entry->frn_bdi_id = frn_bdi_id; __entry->frn_memcg_id = frn_memcg_id; ), TP_printk("bdi %s: cgroup_ino=%lu frn_bdi_id=%u frn_memcg_id=%u", __entry->name, (unsigned long)__entry->cgroup_ino, __entry->frn_bdi_id, __entry->frn_memcg_id ) ); #endif DECLARE_EVENT_CLASS(writeback_write_inode_template, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc), TP_STRUCT__entry ( __array(char, name, 32) __field(ino_t, ino) __field(int, sync_mode) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->sync_mode = wbc->sync_mode; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: ino=%lu sync_mode=%d cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, __entry->sync_mode, (unsigned long)__entry->cgroup_ino ) ); DEFINE_EVENT(writeback_write_inode_template, writeback_write_inode_start, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc) ); DEFINE_EVENT(writeback_write_inode_template, writeback_write_inode, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc) ); DECLARE_EVENT_CLASS(writeback_work_class, TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work), TP_ARGS(wb, work), TP_STRUCT__entry( __array(char, name, 32) __field(long, nr_pages) __field(dev_t, sb_dev) __field(int, sync_mode) __field(int, for_kupdate) __field(int, range_cyclic) __field(int, for_background) __field(int, reason) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->nr_pages = work->nr_pages; __entry->sb_dev = work->sb ? work->sb->s_dev : 0; __entry->sync_mode = work->sync_mode; __entry->for_kupdate = work->for_kupdate; __entry->range_cyclic = work->range_cyclic; __entry->for_background = work->for_background; __entry->reason = work->reason; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: sb_dev %d:%d nr_pages=%ld sync_mode=%d " "kupdate=%d range_cyclic=%d background=%d reason=%s cgroup_ino=%lu", __entry->name, MAJOR(__entry->sb_dev), MINOR(__entry->sb_dev), __entry->nr_pages, __entry->sync_mode, __entry->for_kupdate, __entry->range_cyclic, __entry->for_background, __print_symbolic(__entry->reason, WB_WORK_REASON), (unsigned long)__entry->cgroup_ino ) ); #define DEFINE_WRITEBACK_WORK_EVENT(name) \ DEFINE_EVENT(writeback_work_class, name, \ TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work), \ TP_ARGS(wb, work)) DEFINE_WRITEBACK_WORK_EVENT(writeback_queue); DEFINE_WRITEBACK_WORK_EVENT(writeback_exec); DEFINE_WRITEBACK_WORK_EVENT(writeback_start); DEFINE_WRITEBACK_WORK_EVENT(writeback_written); DEFINE_WRITEBACK_WORK_EVENT(writeback_wait); TRACE_EVENT(writeback_pages_written, TP_PROTO(long pages_written), TP_ARGS(pages_written), TP_STRUCT__entry( __field(long, pages) ), TP_fast_assign( __entry->pages = pages_written; ), TP_printk("%ld", __entry->pages) ); DECLARE_EVENT_CLASS(writeback_class, TP_PROTO(struct bdi_writeback *wb), TP_ARGS(wb), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: cgroup_ino=%lu", __entry->name, (unsigned long)__entry->cgroup_ino ) ); #define DEFINE_WRITEBACK_EVENT(name) \ DEFINE_EVENT(writeback_class, name, \ TP_PROTO(struct bdi_writeback *wb), \ TP_ARGS(wb)) DEFINE_WRITEBACK_EVENT(writeback_wake_background); TRACE_EVENT(writeback_bdi_register, TP_PROTO(struct backing_dev_info *bdi), TP_ARGS(bdi), TP_STRUCT__entry( __array(char, name, 32) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); ), TP_printk("bdi %s", __entry->name ) ); DECLARE_EVENT_CLASS(wbc_class, TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), TP_ARGS(wbc, bdi), TP_STRUCT__entry( __array(char, name, 32) __field(long, nr_to_write) __field(long, pages_skipped) __field(int, sync_mode) __field(int, for_kupdate) __field(int, for_background) __field(int, for_reclaim) __field(int, range_cyclic) __field(long, range_start) __field(long, range_end) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); __entry->nr_to_write = wbc->nr_to_write; __entry->pages_skipped = wbc->pages_skipped; __entry->sync_mode = wbc->sync_mode; __entry->for_kupdate = wbc->for_kupdate; __entry->for_background = wbc->for_background; __entry->for_reclaim = wbc->for_reclaim; __entry->range_cyclic = wbc->range_cyclic; __entry->range_start = (long)wbc->range_start; __entry->range_end = (long)wbc->range_end; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d " "bgrd=%d reclm=%d cyclic=%d " "start=0x%lx end=0x%lx cgroup_ino=%lu", __entry->name, __entry->nr_to_write, __entry->pages_skipped, __entry->sync_mode, __entry->for_kupdate, __entry->for_background, __entry->for_reclaim, __entry->range_cyclic, __entry->range_start, __entry->range_end, (unsigned long)__entry->cgroup_ino ) ) #define DEFINE_WBC_EVENT(name) \ DEFINE_EVENT(wbc_class, name, \ TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), \ TP_ARGS(wbc, bdi)) DEFINE_WBC_EVENT(wbc_writepage); TRACE_EVENT(writeback_queue_io, TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work, unsigned long dirtied_before, int moved), TP_ARGS(wb, work, dirtied_before, moved), TP_STRUCT__entry( __array(char, name, 32) __field(unsigned long, older) __field(long, age) __field(int, moved) __field(int, reason) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->older = dirtied_before; __entry->age = (jiffies - dirtied_before) * 1000 / HZ; __entry->moved = moved; __entry->reason = work->reason; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup_ino=%lu", __entry->name, __entry->older, /* dirtied_before in jiffies */ __entry->age, /* dirtied_before in relative milliseconds */ __entry->moved, __print_symbolic(__entry->reason, WB_WORK_REASON), (unsigned long)__entry->cgroup_ino ) ); TRACE_EVENT(global_dirty_state, TP_PROTO(unsigned long background_thresh, unsigned long dirty_thresh ), TP_ARGS(background_thresh, dirty_thresh ), TP_STRUCT__entry( __field(unsigned long, nr_dirty) __field(unsigned long, nr_writeback) __field(unsigned long, background_thresh) __field(unsigned long, dirty_thresh) __field(unsigned long, dirty_limit) __field(unsigned long, nr_dirtied) __field(unsigned long, nr_written) ), TP_fast_assign( __entry->nr_dirty = global_node_page_state(NR_FILE_DIRTY); __entry->nr_writeback = global_node_page_state(NR_WRITEBACK); __entry->nr_dirtied = global_node_page_state(NR_DIRTIED); __entry->nr_written = global_node_page_state(NR_WRITTEN); __entry->background_thresh = background_thresh; __entry->dirty_thresh = dirty_thresh; __entry->dirty_limit = global_wb_domain.dirty_limit; ), TP_printk("dirty=%lu writeback=%lu " "bg_thresh=%lu thresh=%lu limit=%lu " "dirtied=%lu written=%lu", __entry->nr_dirty, __entry->nr_writeback, __entry->background_thresh, __entry->dirty_thresh, __entry->dirty_limit, __entry->nr_dirtied, __entry->nr_written ) ); #define KBps(x) ((x) << (PAGE_SHIFT - 10)) TRACE_EVENT(bdi_dirty_ratelimit, TP_PROTO(struct bdi_writeback *wb, unsigned long dirty_rate, unsigned long task_ratelimit), TP_ARGS(wb, dirty_rate, task_ratelimit), TP_STRUCT__entry( __array(char, bdi, 32) __field(unsigned long, write_bw) __field(unsigned long, avg_write_bw) __field(unsigned long, dirty_rate) __field(unsigned long, dirty_ratelimit) __field(unsigned long, task_ratelimit) __field(unsigned long, balanced_dirty_ratelimit) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32); __entry->write_bw = KBps(wb->write_bandwidth); __entry->avg_write_bw = KBps(wb->avg_write_bandwidth); __entry->dirty_rate = KBps(dirty_rate); __entry->dirty_ratelimit = KBps(wb->dirty_ratelimit); __entry->task_ratelimit = KBps(task_ratelimit); __entry->balanced_dirty_ratelimit = KBps(wb->balanced_dirty_ratelimit); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: " "write_bw=%lu awrite_bw=%lu dirty_rate=%lu " "dirty_ratelimit=%lu task_ratelimit=%lu " "balanced_dirty_ratelimit=%lu cgroup_ino=%lu", __entry->bdi, __entry->write_bw, /* write bandwidth */ __entry->avg_write_bw, /* avg write bandwidth */ __entry->dirty_rate, /* bdi dirty rate */ __entry->dirty_ratelimit, /* base ratelimit */ __entry->task_ratelimit, /* ratelimit with position control */ __entry->balanced_dirty_ratelimit, /* the balanced ratelimit */ (unsigned long)__entry->cgroup_ino ) ); TRACE_EVENT(balance_dirty_pages, TP_PROTO(struct bdi_writeback *wb, unsigned long thresh, unsigned long bg_thresh, unsigned long dirty, unsigned long bdi_thresh, unsigned long bdi_dirty, unsigned long dirty_ratelimit, unsigned long task_ratelimit, unsigned long dirtied, unsigned long period, long pause, unsigned long start_time), TP_ARGS(wb, thresh, bg_thresh, dirty, bdi_thresh, bdi_dirty, dirty_ratelimit, task_ratelimit, dirtied, period, pause, start_time), TP_STRUCT__entry( __array( char, bdi, 32) __field(unsigned long, limit) __field(unsigned long, setpoint) __field(unsigned long, dirty) __field(unsigned long, bdi_setpoint) __field(unsigned long, bdi_dirty) __field(unsigned long, dirty_ratelimit) __field(unsigned long, task_ratelimit) __field(unsigned int, dirtied) __field(unsigned int, dirtied_pause) __field(unsigned long, paused) __field( long, pause) __field(unsigned long, period) __field( long, think) __field(ino_t, cgroup_ino) ), TP_fast_assign( unsigned long freerun = (thresh + bg_thresh) / 2; strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32); __entry->limit = global_wb_domain.dirty_limit; __entry->setpoint = (global_wb_domain.dirty_limit + freerun) / 2; __entry->dirty = dirty; __entry->bdi_setpoint = __entry->setpoint * bdi_thresh / (thresh + 1); __entry->bdi_dirty = bdi_dirty; __entry->dirty_ratelimit = KBps(dirty_ratelimit); __entry->task_ratelimit = KBps(task_ratelimit); __entry->dirtied = dirtied; __entry->dirtied_pause = current->nr_dirtied_pause; __entry->think = current->dirty_paused_when == 0 ? 0 : (long)(jiffies - current->dirty_paused_when) * 1000/HZ; __entry->period = period * 1000 / HZ; __entry->pause = pause * 1000 / HZ; __entry->paused = (jiffies - start_time) * 1000 / HZ; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: " "limit=%lu setpoint=%lu dirty=%lu " "bdi_setpoint=%lu bdi_dirty=%lu " "dirty_ratelimit=%lu task_ratelimit=%lu " "dirtied=%u dirtied_pause=%u " "paused=%lu pause=%ld period=%lu think=%ld cgroup_ino=%lu", __entry->bdi, __entry->limit, __entry->setpoint, __entry->dirty, __entry->bdi_setpoint, __entry->bdi_dirty, __entry->dirty_ratelimit, __entry->task_ratelimit, __entry->dirtied, __entry->dirtied_pause, __entry->paused, /* ms */ __entry->pause, /* ms */ __entry->period, /* ms */ __entry->think, /* ms */ (unsigned long)__entry->cgroup_ino ) ); TRACE_EVENT(writeback_sb_inodes_requeue, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(unsigned long, state) __field(unsigned long, dirtied_when) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; __entry->cgroup_ino = __trace_wb_assign_cgroup(inode_to_wb(inode)); ), TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, show_inode_state(__entry->state), __entry->dirtied_when, (jiffies - __entry->dirtied_when) / HZ, (unsigned long)__entry->cgroup_ino ) ); DECLARE_EVENT_CLASS(writeback_single_inode_template, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write ), TP_ARGS(inode, wbc, nr_to_write), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(unsigned long, state) __field(unsigned long, dirtied_when) __field(unsigned long, writeback_index) __field(long, nr_to_write) __field(unsigned long, wrote) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; __entry->writeback_index = inode->i_mapping->writeback_index; __entry->nr_to_write = nr_to_write; __entry->wrote = nr_to_write - wbc->nr_to_write; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu " "index=%lu to_write=%ld wrote=%lu cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, show_inode_state(__entry->state), __entry->dirtied_when, (jiffies - __entry->dirtied_when) / HZ, __entry->writeback_index, __entry->nr_to_write, __entry->wrote, (unsigned long)__entry->cgroup_ino ) ); DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode_start, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write), TP_ARGS(inode, wbc, nr_to_write) ); DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write), TP_ARGS(inode, wbc, nr_to_write) ); DECLARE_EVENT_CLASS(writeback_inode_template, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field(unsigned long, state ) __field( __u16, mode ) __field(unsigned long, dirtied_when ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->mode = inode->i_mode; __entry->dirtied_when = inode->dirtied_when; ), TP_printk("dev %d,%d ino %lu dirtied %lu state %s mode 0%o", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long)__entry->ino, __entry->dirtied_when, show_inode_state(__entry->state), __entry->mode) ); DEFINE_EVENT(writeback_inode_template, writeback_lazytime, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, writeback_lazytime_iput, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, writeback_dirty_inode_enqueue, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); /* * Inode writeback list tracking. */ DEFINE_EVENT(writeback_inode_template, sb_mark_inode_writeback, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, sb_clear_inode_writeback, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); #endif /* _TRACE_WRITEBACK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 2 2126 605 801 2045 346 848 39 1456 583 2107 2105 2106 2107 2107 2107 583 583 583 583 583 583 995 970 995 995 995 32 32 32 3320 2415 1983 2664 1416 2252 2227 1030 2192 2 2 144 2118 109 1141 191 1091 1006 117 950 4 3 1 1167 2 5 2166 1159 2157 1218 1218 3 1215 1215 1215 1 1 199 165 1215 2154 2154 1218 1322 1921 58 26 26 26 3 22 22 22 22 22 3312 3311 6 62 509 490 25 768 767 768 768 635 329 659 955 955 954 580 955 124 389 390 692 691 303 441 692 303 112 191 69 69 69 36 33 3329 3329 3300 2155 3300 58 59 130 11 130 1 6 6 16 16 13 11 5 5 1 1 571 498 543 1 1 407 408 1 1 1 1 1 1 1 665 665 665 665 665 825 354 147 147 76 84 84 587 825 354 587 147 147 1027 1031 32 36 4 4 4 604 604 604 210 604 604 604 12 12 819 816 4 819 820 150 677 819 819 818 34 34 150 677 820 819 814 819 817 818 819 818 820 819 1 818 819 816 817 819 817 160 160 160 820 166 323 159 160 160 160 166 166 166 166 166 165 165 166 1 817 819 53 818 801 18 18 817 816 818 818 818 820 819 311 661 819 819 324 665 662 71 71 48 49 49 10 10 49 49 49 22 3 49 9 69 69 48 49 49 48 31 31 31 14 14 14 14 14 34 34 34 33 18 18 18 576 574 574 387 189 575 572 69 575 16 571 1 572 570 571 558 13 13 570 4 4 559 5 9 2 2 571 570 569 27 545 27 15 414 149 74 57 57 151 88 151 20 80 130 131 150 425 422 425 88 151 151 150 40 2 5 36 424 424 151 151 151 151 148 150 151 151 422 425 425 424 88 88 86 583 2 583 583 7 7 22 22 22 85 85 49 49 63 62 63 62 62 63 63 63 29 1417 29 29 29 261 1447 1447 1446 1446 1447 338 338 1447 1447 1447 261 261 261 261 261 261 33 33 583 3302 3306 3190 252 237 33 31 2 583 2198 50 50 50 50 50 33 33 33 2194 50 50 50 1 50 1 1 50 3 18 33 33 18 17 49 49 33 50 33 50 3313 3195 234 247 20 33 33 33 33 33 33 18 17 18 18 18 18 18 33 33 33 33 33 33 18 18 18 18 18 18 18 18 583 583 583 583 22 22 1 22 1 929 106 838 838 751 327 111 826 825 788 111 111 64 60 626 627 567 123 7 622 580 109 112 1640 2164 93 238 962 597 450 1019 1019 3315 2830 1084 987 989 641 558 297 390 767 486 2 692 562 581 1020 336 1011 362 768 390 512 780 989 989 26 88 88 10 181 29 98 66 26 46 59 181 83 98 113 1 113 1 112 164 164 138 1 2 8 127 138 7 5 2 2 3312 3310 3314 3308 3309 3310 3312 2 32 4 40 39 19 24 66 24 3328 50 3312 3308 3311 65 1 65 24 583 583 73 73 72 1 1 71 71 4 68 14 68 2 1 66 67 1 36 29 2 65 64 24 23 1 23 24 24 1 24 2 34 11 1 11 22 22 3 13 2 2 75 1 1 11 64 12 2098 583 37 38 45 45 45 2193 2194 2192 2194 1547 710 2194 2194 38 1325 1859 38 2194 45 1325 1895 1895 1895 116 82 59 151 151 151 87 114 396 644 2133 192 192 2132 2132 55 2112 2112 2098 17 2106 999 2107 1298 1810 1512 637 2107 2107 2107 1604 1503 60 2048 15 15 999 999 581 35 34 23 34 23 4254 4041 583 4259 581 4258 581 581 581 581 38 543 24 557 3 580 2779 2781 104 101 3310 3312 2 3310 166 166 2841 2839 2842 2778 2779 580 71 2132 1792 1342 2133 396 1626 1513 645 60 644 645 71 580 1218 1210 71 583 583 583 583 583 583 583 582 583 583 583 583 583 583 583 583 583 583 583 583 583 583 582 583 583 42 998 999 998 76 77 2 14 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 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NET3 Protocol independent device support routines. * * Derived from the non IP parts of dev.c 1.0.19 * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * * Additional Authors: * Florian la Roche <rzsfl@rz.uni-sb.de> * Alan Cox <gw4pts@gw4pts.ampr.org> * David Hinds <dahinds@users.sourceforge.net> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * Adam Sulmicki <adam@cfar.umd.edu> * Pekka Riikonen <priikone@poesidon.pspt.fi> * * Changes: * D.J. Barrow : Fixed bug where dev->refcnt gets set * to 2 if register_netdev gets called * before net_dev_init & also removed a * few lines of code in the process. * Alan Cox : device private ioctl copies fields back. * Alan Cox : Transmit queue code does relevant * stunts to keep the queue safe. * Alan Cox : Fixed double lock. * Alan Cox : Fixed promisc NULL pointer trap * ???????? : Support the full private ioctl range * Alan Cox : Moved ioctl permission check into * drivers * Tim Kordas : SIOCADDMULTI/SIOCDELMULTI * Alan Cox : 100 backlog just doesn't cut it when * you start doing multicast video 8) * Alan Cox : Rewrote net_bh and list manager. * Alan Cox : Fix ETH_P_ALL echoback lengths. * Alan Cox : Took out transmit every packet pass * Saved a few bytes in the ioctl handler * Alan Cox : Network driver sets packet type before * calling netif_rx. Saves a function * call a packet. * Alan Cox : Hashed net_bh() * Richard Kooijman: Timestamp fixes. * Alan Cox : Wrong field in SIOCGIFDSTADDR * Alan Cox : Device lock protection. * Alan Cox : Fixed nasty side effect of device close * changes. * Rudi Cilibrasi : Pass the right thing to * set_mac_address() * Dave Miller : 32bit quantity for the device lock to * make it work out on a Sparc. * Bjorn Ekwall : Added KERNELD hack. * Alan Cox : Cleaned up the backlog initialise. * Craig Metz : SIOCGIFCONF fix if space for under * 1 device. * Thomas Bogendoerfer : Return ENODEV for dev_open, if there * is no device open function. * Andi Kleen : Fix error reporting for SIOCGIFCONF * Michael Chastain : Fix signed/unsigned for SIOCGIFCONF * Cyrus Durgin : Cleaned for KMOD * Adam Sulmicki : Bug Fix : Network Device Unload * A network device unload needs to purge * the backlog queue. * Paul Rusty Russell : SIOCSIFNAME * Pekka Riikonen : Netdev boot-time settings code * Andrew Morton : Make unregister_netdevice wait * indefinitely on dev->refcnt * J Hadi Salim : - Backlog queue sampling * - netif_rx() feedback */ #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/capability.h> #include <linux/cpu.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/hash.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/if_ether.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/skbuff.h> #include <linux/kthread.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/busy_poll.h> #include <linux/rtnetlink.h> #include <linux/stat.h> #include <net/dsa.h> #include <net/dst.h> #include <net/dst_metadata.h> #include <net/gro.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/checksum.h> #include <net/xfrm.h> #include <linux/highmem.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netpoll.h> #include <linux/rcupdate.h> #include <linux/delay.h> #include <net/iw_handler.h> #include <asm/current.h> #include <linux/audit.h> #include <linux/dmaengine.h> #include <linux/err.h> #include <linux/ctype.h> #include <linux/if_arp.h> #include <linux/if_vlan.h> #include <linux/ip.h> #include <net/ip.h> #include <net/mpls.h> #include <linux/ipv6.h> #include <linux/in.h> #include <linux/jhash.h> #include <linux/random.h> #include <trace/events/napi.h> #include <trace/events/net.h> #include <trace/events/skb.h> #include <trace/events/qdisc.h> #include <linux/inetdevice.h> #include <linux/cpu_rmap.h> #include <linux/static_key.h> #include <linux/hashtable.h> #include <linux/vmalloc.h> #include <linux/if_macvlan.h> #include <linux/errqueue.h> #include <linux/hrtimer.h> #include <linux/netfilter_netdev.h> #include <linux/crash_dump.h> #include <linux/sctp.h> #include <net/udp_tunnel.h> #include <linux/net_namespace.h> #include <linux/indirect_call_wrapper.h> #include <net/devlink.h> #include <linux/pm_runtime.h> #include <linux/prandom.h> #include <linux/once_lite.h> #include <trace/hooks/net.h> #include "dev.h" #include "net-sysfs.h" static DEFINE_SPINLOCK(ptype_lock); struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; struct list_head ptype_all __read_mostly; /* Taps */ static int netif_rx_internal(struct sk_buff *skb); static int call_netdevice_notifiers_info(unsigned long val, struct netdev_notifier_info *info); static int call_netdevice_notifiers_extack(unsigned long val, struct net_device *dev, struct netlink_ext_ack *extack); static struct napi_struct *napi_by_id(unsigned int napi_id); /* * The @dev_base_head list is protected by @dev_base_lock and the rtnl * semaphore. * * Pure readers hold dev_base_lock for reading, or rcu_read_lock() * * Writers must hold the rtnl semaphore while they loop through the * dev_base_head list, and hold dev_base_lock for writing when they do the * actual updates. This allows pure readers to access the list even * while a writer is preparing to update it. * * To put it another way, dev_base_lock is held for writing only to * protect against pure readers; the rtnl semaphore provides the * protection against other writers. * * See, for example usages, register_netdevice() and * unregister_netdevice(), which must be called with the rtnl * semaphore held. */ DEFINE_RWLOCK(dev_base_lock); EXPORT_SYMBOL(dev_base_lock); static DEFINE_MUTEX(ifalias_mutex); /* protects napi_hash addition/deletion and napi_gen_id */ static DEFINE_SPINLOCK(napi_hash_lock); static unsigned int napi_gen_id = NR_CPUS; static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8); static DECLARE_RWSEM(devnet_rename_sem); static inline void dev_base_seq_inc(struct net *net) { while (++net->dev_base_seq == 0) ; } static inline struct hlist_head *dev_name_hash(struct net *net, const char *name) { unsigned int hash = full_name_hash(net, name, strnlen(name, IFNAMSIZ)); return &net->dev_name_head[hash_32(hash, NETDEV_HASHBITS)]; } static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) { return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)]; } static inline void rps_lock_irqsave(struct softnet_data *sd, unsigned long *flags) { if (IS_ENABLED(CONFIG_RPS)) spin_lock_irqsave(&sd->input_pkt_queue.lock, *flags); else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_save(*flags); } static inline void rps_lock_irq_disable(struct softnet_data *sd) { if (IS_ENABLED(CONFIG_RPS)) spin_lock_irq(&sd->input_pkt_queue.lock); else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_disable(); } static inline void rps_unlock_irq_restore(struct softnet_data *sd, unsigned long *flags) { if (IS_ENABLED(CONFIG_RPS)) spin_unlock_irqrestore(&sd->input_pkt_queue.lock, *flags); else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_restore(*flags); } static inline void rps_unlock_irq_enable(struct softnet_data *sd) { if (IS_ENABLED(CONFIG_RPS)) spin_unlock_irq(&sd->input_pkt_queue.lock); else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_enable(); } static struct netdev_name_node *netdev_name_node_alloc(struct net_device *dev, const char *name) { struct netdev_name_node *name_node; name_node = kmalloc(sizeof(*name_node), GFP_KERNEL); if (!name_node) return NULL; INIT_HLIST_NODE(&name_node->hlist); name_node->dev = dev; name_node->name = name; return name_node; } static struct netdev_name_node * netdev_name_node_head_alloc(struct net_device *dev) { struct netdev_name_node *name_node; name_node = netdev_name_node_alloc(dev, dev->name); if (!name_node) return NULL; INIT_LIST_HEAD(&name_node->list); return name_node; } static void netdev_name_node_free(struct netdev_name_node *name_node) { kfree(name_node); } static void netdev_name_node_add(struct net *net, struct netdev_name_node *name_node) { hlist_add_head_rcu(&name_node->hlist, dev_name_hash(net, name_node->name)); } static void netdev_name_node_del(struct netdev_name_node *name_node) { hlist_del_rcu(&name_node->hlist); } static struct netdev_name_node *netdev_name_node_lookup(struct net *net, const char *name) { struct hlist_head *head = dev_name_hash(net, name); struct netdev_name_node *name_node; hlist_for_each_entry(name_node, head, hlist) if (!strcmp(name_node->name, name)) return name_node; return NULL; } static struct netdev_name_node *netdev_name_node_lookup_rcu(struct net *net, const char *name) { struct hlist_head *head = dev_name_hash(net, name); struct netdev_name_node *name_node; hlist_for_each_entry_rcu(name_node, head, hlist) if (!strcmp(name_node->name, name)) return name_node; return NULL; } bool netdev_name_in_use(struct net *net, const char *name) { return netdev_name_node_lookup(net, name); } EXPORT_SYMBOL(netdev_name_in_use); int netdev_name_node_alt_create(struct net_device *dev, const char *name) { struct netdev_name_node *name_node; struct net *net = dev_net(dev); name_node = netdev_name_node_lookup(net, name); if (name_node) return -EEXIST; name_node = netdev_name_node_alloc(dev, name); if (!name_node) return -ENOMEM; netdev_name_node_add(net, name_node); /* The node that holds dev->name acts as a head of per-device list. */ list_add_tail(&name_node->list, &dev->name_node->list); return 0; } static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node) { list_del(&name_node->list); kfree(name_node->name); netdev_name_node_free(name_node); } int netdev_name_node_alt_destroy(struct net_device *dev, const char *name) { struct netdev_name_node *name_node; struct net *net = dev_net(dev); name_node = netdev_name_node_lookup(net, name); if (!name_node) return -ENOENT; /* lookup might have found our primary name or a name belonging * to another device. */ if (name_node == dev->name_node || name_node->dev != dev) return -EINVAL; netdev_name_node_del(name_node); synchronize_rcu(); __netdev_name_node_alt_destroy(name_node); return 0; } static void netdev_name_node_alt_flush(struct net_device *dev) { struct netdev_name_node *name_node, *tmp; list_for_each_entry_safe(name_node, tmp, &dev->name_node->list, list) __netdev_name_node_alt_destroy(name_node); } /* Device list insertion */ static void list_netdevice(struct net_device *dev) { struct netdev_name_node *name_node; struct net *net = dev_net(dev); ASSERT_RTNL(); write_lock(&dev_base_lock); list_add_tail_rcu(&dev->dev_list, &net->dev_base_head); netdev_name_node_add(net, dev->name_node); hlist_add_head_rcu(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); write_unlock(&dev_base_lock); netdev_for_each_altname(dev, name_node) netdev_name_node_add(net, name_node); dev_base_seq_inc(net); } /* Device list removal * caller must respect a RCU grace period before freeing/reusing dev */ static void unlist_netdevice(struct net_device *dev, bool lock) { struct netdev_name_node *name_node; ASSERT_RTNL(); netdev_for_each_altname(dev, name_node) netdev_name_node_del(name_node); /* Unlink dev from the device chain */ if (lock) write_lock(&dev_base_lock); list_del_rcu(&dev->dev_list); netdev_name_node_del(dev->name_node); hlist_del_rcu(&dev->index_hlist); if (lock) write_unlock(&dev_base_lock); dev_base_seq_inc(dev_net(dev)); } /* * Our notifier list */ static RAW_NOTIFIER_HEAD(netdev_chain); /* * Device drivers call our routines to queue packets here. We empty the * queue in the local softnet handler. */ DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); EXPORT_PER_CPU_SYMBOL(softnet_data); #ifdef CONFIG_LOCKDEP /* * register_netdevice() inits txq->_xmit_lock and sets lockdep class * according to dev->type */ static const unsigned short netdev_lock_type[] = { ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25, ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET, ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM, ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP, ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD, ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25, ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP, ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD, ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI, ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE, ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET, ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL, ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM, ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE}; static const char *const netdev_lock_name[] = { "_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET", "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM", "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP", "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD", "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25", "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP", "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD", "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI", "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE", "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET", "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL", "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM", "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE", "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"}; static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)]; static inline unsigned short netdev_lock_pos(unsigned short dev_type) { int i; for (i = 0; i < ARRAY_SIZE(netdev_lock_type); i++) if (netdev_lock_type[i] == dev_type) return i; /* the last key is used by default */ return ARRAY_SIZE(netdev_lock_type) - 1; } static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, unsigned short dev_type) { int i; i = netdev_lock_pos(dev_type); lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i], netdev_lock_name[i]); } static inline void netdev_set_addr_lockdep_class(struct net_device *dev) { int i; i = netdev_lock_pos(dev->type); lockdep_set_class_and_name(&dev->addr_list_lock, &netdev_addr_lock_key[i], netdev_lock_name[i]); } #else static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, unsigned short dev_type) { } static inline void netdev_set_addr_lockdep_class(struct net_device *dev) { } #endif /******************************************************************************* * * Protocol management and registration routines * *******************************************************************************/ /* * Add a protocol ID to the list. Now that the input handler is * smarter we can dispense with all the messy stuff that used to be * here. * * BEWARE!!! Protocol handlers, mangling input packets, * MUST BE last in hash buckets and checking protocol handlers * MUST start from promiscuous ptype_all chain in net_bh. * It is true now, do not change it. * Explanation follows: if protocol handler, mangling packet, will * be the first on list, it is not able to sense, that packet * is cloned and should be copied-on-write, so that it will * change it and subsequent readers will get broken packet. * --ANK (980803) */ static inline struct list_head *ptype_head(const struct packet_type *pt) { struct list_head vendor_pt = { .next = NULL, }; trace_android_vh_ptype_head(pt, &vendor_pt); if (vendor_pt.next) return vendor_pt.next; if (pt->type == htons(ETH_P_ALL)) return pt->dev ? &pt->dev->ptype_all : &ptype_all; else return pt->dev ? &pt->dev->ptype_specific : &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK]; } /** * dev_add_pack - add packet handler * @pt: packet type declaration * * Add a protocol handler to the networking stack. The passed &packet_type * is linked into kernel lists and may not be freed until it has been * removed from the kernel lists. * * This call does not sleep therefore it can not * guarantee all CPU's that are in middle of receiving packets * will see the new packet type (until the next received packet). */ void dev_add_pack(struct packet_type *pt) { struct list_head *head = ptype_head(pt); spin_lock(&ptype_lock); list_add_rcu(&pt->list, head); spin_unlock(&ptype_lock); } EXPORT_SYMBOL(dev_add_pack); /** * __dev_remove_pack - remove packet handler * @pt: packet type declaration * * Remove a protocol handler that was previously added to the kernel * protocol handlers by dev_add_pack(). The passed &packet_type is removed * from the kernel lists and can be freed or reused once this function * returns. * * The packet type might still be in use by receivers * and must not be freed until after all the CPU's have gone * through a quiescent state. */ void __dev_remove_pack(struct packet_type *pt) { struct list_head *head = ptype_head(pt); struct packet_type *pt1; spin_lock(&ptype_lock); list_for_each_entry(pt1, head, list) { if (pt == pt1) { list_del_rcu(&pt->list); goto out; } } pr_warn("dev_remove_pack: %p not found\n", pt); out: spin_unlock(&ptype_lock); } EXPORT_SYMBOL(__dev_remove_pack); /** * dev_remove_pack - remove packet handler * @pt: packet type declaration * * Remove a protocol handler that was previously added to the kernel * protocol handlers by dev_add_pack(). The passed &packet_type is removed * from the kernel lists and can be freed or reused once this function * returns. * * This call sleeps to guarantee that no CPU is looking at the packet * type after return. */ void dev_remove_pack(struct packet_type *pt) { __dev_remove_pack(pt); synchronize_net(); } EXPORT_SYMBOL(dev_remove_pack); /******************************************************************************* * * Device Interface Subroutines * *******************************************************************************/ /** * dev_get_iflink - get 'iflink' value of a interface * @dev: targeted interface * * Indicates the ifindex the interface is linked to. * Physical interfaces have the same 'ifindex' and 'iflink' values. */ int dev_get_iflink(const struct net_device *dev) { if (dev->netdev_ops && dev->netdev_ops->ndo_get_iflink) return dev->netdev_ops->ndo_get_iflink(dev); return dev->ifindex; } EXPORT_SYMBOL(dev_get_iflink); /** * dev_fill_metadata_dst - Retrieve tunnel egress information. * @dev: targeted interface * @skb: The packet. * * For better visibility of tunnel traffic OVS needs to retrieve * egress tunnel information for a packet. Following API allows * user to get this info. */ int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info; if (!dev->netdev_ops || !dev->netdev_ops->ndo_fill_metadata_dst) return -EINVAL; info = skb_tunnel_info_unclone(skb); if (!info) return -ENOMEM; if (unlikely(!(info->mode & IP_TUNNEL_INFO_TX))) return -EINVAL; return dev->netdev_ops->ndo_fill_metadata_dst(dev, skb); } EXPORT_SYMBOL_GPL(dev_fill_metadata_dst); static struct net_device_path *dev_fwd_path(struct net_device_path_stack *stack) { int k = stack->num_paths++; if (WARN_ON_ONCE(k >= NET_DEVICE_PATH_STACK_MAX)) return NULL; return &stack->path[k]; } int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr, struct net_device_path_stack *stack) { const struct net_device *last_dev; struct net_device_path_ctx ctx = { .dev = dev, }; struct net_device_path *path; int ret = 0; memcpy(ctx.daddr, daddr, sizeof(ctx.daddr)); stack->num_paths = 0; while (ctx.dev && ctx.dev->netdev_ops->ndo_fill_forward_path) { last_dev = ctx.dev; path = dev_fwd_path(stack); if (!path) return -1; memset(path, 0, sizeof(struct net_device_path)); ret = ctx.dev->netdev_ops->ndo_fill_forward_path(&ctx, path); if (ret < 0) return -1; if (WARN_ON_ONCE(last_dev == ctx.dev)) return -1; } if (!ctx.dev) return ret; path = dev_fwd_path(stack); if (!path) return -1; path->type = DEV_PATH_ETHERNET; path->dev = ctx.dev; return ret; } EXPORT_SYMBOL_GPL(dev_fill_forward_path); /** * __dev_get_by_name - find a device by its name * @net: the applicable net namespace * @name: name to find * * Find an interface by name. Must be called under RTNL semaphore * or @dev_base_lock. If the name is found a pointer to the device * is returned. If the name is not found then %NULL is returned. The * reference counters are not incremented so the caller must be * careful with locks. */ struct net_device *__dev_get_by_name(struct net *net, const char *name) { struct netdev_name_node *node_name; node_name = netdev_name_node_lookup(net, name); return node_name ? node_name->dev : NULL; } EXPORT_SYMBOL(__dev_get_by_name); /** * dev_get_by_name_rcu - find a device by its name * @net: the applicable net namespace * @name: name to find * * Find an interface by name. * If the name is found a pointer to the device is returned. * If the name is not found then %NULL is returned. * The reference counters are not incremented so the caller must be * careful with locks. The caller must hold RCU lock. */ struct net_device *dev_get_by_name_rcu(struct net *net, const char *name) { struct netdev_name_node *node_name; node_name = netdev_name_node_lookup_rcu(net, name); return node_name ? node_name->dev : NULL; } EXPORT_SYMBOL(dev_get_by_name_rcu); /** * dev_get_by_name - find a device by its name * @net: the applicable net namespace * @name: name to find * * Find an interface by name. This can be called from any * context and does its own locking. The returned handle has * the usage count incremented and the caller must use dev_put() to * release it when it is no longer needed. %NULL is returned if no * matching device is found. */ struct net_device *dev_get_by_name(struct net *net, const char *name) { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_name_rcu(net, name); dev_hold(dev); rcu_read_unlock(); return dev; } EXPORT_SYMBOL(dev_get_by_name); /** * __dev_get_by_index - find a device by its ifindex * @net: the applicable net namespace * @ifindex: index of device * * Search for an interface by index. Returns %NULL if the device * is not found or a pointer to the device. The device has not * had its reference counter increased so the caller must be careful * about locking. The caller must hold either the RTNL semaphore * or @dev_base_lock. */ struct net_device *__dev_get_by_index(struct net *net, int ifindex) { struct net_device *dev; struct hlist_head *head = dev_index_hash(net, ifindex); hlist_for_each_entry(dev, head, index_hlist) if (dev->ifindex == ifindex) return dev; return NULL; } EXPORT_SYMBOL(__dev_get_by_index); /** * dev_get_by_index_rcu - find a device by its ifindex * @net: the applicable net namespace * @ifindex: index of device * * Search for an interface by index. Returns %NULL if the device * is not found or a pointer to the device. The device has not * had its reference counter increased so the caller must be careful * about locking. The caller must hold RCU lock. */ struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex) { struct net_device *dev; struct hlist_head *head = dev_index_hash(net, ifindex); hlist_for_each_entry_rcu(dev, head, index_hlist) if (dev->ifindex == ifindex) return dev; return NULL; } EXPORT_SYMBOL(dev_get_by_index_rcu); /** * dev_get_by_index - find a device by its ifindex * @net: the applicable net namespace * @ifindex: index of device * * Search for an interface by index. Returns NULL if the device * is not found or a pointer to the device. The device returned has * had a reference added and the pointer is safe until the user calls * dev_put to indicate they have finished with it. */ struct net_device *dev_get_by_index(struct net *net, int ifindex) { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); dev_hold(dev); rcu_read_unlock(); return dev; } EXPORT_SYMBOL(dev_get_by_index); /** * dev_get_by_napi_id - find a device by napi_id * @napi_id: ID of the NAPI struct * * Search for an interface by NAPI ID. Returns %NULL if the device * is not found or a pointer to the device. The device has not had * its reference counter increased so the caller must be careful * about locking. The caller must hold RCU lock. */ struct net_device *dev_get_by_napi_id(unsigned int napi_id) { struct napi_struct *napi; WARN_ON_ONCE(!rcu_read_lock_held()); if (napi_id < MIN_NAPI_ID) return NULL; napi = napi_by_id(napi_id); return napi ? napi->dev : NULL; } EXPORT_SYMBOL(dev_get_by_napi_id); /** * netdev_get_name - get a netdevice name, knowing its ifindex. * @net: network namespace * @name: a pointer to the buffer where the name will be stored. * @ifindex: the ifindex of the interface to get the name from. */ int netdev_get_name(struct net *net, char *name, int ifindex) { struct net_device *dev; int ret; down_read(&devnet_rename_sem); rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (!dev) { ret = -ENODEV; goto out; } strcpy(name, dev->name); ret = 0; out: rcu_read_unlock(); up_read(&devnet_rename_sem); return ret; } EXPORT_SYMBOL_GPL(netdev_get_name); static bool dev_addr_cmp(struct net_device *dev, unsigned short type, const char *ha) { return dev->type == type && !memcmp(dev->dev_addr, ha, dev->addr_len); } /** * dev_getbyhwaddr_rcu - find a device by its hardware address * @net: the applicable net namespace * @type: media type of device * @ha: hardware address * * Search for an interface by MAC address. Returns NULL if the device * is not found or a pointer to the device. * The caller must hold RCU. * The returned device has not had its ref count increased * and the caller must therefore be careful about locking * */ struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, const char *ha) { struct net_device *dev; for_each_netdev_rcu(net, dev) if (dev_addr_cmp(dev, type, ha)) return dev; return NULL; } EXPORT_SYMBOL(dev_getbyhwaddr_rcu); /** * dev_getbyhwaddr() - find a device by its hardware address * @net: the applicable net namespace * @type: media type of device * @ha: hardware address * * Similar to dev_getbyhwaddr_rcu(), but the owner needs to hold * rtnl_lock. * * Context: rtnl_lock() must be held. * Return: pointer to the net_device, or NULL if not found */ struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, const char *ha) { struct net_device *dev; ASSERT_RTNL(); for_each_netdev(net, dev) if (dev_addr_cmp(dev, type, ha)) return dev; return NULL; } EXPORT_SYMBOL(dev_getbyhwaddr); struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type) { struct net_device *dev, *ret = NULL; rcu_read_lock(); for_each_netdev_rcu(net, dev) if (dev->type == type) { dev_hold(dev); ret = dev; break; } rcu_read_unlock(); return ret; } EXPORT_SYMBOL(dev_getfirstbyhwtype); /** * __dev_get_by_flags - find any device with given flags * @net: the applicable net namespace * @if_flags: IFF_* values * @mask: bitmask of bits in if_flags to check * * Search for any interface with the given flags. Returns NULL if a device * is not found or a pointer to the device. Must be called inside * rtnl_lock(), and result refcount is unchanged. */ struct net_device *__dev_get_by_flags(struct net *net, unsigned short if_flags, unsigned short mask) { struct net_device *dev, *ret; ASSERT_RTNL(); ret = NULL; for_each_netdev(net, dev) { if (((dev->flags ^ if_flags) & mask) == 0) { ret = dev; break; } } return ret; } EXPORT_SYMBOL(__dev_get_by_flags); /** * dev_valid_name - check if name is okay for network device * @name: name string * * Network device names need to be valid file names to * allow sysfs to work. We also disallow any kind of * whitespace. */ bool dev_valid_name(const char *name) { if (*name == '\0') return false; if (strnlen(name, IFNAMSIZ) == IFNAMSIZ) return false; if (!strcmp(name, ".") || !strcmp(name, "..")) return false; while (*name) { if (*name == '/' || *name == ':' || isspace(*name)) return false; name++; } return true; } EXPORT_SYMBOL(dev_valid_name); /** * __dev_alloc_name - allocate a name for a device * @net: network namespace to allocate the device name in * @name: name format string * @buf: scratch buffer and result name string * * Passed a format string - eg "lt%d" it will try and find a suitable * id. It scans list of devices to build up a free map, then chooses * the first empty slot. The caller must hold the dev_base or rtnl lock * while allocating the name and adding the device in order to avoid * duplicates. * Limited to bits_per_byte * page size devices (ie 32K on most platforms). * Returns the number of the unit assigned or a negative errno code. */ static int __dev_alloc_name(struct net *net, const char *name, char *buf) { int i = 0; const char *p; const int max_netdevices = 8*PAGE_SIZE; unsigned long *inuse; struct net_device *d; if (!dev_valid_name(name)) return -EINVAL; p = strchr(name, '%'); if (p) { /* * Verify the string as this thing may have come from * the user. There must be either one "%d" and no other "%" * characters. */ if (p[1] != 'd' || strchr(p + 2, '%')) return -EINVAL; /* Use one page as a bit array of possible slots */ inuse = (unsigned long *) get_zeroed_page(GFP_ATOMIC); if (!inuse) return -ENOMEM; for_each_netdev(net, d) { struct netdev_name_node *name_node; netdev_for_each_altname(d, name_node) { if (!sscanf(name_node->name, name, &i)) continue; if (i < 0 || i >= max_netdevices) continue; /* avoid cases where sscanf is not exact inverse of printf */ snprintf(buf, IFNAMSIZ, name, i); if (!strncmp(buf, name_node->name, IFNAMSIZ)) __set_bit(i, inuse); } if (!sscanf(d->name, name, &i)) continue; if (i < 0 || i >= max_netdevices) continue; /* avoid cases where sscanf is not exact inverse of printf */ snprintf(buf, IFNAMSIZ, name, i); if (!strncmp(buf, d->name, IFNAMSIZ)) __set_bit(i, inuse); } i = find_first_zero_bit(inuse, max_netdevices); free_page((unsigned long) inuse); } snprintf(buf, IFNAMSIZ, name, i); if (!netdev_name_in_use(net, buf)) return i; /* It is possible to run out of possible slots * when the name is long and there isn't enough space left * for the digits, or if all bits are used. */ return -ENFILE; } static int dev_prep_valid_name(struct net *net, struct net_device *dev, const char *want_name, char *out_name) { int ret; if (!dev_valid_name(want_name)) return -EINVAL; if (strchr(want_name, '%')) { ret = __dev_alloc_name(net, want_name, out_name); return ret < 0 ? ret : 0; } else if (netdev_name_in_use(net, want_name)) { return -EEXIST; } else if (out_name != want_name) { strscpy(out_name, want_name, IFNAMSIZ); } return 0; } static int dev_alloc_name_ns(struct net *net, struct net_device *dev, const char *name) { char buf[IFNAMSIZ]; int ret; BUG_ON(!net); ret = __dev_alloc_name(net, name, buf); if (ret >= 0) strscpy(dev->name, buf, IFNAMSIZ); return ret; } /** * dev_alloc_name - allocate a name for a device * @dev: device * @name: name format string * * Passed a format string - eg "lt%d" it will try and find a suitable * id. It scans list of devices to build up a free map, then chooses * the first empty slot. The caller must hold the dev_base or rtnl lock * while allocating the name and adding the device in order to avoid * duplicates. * Limited to bits_per_byte * page size devices (ie 32K on most platforms). * Returns the number of the unit assigned or a negative errno code. */ int dev_alloc_name(struct net_device *dev, const char *name) { return dev_alloc_name_ns(dev_net(dev), dev, name); } EXPORT_SYMBOL(dev_alloc_name); static int dev_get_valid_name(struct net *net, struct net_device *dev, const char *name) { char buf[IFNAMSIZ]; int ret; ret = dev_prep_valid_name(net, dev, name, buf); if (ret >= 0) strscpy(dev->name, buf, IFNAMSIZ); return ret; } /** * dev_change_name - change name of a device * @dev: device * @newname: name (or format string) must be at least IFNAMSIZ * * Change name of a device, can pass format strings "eth%d". * for wildcarding. */ int dev_change_name(struct net_device *dev, const char *newname) { unsigned char old_assign_type; char oldname[IFNAMSIZ]; int err = 0; int ret; struct net *net; ASSERT_RTNL(); BUG_ON(!dev_net(dev)); net = dev_net(dev); /* Some auto-enslaved devices e.g. failover slaves are * special, as userspace might rename the device after * the interface had been brought up and running since * the point kernel initiated auto-enslavement. Allow * live name change even when these slave devices are * up and running. * * Typically, users of these auto-enslaving devices * don't actually care about slave name change, as * they are supposed to operate on master interface * directly. */ if (dev->flags & IFF_UP && likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK))) return -EBUSY; down_write(&devnet_rename_sem); if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { up_write(&devnet_rename_sem); return 0; } memcpy(oldname, dev->name, IFNAMSIZ); err = dev_get_valid_name(net, dev, newname); if (err < 0) { up_write(&devnet_rename_sem); return err; } if (oldname[0] && !strchr(oldname, '%')) netdev_info(dev, "renamed from %s\n", oldname); old_assign_type = dev->name_assign_type; dev->name_assign_type = NET_NAME_RENAMED; rollback: ret = device_rename(&dev->dev, dev->name); if (ret) { memcpy(dev->name, oldname, IFNAMSIZ); dev->name_assign_type = old_assign_type; up_write(&devnet_rename_sem); return ret; } up_write(&devnet_rename_sem); netdev_adjacent_rename_links(dev, oldname); write_lock(&dev_base_lock); netdev_name_node_del(dev->name_node); write_unlock(&dev_base_lock); synchronize_rcu(); write_lock(&dev_base_lock); netdev_name_node_add(net, dev->name_node); write_unlock(&dev_base_lock); ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev); ret = notifier_to_errno(ret); if (ret) { /* err >= 0 after dev_alloc_name() or stores the first errno */ if (err >= 0) { err = ret; down_write(&devnet_rename_sem); memcpy(dev->name, oldname, IFNAMSIZ); memcpy(oldname, newname, IFNAMSIZ); dev->name_assign_type = old_assign_type; old_assign_type = NET_NAME_RENAMED; goto rollback; } else { netdev_err(dev, "name change rollback failed: %d\n", ret); } } return err; } /** * dev_set_alias - change ifalias of a device * @dev: device * @alias: name up to IFALIASZ * @len: limit of bytes to copy from info * * Set ifalias for a device, */ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) { struct dev_ifalias *new_alias = NULL; if (len >= IFALIASZ) return -EINVAL; if (len) { new_alias = kmalloc(sizeof(*new_alias) + len + 1, GFP_KERNEL); if (!new_alias) return -ENOMEM; memcpy(new_alias->ifalias, alias, len); new_alias->ifalias[len] = 0; } mutex_lock(&ifalias_mutex); new_alias = rcu_replace_pointer(dev->ifalias, new_alias, mutex_is_locked(&ifalias_mutex)); mutex_unlock(&ifalias_mutex); if (new_alias) kfree_rcu(new_alias, rcuhead); return len; } EXPORT_SYMBOL(dev_set_alias); /** * dev_get_alias - get ifalias of a device * @dev: device * @name: buffer to store name of ifalias * @len: size of buffer * * get ifalias for a device. Caller must make sure dev cannot go * away, e.g. rcu read lock or own a reference count to device. */ int dev_get_alias(const struct net_device *dev, char *name, size_t len) { const struct dev_ifalias *alias; int ret = 0; rcu_read_lock(); alias = rcu_dereference(dev->ifalias); if (alias) ret = snprintf(name, len, "%s", alias->ifalias); rcu_read_unlock(); return ret; } /** * netdev_features_change - device changes features * @dev: device to cause notification * * Called to indicate a device has changed features. */ void netdev_features_change(struct net_device *dev) { call_netdevice_notifiers(NETDEV_FEAT_CHANGE, dev); } EXPORT_SYMBOL(netdev_features_change); /** * netdev_state_change - device changes state * @dev: device to cause notification * * Called to indicate a device has changed state. This function calls * the notifier chains for netdev_chain and sends a NEWLINK message * to the routing socket. */ void netdev_state_change(struct net_device *dev) { if (dev->flags & IFF_UP) { struct netdev_notifier_change_info change_info = { .info.dev = dev, }; call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info); rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL); } } EXPORT_SYMBOL(netdev_state_change); /** * __netdev_notify_peers - notify network peers about existence of @dev, * to be called when rtnl lock is already held. * @dev: network device * * Generate traffic such that interested network peers are aware of * @dev, such as by generating a gratuitous ARP. This may be used when * a device wants to inform the rest of the network about some sort of * reconfiguration such as a failover event or virtual machine * migration. */ void __netdev_notify_peers(struct net_device *dev) { ASSERT_RTNL(); call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev); call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev); } EXPORT_SYMBOL(__netdev_notify_peers); /** * netdev_notify_peers - notify network peers about existence of @dev * @dev: network device * * Generate traffic such that interested network peers are aware of * @dev, such as by generating a gratuitous ARP. This may be used when * a device wants to inform the rest of the network about some sort of * reconfiguration such as a failover event or virtual machine * migration. */ void netdev_notify_peers(struct net_device *dev) { rtnl_lock(); __netdev_notify_peers(dev); rtnl_unlock(); } EXPORT_SYMBOL(netdev_notify_peers); static int napi_threaded_poll(void *data); static int napi_kthread_create(struct napi_struct *n) { int err = 0; /* Create and wake up the kthread once to put it in * TASK_INTERRUPTIBLE mode to avoid the blocked task * warning and work with loadavg. */ n->thread = kthread_run(napi_threaded_poll, n, "napi/%s-%d", n->dev->name, n->napi_id); if (IS_ERR(n->thread)) { err = PTR_ERR(n->thread); pr_err("kthread_run failed with err %d\n", err); n->thread = NULL; } return err; } static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; int ret; ASSERT_RTNL(); dev_addr_check(dev); if (!netif_device_present(dev)) { /* may be detached because parent is runtime-suspended */ if (dev->dev.parent) pm_runtime_resume(dev->dev.parent); if (!netif_device_present(dev)) return -ENODEV; } /* Block netpoll from trying to do any rx path servicing. * If we don't do this there is a chance ndo_poll_controller * or ndo_poll may be running while we open the device */ netpoll_poll_disable(dev); ret = call_netdevice_notifiers_extack(NETDEV_PRE_UP, dev, extack); ret = notifier_to_errno(ret); if (ret) return ret; set_bit(__LINK_STATE_START, &dev->state); if (ops->ndo_validate_addr) ret = ops->ndo_validate_addr(dev); if (!ret && ops->ndo_open) ret = ops->ndo_open(dev); netpoll_poll_enable(dev); if (ret) clear_bit(__LINK_STATE_START, &dev->state); else { dev->flags |= IFF_UP; dev_set_rx_mode(dev); dev_activate(dev); add_device_randomness(dev->dev_addr, dev->addr_len); } return ret; } /** * dev_open - prepare an interface for use. * @dev: device to open * @extack: netlink extended ack * * Takes a device from down to up state. The device's private open * function is invoked and then the multicast lists are loaded. Finally * the device is moved into the up state and a %NETDEV_UP message is * sent to the netdev notifier chain. * * Calling this function on an active interface is a nop. On a failure * a negative errno code is returned. */ int dev_open(struct net_device *dev, struct netlink_ext_ack *extack) { int ret; if (dev->flags & IFF_UP) return 0; ret = __dev_open(dev, extack); if (ret < 0) return ret; rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL); call_netdevice_notifiers(NETDEV_UP, dev); return ret; } EXPORT_SYMBOL(dev_open); static void __dev_close_many(struct list_head *head) { struct net_device *dev; ASSERT_RTNL(); might_sleep(); list_for_each_entry(dev, head, close_list) { /* Temporarily disable netpoll until the interface is down */ netpoll_poll_disable(dev); call_netdevice_notifiers(NETDEV_GOING_DOWN, dev); clear_bit(__LINK_STATE_START, &dev->state); /* Synchronize to scheduled poll. We cannot touch poll list, it * can be even on different cpu. So just clear netif_running(). * * dev->stop() will invoke napi_disable() on all of it's * napi_struct instances on this device. */ smp_mb__after_atomic(); /* Commit netif_running(). */ } dev_deactivate_many(head); list_for_each_entry(dev, head, close_list) { const struct net_device_ops *ops = dev->netdev_ops; /* * Call the device specific close. This cannot fail. * Only if device is UP * * We allow it to be called even after a DETACH hot-plug * event. */ if (ops->ndo_stop) ops->ndo_stop(dev); dev->flags &= ~IFF_UP; netpoll_poll_enable(dev); } } static void __dev_close(struct net_device *dev) { LIST_HEAD(single); list_add(&dev->close_list, &single); __dev_close_many(&single); list_del(&single); } void dev_close_many(struct list_head *head, bool unlink) { struct net_device *dev, *tmp; /* Remove the devices that don't need to be closed */ list_for_each_entry_safe(dev, tmp, head, close_list) if (!(dev->flags & IFF_UP)) list_del_init(&dev->close_list); __dev_close_many(head); list_for_each_entry_safe(dev, tmp, head, close_list) { rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL); call_netdevice_notifiers(NETDEV_DOWN, dev); if (unlink) list_del_init(&dev->close_list); } } EXPORT_SYMBOL(dev_close_many); /** * dev_close - shutdown an interface. * @dev: device to shutdown * * This function moves an active device into down state. A * %NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device * is then deactivated and finally a %NETDEV_DOWN is sent to the notifier * chain. */ void dev_close(struct net_device *dev) { if (dev->flags & IFF_UP) { LIST_HEAD(single); list_add(&dev->close_list, &single); dev_close_many(&single, true); list_del(&single); } } EXPORT_SYMBOL(dev_close); /** * dev_disable_lro - disable Large Receive Offload on a device * @dev: device * * Disable Large Receive Offload (LRO) on a net device. Must be * called under RTNL. This is needed if received packets may be * forwarded to another interface. */ void dev_disable_lro(struct net_device *dev) { struct net_device *lower_dev; struct list_head *iter; dev->wanted_features &= ~NETIF_F_LRO; netdev_update_features(dev); if (unlikely(dev->features & NETIF_F_LRO)) netdev_WARN(dev, "failed to disable LRO!\n"); netdev_for_each_lower_dev(dev, lower_dev, iter) dev_disable_lro(lower_dev); } EXPORT_SYMBOL(dev_disable_lro); /** * dev_disable_gro_hw - disable HW Generic Receive Offload on a device * @dev: device * * Disable HW Generic Receive Offload (GRO_HW) on a net device. Must be * called under RTNL. This is needed if Generic XDP is installed on * the device. */ static void dev_disable_gro_hw(struct net_device *dev) { dev->wanted_features &= ~NETIF_F_GRO_HW; netdev_update_features(dev); if (unlikely(dev->features & NETIF_F_GRO_HW)) netdev_WARN(dev, "failed to disable GRO_HW!\n"); } const char *netdev_cmd_to_name(enum netdev_cmd cmd) { #define N(val) \ case NETDEV_##val: \ return "NETDEV_" __stringify(val); switch (cmd) { N(UP) N(DOWN) N(REBOOT) N(CHANGE) N(REGISTER) N(UNREGISTER) N(CHANGEMTU) N(CHANGEADDR) N(GOING_DOWN) N(CHANGENAME) N(FEAT_CHANGE) N(BONDING_FAILOVER) N(PRE_UP) N(PRE_TYPE_CHANGE) N(POST_TYPE_CHANGE) N(POST_INIT) N(RELEASE) N(NOTIFY_PEERS) N(JOIN) N(CHANGEUPPER) N(RESEND_IGMP) N(PRECHANGEMTU) N(CHANGEINFODATA) N(BONDING_INFO) N(PRECHANGEUPPER) N(CHANGELOWERSTATE) N(UDP_TUNNEL_PUSH_INFO) N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN) N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO) N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO) N(PRE_CHANGEADDR) N(OFFLOAD_XSTATS_ENABLE) N(OFFLOAD_XSTATS_DISABLE) N(OFFLOAD_XSTATS_REPORT_USED) N(OFFLOAD_XSTATS_REPORT_DELTA) } #undef N return "UNKNOWN_NETDEV_EVENT"; } EXPORT_SYMBOL_GPL(netdev_cmd_to_name); static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val, struct net_device *dev) { struct netdev_notifier_info info = { .dev = dev, }; return nb->notifier_call(nb, val, &info); } static int call_netdevice_register_notifiers(struct notifier_block *nb, struct net_device *dev) { int err; err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev); err = notifier_to_errno(err); if (err) return err; if (!(dev->flags & IFF_UP)) return 0; call_netdevice_notifier(nb, NETDEV_UP, dev); return 0; } static void call_netdevice_unregister_notifiers(struct notifier_block *nb, struct net_device *dev) { if (dev->flags & IFF_UP) { call_netdevice_notifier(nb, NETDEV_GOING_DOWN, dev); call_netdevice_notifier(nb, NETDEV_DOWN, dev); } call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); } static int call_netdevice_register_net_notifiers(struct notifier_block *nb, struct net *net) { struct net_device *dev; int err; for_each_netdev(net, dev) { err = call_netdevice_register_notifiers(nb, dev); if (err) goto rollback; } return 0; rollback: for_each_netdev_continue_reverse(net, dev) call_netdevice_unregister_notifiers(nb, dev); return err; } static void call_netdevice_unregister_net_notifiers(struct notifier_block *nb, struct net *net) { struct net_device *dev; for_each_netdev(net, dev) call_netdevice_unregister_notifiers(nb, dev); } static int dev_boot_phase = 1; /** * register_netdevice_notifier - register a network notifier block * @nb: notifier * * Register a notifier to be called when network device events occur. * The notifier passed is linked into the kernel structures and must * not be reused until it has been unregistered. A negative errno code * is returned on a failure. * * When registered all registration and up events are replayed * to the new notifier to allow device to have a race free * view of the network device list. */ int register_netdevice_notifier(struct notifier_block *nb) { struct net *net; int err; /* Close race with setup_net() and cleanup_net() */ down_write(&pernet_ops_rwsem); rtnl_lock(); err = raw_notifier_chain_register(&netdev_chain, nb); if (err) goto unlock; if (dev_boot_phase) goto unlock; for_each_net(net) { err = call_netdevice_register_net_notifiers(nb, net); if (err) goto rollback; } unlock: rtnl_unlock(); up_write(&pernet_ops_rwsem); return err; rollback: for_each_net_continue_reverse(net) call_netdevice_unregister_net_notifiers(nb, net); raw_notifier_chain_unregister(&netdev_chain, nb); goto unlock; } EXPORT_SYMBOL(register_netdevice_notifier); /** * unregister_netdevice_notifier - unregister a network notifier block * @nb: notifier * * Unregister a notifier previously registered by * register_netdevice_notifier(). The notifier is unlinked into the * kernel structures and may then be reused. A negative errno code * is returned on a failure. * * After unregistering unregister and down device events are synthesized * for all devices on the device list to the removed notifier to remove * the need for special case cleanup code. */ int unregister_netdevice_notifier(struct notifier_block *nb) { struct net *net; int err; /* Close race with setup_net() and cleanup_net() */ down_write(&pernet_ops_rwsem); rtnl_lock(); err = raw_notifier_chain_unregister(&netdev_chain, nb); if (err) goto unlock; for_each_net(net) call_netdevice_unregister_net_notifiers(nb, net); unlock: rtnl_unlock(); up_write(&pernet_ops_rwsem); return err; } EXPORT_SYMBOL(unregister_netdevice_notifier); static int __register_netdevice_notifier_net(struct net *net, struct notifier_block *nb, bool ignore_call_fail) { int err; err = raw_notifier_chain_register(&net->netdev_chain, nb); if (err) return err; if (dev_boot_phase) return 0; err = call_netdevice_register_net_notifiers(nb, net); if (err && !ignore_call_fail) goto chain_unregister; return 0; chain_unregister: raw_notifier_chain_unregister(&net->netdev_chain, nb); return err; } static int __unregister_netdevice_notifier_net(struct net *net, struct notifier_block *nb) { int err; err = raw_notifier_chain_unregister(&net->netdev_chain, nb); if (err) return err; call_netdevice_unregister_net_notifiers(nb, net); return 0; } /** * register_netdevice_notifier_net - register a per-netns network notifier block * @net: network namespace * @nb: notifier * * Register a notifier to be called when network device events occur. * The notifier passed is linked into the kernel structures and must * not be reused until it has been unregistered. A negative errno code * is returned on a failure. * * When registered all registration and up events are replayed * to the new notifier to allow device to have a race free * view of the network device list. */ int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb) { int err; rtnl_lock(); err = __register_netdevice_notifier_net(net, nb, false); rtnl_unlock(); return err; } EXPORT_SYMBOL(register_netdevice_notifier_net); /** * unregister_netdevice_notifier_net - unregister a per-netns * network notifier block * @net: network namespace * @nb: notifier * * Unregister a notifier previously registered by * register_netdevice_notifier(). The notifier is unlinked into the * kernel structures and may then be reused. A negative errno code * is returned on a failure. * * After unregistering unregister and down device events are synthesized * for all devices on the device list to the removed notifier to remove * the need for special case cleanup code. */ int unregister_netdevice_notifier_net(struct net *net, struct notifier_block *nb) { int err; rtnl_lock(); err = __unregister_netdevice_notifier_net(net, nb); rtnl_unlock(); return err; } EXPORT_SYMBOL(unregister_netdevice_notifier_net); int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) { int err; rtnl_lock(); err = __register_netdevice_notifier_net(dev_net(dev), nb, false); if (!err) { nn->nb = nb; list_add(&nn->list, &dev->net_notifier_list); } rtnl_unlock(); return err; } EXPORT_SYMBOL(register_netdevice_notifier_dev_net); int unregister_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) { int err; rtnl_lock(); list_del(&nn->list); err = __unregister_netdevice_notifier_net(dev_net(dev), nb); rtnl_unlock(); return err; } EXPORT_SYMBOL(unregister_netdevice_notifier_dev_net); static void move_netdevice_notifiers_dev_net(struct net_device *dev, struct net *net) { struct netdev_net_notifier *nn; list_for_each_entry(nn, &dev->net_notifier_list, list) { __unregister_netdevice_notifier_net(dev_net(dev), nn->nb); __register_netdevice_notifier_net(net, nn->nb, true); } } /** * call_netdevice_notifiers_info - call all network notifier blocks * @val: value passed unmodified to notifier function * @info: notifier information data * * Call all network notifier blocks. Parameters and return value * are as for raw_notifier_call_chain(). */ static int call_netdevice_notifiers_info(unsigned long val, struct netdev_notifier_info *info) { struct net *net = dev_net(info->dev); int ret; ASSERT_RTNL(); /* Run per-netns notifier block chain first, then run the global one. * Hopefully, one day, the global one is going to be removed after * all notifier block registrators get converted to be per-netns. */ ret = raw_notifier_call_chain(&net->netdev_chain, val, info); if (ret & NOTIFY_STOP_MASK) return ret; return raw_notifier_call_chain(&netdev_chain, val, info); } /** * call_netdevice_notifiers_info_robust - call per-netns notifier blocks * for and rollback on error * @val_up: value passed unmodified to notifier function * @val_down: value passed unmodified to the notifier function when * recovering from an error on @val_up * @info: notifier information data * * Call all per-netns network notifier blocks, but not notifier blocks on * the global notifier chain. Parameters and return value are as for * raw_notifier_call_chain_robust(). */ static int call_netdevice_notifiers_info_robust(unsigned long val_up, unsigned long val_down, struct netdev_notifier_info *info) { struct net *net = dev_net(info->dev); ASSERT_RTNL(); return raw_notifier_call_chain_robust(&net->netdev_chain, val_up, val_down, info); } static int call_netdevice_notifiers_extack(unsigned long val, struct net_device *dev, struct netlink_ext_ack *extack) { struct netdev_notifier_info info = { .dev = dev, .extack = extack, }; return call_netdevice_notifiers_info(val, &info); } /** * call_netdevice_notifiers - call all network notifier blocks * @val: value passed unmodified to notifier function * @dev: net_device pointer passed unmodified to notifier function * * Call all network notifier blocks. Parameters and return value * are as for raw_notifier_call_chain(). */ int call_netdevice_notifiers(unsigned long val, struct net_device *dev) { return call_netdevice_notifiers_extack(val, dev, NULL); } EXPORT_SYMBOL(call_netdevice_notifiers); /** * call_netdevice_notifiers_mtu - call all network notifier blocks * @val: value passed unmodified to notifier function * @dev: net_device pointer passed unmodified to notifier function * @arg: additional u32 argument passed to the notifier function * * Call all network notifier blocks. Parameters and return value * are as for raw_notifier_call_chain(). */ static int call_netdevice_notifiers_mtu(unsigned long val, struct net_device *dev, u32 arg) { struct netdev_notifier_info_ext info = { .info.dev = dev, .ext.mtu = arg, }; BUILD_BUG_ON(offsetof(struct netdev_notifier_info_ext, info) != 0); return call_netdevice_notifiers_info(val, &info.info); } #ifdef CONFIG_NET_INGRESS static DEFINE_STATIC_KEY_FALSE(ingress_needed_key); void net_inc_ingress_queue(void) { static_branch_inc(&ingress_needed_key); } EXPORT_SYMBOL_GPL(net_inc_ingress_queue); void net_dec_ingress_queue(void) { static_branch_dec(&ingress_needed_key); } EXPORT_SYMBOL_GPL(net_dec_ingress_queue); #endif #ifdef CONFIG_NET_EGRESS static DEFINE_STATIC_KEY_FALSE(egress_needed_key); void net_inc_egress_queue(void) { static_branch_inc(&egress_needed_key); } EXPORT_SYMBOL_GPL(net_inc_egress_queue); void net_dec_egress_queue(void) { static_branch_dec(&egress_needed_key); } EXPORT_SYMBOL_GPL(net_dec_egress_queue); #endif DEFINE_STATIC_KEY_FALSE(netstamp_needed_key); EXPORT_SYMBOL(netstamp_needed_key); #ifdef CONFIG_JUMP_LABEL static atomic_t netstamp_needed_deferred; static atomic_t netstamp_wanted; static void netstamp_clear(struct work_struct *work) { int deferred = atomic_xchg(&netstamp_needed_deferred, 0); int wanted; wanted = atomic_add_return(deferred, &netstamp_wanted); if (wanted > 0) static_branch_enable(&netstamp_needed_key); else static_branch_disable(&netstamp_needed_key); } static DECLARE_WORK(netstamp_work, netstamp_clear); #endif void net_enable_timestamp(void) { #ifdef CONFIG_JUMP_LABEL int wanted; while (1) { wanted = atomic_read(&netstamp_wanted); if (wanted <= 0) break; if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted + 1) == wanted) return; } atomic_inc(&netstamp_needed_deferred); schedule_work(&netstamp_work); #else static_branch_inc(&netstamp_needed_key); #endif } EXPORT_SYMBOL(net_enable_timestamp); void net_disable_timestamp(void) { #ifdef CONFIG_JUMP_LABEL int wanted; while (1) { wanted = atomic_read(&netstamp_wanted); if (wanted <= 1) break; if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted - 1) == wanted) return; } atomic_dec(&netstamp_needed_deferred); schedule_work(&netstamp_work); #else static_branch_dec(&netstamp_needed_key); #endif } EXPORT_SYMBOL(net_disable_timestamp); static inline void net_timestamp_set(struct sk_buff *skb) { skb->tstamp = 0; skb->mono_delivery_time = 0; if (static_branch_unlikely(&netstamp_needed_key)) skb->tstamp = ktime_get_real(); } #define net_timestamp_check(COND, SKB) \ if (static_branch_unlikely(&netstamp_needed_key)) { \ if ((COND) && !(SKB)->tstamp) \ (SKB)->tstamp = ktime_get_real(); \ } \ bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb) { return __is_skb_forwardable(dev, skb, true); } EXPORT_SYMBOL_GPL(is_skb_forwardable); static int __dev_forward_skb2(struct net_device *dev, struct sk_buff *skb, bool check_mtu) { int ret = ____dev_forward_skb(dev, skb, check_mtu); if (likely(!ret)) { skb->protocol = eth_type_trans(skb, dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } return ret; } int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { return __dev_forward_skb2(dev, skb, true); } EXPORT_SYMBOL_GPL(__dev_forward_skb); /** * dev_forward_skb - loopback an skb to another netif * * @dev: destination network device * @skb: buffer to forward * * return values: * NET_RX_SUCCESS (no congestion) * NET_RX_DROP (packet was dropped, but freed) * * dev_forward_skb can be used for injecting an skb from the * start_xmit function of one device into the receive queue * of another device. * * The receiving device may be in another namespace, so * we have to clear all information in the skb that could * impact namespace isolation. */ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { return __dev_forward_skb(dev, skb) ?: netif_rx_internal(skb); } EXPORT_SYMBOL_GPL(dev_forward_skb); int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb) { return __dev_forward_skb2(dev, skb, false) ?: netif_rx_internal(skb); } static inline int deliver_skb(struct sk_buff *skb, struct packet_type *pt_prev, struct net_device *orig_dev) { if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) return -ENOMEM; refcount_inc(&skb->users); return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } static inline void deliver_ptype_list_skb(struct sk_buff *skb, struct packet_type **pt, struct net_device *orig_dev, __be16 type, struct list_head *ptype_list) { struct packet_type *ptype, *pt_prev = *pt; list_for_each_entry_rcu(ptype, ptype_list, list) { if (ptype->type != type) continue; if (pt_prev) deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } *pt = pt_prev; } static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb) { if (!ptype->af_packet_priv || !skb->sk) return false; if (ptype->id_match) return ptype->id_match(ptype, skb->sk); else if ((struct sock *)ptype->af_packet_priv == skb->sk) return true; return false; } /** * dev_nit_active - return true if any network interface taps are in use * * @dev: network device to check for the presence of taps */ bool dev_nit_active(struct net_device *dev) { return !list_empty(&ptype_all) || !list_empty(&dev->ptype_all); } EXPORT_SYMBOL_GPL(dev_nit_active); /* * Support routine. Sends outgoing frames to any network * taps currently in use. */ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) { struct packet_type *ptype; struct sk_buff *skb2 = NULL; struct packet_type *pt_prev = NULL; struct list_head *ptype_list = &ptype_all; rcu_read_lock(); again: list_for_each_entry_rcu(ptype, ptype_list, list) { if (READ_ONCE(ptype->ignore_outgoing)) continue; /* Never send packets back to the socket * they originated from - MvS (miquels@drinkel.ow.org) */ if (skb_loop_sk(ptype, skb)) continue; if (pt_prev) { deliver_skb(skb2, pt_prev, skb->dev); pt_prev = ptype; continue; } /* need to clone skb, done only once */ skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) goto out_unlock; net_timestamp_set(skb2); /* skb->nh should be correctly * set by sender, so that the second statement is * just protection against buggy protocols. */ skb_reset_mac_header(skb2); if (skb_network_header(skb2) < skb2->data || skb_network_header(skb2) > skb_tail_pointer(skb2)) { net_crit_ratelimited("protocol %04x is buggy, dev %s\n", ntohs(skb2->protocol), dev->name); skb_reset_network_header(skb2); } skb2->transport_header = skb2->network_header; skb2->pkt_type = PACKET_OUTGOING; pt_prev = ptype; } if (ptype_list == &ptype_all) { ptype_list = &dev->ptype_all; goto again; } out_unlock: if (pt_prev) { if (!skb_orphan_frags_rx(skb2, GFP_ATOMIC)) pt_prev->func(skb2, skb->dev, pt_prev, skb->dev); else kfree_skb(skb2); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(dev_queue_xmit_nit); /** * netif_setup_tc - Handle tc mappings on real_num_tx_queues change * @dev: Network device * @txq: number of queues available * * If real_num_tx_queues is changed the tc mappings may no longer be * valid. To resolve this verify the tc mapping remains valid and if * not NULL the mapping. With no priorities mapping to this * offset/count pair it will no longer be used. In the worst case TC0 * is invalid nothing can be done so disable priority mappings. If is * expected that drivers will fix this mapping if they can before * calling netif_set_real_num_tx_queues. */ static void netif_setup_tc(struct net_device *dev, unsigned int txq) { int i; struct netdev_tc_txq *tc = &dev->tc_to_txq[0]; /* If TC0 is invalidated disable TC mapping */ if (tc->offset + tc->count > txq) { netdev_warn(dev, "Number of in use tx queues changed invalidating tc mappings. Priority traffic classification disabled!\n"); dev->num_tc = 0; return; } /* Invalidated prio to tc mappings set to TC0 */ for (i = 1; i < TC_BITMASK + 1; i++) { int q = netdev_get_prio_tc_map(dev, i); tc = &dev->tc_to_txq[q]; if (tc->offset + tc->count > txq) { netdev_warn(dev, "Number of in use tx queues changed. Priority %i to tc mapping %i is no longer valid. Setting map to 0\n", i, q); netdev_set_prio_tc_map(dev, i, 0); } } } int netdev_txq_to_tc(struct net_device *dev, unsigned int txq) { if (dev->num_tc) { struct netdev_tc_txq *tc = &dev->tc_to_txq[0]; int i; /* walk through the TCs and see if it falls into any of them */ for (i = 0; i < TC_MAX_QUEUE; i++, tc++) { if ((txq - tc->offset) < tc->count) return i; } /* didn't find it, just return -1 to indicate no match */ return -1; } return 0; } EXPORT_SYMBOL(netdev_txq_to_tc); #ifdef CONFIG_XPS static struct static_key xps_needed __read_mostly; static struct static_key xps_rxqs_needed __read_mostly; static DEFINE_MUTEX(xps_map_mutex); #define xmap_dereference(P) \ rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) static bool remove_xps_queue(struct xps_dev_maps *dev_maps, struct xps_dev_maps *old_maps, int tci, u16 index) { struct xps_map *map = NULL; int pos; if (dev_maps) map = xmap_dereference(dev_maps->attr_map[tci]); if (!map) return false; for (pos = map->len; pos--;) { if (map->queues[pos] != index) continue; if (map->len > 1) { map->queues[pos] = map->queues[--map->len]; break; } if (old_maps) RCU_INIT_POINTER(old_maps->attr_map[tci], NULL); RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL); kfree_rcu(map, rcu); return false; } return true; } static bool remove_xps_queue_cpu(struct net_device *dev, struct xps_dev_maps *dev_maps, int cpu, u16 offset, u16 count) { int num_tc = dev_maps->num_tc; bool active = false; int tci; for (tci = cpu * num_tc; num_tc--; tci++) { int i, j; for (i = count, j = offset; i--; j++) { if (!remove_xps_queue(dev_maps, NULL, tci, j)) break; } active |= i < 0; } return active; } static void reset_xps_maps(struct net_device *dev, struct xps_dev_maps *dev_maps, enum xps_map_type type) { static_key_slow_dec_cpuslocked(&xps_needed); if (type == XPS_RXQS) static_key_slow_dec_cpuslocked(&xps_rxqs_needed); RCU_INIT_POINTER(dev->xps_maps[type], NULL); kfree_rcu(dev_maps, rcu); } static void clean_xps_maps(struct net_device *dev, enum xps_map_type type, u16 offset, u16 count) { struct xps_dev_maps *dev_maps; bool active = false; int i, j; dev_maps = xmap_dereference(dev->xps_maps[type]); if (!dev_maps) return; for (j = 0; j < dev_maps->nr_ids; j++) active |= remove_xps_queue_cpu(dev, dev_maps, j, offset, count); if (!active) reset_xps_maps(dev, dev_maps, type); if (type == XPS_CPUS) { for (i = offset + (count - 1); count--; i--) netdev_queue_numa_node_write( netdev_get_tx_queue(dev, i), NUMA_NO_NODE); } } static void netif_reset_xps_queues(struct net_device *dev, u16 offset, u16 count) { if (!static_key_false(&xps_needed)) return; cpus_read_lock(); mutex_lock(&xps_map_mutex); if (static_key_false(&xps_rxqs_needed)) clean_xps_maps(dev, XPS_RXQS, offset, count); clean_xps_maps(dev, XPS_CPUS, offset, count); mutex_unlock(&xps_map_mutex); cpus_read_unlock(); } static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index) { netif_reset_xps_queues(dev, index, dev->num_tx_queues - index); } static struct xps_map *expand_xps_map(struct xps_map *map, int attr_index, u16 index, bool is_rxqs_map) { struct xps_map *new_map; int alloc_len = XPS_MIN_MAP_ALLOC; int i, pos; for (pos = 0; map && pos < map->len; pos++) { if (map->queues[pos] != index) continue; return map; } /* Need to add tx-queue to this CPU's/rx-queue's existing map */ if (map) { if (pos < map->alloc_len) return map; alloc_len = map->alloc_len * 2; } /* Need to allocate new map to store tx-queue on this CPU's/rx-queue's * map */ if (is_rxqs_map) new_map = kzalloc(XPS_MAP_SIZE(alloc_len), GFP_KERNEL); else new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL, cpu_to_node(attr_index)); if (!new_map) return NULL; for (i = 0; i < pos; i++) new_map->queues[i] = map->queues[i]; new_map->alloc_len = alloc_len; new_map->len = pos; return new_map; } /* Copy xps maps at a given index */ static void xps_copy_dev_maps(struct xps_dev_maps *dev_maps, struct xps_dev_maps *new_dev_maps, int index, int tc, bool skip_tc) { int i, tci = index * dev_maps->num_tc; struct xps_map *map; /* copy maps belonging to foreign traffic classes */ for (i = 0; i < dev_maps->num_tc; i++, tci++) { if (i == tc && skip_tc) continue; /* fill in the new device map from the old device map */ map = xmap_dereference(dev_maps->attr_map[tci]); RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } } /* Must be called under cpus_read_lock */ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, u16 index, enum xps_map_type type) { struct xps_dev_maps *dev_maps, *new_dev_maps = NULL, *old_dev_maps = NULL; const unsigned long *online_mask = NULL; bool active = false, copy = false; int i, j, tci, numa_node_id = -2; int maps_sz, num_tc = 1, tc = 0; struct xps_map *map, *new_map; unsigned int nr_ids; WARN_ON_ONCE(index >= dev->num_tx_queues); if (dev->num_tc) { /* Do not allow XPS on subordinate device directly */ num_tc = dev->num_tc; if (num_tc < 0) return -EINVAL; /* If queue belongs to subordinate dev use its map */ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; tc = netdev_txq_to_tc(dev, index); if (tc < 0) return -EINVAL; } mutex_lock(&xps_map_mutex); dev_maps = xmap_dereference(dev->xps_maps[type]); if (type == XPS_RXQS) { maps_sz = XPS_RXQ_DEV_MAPS_SIZE(num_tc, dev->num_rx_queues); nr_ids = dev->num_rx_queues; } else { maps_sz = XPS_CPU_DEV_MAPS_SIZE(num_tc); if (num_possible_cpus() > 1) online_mask = cpumask_bits(cpu_online_mask); nr_ids = nr_cpu_ids; } if (maps_sz < L1_CACHE_BYTES) maps_sz = L1_CACHE_BYTES; /* The old dev_maps could be larger or smaller than the one we're * setting up now, as dev->num_tc or nr_ids could have been updated in * between. We could try to be smart, but let's be safe instead and only * copy foreign traffic classes if the two map sizes match. */ if (dev_maps && dev_maps->num_tc == num_tc && dev_maps->nr_ids == nr_ids) copy = true; /* allocate memory for queue storage */ for (j = -1; j = netif_attrmask_next_and(j, online_mask, mask, nr_ids), j < nr_ids;) { if (!new_dev_maps) { new_dev_maps = kzalloc(maps_sz, GFP_KERNEL); if (!new_dev_maps) { mutex_unlock(&xps_map_mutex); return -ENOMEM; } new_dev_maps->nr_ids = nr_ids; new_dev_maps->num_tc = num_tc; } tci = j * num_tc + tc; map = copy ? xmap_dereference(dev_maps->attr_map[tci]) : NULL; map = expand_xps_map(map, j, index, type == XPS_RXQS); if (!map) goto error; RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } if (!new_dev_maps) goto out_no_new_maps; if (!dev_maps) { /* Increment static keys at most once per type */ static_key_slow_inc_cpuslocked(&xps_needed); if (type == XPS_RXQS) static_key_slow_inc_cpuslocked(&xps_rxqs_needed); } for (j = 0; j < nr_ids; j++) { bool skip_tc = false; tci = j * num_tc + tc; if (netif_attr_test_mask(j, mask, nr_ids) && netif_attr_test_online(j, online_mask, nr_ids)) { /* add tx-queue to CPU/rx-queue maps */ int pos = 0; skip_tc = true; map = xmap_dereference(new_dev_maps->attr_map[tci]); while ((pos < map->len) && (map->queues[pos] != index)) pos++; if (pos == map->len) map->queues[map->len++] = index; #ifdef CONFIG_NUMA if (type == XPS_CPUS) { if (numa_node_id == -2) numa_node_id = cpu_to_node(j); else if (numa_node_id != cpu_to_node(j)) numa_node_id = -1; } #endif } if (copy) xps_copy_dev_maps(dev_maps, new_dev_maps, j, tc, skip_tc); } rcu_assign_pointer(dev->xps_maps[type], new_dev_maps); /* Cleanup old maps */ if (!dev_maps) goto out_no_old_maps; for (j = 0; j < dev_maps->nr_ids; j++) { for (i = num_tc, tci = j * dev_maps->num_tc; i--; tci++) { map = xmap_dereference(dev_maps->attr_map[tci]); if (!map) continue; if (copy) { new_map = xmap_dereference(new_dev_maps->attr_map[tci]); if (map == new_map) continue; } RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL); kfree_rcu(map, rcu); } } old_dev_maps = dev_maps; out_no_old_maps: dev_maps = new_dev_maps; active = true; out_no_new_maps: if (type == XPS_CPUS) /* update Tx queue numa node */ netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index), (numa_node_id >= 0) ? numa_node_id : NUMA_NO_NODE); if (!dev_maps) goto out_no_maps; /* removes tx-queue from unused CPUs/rx-queues */ for (j = 0; j < dev_maps->nr_ids; j++) { tci = j * dev_maps->num_tc; for (i = 0; i < dev_maps->num_tc; i++, tci++) { if (i == tc && netif_attr_test_mask(j, mask, dev_maps->nr_ids) && netif_attr_test_online(j, online_mask, dev_maps->nr_ids)) continue; active |= remove_xps_queue(dev_maps, copy ? old_dev_maps : NULL, tci, index); } } if (old_dev_maps) kfree_rcu(old_dev_maps, rcu); /* free map if not active */ if (!active) reset_xps_maps(dev, dev_maps, type); out_no_maps: mutex_unlock(&xps_map_mutex); return 0; error: /* remove any maps that we added */ for (j = 0; j < nr_ids; j++) { for (i = num_tc, tci = j * num_tc; i--; tci++) { new_map = xmap_dereference(new_dev_maps->attr_map[tci]); map = copy ? xmap_dereference(dev_maps->attr_map[tci]) : NULL; if (new_map && new_map != map) kfree(new_map); } } mutex_unlock(&xps_map_mutex); kfree(new_dev_maps); return -ENOMEM; } EXPORT_SYMBOL_GPL(__netif_set_xps_queue); int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, u16 index) { int ret; cpus_read_lock(); ret = __netif_set_xps_queue(dev, cpumask_bits(mask), index, XPS_CPUS); cpus_read_unlock(); return ret; } EXPORT_SYMBOL(netif_set_xps_queue); #endif static void netdev_unbind_all_sb_channels(struct net_device *dev) { struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues]; /* Unbind any subordinate channels */ while (txq-- != &dev->_tx[0]) { if (txq->sb_dev) netdev_unbind_sb_channel(dev, txq->sb_dev); } } void netdev_reset_tc(struct net_device *dev) { #ifdef CONFIG_XPS netif_reset_xps_queues_gt(dev, 0); #endif netdev_unbind_all_sb_channels(dev); /* Reset TC configuration of device */ dev->num_tc = 0; memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq)); memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map)); } EXPORT_SYMBOL(netdev_reset_tc); int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset) { if (tc >= dev->num_tc) return -EINVAL; #ifdef CONFIG_XPS netif_reset_xps_queues(dev, offset, count); #endif dev->tc_to_txq[tc].count = count; dev->tc_to_txq[tc].offset = offset; return 0; } EXPORT_SYMBOL(netdev_set_tc_queue); int netdev_set_num_tc(struct net_device *dev, u8 num_tc) { if (num_tc > TC_MAX_QUEUE) return -EINVAL; #ifdef CONFIG_XPS netif_reset_xps_queues_gt(dev, 0); #endif netdev_unbind_all_sb_channels(dev); dev->num_tc = num_tc; return 0; } EXPORT_SYMBOL(netdev_set_num_tc); void netdev_unbind_sb_channel(struct net_device *dev, struct net_device *sb_dev) { struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues]; #ifdef CONFIG_XPS netif_reset_xps_queues_gt(sb_dev, 0); #endif memset(sb_dev->tc_to_txq, 0, sizeof(sb_dev->tc_to_txq)); memset(sb_dev->prio_tc_map, 0, sizeof(sb_dev->prio_tc_map)); while (txq-- != &dev->_tx[0]) { if (txq->sb_dev == sb_dev) txq->sb_dev = NULL; } } EXPORT_SYMBOL(netdev_unbind_sb_channel); int netdev_bind_sb_channel_queue(struct net_device *dev, struct net_device *sb_dev, u8 tc, u16 count, u16 offset) { /* Make certain the sb_dev and dev are already configured */ if (sb_dev->num_tc >= 0 || tc >= dev->num_tc) return -EINVAL; /* We cannot hand out queues we don't have */ if ((offset + count) > dev->real_num_tx_queues) return -EINVAL; /* Record the mapping */ sb_dev->tc_to_txq[tc].count = count; sb_dev->tc_to_txq[tc].offset = offset; /* Provide a way for Tx queue to find the tc_to_txq map or * XPS map for itself. */ while (count--) netdev_get_tx_queue(dev, count + offset)->sb_dev = sb_dev; return 0; } EXPORT_SYMBOL(netdev_bind_sb_channel_queue); int netdev_set_sb_channel(struct net_device *dev, u16 channel) { /* Do not use a multiqueue device to represent a subordinate channel */ if (netif_is_multiqueue(dev)) return -ENODEV; /* We allow channels 1 - 32767 to be used for subordinate channels. * Channel 0 is meant to be "native" mode and used only to represent * the main root device. We allow writing 0 to reset the device back * to normal mode after being used as a subordinate channel. */ if (channel > S16_MAX) return -EINVAL; dev->num_tc = -channel; return 0; } EXPORT_SYMBOL(netdev_set_sb_channel); /* * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues * greater than real_num_tx_queues stale skbs on the qdisc must be flushed. */ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) { bool disabling; int rc; disabling = txq < dev->real_num_tx_queues; if (txq < 1 || txq > dev->num_tx_queues) return -EINVAL; if (dev->reg_state == NETREG_REGISTERED || dev->reg_state == NETREG_UNREGISTERING) { ASSERT_RTNL(); rc = netdev_queue_update_kobjects(dev, dev->real_num_tx_queues, txq); if (rc) return rc; if (dev->num_tc) netif_setup_tc(dev, txq); dev_qdisc_change_real_num_tx(dev, txq); dev->real_num_tx_queues = txq; if (disabling) { synchronize_net(); qdisc_reset_all_tx_gt(dev, txq); #ifdef CONFIG_XPS netif_reset_xps_queues_gt(dev, txq); #endif } } else { dev->real_num_tx_queues = txq; } return 0; } EXPORT_SYMBOL(netif_set_real_num_tx_queues); #ifdef CONFIG_SYSFS /** * netif_set_real_num_rx_queues - set actual number of RX queues used * @dev: Network device * @rxq: Actual number of RX queues * * This must be called either with the rtnl_lock held or before * registration of the net device. Returns 0 on success, or a * negative error code. If called before registration, it always * succeeds. */ int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq) { int rc; if (rxq < 1 || rxq > dev->num_rx_queues) return -EINVAL; if (dev->reg_state == NETREG_REGISTERED) { ASSERT_RTNL(); rc = net_rx_queue_update_kobjects(dev, dev->real_num_rx_queues, rxq); if (rc) return rc; } dev->real_num_rx_queues = rxq; return 0; } EXPORT_SYMBOL(netif_set_real_num_rx_queues); #endif /** * netif_set_real_num_queues - set actual number of RX and TX queues used * @dev: Network device * @txq: Actual number of TX queues * @rxq: Actual number of RX queues * * Set the real number of both TX and RX queues. * Does nothing if the number of queues is already correct. */ int netif_set_real_num_queues(struct net_device *dev, unsigned int txq, unsigned int rxq) { unsigned int old_rxq = dev->real_num_rx_queues; int err; if (txq < 1 || txq > dev->num_tx_queues || rxq < 1 || rxq > dev->num_rx_queues) return -EINVAL; /* Start from increases, so the error path only does decreases - * decreases can't fail. */ if (rxq > dev->real_num_rx_queues) { err = netif_set_real_num_rx_queues(dev, rxq); if (err) return err; } if (txq > dev->real_num_tx_queues) { err = netif_set_real_num_tx_queues(dev, txq); if (err) goto undo_rx; } if (rxq < dev->real_num_rx_queues) WARN_ON(netif_set_real_num_rx_queues(dev, rxq)); if (txq < dev->real_num_tx_queues) WARN_ON(netif_set_real_num_tx_queues(dev, txq)); return 0; undo_rx: WARN_ON(netif_set_real_num_rx_queues(dev, old_rxq)); return err; } EXPORT_SYMBOL(netif_set_real_num_queues); /** * netif_set_tso_max_size() - set the max size of TSO frames supported * @dev: netdev to update * @size: max skb->len of a TSO frame * * Set the limit on the size of TSO super-frames the device can handle. * Unless explicitly set the stack will assume the value of * %GSO_LEGACY_MAX_SIZE. */ void netif_set_tso_max_size(struct net_device *dev, unsigned int size) { dev->tso_max_size = min(GSO_MAX_SIZE, size); if (size < READ_ONCE(dev->gso_max_size)) netif_set_gso_max_size(dev, size); } EXPORT_SYMBOL(netif_set_tso_max_size); /** * netif_set_tso_max_segs() - set the max number of segs supported for TSO * @dev: netdev to update * @segs: max number of TCP segments * * Set the limit on the number of TCP segments the device can generate from * a single TSO super-frame. * Unless explicitly set the stack will assume the value of %GSO_MAX_SEGS. */ void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs) { dev->tso_max_segs = segs; if (segs < READ_ONCE(dev->gso_max_segs)) netif_set_gso_max_segs(dev, segs); } EXPORT_SYMBOL(netif_set_tso_max_segs); /** * netif_inherit_tso_max() - copy all TSO limits from a lower device to an upper * @to: netdev to update * @from: netdev from which to copy the limits */ void netif_inherit_tso_max(struct net_device *to, const struct net_device *from) { netif_set_tso_max_size(to, from->tso_max_size); netif_set_tso_max_segs(to, from->tso_max_segs); } EXPORT_SYMBOL(netif_inherit_tso_max); /** * netif_get_num_default_rss_queues - default number of RSS queues * * Default value is the number of physical cores if there are only 1 or 2, or * divided by 2 if there are more. */ int netif_get_num_default_rss_queues(void) { cpumask_var_t cpus; int cpu, count = 0; if (unlikely(is_kdump_kernel() || !zalloc_cpumask_var(&cpus, GFP_KERNEL))) return 1; cpumask_copy(cpus, cpu_online_mask); for_each_cpu(cpu, cpus) { ++count; cpumask_andnot(cpus, cpus, topology_sibling_cpumask(cpu)); } free_cpumask_var(cpus); return count > 2 ? DIV_ROUND_UP(count, 2) : count; } EXPORT_SYMBOL(netif_get_num_default_rss_queues); static void __netif_reschedule(struct Qdisc *q) { struct softnet_data *sd; unsigned long flags; local_irq_save(flags); sd = this_cpu_ptr(&softnet_data); q->next_sched = NULL; *sd->output_queue_tailp = q; sd->output_queue_tailp = &q->next_sched; raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } void __netif_schedule(struct Qdisc *q) { if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state)) __netif_reschedule(q); } EXPORT_SYMBOL(__netif_schedule); struct dev_kfree_skb_cb { enum skb_free_reason reason; }; static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb) { return (struct dev_kfree_skb_cb *)skb->cb; } void netif_schedule_queue(struct netdev_queue *txq) { rcu_read_lock(); if (!netif_xmit_stopped(txq)) { struct Qdisc *q = rcu_dereference(txq->qdisc); __netif_schedule(q); } rcu_read_unlock(); } EXPORT_SYMBOL(netif_schedule_queue); void netif_tx_wake_queue(struct netdev_queue *dev_queue) { if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state)) { struct Qdisc *q; rcu_read_lock(); q = rcu_dereference(dev_queue->qdisc); __netif_schedule(q); rcu_read_unlock(); } } EXPORT_SYMBOL(netif_tx_wake_queue); void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason) { unsigned long flags; if (unlikely(!skb)) return; if (likely(refcount_read(&skb->users) == 1)) { smp_rmb(); refcount_set(&skb->users, 0); } else if (likely(!refcount_dec_and_test(&skb->users))) { return; } get_kfree_skb_cb(skb)->reason = reason; local_irq_save(flags); skb->next = __this_cpu_read(softnet_data.completion_queue); __this_cpu_write(softnet_data.completion_queue, skb); raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } EXPORT_SYMBOL(__dev_kfree_skb_irq); void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason) { if (in_hardirq() || irqs_disabled()) __dev_kfree_skb_irq(skb, reason); else if (unlikely(reason == SKB_REASON_DROPPED)) kfree_skb(skb); else consume_skb(skb); } EXPORT_SYMBOL(__dev_kfree_skb_any); /** * netif_device_detach - mark device as removed * @dev: network device * * Mark device as removed from system and therefore no longer available. */ void netif_device_detach(struct net_device *dev) { if (test_and_clear_bit(__LINK_STATE_PRESENT, &dev->state) && netif_running(dev)) { netif_tx_stop_all_queues(dev); } } EXPORT_SYMBOL(netif_device_detach); /** * netif_device_attach - mark device as attached * @dev: network device * * Mark device as attached from system and restart if needed. */ void netif_device_attach(struct net_device *dev) { if (!test_and_set_bit(__LINK_STATE_PRESENT, &dev->state) && netif_running(dev)) { netif_tx_wake_all_queues(dev); __netdev_watchdog_up(dev); } } EXPORT_SYMBOL(netif_device_attach); /* * Returns a Tx hash based on the given packet descriptor a Tx queues' number * to be used as a distribution range. */ static u16 skb_tx_hash(const struct net_device *dev, const struct net_device *sb_dev, struct sk_buff *skb) { u32 hash; u16 qoffset = 0; u16 qcount = dev->real_num_tx_queues; if (dev->num_tc) { u8 tc = netdev_get_prio_tc_map(dev, skb->priority); qoffset = sb_dev->tc_to_txq[tc].offset; qcount = sb_dev->tc_to_txq[tc].count; if (unlikely(!qcount)) { net_warn_ratelimited("%s: invalid qcount, qoffset %u for tc %u\n", sb_dev->name, qoffset, tc); qoffset = 0; qcount = dev->real_num_tx_queues; } } if (skb_rx_queue_recorded(skb)) { DEBUG_NET_WARN_ON_ONCE(qcount == 0); hash = skb_get_rx_queue(skb); if (hash >= qoffset) hash -= qoffset; while (unlikely(hash >= qcount)) hash -= qcount; return hash + qoffset; } return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset; } static void skb_warn_bad_offload(const struct sk_buff *skb) { static const netdev_features_t null_features; struct net_device *dev = skb->dev; const char *name = ""; if (!net_ratelimit()) return; if (dev) { if (dev->dev.parent) name = dev_driver_string(dev->dev.parent); else name = netdev_name(dev); } skb_dump(KERN_WARNING, skb, false); WARN(1, "%s: caps=(%pNF, %pNF)\n", name, dev ? &dev->features : &null_features, skb->sk ? &skb->sk->sk_route_caps : &null_features); } /* * Invalidate hardware checksum when packet is to be mangled, and * complete checksum manually on outgoing path. */ int skb_checksum_help(struct sk_buff *skb) { __wsum csum; int ret = 0, offset; if (skb->ip_summed == CHECKSUM_COMPLETE) goto out_set_summed; if (unlikely(skb_is_gso(skb))) { skb_warn_bad_offload(skb); return -EINVAL; } /* Before computing a checksum, we should make sure no frag could * be modified by an external entity : checksum could be wrong. */ if (skb_has_shared_frag(skb)) { ret = __skb_linearize(skb); if (ret) goto out; } offset = skb_checksum_start_offset(skb); ret = -EINVAL; if (unlikely(offset >= skb_headlen(skb))) { DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); WARN_ONCE(true, "offset (%d) >= skb_headlen() (%u)\n", offset, skb_headlen(skb)); goto out; } csum = skb_checksum(skb, offset, skb->len - offset, 0); offset += skb->csum_offset; if (unlikely(offset + sizeof(__sum16) > skb_headlen(skb))) { DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); WARN_ONCE(true, "offset+2 (%zu) > skb_headlen() (%u)\n", offset + sizeof(__sum16), skb_headlen(skb)); goto out; } ret = skb_ensure_writable(skb, offset + sizeof(__sum16)); if (ret) goto out; *(__sum16 *)(skb->data + offset) = csum_fold(csum) ?: CSUM_MANGLED_0; out_set_summed: skb->ip_summed = CHECKSUM_NONE; out: return ret; } EXPORT_SYMBOL(skb_checksum_help); int skb_crc32c_csum_help(struct sk_buff *skb) { __le32 crc32c_csum; int ret = 0, offset, start; if (skb->ip_summed != CHECKSUM_PARTIAL) goto out; if (unlikely(skb_is_gso(skb))) goto out; /* Before computing a checksum, we should make sure no frag could * be modified by an external entity : checksum could be wrong. */ if (unlikely(skb_has_shared_frag(skb))) { ret = __skb_linearize(skb); if (ret) goto out; } start = skb_checksum_start_offset(skb); offset = start + offsetof(struct sctphdr, checksum); if (WARN_ON_ONCE(offset >= skb_headlen(skb))) { ret = -EINVAL; goto out; } ret = skb_ensure_writable(skb, offset + sizeof(__le32)); if (ret) goto out; crc32c_csum = cpu_to_le32(~__skb_checksum(skb, start, skb->len - start, ~(__u32)0, crc32c_csum_stub)); *(__le32 *)(skb->data + offset) = crc32c_csum; skb->ip_summed = CHECKSUM_NONE; skb->csum_not_inet = 0; out: return ret; } __be16 skb_network_protocol(struct sk_buff *skb, int *depth) { __be16 type = skb->protocol; /* Tunnel gso handlers can set protocol to ethernet. */ if (type == htons(ETH_P_TEB)) { struct ethhdr *eth; if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr)))) return 0; eth = (struct ethhdr *)skb->data; type = eth->h_proto; } return vlan_get_protocol_and_depth(skb, type, depth); } /* openvswitch calls this on rx path, so we need a different check. */ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) { if (tx_path) return skb->ip_summed != CHECKSUM_PARTIAL && skb->ip_summed != CHECKSUM_UNNECESSARY; return skb->ip_summed == CHECKSUM_NONE; } /** * __skb_gso_segment - Perform segmentation on skb. * @skb: buffer to segment * @features: features for the output path (see dev->features) * @tx_path: whether it is called in TX path * * This function segments the given skb and returns a list of segments. * * It may return NULL if the skb requires no segmentation. This is * only possible when GSO is used for verifying header integrity. * * Segmentation preserves SKB_GSO_CB_OFFSET bytes of previous skb cb. */ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path) { struct sk_buff *segs; if (unlikely(skb_needs_check(skb, tx_path))) { int err; /* We're going to init ->check field in TCP or UDP header */ err = skb_cow_head(skb, 0); if (err < 0) return ERR_PTR(err); } /* Only report GSO partial support if it will enable us to * support segmentation on this frame without needing additional * work. */ if (features & NETIF_F_GSO_PARTIAL) { netdev_features_t partial_features = NETIF_F_GSO_ROBUST; struct net_device *dev = skb->dev; partial_features |= dev->features & dev->gso_partial_features; if (!skb_gso_ok(skb, features | partial_features)) features &= ~NETIF_F_GSO_PARTIAL; } BUILD_BUG_ON(SKB_GSO_CB_OFFSET + sizeof(*SKB_GSO_CB(skb)) > sizeof(skb->cb)); SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb); SKB_GSO_CB(skb)->encap_level = 0; skb_reset_mac_header(skb); skb_reset_mac_len(skb); segs = skb_mac_gso_segment(skb, features); if (segs != skb && unlikely(skb_needs_check(skb, tx_path) && !IS_ERR(segs))) skb_warn_bad_offload(skb); return segs; } EXPORT_SYMBOL(__skb_gso_segment); /* Take action when hardware reception checksum errors are detected. */ #ifdef CONFIG_BUG static void do_netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb) { netdev_err(dev, "hw csum failure\n"); skb_dump(KERN_ERR, skb, true); dump_stack(); } void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb) { DO_ONCE_LITE(do_netdev_rx_csum_fault, dev, skb); } EXPORT_SYMBOL(netdev_rx_csum_fault); #endif /* XXX: check that highmem exists at all on the given machine. */ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_HIGHMEM int i; if (!(dev->features & NETIF_F_HIGHDMA)) { for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; if (PageHighMem(skb_frag_page(frag))) return 1; } } #endif return 0; } /* If MPLS offload request, verify we are testing hardware MPLS features * instead of standard features for the netdev. */ #if IS_ENABLED(CONFIG_NET_MPLS_GSO) static netdev_features_t net_mpls_features(struct sk_buff *skb, netdev_features_t features, __be16 type) { if (eth_p_mpls(type)) features &= skb->dev->mpls_features; return features; } #else static netdev_features_t net_mpls_features(struct sk_buff *skb, netdev_features_t features, __be16 type) { return features; } #endif static netdev_features_t harmonize_features(struct sk_buff *skb, netdev_features_t features) { __be16 type; type = skb_network_protocol(skb, NULL); features = net_mpls_features(skb, features, type); if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, type)) { features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } if (illegal_highdma(skb->dev, skb)) features &= ~NETIF_F_SG; return features; } netdev_features_t passthru_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { return features; } EXPORT_SYMBOL(passthru_features_check); static netdev_features_t dflt_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { return vlan_features_check(skb, features); } static netdev_features_t gso_features_check(const struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { u16 gso_segs = skb_shinfo(skb)->gso_segs; if (gso_segs > READ_ONCE(dev->gso_max_segs)) return features & ~NETIF_F_GSO_MASK; if (unlikely(skb->len >= READ_ONCE(dev->gso_max_size))) return features & ~NETIF_F_GSO_MASK; if (!skb_shinfo(skb)->gso_type) { skb_warn_bad_offload(skb); return features & ~NETIF_F_GSO_MASK; } /* Support for GSO partial features requires software * intervention before we can actually process the packets * so we need to strip support for any partial features now * and we can pull them back in after we have partially * segmented the frame. */ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL)) features &= ~dev->gso_partial_features; /* Make sure to clear the IPv4 ID mangling feature if the * IPv4 header has the potential to be fragmented. */ if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) { struct iphdr *iph = skb->encapsulation ? inner_ip_hdr(skb) : ip_hdr(skb); if (!(iph->frag_off & htons(IP_DF))) features &= ~NETIF_F_TSO_MANGLEID; } return features; } netdev_features_t netif_skb_features(struct sk_buff *skb) { struct net_device *dev = skb->dev; netdev_features_t features = dev->features; if (skb_is_gso(skb)) features = gso_features_check(skb, dev, features); /* If encapsulation offload request, verify we are testing * hardware encapsulation features instead of standard * features for the netdev */ if (skb->encapsulation) features &= dev->hw_enc_features; if (skb_vlan_tagged(skb)) features = netdev_intersect_features(features, dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); if (dev->netdev_ops->ndo_features_check) features &= dev->netdev_ops->ndo_features_check(skb, dev, features); else features &= dflt_features_check(skb, dev, features); return harmonize_features(skb, features); } EXPORT_SYMBOL(netif_skb_features); static int xmit_one(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, bool more) { unsigned int len; int rc; if (dev_nit_active(dev)) dev_queue_xmit_nit(skb, dev); len = skb->len; trace_net_dev_start_xmit(skb, dev); trace_android_vh_dc_send_copy(skb, dev); rc = netdev_start_xmit(skb, dev, txq, more); trace_net_dev_xmit(skb, rc, dev, len); return rc; } struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *dev, struct netdev_queue *txq, int *ret) { struct sk_buff *skb = first; int rc = NETDEV_TX_OK; while (skb) { struct sk_buff *next = skb->next; skb_mark_not_on_list(skb); rc = xmit_one(skb, dev, txq, next != NULL); if (unlikely(!dev_xmit_complete(rc))) { skb->next = next; goto out; } skb = next; if (netif_tx_queue_stopped(txq) && skb) { rc = NETDEV_TX_BUSY; break; } } out: *ret = rc; return skb; } static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb, netdev_features_t features) { if (skb_vlan_tag_present(skb) && !vlan_hw_offload_capable(features, skb->vlan_proto)) skb = __vlan_hwaccel_push_inside(skb); return skb; } int skb_csum_hwoffload_help(struct sk_buff *skb, const netdev_features_t features) { if (unlikely(skb_csum_is_sctp(skb))) return !!(features & NETIF_F_SCTP_CRC) ? 0 : skb_crc32c_csum_help(skb); if (features & NETIF_F_HW_CSUM) return 0; if (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) { if (vlan_get_protocol(skb) == htons(ETH_P_IPV6) && skb_network_header_len(skb) != sizeof(struct ipv6hdr) && !ipv6_has_hopopt_jumbo(skb)) goto sw_checksum; switch (skb->csum_offset) { case offsetof(struct tcphdr, check): case offsetof(struct udphdr, check): return 0; } } sw_checksum: return skb_checksum_help(skb); } EXPORT_SYMBOL(skb_csum_hwoffload_help); static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev, bool *again) { netdev_features_t features; features = netif_skb_features(skb); skb = validate_xmit_vlan(skb, features); if (unlikely(!skb)) goto out_null; skb = sk_validate_xmit_skb(skb, dev); if (unlikely(!skb)) goto out_null; if (netif_needs_gso(skb, features)) { struct sk_buff *segs; segs = skb_gso_segment(skb, features); if (IS_ERR(segs)) { goto out_kfree_skb; } else if (segs) { consume_skb(skb); skb = segs; } } else { if (skb_needs_linearize(skb, features) && __skb_linearize(skb)) goto out_kfree_skb; /* If packet is not checksummed and device does not * support checksumming for this protocol, complete * checksumming here. */ if (skb->ip_summed == CHECKSUM_PARTIAL) { if (skb->encapsulation) skb_set_inner_transport_header(skb, skb_checksum_start_offset(skb)); else skb_set_transport_header(skb, skb_checksum_start_offset(skb)); if (skb_csum_hwoffload_help(skb, features)) goto out_kfree_skb; } } skb = validate_xmit_xfrm(skb, features, again); return skb; out_kfree_skb: kfree_skb(skb); out_null: dev_core_stats_tx_dropped_inc(dev); return NULL; } struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again) { struct sk_buff *next, *head = NULL, *tail; for (; skb != NULL; skb = next) { next = skb->next; skb_mark_not_on_list(skb); /* in case skb wont be segmented, point to itself */ skb->prev = skb; skb = validate_xmit_skb(skb, dev, again); if (!skb) continue; if (!head) head = skb; else tail->next = skb; /* If skb was segmented, skb->prev points to * the last segment. If not, it still contains skb. */ tail = skb->prev; } return head; } EXPORT_SYMBOL_GPL(validate_xmit_skb_list); static void qdisc_pkt_len_init(struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb); qdisc_skb_cb(skb)->pkt_len = skb->len; /* To get more precise estimation of bytes sent on wire, * we add to pkt_len the headers size of all segments */ if (shinfo->gso_size && skb_transport_header_was_set(skb)) { unsigned int hdr_len; u16 gso_segs = shinfo->gso_segs; /* mac layer + network layer */ hdr_len = skb_transport_header(skb) - skb_mac_header(skb); /* + transport layer */ if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) { const struct tcphdr *th; struct tcphdr _tcphdr; th = skb_header_pointer(skb, skb_transport_offset(skb), sizeof(_tcphdr), &_tcphdr); if (likely(th)) hdr_len += __tcp_hdrlen(th); } else if (shinfo->gso_type & SKB_GSO_UDP_L4) { struct udphdr _udphdr; if (skb_header_pointer(skb, skb_transport_offset(skb), sizeof(_udphdr), &_udphdr)) hdr_len += sizeof(struct udphdr); } if (unlikely(shinfo->gso_type & SKB_GSO_DODGY)) { int payload = skb->len - hdr_len; /* Malicious packet. */ if (payload <= 0) return; gso_segs = DIV_ROUND_UP(payload, shinfo->gso_size); } qdisc_skb_cb(skb)->pkt_len += (gso_segs - 1) * hdr_len; } } static int dev_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *q, struct sk_buff **to_free, struct netdev_queue *txq) { int rc; rc = q->enqueue(skb, q, to_free) & NET_XMIT_MASK; if (rc == NET_XMIT_SUCCESS) trace_qdisc_enqueue(q, txq, skb); return rc; } static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, struct net_device *dev, struct netdev_queue *txq) { spinlock_t *root_lock = qdisc_lock(q); struct sk_buff *to_free = NULL; bool contended; int rc; qdisc_calculate_pkt_len(skb, q); if (q->flags & TCQ_F_NOLOCK) { if (q->flags & TCQ_F_CAN_BYPASS && nolock_qdisc_is_empty(q) && qdisc_run_begin(q)) { /* Retest nolock_qdisc_is_empty() within the protection * of q->seqlock to protect from racing with requeuing. */ if (unlikely(!nolock_qdisc_is_empty(q))) { rc = dev_qdisc_enqueue(skb, q, &to_free, txq); __qdisc_run(q); qdisc_run_end(q); goto no_lock_out; } qdisc_bstats_cpu_update(q, skb); if (sch_direct_xmit(skb, q, dev, txq, NULL, true) && !nolock_qdisc_is_empty(q)) __qdisc_run(q); qdisc_run_end(q); return NET_XMIT_SUCCESS; } rc = dev_qdisc_enqueue(skb, q, &to_free, txq); qdisc_run(q); no_lock_out: if (unlikely(to_free)) kfree_skb_list_reason(to_free, SKB_DROP_REASON_QDISC_DROP); return rc; } /* * Heuristic to force contended enqueues to serialize on a * separate lock before trying to get qdisc main lock. * This permits qdisc->running owner to get the lock more * often and dequeue packets faster. * On PREEMPT_RT it is possible to preempt the qdisc owner during xmit * and then other tasks will only enqueue packets. The packets will be * sent after the qdisc owner is scheduled again. To prevent this * scenario the task always serialize on the lock. */ contended = qdisc_is_running(q) || IS_ENABLED(CONFIG_PREEMPT_RT); if (unlikely(contended)) spin_lock(&q->busylock); spin_lock(root_lock); if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { __qdisc_drop(skb, &to_free); rc = NET_XMIT_DROP; } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) && qdisc_run_begin(q)) { /* * This is a work-conserving queue; there are no old skbs * waiting to be sent out; and the qdisc is not running - * xmit the skb directly. */ qdisc_bstats_update(q, skb); if (sch_direct_xmit(skb, q, dev, txq, root_lock, true)) { if (unlikely(contended)) { spin_unlock(&q->busylock); contended = false; } __qdisc_run(q); } qdisc_run_end(q); rc = NET_XMIT_SUCCESS; } else { rc = dev_qdisc_enqueue(skb, q, &to_free, txq); if (qdisc_run_begin(q)) { if (unlikely(contended)) { spin_unlock(&q->busylock); contended = false; } __qdisc_run(q); qdisc_run_end(q); } } spin_unlock(root_lock); if (unlikely(to_free)) kfree_skb_list_reason(to_free, SKB_DROP_REASON_QDISC_DROP); if (unlikely(contended)) spin_unlock(&q->busylock); return rc; } #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) static void skb_update_prio(struct sk_buff *skb) { const struct netprio_map *map; const struct sock *sk; unsigned int prioidx; if (skb->priority) return; map = rcu_dereference_bh(skb->dev->priomap); if (!map) return; sk = skb_to_full_sk(skb); if (!sk) return; prioidx = sock_cgroup_prioidx(&sk->sk_cgrp_data); if (prioidx < map->priomap_len) skb->priority = map->priomap[prioidx]; } #else #define skb_update_prio(skb) #endif /** * dev_loopback_xmit - loop back @skb * @net: network namespace this loopback is happening in * @sk: sk needed to be a netfilter okfn * @skb: buffer to transmit */ int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) { skb_reset_mac_header(skb); __skb_pull(skb, skb_network_offset(skb)); skb->pkt_type = PACKET_LOOPBACK; if (skb->ip_summed == CHECKSUM_NONE) skb->ip_summed = CHECKSUM_UNNECESSARY; DEBUG_NET_WARN_ON_ONCE(!skb_dst(skb)); skb_dst_force(skb); netif_rx(skb); return 0; } EXPORT_SYMBOL(dev_loopback_xmit); #ifdef CONFIG_NET_EGRESS static struct sk_buff * sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) { #ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc *miniq = rcu_dereference_bh(dev->miniq_egress); struct tcf_result cl_res; if (!miniq) return skb; /* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */ tc_skb_cb(skb)->mru = 0; tc_skb_cb(skb)->post_ct = false; mini_qdisc_bstats_cpu_update(miniq, skb); switch (tcf_classify(skb, miniq->block, miniq->filter_list, &cl_res, false)) { case TC_ACT_OK: case TC_ACT_RECLASSIFY: skb->tc_index = TC_H_MIN(cl_res.classid); break; case TC_ACT_SHOT: mini_qdisc_qstats_cpu_drop(miniq); *ret = NET_XMIT_DROP; kfree_skb_reason(skb, SKB_DROP_REASON_TC_EGRESS); return NULL; case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: *ret = NET_XMIT_SUCCESS; consume_skb(skb); return NULL; case TC_ACT_REDIRECT: /* No need to push/pop skb's mac_header here on egress! */ skb_do_redirect(skb); *ret = NET_XMIT_SUCCESS; return NULL; default: break; } #endif /* CONFIG_NET_CLS_ACT */ return skb; } static struct netdev_queue * netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb) { int qm = skb_get_queue_mapping(skb); return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm)); } static bool netdev_xmit_txqueue_skipped(void) { return __this_cpu_read(softnet_data.xmit.skip_txqueue); } void netdev_xmit_skip_txqueue(bool skip) { __this_cpu_write(softnet_data.xmit.skip_txqueue, skip); } EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue); #endif /* CONFIG_NET_EGRESS */ #ifdef CONFIG_XPS static int __get_xps_queue_idx(struct net_device *dev, struct sk_buff *skb, struct xps_dev_maps *dev_maps, unsigned int tci) { int tc = netdev_get_prio_tc_map(dev, skb->priority); struct xps_map *map; int queue_index = -1; if (tc >= dev_maps->num_tc || tci >= dev_maps->nr_ids) return queue_index; tci *= dev_maps->num_tc; tci += tc; map = rcu_dereference(dev_maps->attr_map[tci]); if (map) { if (map->len == 1) queue_index = map->queues[0]; else queue_index = map->queues[reciprocal_scale( skb_get_hash(skb), map->len)]; if (unlikely(queue_index >= dev->real_num_tx_queues)) queue_index = -1; } return queue_index; } #endif static int get_xps_queue(struct net_device *dev, struct net_device *sb_dev, struct sk_buff *skb) { #ifdef CONFIG_XPS struct xps_dev_maps *dev_maps; struct sock *sk = skb->sk; int queue_index = -1; if (!static_key_false(&xps_needed)) return -1; rcu_read_lock(); if (!static_key_false(&xps_rxqs_needed)) goto get_cpus_map; dev_maps = rcu_dereference(sb_dev->xps_maps[XPS_RXQS]); if (dev_maps) { int tci = sk_rx_queue_get(sk); if (tci >= 0) queue_index = __get_xps_queue_idx(dev, skb, dev_maps, tci); } get_cpus_map: if (queue_index < 0) { dev_maps = rcu_dereference(sb_dev->xps_maps[XPS_CPUS]); if (dev_maps) { unsigned int tci = skb->sender_cpu - 1; queue_index = __get_xps_queue_idx(dev, skb, dev_maps, tci); } } rcu_read_unlock(); return queue_index; #else return -1; #endif } u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { return 0; } EXPORT_SYMBOL(dev_pick_tx_zero); u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { return (u16)raw_smp_processor_id() % dev->real_num_tx_queues; } EXPORT_SYMBOL(dev_pick_tx_cpu_id); u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { struct sock *sk = skb->sk; int queue_index = sk_tx_queue_get(sk); sb_dev = sb_dev ? : dev; if (queue_index < 0 || skb->ooo_okay || queue_index >= dev->real_num_tx_queues) { int new_index = get_xps_queue(dev, sb_dev, skb); if (new_index < 0) new_index = skb_tx_hash(dev, sb_dev, skb); if (queue_index != new_index && sk && sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache)) sk_tx_queue_set(sk, new_index); queue_index = new_index; } return queue_index; } EXPORT_SYMBOL(netdev_pick_tx); struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { int queue_index = 0; #ifdef CONFIG_XPS u32 sender_cpu = skb->sender_cpu - 1; if (sender_cpu >= (u32)NR_CPUS) skb->sender_cpu = raw_smp_processor_id() + 1; #endif if (dev->real_num_tx_queues != 1) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_select_queue) queue_index = ops->ndo_select_queue(dev, skb, sb_dev); else queue_index = netdev_pick_tx(dev, skb, sb_dev); queue_index = netdev_cap_txqueue(dev, queue_index); } skb_set_queue_mapping(skb, queue_index); return netdev_get_tx_queue(dev, queue_index); } /** * __dev_queue_xmit() - transmit a buffer * @skb: buffer to transmit * @sb_dev: suboordinate device used for L2 forwarding offload * * Queue a buffer for transmission to a network device. The caller must * have set the device and priority and built the buffer before calling * this function. The function can be called from an interrupt. * * When calling this method, interrupts MUST be enabled. This is because * the BH enable code must have IRQs enabled so that it will not deadlock. * * Regardless of the return value, the skb is consumed, so it is currently * difficult to retry a send to this method. (You can bump the ref count * before sending to hold a reference for retry if you are careful.) * * Return: * * 0 - buffer successfully transmitted * * positive qdisc return code - NET_XMIT_DROP etc. * * negative errno - other errors */ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) { struct net_device *dev = skb->dev; struct netdev_queue *txq = NULL; struct Qdisc *q; int rc = -ENOMEM; bool again = false; skb_reset_mac_header(skb); skb_assert_len(skb); if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP)) __skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SCHED); /* Disable soft irqs for various locks below. Also * stops preemption for RCU. */ rcu_read_lock_bh(); skb_update_prio(skb); qdisc_pkt_len_init(skb); #ifdef CONFIG_NET_CLS_ACT skb->tc_at_ingress = 0; #endif #ifdef CONFIG_NET_EGRESS if (static_branch_unlikely(&egress_needed_key)) { if (nf_hook_egress_active()) { skb = nf_hook_egress(skb, &rc, dev); if (!skb) goto out; } netdev_xmit_skip_txqueue(false); nf_skip_egress(skb, true); skb = sch_handle_egress(skb, &rc, dev); if (!skb) goto out; nf_skip_egress(skb, false); if (netdev_xmit_txqueue_skipped()) txq = netdev_tx_queue_mapping(dev, skb); } #endif /* If device/qdisc don't need skb->dst, release it right now while * its hot in this cpu cache. */ if (dev->priv_flags & IFF_XMIT_DST_RELEASE) skb_dst_drop(skb); else skb_dst_force(skb); if (!txq) txq = netdev_core_pick_tx(dev, skb, sb_dev); q = rcu_dereference_bh(txq->qdisc); trace_net_dev_queue(skb); if (q->enqueue) { rc = __dev_xmit_skb(skb, q, dev, txq); goto out; } /* The device has no queue. Common case for software devices: * loopback, all the sorts of tunnels... * Really, it is unlikely that netif_tx_lock protection is necessary * here. (f.e. loopback and IP tunnels are clean ignoring statistics * counters.) * However, it is possible, that they rely on protection * made by us here. * Check this and shot the lock. It is not prone from deadlocks. *Either shot noqueue qdisc, it is even simpler 8) */ if (dev->flags & IFF_UP) { int cpu = smp_processor_id(); /* ok because BHs are off */ /* Other cpus might concurrently change txq->xmit_lock_owner * to -1 or to their cpu id, but not to our id. */ if (READ_ONCE(txq->xmit_lock_owner) != cpu) { if (dev_xmit_recursion()) goto recursion_alert; skb = validate_xmit_skb(skb, dev, &again); if (!skb) goto out; HARD_TX_LOCK(dev, txq, cpu); if (!netif_xmit_stopped(txq)) { dev_xmit_recursion_inc(); skb = dev_hard_start_xmit(skb, dev, txq, &rc); dev_xmit_recursion_dec(); if (dev_xmit_complete(rc)) { HARD_TX_UNLOCK(dev, txq); goto out; } } HARD_TX_UNLOCK(dev, txq); net_crit_ratelimited("Virtual device %s asks to queue packet!\n", dev->name); } else { /* Recursion is detected! It is possible, * unfortunately */ recursion_alert: net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n", dev->name); } } rc = -ENETDOWN; rcu_read_unlock_bh(); dev_core_stats_tx_dropped_inc(dev); kfree_skb_list(skb); return rc; out: rcu_read_unlock_bh(); return rc; } EXPORT_SYMBOL(__dev_queue_xmit); int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id) { struct net_device *dev = skb->dev; struct sk_buff *orig_skb = skb; struct netdev_queue *txq; int ret = NETDEV_TX_BUSY; bool again = false; if (unlikely(!netif_running(dev) || !netif_carrier_ok(dev))) goto drop; skb = validate_xmit_skb_list(skb, dev, &again); if (skb != orig_skb) goto drop; skb_set_queue_mapping(skb, queue_id); txq = skb_get_tx_queue(dev, skb); local_bh_disable(); dev_xmit_recursion_inc(); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_drv_stopped(txq)) ret = netdev_start_xmit(skb, dev, txq, false); HARD_TX_UNLOCK(dev, txq); dev_xmit_recursion_dec(); local_bh_enable(); return ret; drop: dev_core_stats_tx_dropped_inc(dev); kfree_skb_list(skb); return NET_XMIT_DROP; } EXPORT_SYMBOL(__dev_direct_xmit); /************************************************************************* * Receiver routines *************************************************************************/ int netdev_max_backlog __read_mostly = 1000; EXPORT_SYMBOL(netdev_max_backlog); int netdev_tstamp_prequeue __read_mostly = 1; unsigned int sysctl_skb_defer_max __read_mostly = 64; int netdev_budget __read_mostly = 300; /* Must be at least 2 jiffes to guarantee 1 jiffy timeout */ unsigned int __read_mostly netdev_budget_usecs = 2 * USEC_PER_SEC / HZ; int weight_p __read_mostly = 64; /* old backlog weight */ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ int dev_rx_weight __read_mostly = 64; int dev_tx_weight __read_mostly = 64; /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, struct napi_struct *napi) { struct task_struct *thread; lockdep_assert_irqs_disabled(); if (test_bit(NAPI_STATE_THREADED, &napi->state)) { /* Paired with smp_mb__before_atomic() in * napi_enable()/dev_set_threaded(). * Use READ_ONCE() to guarantee a complete * read on napi->thread. Only call * wake_up_process() when it's not NULL. */ thread = READ_ONCE(napi->thread); if (thread) { /* Avoid doing set_bit() if the thread is in * INTERRUPTIBLE state, cause napi_thread_wait() * makes sure to proceed with napi polling * if the thread is explicitly woken from here. */ if (READ_ONCE(thread->__state) != TASK_INTERRUPTIBLE) set_bit(NAPI_STATE_SCHED_THREADED, &napi->state); wake_up_process(thread); return; } } list_add_tail(&napi->poll_list, &sd->poll_list); __raise_softirq_irqoff(NET_RX_SOFTIRQ); } #ifdef CONFIG_RPS /* One global table that all flow-based protocols share. */ struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly; EXPORT_SYMBOL(rps_sock_flow_table); u32 rps_cpu_mask __read_mostly; EXPORT_SYMBOL(rps_cpu_mask); struct static_key_false rps_needed __read_mostly; EXPORT_SYMBOL(rps_needed); struct static_key_false rfs_needed __read_mostly; EXPORT_SYMBOL(rfs_needed); static struct rps_dev_flow * set_rps_cpu(struct net_device *dev, struct sk_buff *skb, struct rps_dev_flow *rflow, u16 next_cpu) { if (next_cpu < nr_cpu_ids) { #ifdef CONFIG_RFS_ACCEL struct netdev_rx_queue *rxqueue; struct rps_dev_flow_table *flow_table; struct rps_dev_flow *old_rflow; u32 flow_id; u16 rxq_index; int rc; /* Should we steer this flow to a different hardware queue? */ if (!skb_rx_queue_recorded(skb) || !dev->rx_cpu_rmap || !(dev->features & NETIF_F_NTUPLE)) goto out; rxq_index = cpu_rmap_lookup_index(dev->rx_cpu_rmap, next_cpu); if (rxq_index == skb_get_rx_queue(skb)) goto out; rxqueue = dev->_rx + rxq_index; flow_table = rcu_dereference(rxqueue->rps_flow_table); if (!flow_table) goto out; flow_id = skb_get_hash(skb) & flow_table->mask; rc = dev->netdev_ops->ndo_rx_flow_steer(dev, skb, rxq_index, flow_id); if (rc < 0) goto out; old_rflow = rflow; rflow = &flow_table->flows[flow_id]; rflow->filter = rc; if (old_rflow->filter == rflow->filter) old_rflow->filter = RPS_NO_FILTER; out: #endif rflow->last_qtail = per_cpu(softnet_data, next_cpu).input_queue_head; } rflow->cpu = next_cpu; return rflow; } /* * get_rps_cpu is called from netif_receive_skb and returns the target * CPU from the RPS map of the receiving queue for a given skb. * rcu_read_lock must be held on entry. */ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, struct rps_dev_flow **rflowp) { const struct rps_sock_flow_table *sock_flow_table; struct netdev_rx_queue *rxqueue = dev->_rx; struct rps_dev_flow_table *flow_table; struct rps_map *map; int cpu = -1; u32 tcpu; u32 hash; if (skb_rx_queue_recorded(skb)) { u16 index = skb_get_rx_queue(skb); if (unlikely(index >= dev->real_num_rx_queues)) { WARN_ONCE(dev->real_num_rx_queues > 1, "%s received packet on queue %u, but number " "of RX queues is %u\n", dev->name, index, dev->real_num_rx_queues); goto done; } rxqueue += index; } /* Avoid computing hash if RFS/RPS is not active for this rxqueue */ flow_table = rcu_dereference(rxqueue->rps_flow_table); map = rcu_dereference(rxqueue->rps_map); if (!flow_table && !map) goto done; skb_reset_network_header(skb); hash = skb_get_hash(skb); if (!hash) goto done; sock_flow_table = rcu_dereference(rps_sock_flow_table); if (flow_table && sock_flow_table) { struct rps_dev_flow *rflow; u32 next_cpu; u32 ident; /* First check into global flow table if there is a match. * This READ_ONCE() pairs with WRITE_ONCE() from rps_record_sock_flow(). */ ident = READ_ONCE(sock_flow_table->ents[hash & sock_flow_table->mask]); if ((ident ^ hash) & ~rps_cpu_mask) goto try_rps; next_cpu = ident & rps_cpu_mask; /* OK, now we know there is a match, * we can look at the local (per receive queue) flow table */ rflow = &flow_table->flows[hash & flow_table->mask]; tcpu = rflow->cpu; /* * If the desired CPU (where last recvmsg was done) is * different from current CPU (one in the rx-queue flow * table entry), switch if one of the following holds: * - Current CPU is unset (>= nr_cpu_ids). * - Current CPU is offline. * - The current CPU's queue tail has advanced beyond the * last packet that was enqueued using this table entry. * This guarantees that all previous packets for the flow * have been dequeued, thus preserving in order delivery. */ if (unlikely(tcpu != next_cpu) && (tcpu >= nr_cpu_ids || !cpu_online(tcpu) || ((int)(per_cpu(softnet_data, tcpu).input_queue_head - rflow->last_qtail)) >= 0)) { tcpu = next_cpu; rflow = set_rps_cpu(dev, skb, rflow, next_cpu); } if (tcpu < nr_cpu_ids && cpu_online(tcpu)) { *rflowp = rflow; cpu = tcpu; goto done; } } try_rps: if (map) { tcpu = map->cpus[reciprocal_scale(hash, map->len)]; if (cpu_online(tcpu)) { cpu = tcpu; goto done; } } done: return cpu; } #ifdef CONFIG_RFS_ACCEL /** * rps_may_expire_flow - check whether an RFS hardware filter may be removed * @dev: Device on which the filter was set * @rxq_index: RX queue index * @flow_id: Flow ID passed to ndo_rx_flow_steer() * @filter_id: Filter ID returned by ndo_rx_flow_steer() * * Drivers that implement ndo_rx_flow_steer() should periodically call * this function for each installed filter and remove the filters for * which it returns %true. */ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id, u16 filter_id) { struct netdev_rx_queue *rxqueue = dev->_rx + rxq_index; struct rps_dev_flow_table *flow_table; struct rps_dev_flow *rflow; bool expire = true; unsigned int cpu; rcu_read_lock(); flow_table = rcu_dereference(rxqueue->rps_flow_table); if (flow_table && flow_id <= flow_table->mask) { rflow = &flow_table->flows[flow_id]; cpu = READ_ONCE(rflow->cpu); if (rflow->filter == filter_id && cpu < nr_cpu_ids && ((int)(per_cpu(softnet_data, cpu).input_queue_head - rflow->last_qtail) < (int)(10 * flow_table->mask))) expire = false; } rcu_read_unlock(); return expire; } EXPORT_SYMBOL(rps_may_expire_flow); #endif /* CONFIG_RFS_ACCEL */ /* Called from hardirq (IPI) context */ static void rps_trigger_softirq(void *data) { struct softnet_data *sd = data; ____napi_schedule(sd, &sd->backlog); sd->received_rps++; } #endif /* CONFIG_RPS */ /* Called from hardirq (IPI) context */ static void trigger_rx_softirq(void *data) { struct softnet_data *sd = data; __raise_softirq_irqoff(NET_RX_SOFTIRQ); smp_store_release(&sd->defer_ipi_scheduled, 0); } /* * Check if this softnet_data structure is another cpu one * If yes, queue it to our IPI list and return 1 * If no, return 0 */ static int napi_schedule_rps(struct softnet_data *sd) { struct softnet_data *mysd = this_cpu_ptr(&softnet_data); #ifdef CONFIG_RPS if (sd != mysd) { sd->rps_ipi_next = mysd->rps_ipi_list; mysd->rps_ipi_list = sd; __raise_softirq_irqoff(NET_RX_SOFTIRQ); return 1; } #endif /* CONFIG_RPS */ __napi_schedule_irqoff(&mysd->backlog); return 0; } #ifdef CONFIG_NET_FLOW_LIMIT int netdev_flow_limit_table_len __read_mostly = (1 << 12); #endif static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen) { #ifdef CONFIG_NET_FLOW_LIMIT struct sd_flow_limit *fl; struct softnet_data *sd; unsigned int old_flow, new_flow; if (qlen < (READ_ONCE(netdev_max_backlog) >> 1)) return false; sd = this_cpu_ptr(&softnet_data); rcu_read_lock(); fl = rcu_dereference(sd->flow_limit); if (fl) { new_flow = skb_get_hash(skb) & (fl->num_buckets - 1); old_flow = fl->history[fl->history_head]; fl->history[fl->history_head] = new_flow; fl->history_head++; fl->history_head &= FLOW_LIMIT_HISTORY - 1; if (likely(fl->buckets[old_flow])) fl->buckets[old_flow]--; if (++fl->buckets[new_flow] > (FLOW_LIMIT_HISTORY >> 1)) { fl->count++; rcu_read_unlock(); return true; } } rcu_read_unlock(); #endif return false; } /* * enqueue_to_backlog is called to queue an skb to a per CPU backlog * queue (may be a remote CPU queue). */ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, unsigned int *qtail) { enum skb_drop_reason reason; struct softnet_data *sd; unsigned long flags; unsigned int qlen; reason = SKB_DROP_REASON_NOT_SPECIFIED; sd = &per_cpu(softnet_data, cpu); rps_lock_irqsave(sd, &flags); if (!netif_running(skb->dev)) goto drop; qlen = skb_queue_len(&sd->input_pkt_queue); if (qlen <= READ_ONCE(netdev_max_backlog) && !skb_flow_limit(skb, qlen)) { if (qlen) { enqueue: __skb_queue_tail(&sd->input_pkt_queue, skb); input_queue_tail_incr_save(sd, qtail); rps_unlock_irq_restore(sd, &flags); return NET_RX_SUCCESS; } /* Schedule NAPI for backlog device * We can use non atomic operation since we own the queue lock */ if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) napi_schedule_rps(sd); goto enqueue; } reason = SKB_DROP_REASON_CPU_BACKLOG; drop: sd->dropped++; rps_unlock_irq_restore(sd, &flags); dev_core_stats_rx_dropped_inc(skb->dev); kfree_skb_reason(skb, reason); return NET_RX_DROP; } static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb) { struct net_device *dev = skb->dev; struct netdev_rx_queue *rxqueue; rxqueue = dev->_rx; if (skb_rx_queue_recorded(skb)) { u16 index = skb_get_rx_queue(skb); if (unlikely(index >= dev->real_num_rx_queues)) { WARN_ONCE(dev->real_num_rx_queues > 1, "%s received packet on queue %u, but number " "of RX queues is %u\n", dev->name, index, dev->real_num_rx_queues); return rxqueue; /* Return first rxqueue */ } rxqueue += index; } return rxqueue; } u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { void *orig_data, *orig_data_end, *hard_start; struct netdev_rx_queue *rxqueue; bool orig_bcast, orig_host; u32 mac_len, frame_sz; __be16 orig_eth_type; struct ethhdr *eth; u32 metalen, act; int off; /* The XDP program wants to see the packet starting at the MAC * header. */ mac_len = skb->data - skb_mac_header(skb); hard_start = skb->data - skb_headroom(skb); /* SKB "head" area always have tailroom for skb_shared_info */ frame_sz = (void *)skb_end_pointer(skb) - hard_start; frame_sz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); rxqueue = netif_get_rxqueue(skb); xdp_init_buff(xdp, frame_sz, &rxqueue->xdp_rxq); xdp_prepare_buff(xdp, hard_start, skb_headroom(skb) - mac_len, skb_headlen(skb) + mac_len, true); orig_data_end = xdp->data_end; orig_data = xdp->data; eth = (struct ethhdr *)xdp->data; orig_host = ether_addr_equal_64bits(eth->h_dest, skb->dev->dev_addr); orig_bcast = is_multicast_ether_addr_64bits(eth->h_dest); orig_eth_type = eth->h_proto; act = bpf_prog_run_xdp(xdp_prog, xdp); /* check if bpf_xdp_adjust_head was used */ off = xdp->data - orig_data; if (off) { if (off > 0) __skb_pull(skb, off); else if (off < 0) __skb_push(skb, -off); skb->mac_header += off; skb_reset_network_header(skb); } /* check if bpf_xdp_adjust_tail was used */ off = xdp->data_end - orig_data_end; if (off != 0) { skb_set_tail_pointer(skb, xdp->data_end - xdp->data); skb->len += off; /* positive on grow, negative on shrink */ } /* check if XDP changed eth hdr such SKB needs update */ eth = (struct ethhdr *)xdp->data; if ((orig_eth_type != eth->h_proto) || (orig_host != ether_addr_equal_64bits(eth->h_dest, skb->dev->dev_addr)) || (orig_bcast != is_multicast_ether_addr_64bits(eth->h_dest))) { __skb_push(skb, ETH_HLEN); skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, skb->dev); } /* Redirect/Tx gives L2 packet, code that will reuse skb must __skb_pull * before calling us again on redirect path. We do not call do_redirect * as we leave that up to the caller. * * Caller is responsible for managing lifetime of skb (i.e. calling * kfree_skb in response to actions it cannot handle/XDP_DROP). */ switch (act) { case XDP_REDIRECT: case XDP_TX: __skb_push(skb, mac_len); break; case XDP_PASS: metalen = xdp->data - xdp->data_meta; if (metalen) skb_metadata_set(skb, metalen); break; } return act; } static u32 netif_receive_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { u32 act = XDP_DROP; /* Reinjected packets coming from act_mirred or similar should * not get XDP generic processing. */ if (skb_is_redirected(skb)) return XDP_PASS; /* XDP packets must be linear and must have sufficient headroom * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also * native XDP provides, thus we need to do it here as well. */ if (skb_cloned(skb) || skb_is_nonlinear(skb) || skb_headroom(skb) < XDP_PACKET_HEADROOM) { int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); int troom = skb->tail + skb->data_len - skb->end; /* In case we have to go down the path and also linearize, * then lets do the pskb_expand_head() work just once here. */ if (pskb_expand_head(skb, hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0, troom > 0 ? troom + 128 : 0, GFP_ATOMIC)) goto do_drop; if (skb_linearize(skb)) goto do_drop; } act = bpf_prog_run_generic_xdp(skb, xdp, xdp_prog); switch (act) { case XDP_REDIRECT: case XDP_TX: case XDP_PASS: break; default: bpf_warn_invalid_xdp_action(skb->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(skb->dev, xdp_prog, act); fallthrough; case XDP_DROP: do_drop: kfree_skb(skb); break; } return act; } /* When doing generic XDP we have to bypass the qdisc layer and the * network taps in order to match in-driver-XDP behavior. This also means * that XDP packets are able to starve other packets going through a qdisc, * and DDOS attacks will be more effective. In-driver-XDP use dedicated TX * queues, so they do not have this starvation issue. */ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) { struct net_device *dev = skb->dev; struct netdev_queue *txq; bool free_skb = true; int cpu, rc; txq = netdev_core_pick_tx(dev, skb, NULL); cpu = smp_processor_id(); HARD_TX_LOCK(dev, txq, cpu); if (!netif_xmit_frozen_or_drv_stopped(txq)) { rc = netdev_start_xmit(skb, dev, txq, 0); if (dev_xmit_complete(rc)) free_skb = false; } HARD_TX_UNLOCK(dev, txq); if (free_skb) { trace_xdp_exception(dev, xdp_prog, XDP_TX); dev_core_stats_tx_dropped_inc(dev); kfree_skb(skb); } } static DEFINE_STATIC_KEY_FALSE(generic_xdp_needed_key); int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb) { if (xdp_prog) { struct xdp_buff xdp; u32 act; int err; act = netif_receive_generic_xdp(skb, &xdp, xdp_prog); if (act != XDP_PASS) { switch (act) { case XDP_REDIRECT: err = xdp_do_generic_redirect(skb->dev, skb, &xdp, xdp_prog); if (err) goto out_redir; break; case XDP_TX: generic_xdp_tx(skb, xdp_prog); break; } return XDP_DROP; } } return XDP_PASS; out_redir: kfree_skb_reason(skb, SKB_DROP_REASON_XDP); return XDP_DROP; } EXPORT_SYMBOL_GPL(do_xdp_generic); static int netif_rx_internal(struct sk_buff *skb) { int ret; net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); trace_netif_rx(skb); #ifdef CONFIG_RPS if (static_branch_unlikely(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu; rcu_read_lock(); cpu = get_rps_cpu(skb->dev, skb, &rflow); if (cpu < 0) cpu = smp_processor_id(); ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); } else #endif { unsigned int qtail; ret = enqueue_to_backlog(skb, smp_processor_id(), &qtail); } return ret; } /** * __netif_rx - Slightly optimized version of netif_rx * @skb: buffer to post * * This behaves as netif_rx except that it does not disable bottom halves. * As a result this function may only be invoked from the interrupt context * (either hard or soft interrupt). */ int __netif_rx(struct sk_buff *skb) { int ret; lockdep_assert_once(hardirq_count() | softirq_count()); trace_netif_rx_entry(skb); ret = netif_rx_internal(skb); trace_netif_rx_exit(ret); return ret; } EXPORT_SYMBOL(__netif_rx); /** * netif_rx - post buffer to the network code * @skb: buffer to post * * This function receives a packet from a device driver and queues it for * the upper (protocol) levels to process via the backlog NAPI device. It * always succeeds. The buffer may be dropped during processing for * congestion control or by the protocol layers. * The network buffer is passed via the backlog NAPI device. Modern NIC * driver should use NAPI and GRO. * This function can used from interrupt and from process context. The * caller from process context must not disable interrupts before invoking * this function. * * return values: * NET_RX_SUCCESS (no congestion) * NET_RX_DROP (packet was dropped) * */ int netif_rx(struct sk_buff *skb) { bool need_bh_off = !(hardirq_count() | softirq_count()); int ret; if (need_bh_off) local_bh_disable(); trace_netif_rx_entry(skb); ret = netif_rx_internal(skb); trace_netif_rx_exit(ret); if (need_bh_off) local_bh_enable(); return ret; } EXPORT_SYMBOL(netif_rx); static __latent_entropy void net_tx_action(struct softirq_action *h) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); if (sd->completion_queue) { struct sk_buff *clist; local_irq_disable(); clist = sd->completion_queue; sd->completion_queue = NULL; local_irq_enable(); while (clist) { struct sk_buff *skb = clist; clist = clist->next; WARN_ON(refcount_read(&skb->users)); if (likely(get_kfree_skb_cb(skb)->reason == SKB_REASON_CONSUMED)) trace_consume_skb(skb); else trace_kfree_skb(skb, net_tx_action, SKB_DROP_REASON_NOT_SPECIFIED); if (skb->fclone != SKB_FCLONE_UNAVAILABLE) __kfree_skb(skb); else __kfree_skb_defer(skb); } } if (sd->output_queue) { struct Qdisc *head; local_irq_disable(); head = sd->output_queue; sd->output_queue = NULL; sd->output_queue_tailp = &sd->output_queue; local_irq_enable(); rcu_read_lock(); while (head) { struct Qdisc *q = head; spinlock_t *root_lock = NULL; head = head->next_sched; /* We need to make sure head->next_sched is read * before clearing __QDISC_STATE_SCHED */ smp_mb__before_atomic(); if (!(q->flags & TCQ_F_NOLOCK)) { root_lock = qdisc_lock(q); spin_lock(root_lock); } else if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { /* There is a synchronize_net() between * STATE_DEACTIVATED flag being set and * qdisc_reset()/some_qdisc_is_busy() in * dev_deactivate(), so we can safely bail out * early here to avoid data race between * qdisc_deactivate() and some_qdisc_is_busy() * for lockless qdisc. */ clear_bit(__QDISC_STATE_SCHED, &q->state); continue; } clear_bit(__QDISC_STATE_SCHED, &q->state); qdisc_run(q); if (root_lock) spin_unlock(root_lock); } rcu_read_unlock(); } xfrm_dev_backlog(sd); } #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_ATM_LANE) /* This hook is defined here for ATM LANE */ int (*br_fdb_test_addr_hook)(struct net_device *dev, unsigned char *addr) __read_mostly; EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); #endif static inline struct sk_buff * sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev, bool *another) { #ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc *miniq = rcu_dereference_bh(skb->dev->miniq_ingress); struct tcf_result cl_res; /* If there's at least one ingress present somewhere (so * we get here via enabled static key), remaining devices * that are not configured with an ingress qdisc will bail * out here. */ if (!miniq) return skb; if (*pt_prev) { *ret = deliver_skb(skb, *pt_prev, orig_dev); *pt_prev = NULL; } qdisc_skb_cb(skb)->pkt_len = skb->len; tc_skb_cb(skb)->mru = 0; tc_skb_cb(skb)->post_ct = false; skb->tc_at_ingress = 1; mini_qdisc_bstats_cpu_update(miniq, skb); switch (tcf_classify(skb, miniq->block, miniq->filter_list, &cl_res, false)) { case TC_ACT_OK: case TC_ACT_RECLASSIFY: skb->tc_index = TC_H_MIN(cl_res.classid); break; case TC_ACT_SHOT: mini_qdisc_qstats_cpu_drop(miniq); kfree_skb_reason(skb, SKB_DROP_REASON_TC_INGRESS); *ret = NET_RX_DROP; return NULL; case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: consume_skb(skb); *ret = NET_RX_SUCCESS; return NULL; case TC_ACT_REDIRECT: /* skb_mac_header check was done by cls/act_bpf, so * we can safely push the L2 header back before * redirecting to another netdev */ __skb_push(skb, skb->mac_len); if (skb_do_redirect(skb) == -EAGAIN) { __skb_pull(skb, skb->mac_len); *another = true; break; } *ret = NET_RX_SUCCESS; return NULL; case TC_ACT_CONSUMED: *ret = NET_RX_SUCCESS; return NULL; default: break; } #endif /* CONFIG_NET_CLS_ACT */ return skb; } /** * netdev_is_rx_handler_busy - check if receive handler is registered * @dev: device to check * * Check if a receive handler is already registered for a given device. * Return true if there one. * * The caller must hold the rtnl_mutex. */ bool netdev_is_rx_handler_busy(struct net_device *dev) { ASSERT_RTNL(); return dev && rtnl_dereference(dev->rx_handler); } EXPORT_SYMBOL_GPL(netdev_is_rx_handler_busy); /** * netdev_rx_handler_register - register receive handler * @dev: device to register a handler for * @rx_handler: receive handler to register * @rx_handler_data: data pointer that is used by rx handler * * Register a receive handler for a device. This handler will then be * called from __netif_receive_skb. A negative errno code is returned * on a failure. * * The caller must hold the rtnl_mutex. * * For a general description of rx_handler, see enum rx_handler_result. */ int netdev_rx_handler_register(struct net_device *dev, rx_handler_func_t *rx_handler, void *rx_handler_data) { if (netdev_is_rx_handler_busy(dev)) return -EBUSY; if (dev->priv_flags & IFF_NO_RX_HANDLER) return -EINVAL; /* Note: rx_handler_data must be set before rx_handler */ rcu_assign_pointer(dev->rx_handler_data, rx_handler_data); rcu_assign_pointer(dev->rx_handler, rx_handler); return 0; } EXPORT_SYMBOL_GPL(netdev_rx_handler_register); /** * netdev_rx_handler_unregister - unregister receive handler * @dev: device to unregister a handler from * * Unregister a receive handler from a device. * * The caller must hold the rtnl_mutex. */ void netdev_rx_handler_unregister(struct net_device *dev) { ASSERT_RTNL(); RCU_INIT_POINTER(dev->rx_handler, NULL); /* a reader seeing a non NULL rx_handler in a rcu_read_lock() * section has a guarantee to see a non NULL rx_handler_data * as well. */ synchronize_net(); RCU_INIT_POINTER(dev->rx_handler_data, NULL); } EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); /* * Limit the use of PFMEMALLOC reserves to those protocols that implement * the special handling of PFMEMALLOC skbs. */ static bool skb_pfmemalloc_protocol(struct sk_buff *skb) { switch (skb->protocol) { case htons(ETH_P_ARP): case htons(ETH_P_IP): case htons(ETH_P_IPV6): case htons(ETH_P_8021Q): case htons(ETH_P_8021AD): return true; default: return false; } } static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev) { if (nf_hook_ingress_active(skb)) { int ingress_retval; if (*pt_prev) { *ret = deliver_skb(skb, *pt_prev, orig_dev); *pt_prev = NULL; } rcu_read_lock(); ingress_retval = nf_hook_ingress(skb); rcu_read_unlock(); return ingress_retval; } return 0; } static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc, struct packet_type **ppt_prev) { struct packet_type *ptype, *pt_prev; rx_handler_func_t *rx_handler; struct sk_buff *skb = *pskb; struct net_device *orig_dev; bool deliver_exact = false; int ret = NET_RX_DROP; __be16 type; int flag = 0; net_timestamp_check(!READ_ONCE(netdev_tstamp_prequeue), skb); trace_netif_receive_skb(skb); orig_dev = skb->dev; skb_reset_network_header(skb); if (!skb_transport_header_was_set(skb)) skb_reset_transport_header(skb); skb_reset_mac_len(skb); pt_prev = NULL; another_round: skb->skb_iif = skb->dev->ifindex; __this_cpu_inc(softnet_data.processed); trace_android_vh_dc_receive(skb, &flag); if (flag != 0) return NET_RX_DROP; if (static_branch_unlikely(&generic_xdp_needed_key)) { int ret2; migrate_disable(); ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb); migrate_enable(); if (ret2 != XDP_PASS) { ret = NET_RX_DROP; goto out; } } if (eth_type_vlan(skb->protocol)) { skb = skb_vlan_untag(skb); if (unlikely(!skb)) goto out; } if (skb_skip_tc_classify(skb)) goto skip_classify; if (pfmemalloc) goto skip_taps; list_for_each_entry_rcu(ptype, &ptype_all, list) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } list_for_each_entry_rcu(ptype, &skb->dev->ptype_all, list) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } skip_taps: #ifdef CONFIG_NET_INGRESS if (static_branch_unlikely(&ingress_needed_key)) { bool another = false; nf_skip_egress(skb, true); skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev, &another); if (another) goto another_round; if (!skb) goto out; nf_skip_egress(skb, false); if (nf_ingress(skb, &pt_prev, &ret, orig_dev) < 0) goto out; } #endif skb_reset_redirect(skb); skip_classify: if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) goto drop; if (skb_vlan_tag_present(skb)) { if (pt_prev) { ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = NULL; } if (vlan_do_receive(&skb)) goto another_round; else if (unlikely(!skb)) goto out; } rx_handler = rcu_dereference(skb->dev->rx_handler); if (rx_handler) { if (pt_prev) { ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = NULL; } switch (rx_handler(&skb)) { case RX_HANDLER_CONSUMED: ret = NET_RX_SUCCESS; goto out; case RX_HANDLER_ANOTHER: goto another_round; case RX_HANDLER_EXACT: deliver_exact = true; break; case RX_HANDLER_PASS: break; default: BUG(); } } if (unlikely(skb_vlan_tag_present(skb)) && !netdev_uses_dsa(skb->dev)) { check_vlan_id: if (skb_vlan_tag_get_id(skb)) { /* Vlan id is non 0 and vlan_do_receive() above couldn't * find vlan device. */ skb->pkt_type = PACKET_OTHERHOST; } else if (eth_type_vlan(skb->protocol)) { /* Outer header is 802.1P with vlan 0, inner header is * 802.1Q or 802.1AD and vlan_do_receive() above could * not find vlan dev for vlan id 0. */ __vlan_hwaccel_clear_tag(skb); skb = skb_vlan_untag(skb); if (unlikely(!skb)) goto out; if (vlan_do_receive(&skb)) /* After stripping off 802.1P header with vlan 0 * vlan dev is found for inner header. */ goto another_round; else if (unlikely(!skb)) goto out; else /* We have stripped outer 802.1P vlan 0 header. * But could not find vlan dev. * check again for vlan id to set OTHERHOST. */ goto check_vlan_id; } /* Note: we might in the future use prio bits * and set skb->priority like in vlan_do_receive() * For the time being, just ignore Priority Code Point */ __vlan_hwaccel_clear_tag(skb); } type = skb->protocol; /* deliver only exact match when indicated */ if (likely(!deliver_exact)) { deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, &ptype_base[ntohs(type) & PTYPE_HASH_MASK]); } deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, &orig_dev->ptype_specific); if (unlikely(skb->dev != orig_dev)) { deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, &skb->dev->ptype_specific); } if (pt_prev) { if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) goto drop; *ppt_prev = pt_prev; } else { drop: if (!deliver_exact) dev_core_stats_rx_dropped_inc(skb->dev); else dev_core_stats_rx_nohandler_inc(skb->dev); kfree_skb_reason(skb, SKB_DROP_REASON_UNHANDLED_PROTO); /* Jamal, now you will not able to escape explaining * me how you were going to use this. :-) */ ret = NET_RX_DROP; } out: /* The invariant here is that if *ppt_prev is not NULL * then skb should also be non-NULL. * * Apparently *ppt_prev assignment above holds this invariant due to * skb dereferencing near it. */ *pskb = skb; return ret; } static int __netif_receive_skb_one_core(struct sk_buff *skb, bool pfmemalloc) { struct net_device *orig_dev = skb->dev; struct packet_type *pt_prev = NULL; int ret; ret = __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev); if (pt_prev) ret = INDIRECT_CALL_INET(pt_prev->func, ipv6_rcv, ip_rcv, skb, skb->dev, pt_prev, orig_dev); return ret; } /** * netif_receive_skb_core - special purpose version of netif_receive_skb * @skb: buffer to process * * More direct receive version of netif_receive_skb(). It should * only be used by callers that have a need to skip RPS and Generic XDP. * Caller must also take care of handling if ``(page_is_)pfmemalloc``. * * This function may only be called from softirq context and interrupts * should be enabled. * * Return values (usually ignored): * NET_RX_SUCCESS: no congestion * NET_RX_DROP: packet was dropped */ int netif_receive_skb_core(struct sk_buff *skb) { int ret; rcu_read_lock(); ret = __netif_receive_skb_one_core(skb, false); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(netif_receive_skb_core); static inline void __netif_receive_skb_list_ptype(struct list_head *head, struct packet_type *pt_prev, struct net_device *orig_dev) { struct sk_buff *skb, *next; if (!pt_prev) return; if (list_empty(head)) return; if (pt_prev->list_func != NULL) INDIRECT_CALL_INET(pt_prev->list_func, ipv6_list_rcv, ip_list_rcv, head, pt_prev, orig_dev); else list_for_each_entry_safe(skb, next, head, list) { skb_list_del_init(skb); pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } } static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc) { /* Fast-path assumptions: * - There is no RX handler. * - Only one packet_type matches. * If either of these fails, we will end up doing some per-packet * processing in-line, then handling the 'last ptype' for the whole * sublist. This can't cause out-of-order delivery to any single ptype, * because the 'last ptype' must be constant across the sublist, and all * other ptypes are handled per-packet. */ /* Current (common) ptype of sublist */ struct packet_type *pt_curr = NULL; /* Current (common) orig_dev of sublist */ struct net_device *od_curr = NULL; struct list_head sublist; struct sk_buff *skb, *next; INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { struct net_device *orig_dev = skb->dev; struct packet_type *pt_prev = NULL; skb_list_del_init(skb); __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev); if (!pt_prev) continue; if (pt_curr != pt_prev || od_curr != orig_dev) { /* dispatch old sublist */ __netif_receive_skb_list_ptype(&sublist, pt_curr, od_curr); /* start new sublist */ INIT_LIST_HEAD(&sublist); pt_curr = pt_prev; od_curr = orig_dev; } list_add_tail(&skb->list, &sublist); } /* dispatch final sublist */ __netif_receive_skb_list_ptype(&sublist, pt_curr, od_curr); } static int __netif_receive_skb(struct sk_buff *skb) { int ret; if (sk_memalloc_socks() && skb_pfmemalloc(skb)) { unsigned int noreclaim_flag; /* * PFMEMALLOC skbs are special, they should * - be delivered to SOCK_MEMALLOC sockets only * - stay away from userspace * - have bounded memory usage * * Use PF_MEMALLOC as this saves us from propagating the allocation * context down to all allocation sites. */ noreclaim_flag = memalloc_noreclaim_save(); ret = __netif_receive_skb_one_core(skb, true); memalloc_noreclaim_restore(noreclaim_flag); } else ret = __netif_receive_skb_one_core(skb, false); return ret; } static void __netif_receive_skb_list(struct list_head *head) { unsigned long noreclaim_flag = 0; struct sk_buff *skb, *next; bool pfmemalloc = false; /* Is current sublist PF_MEMALLOC? */ list_for_each_entry_safe(skb, next, head, list) { if ((sk_memalloc_socks() && skb_pfmemalloc(skb)) != pfmemalloc) { struct list_head sublist; /* Handle the previous sublist */ list_cut_before(&sublist, head, &skb->list); if (!list_empty(&sublist)) __netif_receive_skb_list_core(&sublist, pfmemalloc); pfmemalloc = !pfmemalloc; /* See comments in __netif_receive_skb */ if (pfmemalloc) noreclaim_flag = memalloc_noreclaim_save(); else memalloc_noreclaim_restore(noreclaim_flag); } } /* Handle the remaining sublist */ if (!list_empty(head)) __netif_receive_skb_list_core(head, pfmemalloc); /* Restore pflags */ if (pfmemalloc) memalloc_noreclaim_restore(noreclaim_flag); } static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) { struct bpf_prog *old = rtnl_dereference(dev->xdp_prog); struct bpf_prog *new = xdp->prog; int ret = 0; switch (xdp->command) { case XDP_SETUP_PROG: rcu_assign_pointer(dev->xdp_prog, new); if (old) bpf_prog_put(old); if (old && !new) { static_branch_dec(&generic_xdp_needed_key); } else if (new && !old) { static_branch_inc(&generic_xdp_needed_key); dev_disable_lro(dev); dev_disable_gro_hw(dev); } break; default: ret = -EINVAL; break; } return ret; } static int netif_receive_skb_internal(struct sk_buff *skb) { int ret; net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; rcu_read_lock(); #ifdef CONFIG_RPS if (static_branch_unlikely(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu = get_rps_cpu(skb->dev, skb, &rflow); if (cpu >= 0) { ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); return ret; } } #endif ret = __netif_receive_skb(skb); rcu_read_unlock(); return ret; } void netif_receive_skb_list_internal(struct list_head *head) { struct sk_buff *skb, *next; struct list_head sublist; INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); skb_list_del_init(skb); if (!skb_defer_rx_timestamp(skb)) list_add_tail(&skb->list, &sublist); } list_splice_init(&sublist, head); rcu_read_lock(); #ifdef CONFIG_RPS if (static_branch_unlikely(&rps_needed)) { list_for_each_entry_safe(skb, next, head, list) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu = get_rps_cpu(skb->dev, skb, &rflow); if (cpu >= 0) { /* Will be handled, remove from list */ skb_list_del_init(skb); enqueue_to_backlog(skb, cpu, &rflow->last_qtail); } } } #endif __netif_receive_skb_list(head); rcu_read_unlock(); } /** * netif_receive_skb - process receive buffer from network * @skb: buffer to process * * netif_receive_skb() is the main receive data processing function. * It always succeeds. The buffer may be dropped during processing * for congestion control or by the protocol layers. * * This function may only be called from softirq context and interrupts * should be enabled. * * Return values (usually ignored): * NET_RX_SUCCESS: no congestion * NET_RX_DROP: packet was dropped */ int netif_receive_skb(struct sk_buff *skb) { int ret; trace_netif_receive_skb_entry(skb); ret = netif_receive_skb_internal(skb); trace_netif_receive_skb_exit(ret); return ret; } EXPORT_SYMBOL(netif_receive_skb); /** * netif_receive_skb_list - process many receive buffers from network * @head: list of skbs to process. * * Since return value of netif_receive_skb() is normally ignored, and * wouldn't be meaningful for a list, this function returns void. * * This function may only be called from softirq context and interrupts * should be enabled. */ void netif_receive_skb_list(struct list_head *head) { struct sk_buff *skb; if (list_empty(head)) return; if (trace_netif_receive_skb_list_entry_enabled()) { list_for_each_entry(skb, head, list) trace_netif_receive_skb_list_entry(skb); } netif_receive_skb_list_internal(head); trace_netif_receive_skb_list_exit(0); } EXPORT_SYMBOL(netif_receive_skb_list); static DEFINE_PER_CPU(struct work_struct, flush_works); /* Network device is going away, flush any packets still pending */ static void flush_backlog(struct work_struct *work) { struct sk_buff *skb, *tmp; struct softnet_data *sd; local_bh_disable(); sd = this_cpu_ptr(&softnet_data); rps_lock_irq_disable(sd); skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->input_pkt_queue); dev_kfree_skb_irq(skb); input_queue_head_incr(sd); } } rps_unlock_irq_enable(sd); skb_queue_walk_safe(&sd->process_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->process_queue); kfree_skb(skb); input_queue_head_incr(sd); } } local_bh_enable(); } static bool flush_required(int cpu) { #if IS_ENABLED(CONFIG_RPS) struct softnet_data *sd = &per_cpu(softnet_data, cpu); bool do_flush; rps_lock_irq_disable(sd); /* as insertion into process_queue happens with the rps lock held, * process_queue access may race only with dequeue */ do_flush = !skb_queue_empty(&sd->input_pkt_queue) || !skb_queue_empty_lockless(&sd->process_queue); rps_unlock_irq_enable(sd); return do_flush; #endif /* without RPS we can't safely check input_pkt_queue: during a * concurrent remote skb_queue_splice() we can detect as empty both * input_pkt_queue and process_queue even if the latter could end-up * containing a lot of packets. */ return true; } static void flush_all_backlogs(void) { static cpumask_t flush_cpus; unsigned int cpu; /* since we are under rtnl lock protection we can use static data * for the cpumask and avoid allocating on stack the possibly * large mask */ ASSERT_RTNL(); cpus_read_lock(); cpumask_clear(&flush_cpus); for_each_online_cpu(cpu) { if (flush_required(cpu)) { queue_work_on(cpu, system_highpri_wq, per_cpu_ptr(&flush_works, cpu)); cpumask_set_cpu(cpu, &flush_cpus); } } /* we can have in flight packet[s] on the cpus we are not flushing, * synchronize_net() in unregister_netdevice_many() will take care of * them */ for_each_cpu(cpu, &flush_cpus) flush_work(per_cpu_ptr(&flush_works, cpu)); cpus_read_unlock(); } static void net_rps_send_ipi(struct softnet_data *remsd) { #ifdef CONFIG_RPS while (remsd) { struct softnet_data *next = remsd->rps_ipi_next; if (cpu_online(remsd->cpu)) smp_call_function_single_async(remsd->cpu, &remsd->csd); remsd = next; } #endif } /* * net_rps_action_and_irq_enable sends any pending IPI's for rps. * Note: called with local irq disabled, but exits with local irq enabled. */ static void net_rps_action_and_irq_enable(struct softnet_data *sd) { #ifdef CONFIG_RPS struct softnet_data *remsd = sd->rps_ipi_list; if (remsd) { sd->rps_ipi_list = NULL; local_irq_enable(); /* Send pending IPI's to kick RPS processing on remote cpus. */ net_rps_send_ipi(remsd); } else #endif local_irq_enable(); } static bool sd_has_rps_ipi_waiting(struct softnet_data *sd) { #ifdef CONFIG_RPS return sd->rps_ipi_list != NULL; #else return false; #endif } static int process_backlog(struct napi_struct *napi, int quota) { struct softnet_data *sd = container_of(napi, struct softnet_data, backlog); bool again = true; int work = 0; /* Check if we have pending ipi, its better to send them now, * not waiting net_rx_action() end. */ if (sd_has_rps_ipi_waiting(sd)) { local_irq_disable(); net_rps_action_and_irq_enable(sd); } napi->weight = READ_ONCE(dev_rx_weight); while (again) { struct sk_buff *skb; while ((skb = __skb_dequeue(&sd->process_queue))) { rcu_read_lock(); __netif_receive_skb(skb); rcu_read_unlock(); input_queue_head_incr(sd); if (++work >= quota) return work; } rps_lock_irq_disable(sd); if (skb_queue_empty(&sd->input_pkt_queue)) { /* * Inline a custom version of __napi_complete(). * only current cpu owns and manipulates this napi, * and NAPI_STATE_SCHED is the only possible flag set * on backlog. * We can use a plain write instead of clear_bit(), * and we dont need an smp_mb() memory barrier. */ napi->state = 0; again = false; } else { skb_queue_splice_tail_init(&sd->input_pkt_queue, &sd->process_queue); } rps_unlock_irq_enable(sd); } return work; } /** * __napi_schedule - schedule for receive * @n: entry to schedule * * The entry's receive function will be scheduled to run. * Consider using __napi_schedule_irqoff() if hard irqs are masked. */ void __napi_schedule(struct napi_struct *n) { unsigned long flags; local_irq_save(flags); ____napi_schedule(this_cpu_ptr(&softnet_data), n); local_irq_restore(flags); } EXPORT_SYMBOL(__napi_schedule); /** * napi_schedule_prep - check if napi can be scheduled * @n: napi context * * Test if NAPI routine is already running, and if not mark * it as running. This is used as a condition variable to * insure only one NAPI poll instance runs. We also make * sure there is no pending NAPI disable. */ bool napi_schedule_prep(struct napi_struct *n) { unsigned long val, new; do { val = READ_ONCE(n->state); if (unlikely(val & NAPIF_STATE_DISABLE)) return false; new = val | NAPIF_STATE_SCHED; /* Sets STATE_MISSED bit if STATE_SCHED was already set * This was suggested by Alexander Duyck, as compiler * emits better code than : * if (val & NAPIF_STATE_SCHED) * new |= NAPIF_STATE_MISSED; */ new |= (val & NAPIF_STATE_SCHED) / NAPIF_STATE_SCHED * NAPIF_STATE_MISSED; } while (cmpxchg(&n->state, val, new) != val); return !(val & NAPIF_STATE_SCHED); } EXPORT_SYMBOL(napi_schedule_prep); /** * __napi_schedule_irqoff - schedule for receive * @n: entry to schedule * * Variant of __napi_schedule() assuming hard irqs are masked. * * On PREEMPT_RT enabled kernels this maps to __napi_schedule() * because the interrupt disabled assumption might not be true * due to force-threaded interrupts and spinlock substitution. */ void __napi_schedule_irqoff(struct napi_struct *n) { if (!IS_ENABLED(CONFIG_PREEMPT_RT)) ____napi_schedule(this_cpu_ptr(&softnet_data), n); else __napi_schedule(n); } EXPORT_SYMBOL(__napi_schedule_irqoff); bool napi_complete_done(struct napi_struct *n, int work_done) { unsigned long flags, val, new, timeout = 0; bool ret = true; /* * 1) Don't let napi dequeue from the cpu poll list * just in case its running on a different cpu. * 2) If we are busy polling, do nothing here, we have * the guarantee we will be called later. */ if (unlikely(n->state & (NAPIF_STATE_NPSVC | NAPIF_STATE_IN_BUSY_POLL))) return false; if (work_done) { if (n->gro_bitmask) timeout = READ_ONCE(n->dev->gro_flush_timeout); n->defer_hard_irqs_count = READ_ONCE(n->dev->napi_defer_hard_irqs); } if (n->defer_hard_irqs_count > 0) { n->defer_hard_irqs_count--; timeout = READ_ONCE(n->dev->gro_flush_timeout); if (timeout) ret = false; } if (n->gro_bitmask) { /* When the NAPI instance uses a timeout and keeps postponing * it, we need to bound somehow the time packets are kept in * the GRO layer */ napi_gro_flush(n, !!timeout); } gro_normal_list(n); if (unlikely(!list_empty(&n->poll_list))) { /* If n->poll_list is not empty, we need to mask irqs */ local_irq_save(flags); list_del_init(&n->poll_list); local_irq_restore(flags); } do { val = READ_ONCE(n->state); WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED)); new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED | NAPIF_STATE_SCHED_THREADED | NAPIF_STATE_PREFER_BUSY_POLL); /* If STATE_MISSED was set, leave STATE_SCHED set, * because we will call napi->poll() one more time. * This C code was suggested by Alexander Duyck to help gcc. */ new |= (val & NAPIF_STATE_MISSED) / NAPIF_STATE_MISSED * NAPIF_STATE_SCHED; } while (cmpxchg(&n->state, val, new) != val); if (unlikely(val & NAPIF_STATE_MISSED)) { __napi_schedule(n); return false; } if (timeout) hrtimer_start(&n->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); return ret; } EXPORT_SYMBOL(napi_complete_done); /* must be called under rcu_read_lock(), as we dont take a reference */ static struct napi_struct *napi_by_id(unsigned int napi_id) { unsigned int hash = napi_id % HASH_SIZE(napi_hash); struct napi_struct *napi; hlist_for_each_entry_rcu(napi, &napi_hash[hash], napi_hash_node) if (napi->napi_id == napi_id) return napi; return NULL; } #if defined(CONFIG_NET_RX_BUSY_POLL) static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule) { if (!skip_schedule) { gro_normal_list(napi); __napi_schedule(napi); return; } if (napi->gro_bitmask) { /* flush too old packets * If HZ < 1000, flush all packets. */ napi_gro_flush(napi, HZ >= 1000); } gro_normal_list(napi); clear_bit(NAPI_STATE_SCHED, &napi->state); } static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool prefer_busy_poll, u16 budget) { bool skip_schedule = false; unsigned long timeout; int rc; /* Busy polling means there is a high chance device driver hard irq * could not grab NAPI_STATE_SCHED, and that NAPI_STATE_MISSED was * set in napi_schedule_prep(). * Since we are about to call napi->poll() once more, we can safely * clear NAPI_STATE_MISSED. * * Note: x86 could use a single "lock and ..." instruction * to perform these two clear_bit() */ clear_bit(NAPI_STATE_MISSED, &napi->state); clear_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state); local_bh_disable(); if (prefer_busy_poll) { napi->defer_hard_irqs_count = READ_ONCE(napi->dev->napi_defer_hard_irqs); timeout = READ_ONCE(napi->dev->gro_flush_timeout); if (napi->defer_hard_irqs_count && timeout) { hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); skip_schedule = true; } } /* All we really want here is to re-enable device interrupts. * Ideally, a new ndo_busy_poll_stop() could avoid another round. */ rc = napi->poll(napi, budget); /* We can't gro_normal_list() here, because napi->poll() might have * rearmed the napi (napi_complete_done()) in which case it could * already be running on another CPU. */ trace_napi_poll(napi, rc, budget); netpoll_poll_unlock(have_poll_lock); if (rc == budget) __busy_poll_stop(napi, skip_schedule); local_bh_enable(); } void napi_busy_loop(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), void *loop_end_arg, bool prefer_busy_poll, u16 budget) { unsigned long start_time = loop_end ? busy_loop_current_time() : 0; int (*napi_poll)(struct napi_struct *napi, int budget); void *have_poll_lock = NULL; struct napi_struct *napi; restart: napi_poll = NULL; rcu_read_lock(); napi = napi_by_id(napi_id); if (!napi) goto out; preempt_disable(); for (;;) { int work = 0; local_bh_disable(); if (!napi_poll) { unsigned long val = READ_ONCE(napi->state); /* If multiple threads are competing for this napi, * we avoid dirtying napi->state as much as we can. */ if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED | NAPIF_STATE_IN_BUSY_POLL)) { if (prefer_busy_poll) set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); goto count; } if (cmpxchg(&napi->state, val, val | NAPIF_STATE_IN_BUSY_POLL | NAPIF_STATE_SCHED) != val) { if (prefer_busy_poll) set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); goto count; } have_poll_lock = netpoll_poll_lock(napi); napi_poll = napi->poll; } work = napi_poll(napi, budget); trace_napi_poll(napi, work, budget); gro_normal_list(napi); count: if (work > 0) __NET_ADD_STATS(dev_net(napi->dev), LINUX_MIB_BUSYPOLLRXPACKETS, work); local_bh_enable(); if (!loop_end || loop_end(loop_end_arg, start_time)) break; if (unlikely(need_resched())) { if (napi_poll) busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget); preempt_enable(); rcu_read_unlock(); cond_resched(); if (loop_end(loop_end_arg, start_time)) return; goto restart; } cpu_relax(); } if (napi_poll) busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget); preempt_enable(); out: rcu_read_unlock(); } EXPORT_SYMBOL(napi_busy_loop); #endif /* CONFIG_NET_RX_BUSY_POLL */ static void napi_hash_add(struct napi_struct *napi) { if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state)) return; spin_lock(&napi_hash_lock); /* 0..NR_CPUS range is reserved for sender_cpu use */ do { if (unlikely(++napi_gen_id < MIN_NAPI_ID)) napi_gen_id = MIN_NAPI_ID; } while (napi_by_id(napi_gen_id)); napi->napi_id = napi_gen_id; hlist_add_head_rcu(&napi->napi_hash_node, &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]); spin_unlock(&napi_hash_lock); } /* Warning : caller is responsible to make sure rcu grace period * is respected before freeing memory containing @napi */ static void napi_hash_del(struct napi_struct *napi) { spin_lock(&napi_hash_lock); hlist_del_init_rcu(&napi->napi_hash_node); spin_unlock(&napi_hash_lock); } static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) { struct napi_struct *napi; napi = container_of(timer, struct napi_struct, timer); /* Note : we use a relaxed variant of napi_schedule_prep() not setting * NAPI_STATE_MISSED, since we do not react to a device IRQ. */ if (!napi_disable_pending(napi) && !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) { clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); __napi_schedule_irqoff(napi); } return HRTIMER_NORESTART; } static void init_gro_hash(struct napi_struct *napi) { int i; for (i = 0; i < GRO_HASH_BUCKETS; i++) { INIT_LIST_HEAD(&napi->gro_hash[i].list); napi->gro_hash[i].count = 0; } napi->gro_bitmask = 0; } int dev_set_threaded(struct net_device *dev, bool threaded) { struct napi_struct *napi; int err = 0; if (dev->threaded == threaded) return 0; if (threaded) { list_for_each_entry(napi, &dev->napi_list, dev_list) { if (!napi->thread) { err = napi_kthread_create(napi); if (err) { threaded = false; break; } } } } dev->threaded = threaded; /* Make sure kthread is created before THREADED bit * is set. */ smp_mb__before_atomic(); /* Setting/unsetting threaded mode on a napi might not immediately * take effect, if the current napi instance is actively being * polled. In this case, the switch between threaded mode and * softirq mode will happen in the next round of napi_schedule(). * This should not cause hiccups/stalls to the live traffic. */ list_for_each_entry(napi, &dev->napi_list, dev_list) { if (threaded) set_bit(NAPI_STATE_THREADED, &napi->state); else clear_bit(NAPI_STATE_THREADED, &napi->state); } return err; } EXPORT_SYMBOL(dev_set_threaded); void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { if (WARN_ON(test_and_set_bit(NAPI_STATE_LISTED, &napi->state))) return; INIT_LIST_HEAD(&napi->poll_list); INIT_HLIST_NODE(&napi->napi_hash_node); hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); napi->timer.function = napi_watchdog; init_gro_hash(napi); napi->skb = NULL; INIT_LIST_HEAD(&napi->rx_list); napi->rx_count = 0; napi->poll = poll; if (weight > NAPI_POLL_WEIGHT) netdev_err_once(dev, "%s() called with weight %d\n", __func__, weight); napi->weight = weight; napi->dev = dev; #ifdef CONFIG_NETPOLL napi->poll_owner = -1; #endif set_bit(NAPI_STATE_SCHED, &napi->state); set_bit(NAPI_STATE_NPSVC, &napi->state); list_add_rcu(&napi->dev_list, &dev->napi_list); napi_hash_add(napi); napi_get_frags_check(napi); /* Create kthread for this napi if dev->threaded is set. * Clear dev->threaded if kthread creation failed so that * threaded mode will not be enabled in napi_enable(). */ if (dev->threaded && napi_kthread_create(napi)) dev->threaded = 0; } EXPORT_SYMBOL(netif_napi_add_weight); void napi_disable(struct napi_struct *n) { unsigned long val, new; might_sleep(); set_bit(NAPI_STATE_DISABLE, &n->state); for ( ; ; ) { val = READ_ONCE(n->state); if (val & (NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC)) { usleep_range(20, 200); continue; } new = val | NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC; new &= ~(NAPIF_STATE_THREADED | NAPIF_STATE_PREFER_BUSY_POLL); if (cmpxchg(&n->state, val, new) == val) break; } hrtimer_cancel(&n->timer); clear_bit(NAPI_STATE_DISABLE, &n->state); } EXPORT_SYMBOL(napi_disable); /** * napi_enable - enable NAPI scheduling * @n: NAPI context * * Resume NAPI from being scheduled on this context. * Must be paired with napi_disable. */ void napi_enable(struct napi_struct *n) { unsigned long val, new; do { val = READ_ONCE(n->state); BUG_ON(!test_bit(NAPI_STATE_SCHED, &val)); new = val & ~(NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC); if (n->dev->threaded && n->thread) new |= NAPIF_STATE_THREADED; } while (cmpxchg(&n->state, val, new) != val); } EXPORT_SYMBOL(napi_enable); static void flush_gro_hash(struct napi_struct *napi) { int i; for (i = 0; i < GRO_HASH_BUCKETS; i++) { struct sk_buff *skb, *n; list_for_each_entry_safe(skb, n, &napi->gro_hash[i].list, list) kfree_skb(skb); napi->gro_hash[i].count = 0; } } /* Must be called in process context */ void __netif_napi_del(struct napi_struct *napi) { if (!test_and_clear_bit(NAPI_STATE_LISTED, &napi->state)) return; napi_hash_del(napi); list_del_rcu(&napi->dev_list); napi_free_frags(napi); flush_gro_hash(napi); napi->gro_bitmask = 0; if (napi->thread) { kthread_stop(napi->thread); napi->thread = NULL; } } EXPORT_SYMBOL(__netif_napi_del); static int __napi_poll(struct napi_struct *n, bool *repoll) { int work, weight; weight = n->weight; /* This NAPI_STATE_SCHED test is for avoiding a race * with netpoll's poll_napi(). Only the entity which * obtains the lock and sees NAPI_STATE_SCHED set will * actually make the ->poll() call. Therefore we avoid * accidentally calling ->poll() when NAPI is not scheduled. */ work = 0; if (test_bit(NAPI_STATE_SCHED, &n->state)) { work = n->poll(n, weight); trace_napi_poll(n, work, weight); } if (unlikely(work > weight)) netdev_err_once(n->dev, "NAPI poll function %pS returned %d, exceeding its budget of %d.\n", n->poll, work, weight); if (likely(work < weight)) return work; /* Drivers must not modify the NAPI state if they * consume the entire weight. In such cases this code * still "owns" the NAPI instance and therefore can * move the instance around on the list at-will. */ if (unlikely(napi_disable_pending(n))) { napi_complete(n); return work; } /* The NAPI context has more processing work, but busy-polling * is preferred. Exit early. */ if (napi_prefer_busy_poll(n)) { if (napi_complete_done(n, work)) { /* If timeout is not set, we need to make sure * that the NAPI is re-scheduled. */ napi_schedule(n); } return work; } if (n->gro_bitmask) { /* flush too old packets * If HZ < 1000, flush all packets. */ napi_gro_flush(n, HZ >= 1000); } gro_normal_list(n); /* Some drivers may have called napi_schedule * prior to exhausting their budget. */ if (unlikely(!list_empty(&n->poll_list))) { pr_warn_once("%s: Budget exhausted after napi rescheduled\n", n->dev ? n->dev->name : "backlog"); return work; } *repoll = true; return work; } static int napi_poll(struct napi_struct *n, struct list_head *repoll) { bool do_repoll = false; void *have; int work; list_del_init(&n->poll_list); have = netpoll_poll_lock(n); work = __napi_poll(n, &do_repoll); if (do_repoll) list_add_tail(&n->poll_list, repoll); netpoll_poll_unlock(have); return work; } static int napi_thread_wait(struct napi_struct *napi) { bool woken = false; set_current_state(TASK_INTERRUPTIBLE); while (!kthread_should_stop()) { /* Testing SCHED_THREADED bit here to make sure the current * kthread owns this napi and could poll on this napi. * Testing SCHED bit is not enough because SCHED bit might be * set by some other busy poll thread or by napi_disable(). */ if (test_bit(NAPI_STATE_SCHED_THREADED, &napi->state) || woken) { WARN_ON(!list_empty(&napi->poll_list)); __set_current_state(TASK_RUNNING); return 0; } schedule(); /* woken being true indicates this thread owns this napi. */ woken = true; set_current_state(TASK_INTERRUPTIBLE); } __set_current_state(TASK_RUNNING); return -1; } static int napi_threaded_poll(void *data) { struct napi_struct *napi = data; void *have; while (!napi_thread_wait(napi)) { unsigned long last_qs = jiffies; for (;;) { bool repoll = false; local_bh_disable(); have = netpoll_poll_lock(napi); __napi_poll(napi, &repoll); netpoll_poll_unlock(have); local_bh_enable(); if (!repoll) break; rcu_softirq_qs_periodic(last_qs); cond_resched(); } } return 0; } static void skb_defer_free_flush(struct softnet_data *sd) { struct sk_buff *skb, *next; unsigned long flags; /* Paired with WRITE_ONCE() in skb_attempt_defer_free() */ if (!READ_ONCE(sd->defer_list)) return; spin_lock_irqsave(&sd->defer_lock, flags); skb = sd->defer_list; sd->defer_list = NULL; sd->defer_count = 0; spin_unlock_irqrestore(&sd->defer_lock, flags); while (skb != NULL) { next = skb->next; napi_consume_skb(skb, 1); skb = next; } } static __latent_entropy void net_rx_action(struct softirq_action *h) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); unsigned long time_limit = jiffies + usecs_to_jiffies(READ_ONCE(netdev_budget_usecs)); int budget = READ_ONCE(netdev_budget); LIST_HEAD(list); LIST_HEAD(repoll); local_irq_disable(); list_splice_init(&sd->poll_list, &list); local_irq_enable(); for (;;) { struct napi_struct *n; skb_defer_free_flush(sd); if (list_empty(&list)) { if (!sd_has_rps_ipi_waiting(sd) && list_empty(&repoll)) goto end; break; } n = list_first_entry(&list, struct napi_struct, poll_list); budget -= napi_poll(n, &repoll); /* If softirq window is exhausted then punt. * Allow this to run for 2 jiffies since which will allow * an average latency of 1.5/HZ. */ if (unlikely(budget <= 0 || time_after_eq(jiffies, time_limit))) { sd->time_squeeze++; break; } } local_irq_disable(); list_splice_tail_init(&sd->poll_list, &list); list_splice_tail(&repoll, &list); list_splice(&list, &sd->poll_list); if (!list_empty(&sd->poll_list)) __raise_softirq_irqoff(NET_RX_SOFTIRQ); net_rps_action_and_irq_enable(sd); end:; } struct netdev_adjacent { struct net_device *dev; netdevice_tracker dev_tracker; /* upper master flag, there can only be one master device per list */ bool master; /* lookup ignore flag */ bool ignore; /* counter for the number of times this device was added to us */ u16 ref_nr; /* private field for the users */ void *private; struct list_head list; struct rcu_head rcu; }; static struct netdev_adjacent *__netdev_find_adj(struct net_device *adj_dev, struct list_head *adj_list) { struct netdev_adjacent *adj; list_for_each_entry(adj, adj_list, list) { if (adj->dev == adj_dev) return adj; } return NULL; } static int ____netdev_has_upper_dev(struct net_device *upper_dev, struct netdev_nested_priv *priv) { struct net_device *dev = (struct net_device *)priv->data; return upper_dev == dev; } /** * netdev_has_upper_dev - Check if device is linked to an upper device * @dev: device * @upper_dev: upper device to check * * Find out if a device is linked to specified upper device and return true * in case it is. Note that this checks only immediate upper device, * not through a complete stack of devices. The caller must hold the RTNL lock. */ bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev) { struct netdev_nested_priv priv = { .data = (void *)upper_dev, }; ASSERT_RTNL(); return netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, &priv); } EXPORT_SYMBOL(netdev_has_upper_dev); /** * netdev_has_upper_dev_all_rcu - Check if device is linked to an upper device * @dev: device * @upper_dev: upper device to check * * Find out if a device is linked to specified upper device and return true * in case it is. Note that this checks the entire upper device chain. * The caller must hold rcu lock. */ bool netdev_has_upper_dev_all_rcu(struct net_device *dev, struct net_device *upper_dev) { struct netdev_nested_priv priv = { .data = (void *)upper_dev, }; return !!netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, &priv); } EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu); /** * netdev_has_any_upper_dev - Check if device is linked to some device * @dev: device * * Find out if a device is linked to an upper device and return true in case * it is. The caller must hold the RTNL lock. */ bool netdev_has_any_upper_dev(struct net_device *dev) { ASSERT_RTNL(); return !list_empty(&dev->adj_list.upper); } EXPORT_SYMBOL(netdev_has_any_upper_dev); /** * netdev_master_upper_dev_get - Get master upper device * @dev: device * * Find a master upper device and return pointer to it or NULL in case * it's not there. The caller must hold the RTNL lock. */ struct net_device *netdev_master_upper_dev_get(struct net_device *dev) { struct netdev_adjacent *upper; ASSERT_RTNL(); if (list_empty(&dev->adj_list.upper)) return NULL; upper = list_first_entry(&dev->adj_list.upper, struct netdev_adjacent, list); if (likely(upper->master)) return upper->dev; return NULL; } EXPORT_SYMBOL(netdev_master_upper_dev_get); static struct net_device *__netdev_master_upper_dev_get(struct net_device *dev) { struct netdev_adjacent *upper; ASSERT_RTNL(); if (list_empty(&dev->adj_list.upper)) return NULL; upper = list_first_entry(&dev->adj_list.upper, struct netdev_adjacent, list); if (likely(upper->master) && !upper->ignore) return upper->dev; return NULL; } /** * netdev_has_any_lower_dev - Check if device is linked to some device * @dev: device * * Find out if a device is linked to a lower device and return true in case * it is. The caller must hold the RTNL lock. */ static bool netdev_has_any_lower_dev(struct net_device *dev) { ASSERT_RTNL(); return !list_empty(&dev->adj_list.lower); } void *netdev_adjacent_get_private(struct list_head *adj_list) { struct netdev_adjacent *adj; adj = list_entry(adj_list, struct netdev_adjacent, list); return adj->private; } EXPORT_SYMBOL(netdev_adjacent_get_private); /** * netdev_upper_get_next_dev_rcu - Get the next dev from upper list * @dev: device * @iter: list_head ** of the current position * * Gets the next device from the dev's upper list, starting from iter * position. The caller must hold RCU read lock. */ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *upper; WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held()); upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); if (&upper->list == &dev->adj_list.upper) return NULL; *iter = &upper->list; return upper->dev; } EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu); static struct net_device *__netdev_next_upper_dev(struct net_device *dev, struct list_head **iter, bool *ignore) { struct netdev_adjacent *upper; upper = list_entry((*iter)->next, struct netdev_adjacent, list); if (&upper->list == &dev->adj_list.upper) return NULL; *iter = &upper->list; *ignore = upper->ignore; return upper->dev; } static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *upper; WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held()); upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); if (&upper->list == &dev->adj_list.upper) return NULL; *iter = &upper->list; return upper->dev; } static int __netdev_walk_all_upper_dev(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; bool ignore; now = dev; iter = &dev->adj_list.upper; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { udev = __netdev_next_upper_dev(now, &iter, &ignore); if (!udev) break; if (ignore) continue; next = udev; niter = &udev->adj_list.upper; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } int netdev_walk_all_upper_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; now = dev; iter = &dev->adj_list.upper; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { udev = netdev_next_upper_dev_rcu(now, &iter); if (!udev) break; next = udev; niter = &udev->adj_list.upper; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } EXPORT_SYMBOL_GPL(netdev_walk_all_upper_dev_rcu); static bool __netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev) { struct netdev_nested_priv priv = { .flags = 0, .data = (void *)upper_dev, }; ASSERT_RTNL(); return __netdev_walk_all_upper_dev(dev, ____netdev_has_upper_dev, &priv); } /** * netdev_lower_get_next_private - Get the next ->private from the * lower neighbour list * @dev: device * @iter: list_head ** of the current position * * Gets the next netdev_adjacent->private from the dev's lower neighbour * list, starting from iter position. The caller must hold either hold the * RTNL lock or its own locking that guarantees that the neighbour lower * list will remain unchanged. */ void *netdev_lower_get_next_private(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; lower = list_entry(*iter, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = lower->list.next; return lower->private; } EXPORT_SYMBOL(netdev_lower_get_next_private); /** * netdev_lower_get_next_private_rcu - Get the next ->private from the * lower neighbour list, RCU * variant * @dev: device * @iter: list_head ** of the current position * * Gets the next netdev_adjacent->private from the dev's lower neighbour * list, starting from iter position. The caller must hold RCU read lock. */ void *netdev_lower_get_next_private_rcu(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = &lower->list; return lower->private; } EXPORT_SYMBOL(netdev_lower_get_next_private_rcu); /** * netdev_lower_get_next - Get the next device from the lower neighbour * list * @dev: device * @iter: list_head ** of the current position * * Gets the next netdev_adjacent from the dev's lower neighbour * list, starting from iter position. The caller must hold RTNL lock or * its own locking that guarantees that the neighbour lower * list will remain unchanged. */ void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; lower = list_entry(*iter, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = lower->list.next; return lower->dev; } EXPORT_SYMBOL(netdev_lower_get_next); static struct net_device *netdev_next_lower_dev(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; lower = list_entry((*iter)->next, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = &lower->list; return lower->dev; } static struct net_device *__netdev_next_lower_dev(struct net_device *dev, struct list_head **iter, bool *ignore) { struct netdev_adjacent *lower; lower = list_entry((*iter)->next, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = &lower->list; *ignore = lower->ignore; return lower->dev; } int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; now = dev; iter = &dev->adj_list.lower; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { ldev = netdev_next_lower_dev(now, &iter); if (!ldev) break; next = ldev; niter = &ldev->adj_list.lower; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev); static int __netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; bool ignore; now = dev; iter = &dev->adj_list.lower; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { ldev = __netdev_next_lower_dev(now, &iter, &ignore); if (!ldev) break; if (ignore) continue; next = ldev; niter = &ldev->adj_list.lower; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = &lower->list; return lower->dev; } EXPORT_SYMBOL(netdev_next_lower_dev_rcu); static u8 __netdev_upper_depth(struct net_device *dev) { struct net_device *udev; struct list_head *iter; u8 max_depth = 0; bool ignore; for (iter = &dev->adj_list.upper, udev = __netdev_next_upper_dev(dev, &iter, &ignore); udev; udev = __netdev_next_upper_dev(dev, &iter, &ignore)) { if (ignore) continue; if (max_depth < udev->upper_level) max_depth = udev->upper_level; } return max_depth; } static u8 __netdev_lower_depth(struct net_device *dev) { struct net_device *ldev; struct list_head *iter; u8 max_depth = 0; bool ignore; for (iter = &dev->adj_list.lower, ldev = __netdev_next_lower_dev(dev, &iter, &ignore); ldev; ldev = __netdev_next_lower_dev(dev, &iter, &ignore)) { if (ignore) continue; if (max_depth < ldev->lower_level) max_depth = ldev->lower_level; } return max_depth; } static int __netdev_update_upper_level(struct net_device *dev, struct netdev_nested_priv *__unused) { dev->upper_level = __netdev_upper_depth(dev) + 1; return 0; } #ifdef CONFIG_LOCKDEP static LIST_HEAD(net_unlink_list); static void net_unlink_todo(struct net_device *dev) { if (list_empty(&dev->unlink_list)) list_add_tail(&dev->unlink_list, &net_unlink_list); } #endif static int __netdev_update_lower_level(struct net_device *dev, struct netdev_nested_priv *priv) { dev->lower_level = __netdev_lower_depth(dev) + 1; #ifdef CONFIG_LOCKDEP if (!priv) return 0; if (priv->flags & NESTED_SYNC_IMM) dev->nested_level = dev->lower_level - 1; if (priv->flags & NESTED_SYNC_TODO) net_unlink_todo(dev); #endif return 0; } int netdev_walk_all_lower_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; now = dev; iter = &dev->adj_list.lower; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { ldev = netdev_next_lower_dev_rcu(now, &iter); if (!ldev) break; next = ldev; niter = &ldev->adj_list.lower; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev_rcu); /** * netdev_lower_get_first_private_rcu - Get the first ->private from the * lower neighbour list, RCU * variant * @dev: device * * Gets the first netdev_adjacent->private from the dev's lower neighbour * list. The caller must hold RCU read lock. */ void *netdev_lower_get_first_private_rcu(struct net_device *dev) { struct netdev_adjacent *lower; lower = list_first_or_null_rcu(&dev->adj_list.lower, struct netdev_adjacent, list); if (lower) return lower->private; return NULL; } EXPORT_SYMBOL(netdev_lower_get_first_private_rcu); /** * netdev_master_upper_dev_get_rcu - Get master upper device * @dev: device * * Find a master upper device and return pointer to it or NULL in case * it's not there. The caller must hold the RCU read lock. */ struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev) { struct netdev_adjacent *upper; upper = list_first_or_null_rcu(&dev->adj_list.upper, struct netdev_adjacent, list); if (upper && likely(upper->master)) return upper->dev; return NULL; } EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu); static int netdev_adjacent_sysfs_add(struct net_device *dev, struct net_device *adj_dev, struct list_head *dev_list) { char linkname[IFNAMSIZ+7]; sprintf(linkname, dev_list == &dev->adj_list.upper ? "upper_%s" : "lower_%s", adj_dev->name); return sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj), linkname); } static void netdev_adjacent_sysfs_del(struct net_device *dev, char *name, struct list_head *dev_list) { char linkname[IFNAMSIZ+7]; sprintf(linkname, dev_list == &dev->adj_list.upper ? "upper_%s" : "lower_%s", name); sysfs_remove_link(&(dev->dev.kobj), linkname); } static inline bool netdev_adjacent_is_neigh_list(struct net_device *dev, struct net_device *adj_dev, struct list_head *dev_list) { return (dev_list == &dev->adj_list.upper || dev_list == &dev->adj_list.lower) && net_eq(dev_net(dev), dev_net(adj_dev)); } static int __netdev_adjacent_dev_insert(struct net_device *dev, struct net_device *adj_dev, struct list_head *dev_list, void *private, bool master) { struct netdev_adjacent *adj; int ret; adj = __netdev_find_adj(adj_dev, dev_list); if (adj) { adj->ref_nr += 1; pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d\n", dev->name, adj_dev->name, adj->ref_nr); return 0; } adj = kmalloc(sizeof(*adj), GFP_KERNEL); if (!adj) return -ENOMEM; adj->dev = adj_dev; adj->master = master; adj->ref_nr = 1; adj->private = private; adj->ignore = false; netdev_hold(adj_dev, &adj->dev_tracker, GFP_KERNEL); pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d; dev_hold on %s\n", dev->name, adj_dev->name, adj->ref_nr, adj_dev->name); if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) { ret = netdev_adjacent_sysfs_add(dev, adj_dev, dev_list); if (ret) goto free_adj; } /* Ensure that master link is always the first item in list. */ if (master) { ret = sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj), "master"); if (ret) goto remove_symlinks; list_add_rcu(&adj->list, dev_list); } else { list_add_tail_rcu(&adj->list, dev_list); } return 0; remove_symlinks: if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); free_adj: netdev_put(adj_dev, &adj->dev_tracker); kfree(adj); return ret; } static void __netdev_adjacent_dev_remove(struct net_device *dev, struct net_device *adj_dev, u16 ref_nr, struct list_head *dev_list) { struct netdev_adjacent *adj; pr_debug("Remove adjacency: dev %s adj_dev %s ref_nr %d\n", dev->name, adj_dev->name, ref_nr); adj = __netdev_find_adj(adj_dev, dev_list); if (!adj) { pr_err("Adjacency does not exist for device %s from %s\n", dev->name, adj_dev->name); WARN_ON(1); return; } if (adj->ref_nr > ref_nr) { pr_debug("adjacency: %s to %s ref_nr - %d = %d\n", dev->name, adj_dev->name, ref_nr, adj->ref_nr - ref_nr); adj->ref_nr -= ref_nr; return; } if (adj->master) sysfs_remove_link(&(dev->dev.kobj), "master"); if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); list_del_rcu(&adj->list); pr_debug("adjacency: dev_put for %s, because link removed from %s to %s\n", adj_dev->name, dev->name, adj_dev->name); netdev_put(adj_dev, &adj->dev_tracker); kfree_rcu(adj, rcu); } static int __netdev_adjacent_dev_link_lists(struct net_device *dev, struct net_device *upper_dev, struct list_head *up_list, struct list_head *down_list, void *private, bool master) { int ret; ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list, private, master); if (ret) return ret; ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list, private, false); if (ret) { __netdev_adjacent_dev_remove(dev, upper_dev, 1, up_list); return ret; } return 0; } static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev, struct net_device *upper_dev, u16 ref_nr, struct list_head *up_list, struct list_head *down_list) { __netdev_adjacent_dev_remove(dev, upper_dev, ref_nr, up_list); __netdev_adjacent_dev_remove(upper_dev, dev, ref_nr, down_list); } static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, struct net_device *upper_dev, void *private, bool master) { return __netdev_adjacent_dev_link_lists(dev, upper_dev, &dev->adj_list.upper, &upper_dev->adj_list.lower, private, master); } static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, struct net_device *upper_dev) { __netdev_adjacent_dev_unlink_lists(dev, upper_dev, 1, &dev->adj_list.upper, &upper_dev->adj_list.lower); } static int __netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, bool master, void *upper_priv, void *upper_info, struct netdev_nested_priv *priv, struct netlink_ext_ack *extack) { struct netdev_notifier_changeupper_info changeupper_info = { .info = { .dev = dev, .extack = extack, }, .upper_dev = upper_dev, .master = master, .linking = true, .upper_info = upper_info, }; struct net_device *master_dev; int ret = 0; ASSERT_RTNL(); if (dev == upper_dev) return -EBUSY; /* To prevent loops, check if dev is not upper device to upper_dev. */ if (__netdev_has_upper_dev(upper_dev, dev)) return -EBUSY; if ((dev->lower_level + upper_dev->upper_level) > MAX_NEST_DEV) return -EMLINK; if (!master) { if (__netdev_has_upper_dev(dev, upper_dev)) return -EEXIST; } else { master_dev = __netdev_master_upper_dev_get(dev); if (master_dev) return master_dev == upper_dev ? -EEXIST : -EBUSY; } ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, &changeupper_info.info); ret = notifier_to_errno(ret); if (ret) return ret; ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, upper_priv, master); if (ret) return ret; ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, &changeupper_info.info); ret = notifier_to_errno(ret); if (ret) goto rollback; __netdev_update_upper_level(dev, NULL); __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); __netdev_update_lower_level(upper_dev, priv); __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, priv); return 0; rollback: __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); return ret; } /** * netdev_upper_dev_link - Add a link to the upper device * @dev: device * @upper_dev: new upper device * @extack: netlink extended ack * * Adds a link to device which is upper to this one. The caller must hold * the RTNL lock. On a failure a negative errno code is returned. * On success the reference counts are adjusted and the function * returns zero. */ int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, struct netlink_ext_ack *extack) { struct netdev_nested_priv priv = { .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, .data = NULL, }; return __netdev_upper_dev_link(dev, upper_dev, false, NULL, NULL, &priv, extack); } EXPORT_SYMBOL(netdev_upper_dev_link); /** * netdev_master_upper_dev_link - Add a master link to the upper device * @dev: device * @upper_dev: new upper device * @upper_priv: upper device private * @upper_info: upper info to be passed down via notifier * @extack: netlink extended ack * * Adds a link to device which is upper to this one. In this case, only * one master upper device can be linked, although other non-master devices * might be linked as well. The caller must hold the RTNL lock. * On a failure a negative errno code is returned. On success the reference * counts are adjusted and the function returns zero. */ int netdev_master_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, void *upper_priv, void *upper_info, struct netlink_ext_ack *extack) { struct netdev_nested_priv priv = { .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, .data = NULL, }; return __netdev_upper_dev_link(dev, upper_dev, true, upper_priv, upper_info, &priv, extack); } EXPORT_SYMBOL(netdev_master_upper_dev_link); static void __netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev, struct netdev_nested_priv *priv) { struct netdev_notifier_changeupper_info changeupper_info = { .info = { .dev = dev, }, .upper_dev = upper_dev, .linking = false, }; ASSERT_RTNL(); changeupper_info.master = netdev_master_upper_dev_get(dev) == upper_dev; call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, &changeupper_info.info); __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, &changeupper_info.info); __netdev_update_upper_level(dev, NULL); __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); __netdev_update_lower_level(upper_dev, priv); __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, priv); } /** * netdev_upper_dev_unlink - Removes a link to upper device * @dev: device * @upper_dev: new upper device * * Removes a link to device which is upper to this one. The caller must hold * the RTNL lock. */ void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev) { struct netdev_nested_priv priv = { .flags = NESTED_SYNC_TODO, .data = NULL, }; __netdev_upper_dev_unlink(dev, upper_dev, &priv); } EXPORT_SYMBOL(netdev_upper_dev_unlink); static void __netdev_adjacent_dev_set(struct net_device *upper_dev, struct net_device *lower_dev, bool val) { struct netdev_adjacent *adj; adj = __netdev_find_adj(lower_dev, &upper_dev->adj_list.lower); if (adj) adj->ignore = val; adj = __netdev_find_adj(upper_dev, &lower_dev->adj_list.upper); if (adj) adj->ignore = val; } static void netdev_adjacent_dev_disable(struct net_device *upper_dev, struct net_device *lower_dev) { __netdev_adjacent_dev_set(upper_dev, lower_dev, true); } static void netdev_adjacent_dev_enable(struct net_device *upper_dev, struct net_device *lower_dev) { __netdev_adjacent_dev_set(upper_dev, lower_dev, false); } int netdev_adjacent_change_prepare(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev, struct netlink_ext_ack *extack) { struct netdev_nested_priv priv = { .flags = 0, .data = NULL, }; int err; if (!new_dev) return 0; if (old_dev && new_dev != old_dev) netdev_adjacent_dev_disable(dev, old_dev); err = __netdev_upper_dev_link(new_dev, dev, false, NULL, NULL, &priv, extack); if (err) { if (old_dev && new_dev != old_dev) netdev_adjacent_dev_enable(dev, old_dev); return err; } return 0; } EXPORT_SYMBOL(netdev_adjacent_change_prepare); void netdev_adjacent_change_commit(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev) { struct netdev_nested_priv priv = { .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, .data = NULL, }; if (!new_dev || !old_dev) return; if (new_dev == old_dev) return; netdev_adjacent_dev_enable(dev, old_dev); __netdev_upper_dev_unlink(old_dev, dev, &priv); } EXPORT_SYMBOL(netdev_adjacent_change_commit); void netdev_adjacent_change_abort(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev) { struct netdev_nested_priv priv = { .flags = 0, .data = NULL, }; if (!new_dev) return; if (old_dev && new_dev != old_dev) netdev_adjacent_dev_enable(dev, old_dev); __netdev_upper_dev_unlink(new_dev, dev, &priv); } EXPORT_SYMBOL(netdev_adjacent_change_abort); /** * netdev_bonding_info_change - Dispatch event about slave change * @dev: device * @bonding_info: info to dispatch * * Send NETDEV_BONDING_INFO to netdev notifiers with info. * The caller must hold the RTNL lock. */ void netdev_bonding_info_change(struct net_device *dev, struct netdev_bonding_info *bonding_info) { struct netdev_notifier_bonding_info info = { .info.dev = dev, }; memcpy(&info.bonding_info, bonding_info, sizeof(struct netdev_bonding_info)); call_netdevice_notifiers_info(NETDEV_BONDING_INFO, &info.info); } EXPORT_SYMBOL(netdev_bonding_info_change); static int netdev_offload_xstats_enable_l3(struct net_device *dev, struct netlink_ext_ack *extack) { struct netdev_notifier_offload_xstats_info info = { .info.dev = dev, .info.extack = extack, .type = NETDEV_OFFLOAD_XSTATS_TYPE_L3, }; int err; int rc; dev->offload_xstats_l3 = kzalloc(sizeof(*dev->offload_xstats_l3), GFP_KERNEL); if (!dev->offload_xstats_l3) return -ENOMEM; rc = call_netdevice_notifiers_info_robust(NETDEV_OFFLOAD_XSTATS_ENABLE, NETDEV_OFFLOAD_XSTATS_DISABLE, &info.info); err = notifier_to_errno(rc); if (err) goto free_stats; return 0; free_stats: kfree(dev->offload_xstats_l3); dev->offload_xstats_l3 = NULL; return err; } int netdev_offload_xstats_enable(struct net_device *dev, enum netdev_offload_xstats_type type, struct netlink_ext_ack *extack) { ASSERT_RTNL(); if (netdev_offload_xstats_enabled(dev, type)) return -EALREADY; switch (type) { case NETDEV_OFFLOAD_XSTATS_TYPE_L3: return netdev_offload_xstats_enable_l3(dev, extack); } WARN_ON(1); return -EINVAL; } EXPORT_SYMBOL(netdev_offload_xstats_enable); static void netdev_offload_xstats_disable_l3(struct net_device *dev) { struct netdev_notifier_offload_xstats_info info = { .info.dev = dev, .type = NETDEV_OFFLOAD_XSTATS_TYPE_L3, }; call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_DISABLE, &info.info); kfree(dev->offload_xstats_l3); dev->offload_xstats_l3 = NULL; } int netdev_offload_xstats_disable(struct net_device *dev, enum netdev_offload_xstats_type type) { ASSERT_RTNL(); if (!netdev_offload_xstats_enabled(dev, type)) return -EALREADY; switch (type) { case NETDEV_OFFLOAD_XSTATS_TYPE_L3: netdev_offload_xstats_disable_l3(dev); return 0; } WARN_ON(1); return -EINVAL; } EXPORT_SYMBOL(netdev_offload_xstats_disable); static void netdev_offload_xstats_disable_all(struct net_device *dev) { netdev_offload_xstats_disable(dev, NETDEV_OFFLOAD_XSTATS_TYPE_L3); } static struct rtnl_hw_stats64 * netdev_offload_xstats_get_ptr(const struct net_device *dev, enum netdev_offload_xstats_type type) { switch (type) { case NETDEV_OFFLOAD_XSTATS_TYPE_L3: return dev->offload_xstats_l3; } WARN_ON(1); return NULL; } bool netdev_offload_xstats_enabled(const struct net_device *dev, enum netdev_offload_xstats_type type) { ASSERT_RTNL(); return netdev_offload_xstats_get_ptr(dev, type); } EXPORT_SYMBOL(netdev_offload_xstats_enabled); struct netdev_notifier_offload_xstats_ru { bool used; }; struct netdev_notifier_offload_xstats_rd { struct rtnl_hw_stats64 stats; bool used; }; static void netdev_hw_stats64_add(struct rtnl_hw_stats64 *dest, const struct rtnl_hw_stats64 *src) { dest->rx_packets += src->rx_packets; dest->tx_packets += src->tx_packets; dest->rx_bytes += src->rx_bytes; dest->tx_bytes += src->tx_bytes; dest->rx_errors += src->rx_errors; dest->tx_errors += src->tx_errors; dest->rx_dropped += src->rx_dropped; dest->tx_dropped += src->tx_dropped; dest->multicast += src->multicast; } static int netdev_offload_xstats_get_used(struct net_device *dev, enum netdev_offload_xstats_type type, bool *p_used, struct netlink_ext_ack *extack) { struct netdev_notifier_offload_xstats_ru report_used = {}; struct netdev_notifier_offload_xstats_info info = { .info.dev = dev, .info.extack = extack, .type = type, .report_used = &report_used, }; int rc; WARN_ON(!netdev_offload_xstats_enabled(dev, type)); rc = call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_REPORT_USED, &info.info); *p_used = report_used.used; return notifier_to_errno(rc); } static int netdev_offload_xstats_get_stats(struct net_device *dev, enum netdev_offload_xstats_type type, struct rtnl_hw_stats64 *p_stats, bool *p_used, struct netlink_ext_ack *extack) { struct netdev_notifier_offload_xstats_rd report_delta = {}; struct netdev_notifier_offload_xstats_info info = { .info.dev = dev, .info.extack = extack, .type = type, .report_delta = &report_delta, }; struct rtnl_hw_stats64 *stats; int rc; stats = netdev_offload_xstats_get_ptr(dev, type); if (WARN_ON(!stats)) return -EINVAL; rc = call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_REPORT_DELTA, &info.info); /* Cache whatever we got, even if there was an error, otherwise the * successful stats retrievals would get lost. */ netdev_hw_stats64_add(stats, &report_delta.stats); if (p_stats) *p_stats = *stats; *p_used = report_delta.used; return notifier_to_errno(rc); } int netdev_offload_xstats_get(struct net_device *dev, enum netdev_offload_xstats_type type, struct rtnl_hw_stats64 *p_stats, bool *p_used, struct netlink_ext_ack *extack) { ASSERT_RTNL(); if (p_stats) return netdev_offload_xstats_get_stats(dev, type, p_stats, p_used, extack); else return netdev_offload_xstats_get_used(dev, type, p_used, extack); } EXPORT_SYMBOL(netdev_offload_xstats_get); void netdev_offload_xstats_report_delta(struct netdev_notifier_offload_xstats_rd *report_delta, const struct rtnl_hw_stats64 *stats) { report_delta->used = true; netdev_hw_stats64_add(&report_delta->stats, stats); } EXPORT_SYMBOL(netdev_offload_xstats_report_delta); void netdev_offload_xstats_report_used(struct netdev_notifier_offload_xstats_ru *report_used) { report_used->used = true; } EXPORT_SYMBOL(netdev_offload_xstats_report_used); void netdev_offload_xstats_push_delta(struct net_device *dev, enum netdev_offload_xstats_type type, const struct rtnl_hw_stats64 *p_stats) { struct rtnl_hw_stats64 *stats; ASSERT_RTNL(); stats = netdev_offload_xstats_get_ptr(dev, type); if (WARN_ON(!stats)) return; netdev_hw_stats64_add(stats, p_stats); } EXPORT_SYMBOL(netdev_offload_xstats_push_delta); /** * netdev_get_xmit_slave - Get the xmit slave of master device * @dev: device * @skb: The packet * @all_slaves: assume all the slaves are active * * The reference counters are not incremented so the caller must be * careful with locks. The caller must hold RCU lock. * %NULL is returned if no slave is found. */ struct net_device *netdev_get_xmit_slave(struct net_device *dev, struct sk_buff *skb, bool all_slaves) { const struct net_device_ops *ops = dev->netdev_ops; if (!ops->ndo_get_xmit_slave) return NULL; return ops->ndo_get_xmit_slave(dev, skb, all_slaves); } EXPORT_SYMBOL(netdev_get_xmit_slave); static struct net_device *netdev_sk_get_lower_dev(struct net_device *dev, struct sock *sk) { const struct net_device_ops *ops = dev->netdev_ops; if (!ops->ndo_sk_get_lower_dev) return NULL; return ops->ndo_sk_get_lower_dev(dev, sk); } /** * netdev_sk_get_lowest_dev - Get the lowest device in chain given device and socket * @dev: device * @sk: the socket * * %NULL is returned if no lower device is found. */ struct net_device *netdev_sk_get_lowest_dev(struct net_device *dev, struct sock *sk) { struct net_device *lower; lower = netdev_sk_get_lower_dev(dev, sk); while (lower) { dev = lower; lower = netdev_sk_get_lower_dev(dev, sk); } return dev; } EXPORT_SYMBOL(netdev_sk_get_lowest_dev); static void netdev_adjacent_add_links(struct net_device *dev) { struct netdev_adjacent *iter; struct net *net = dev_net(dev); list_for_each_entry(iter, &dev->adj_list.upper, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_add(iter->dev, dev, &iter->dev->adj_list.lower); netdev_adjacent_sysfs_add(dev, iter->dev, &dev->adj_list.upper); } list_for_each_entry(iter, &dev->adj_list.lower, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_add(iter->dev, dev, &iter->dev->adj_list.upper); netdev_adjacent_sysfs_add(dev, iter->dev, &dev->adj_list.lower); } } static void netdev_adjacent_del_links(struct net_device *dev) { struct netdev_adjacent *iter; struct net *net = dev_net(dev); list_for_each_entry(iter, &dev->adj_list.upper, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_del(iter->dev, dev->name, &iter->dev->adj_list.lower); netdev_adjacent_sysfs_del(dev, iter->dev->name, &dev->adj_list.upper); } list_for_each_entry(iter, &dev->adj_list.lower, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_del(iter->dev, dev->name, &iter->dev->adj_list.upper); netdev_adjacent_sysfs_del(dev, iter->dev->name, &dev->adj_list.lower); } } void netdev_adjacent_rename_links(struct net_device *dev, char *oldname) { struct netdev_adjacent *iter; struct net *net = dev_net(dev); list_for_each_entry(iter, &dev->adj_list.upper, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_del(iter->dev, oldname, &iter->dev->adj_list.lower); netdev_adjacent_sysfs_add(iter->dev, dev, &iter->dev->adj_list.lower); } list_for_each_entry(iter, &dev->adj_list.lower, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_del(iter->dev, oldname, &iter->dev->adj_list.upper); netdev_adjacent_sysfs_add(iter->dev, dev, &iter->dev->adj_list.upper); } } void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev) { struct netdev_adjacent *lower; if (!lower_dev) return NULL; lower = __netdev_find_adj(lower_dev, &dev->adj_list.lower); if (!lower) return NULL; return lower->private; } EXPORT_SYMBOL(netdev_lower_dev_get_private); /** * netdev_lower_state_changed - Dispatch event about lower device state change * @lower_dev: device * @lower_state_info: state to dispatch * * Send NETDEV_CHANGELOWERSTATE to netdev notifiers with info. * The caller must hold the RTNL lock. */ void netdev_lower_state_changed(struct net_device *lower_dev, void *lower_state_info) { struct netdev_notifier_changelowerstate_info changelowerstate_info = { .info.dev = lower_dev, }; ASSERT_RTNL(); changelowerstate_info.lower_state_info = lower_state_info; call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE, &changelowerstate_info.info); } EXPORT_SYMBOL(netdev_lower_state_changed); static void dev_change_rx_flags(struct net_device *dev, int flags) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_change_rx_flags) ops->ndo_change_rx_flags(dev, flags); } static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify) { unsigned int old_flags = dev->flags; kuid_t uid; kgid_t gid; ASSERT_RTNL(); dev->flags |= IFF_PROMISC; dev->promiscuity += inc; if (dev->promiscuity == 0) { /* * Avoid overflow. * If inc causes overflow, untouch promisc and return error. */ if (inc < 0) dev->flags &= ~IFF_PROMISC; else { dev->promiscuity -= inc; netdev_warn(dev, "promiscuity touches roof, set promiscuity failed. promiscuity feature of device might be broken.\n"); return -EOVERFLOW; } } if (dev->flags != old_flags) { pr_info("device %s %s promiscuous mode\n", dev->name, dev->flags & IFF_PROMISC ? "entered" : "left"); if (audit_enabled) { current_uid_gid(&uid, &gid); audit_log(audit_context(), GFP_ATOMIC, AUDIT_ANOM_PROMISCUOUS, "dev=%s prom=%d old_prom=%d auid=%u uid=%u gid=%u ses=%u", dev->name, (dev->flags & IFF_PROMISC), (old_flags & IFF_PROMISC), from_kuid(&init_user_ns, audit_get_loginuid(current)), from_kuid(&init_user_ns, uid), from_kgid(&init_user_ns, gid), audit_get_sessionid(current)); } dev_change_rx_flags(dev, IFF_PROMISC); } if (notify) __dev_notify_flags(dev, old_flags, IFF_PROMISC); return 0; } /** * dev_set_promiscuity - update promiscuity count on a device * @dev: device * @inc: modifier * * Add or remove promiscuity from a device. While the count in the device * remains above zero the interface remains promiscuous. Once it hits zero * the device reverts back to normal filtering operation. A negative inc * value is used to drop promiscuity on the device. * Return 0 if successful or a negative errno code on error. */ int dev_set_promiscuity(struct net_device *dev, int inc) { unsigned int old_flags = dev->flags; int err; err = __dev_set_promiscuity(dev, inc, true); if (err < 0) return err; if (dev->flags != old_flags) dev_set_rx_mode(dev); return err; } EXPORT_SYMBOL(dev_set_promiscuity); static int __dev_set_allmulti(struct net_device *dev, int inc, bool notify) { unsigned int old_flags = dev->flags, old_gflags = dev->gflags; ASSERT_RTNL(); dev->flags |= IFF_ALLMULTI; dev->allmulti += inc; if (dev->allmulti == 0) { /* * Avoid overflow. * If inc causes overflow, untouch allmulti and return error. */ if (inc < 0) dev->flags &= ~IFF_ALLMULTI; else { dev->allmulti -= inc; netdev_warn(dev, "allmulti touches roof, set allmulti failed. allmulti feature of device might be broken.\n"); return -EOVERFLOW; } } if (dev->flags ^ old_flags) { dev_change_rx_flags(dev, IFF_ALLMULTI); dev_set_rx_mode(dev); if (notify) __dev_notify_flags(dev, old_flags, dev->gflags ^ old_gflags); } return 0; } /** * dev_set_allmulti - update allmulti count on a device * @dev: device * @inc: modifier * * Add or remove reception of all multicast frames to a device. While the * count in the device remains above zero the interface remains listening * to all interfaces. Once it hits zero the device reverts back to normal * filtering operation. A negative @inc value is used to drop the counter * when releasing a resource needing all multicasts. * Return 0 if successful or a negative errno code on error. */ int dev_set_allmulti(struct net_device *dev, int inc) { return __dev_set_allmulti(dev, inc, true); } EXPORT_SYMBOL(dev_set_allmulti); /* * Upload unicast and multicast address lists to device and * configure RX filtering. When the device doesn't support unicast * filtering it is put in promiscuous mode while unicast addresses * are present. */ void __dev_set_rx_mode(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; /* dev_open will call this function so the list will stay sane. */ if (!(dev->flags&IFF_UP)) return; if (!netif_device_present(dev)) return; if (!(dev->priv_flags & IFF_UNICAST_FLT)) { /* Unicast addresses changes may only happen under the rtnl, * therefore calling __dev_set_promiscuity here is safe. */ if (!netdev_uc_empty(dev) && !dev->uc_promisc) { __dev_set_promiscuity(dev, 1, false); dev->uc_promisc = true; } else if (netdev_uc_empty(dev) && dev->uc_promisc) { __dev_set_promiscuity(dev, -1, false); dev->uc_promisc = false; } } if (ops->ndo_set_rx_mode) ops->ndo_set_rx_mode(dev); } void dev_set_rx_mode(struct net_device *dev) { netif_addr_lock_bh(dev); __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); } /** * dev_get_flags - get flags reported to userspace * @dev: device * * Get the combination of flag bits exported through APIs to userspace. */ unsigned int dev_get_flags(const struct net_device *dev) { unsigned int flags; flags = (dev->flags & ~(IFF_PROMISC | IFF_ALLMULTI | IFF_RUNNING | IFF_LOWER_UP | IFF_DORMANT)) | (dev->gflags & (IFF_PROMISC | IFF_ALLMULTI)); if (netif_running(dev)) { if (netif_oper_up(dev)) flags |= IFF_RUNNING; if (netif_carrier_ok(dev)) flags |= IFF_LOWER_UP; if (netif_dormant(dev)) flags |= IFF_DORMANT; } return flags; } EXPORT_SYMBOL(dev_get_flags); int __dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack) { unsigned int old_flags = dev->flags; int ret; ASSERT_RTNL(); /* * Set the flags on our device. */ dev->flags = (flags & (IFF_DEBUG | IFF_NOTRAILERS | IFF_NOARP | IFF_DYNAMIC | IFF_MULTICAST | IFF_PORTSEL | IFF_AUTOMEDIA)) | (dev->flags & (IFF_UP | IFF_VOLATILE | IFF_PROMISC | IFF_ALLMULTI)); /* * Load in the correct multicast list now the flags have changed. */ if ((old_flags ^ flags) & IFF_MULTICAST) dev_change_rx_flags(dev, IFF_MULTICAST); dev_set_rx_mode(dev); /* * Have we downed the interface. We handle IFF_UP ourselves * according to user attempts to set it, rather than blindly * setting it. */ ret = 0; if ((old_flags ^ flags) & IFF_UP) { if (old_flags & IFF_UP) __dev_close(dev); else ret = __dev_open(dev, extack); } if ((flags ^ dev->gflags) & IFF_PROMISC) { int inc = (flags & IFF_PROMISC) ? 1 : -1; unsigned int old_flags = dev->flags; dev->gflags ^= IFF_PROMISC; if (__dev_set_promiscuity(dev, inc, false) >= 0) if (dev->flags != old_flags) dev_set_rx_mode(dev); } /* NOTE: order of synchronization of IFF_PROMISC and IFF_ALLMULTI * is important. Some (broken) drivers set IFF_PROMISC, when * IFF_ALLMULTI is requested not asking us and not reporting. */ if ((flags ^ dev->gflags) & IFF_ALLMULTI) { int inc = (flags & IFF_ALLMULTI) ? 1 : -1; dev->gflags ^= IFF_ALLMULTI; __dev_set_allmulti(dev, inc, false); } return ret; } void __dev_notify_flags(struct net_device *dev, unsigned int old_flags, unsigned int gchanges) { unsigned int changes = dev->flags ^ old_flags; if (gchanges) rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges, GFP_ATOMIC); if (changes & IFF_UP) { if (dev->flags & IFF_UP) call_netdevice_notifiers(NETDEV_UP, dev); else call_netdevice_notifiers(NETDEV_DOWN, dev); } if (dev->flags & IFF_UP && (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) { struct netdev_notifier_change_info change_info = { .info = { .dev = dev, }, .flags_changed = changes, }; call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info); } } /** * dev_change_flags - change device settings * @dev: device * @flags: device state flags * @extack: netlink extended ack * * Change settings on device based state flags. The flags are * in the userspace exported format. */ int dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack) { int ret; unsigned int changes, old_flags = dev->flags, old_gflags = dev->gflags; ret = __dev_change_flags(dev, flags, extack); if (ret < 0) return ret; changes = (old_flags ^ dev->flags) | (old_gflags ^ dev->gflags); __dev_notify_flags(dev, old_flags, changes); return ret; } EXPORT_SYMBOL(dev_change_flags); int __dev_set_mtu(struct net_device *dev, int new_mtu) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_change_mtu) return ops->ndo_change_mtu(dev, new_mtu); /* Pairs with all the lockless reads of dev->mtu in the stack */ WRITE_ONCE(dev->mtu, new_mtu); return 0; } EXPORT_SYMBOL(__dev_set_mtu); int dev_validate_mtu(struct net_device *dev, int new_mtu, struct netlink_ext_ack *extack) { /* MTU must be positive, and in range */ if (new_mtu < 0 || new_mtu < dev->min_mtu) { NL_SET_ERR_MSG(extack, "mtu less than device minimum"); return -EINVAL; } if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) { NL_SET_ERR_MSG(extack, "mtu greater than device maximum"); return -EINVAL; } return 0; } /** * dev_set_mtu_ext - Change maximum transfer unit * @dev: device * @new_mtu: new transfer unit * @extack: netlink extended ack * * Change the maximum transfer size of the network device. */ int dev_set_mtu_ext(struct net_device *dev, int new_mtu, struct netlink_ext_ack *extack) { int err, orig_mtu; if (new_mtu == dev->mtu) return 0; err = dev_validate_mtu(dev, new_mtu, extack); if (err) return err; if (!netif_device_present(dev)) return -ENODEV; err = call_netdevice_notifiers(NETDEV_PRECHANGEMTU, dev); err = notifier_to_errno(err); if (err) return err; orig_mtu = dev->mtu; err = __dev_set_mtu(dev, new_mtu); if (!err) { err = call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev, orig_mtu); err = notifier_to_errno(err); if (err) { /* setting mtu back and notifying everyone again, * so that they have a chance to revert changes. */ __dev_set_mtu(dev, orig_mtu); call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev, new_mtu); } } return err; } int dev_set_mtu(struct net_device *dev, int new_mtu) { struct netlink_ext_ack extack; int err; memset(&extack, 0, sizeof(extack)); err = dev_set_mtu_ext(dev, new_mtu, &extack); if (err && extack._msg) net_err_ratelimited("%s: %s\n", dev->name, extack._msg); return err; } EXPORT_SYMBOL(dev_set_mtu); /** * dev_change_tx_queue_len - Change TX queue length of a netdevice * @dev: device * @new_len: new tx queue length */ int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len) { unsigned int orig_len = dev->tx_queue_len; int res; if (new_len != (unsigned int)new_len) return -ERANGE; if (new_len != orig_len) { dev->tx_queue_len = new_len; res = call_netdevice_notifiers(NETDEV_CHANGE_TX_QUEUE_LEN, dev); res = notifier_to_errno(res); if (res) goto err_rollback; res = dev_qdisc_change_tx_queue_len(dev); if (res) goto err_rollback; } return 0; err_rollback: netdev_err(dev, "refused to change device tx_queue_len\n"); dev->tx_queue_len = orig_len; return res; } /** * dev_set_group - Change group this device belongs to * @dev: device * @new_group: group this device should belong to */ void dev_set_group(struct net_device *dev, int new_group) { dev->group = new_group; } /** * dev_pre_changeaddr_notify - Call NETDEV_PRE_CHANGEADDR. * @dev: device * @addr: new address * @extack: netlink extended ack */ int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr, struct netlink_ext_ack *extack) { struct netdev_notifier_pre_changeaddr_info info = { .info.dev = dev, .info.extack = extack, .dev_addr = addr, }; int rc; rc = call_netdevice_notifiers_info(NETDEV_PRE_CHANGEADDR, &info.info); return notifier_to_errno(rc); } EXPORT_SYMBOL(dev_pre_changeaddr_notify); /** * dev_set_mac_address - Change Media Access Control Address * @dev: device * @sa: new address * @extack: netlink extended ack * * Change the hardware (MAC) address of the device */ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; int err; if (!ops->ndo_set_mac_address) return -EOPNOTSUPP; if (sa->sa_family != dev->type) return -EINVAL; if (!netif_device_present(dev)) return -ENODEV; err = dev_pre_changeaddr_notify(dev, sa->sa_data, extack); if (err) return err; err = ops->ndo_set_mac_address(dev, sa); if (err) return err; dev->addr_assign_type = NET_ADDR_SET; call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); add_device_randomness(dev->dev_addr, dev->addr_len); return 0; } EXPORT_SYMBOL(dev_set_mac_address); static DECLARE_RWSEM(dev_addr_sem); int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa, struct netlink_ext_ack *extack) { int ret; down_write(&dev_addr_sem); ret = dev_set_mac_address(dev, sa, extack); up_write(&dev_addr_sem); return ret; } EXPORT_SYMBOL(dev_set_mac_address_user); int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name) { size_t size = sizeof(sa->sa_data); struct net_device *dev; int ret = 0; down_read(&dev_addr_sem); rcu_read_lock(); dev = dev_get_by_name_rcu(net, dev_name); if (!dev) { ret = -ENODEV; goto unlock; } if (!dev->addr_len) memset(sa->sa_data, 0, size); else memcpy(sa->sa_data, dev->dev_addr, min_t(size_t, size, dev->addr_len)); sa->sa_family = dev->type; unlock: rcu_read_unlock(); up_read(&dev_addr_sem); return ret; } EXPORT_SYMBOL(dev_get_mac_address); /** * dev_change_carrier - Change device carrier * @dev: device * @new_carrier: new value * * Change device carrier */ int dev_change_carrier(struct net_device *dev, bool new_carrier) { const struct net_device_ops *ops = dev->netdev_ops; if (!ops->ndo_change_carrier) return -EOPNOTSUPP; if (!netif_device_present(dev)) return -ENODEV; return ops->ndo_change_carrier(dev, new_carrier); } /** * dev_get_phys_port_id - Get device physical port ID * @dev: device * @ppid: port ID * * Get device physical port ID */ int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_item_id *ppid) { const struct net_device_ops *ops = dev->netdev_ops; if (!ops->ndo_get_phys_port_id) return -EOPNOTSUPP; return ops->ndo_get_phys_port_id(dev, ppid); } /** * dev_get_phys_port_name - Get device physical port name * @dev: device * @name: port name * @len: limit of bytes to copy to name * * Get device physical port name */ int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len) { const struct net_device_ops *ops = dev->netdev_ops; int err; if (ops->ndo_get_phys_port_name) { err = ops->ndo_get_phys_port_name(dev, name, len); if (err != -EOPNOTSUPP) return err; } return devlink_compat_phys_port_name_get(dev, name, len); } /** * dev_get_port_parent_id - Get the device's port parent identifier * @dev: network device * @ppid: pointer to a storage for the port's parent identifier * @recurse: allow/disallow recursion to lower devices * * Get the devices's port parent identifier */ int dev_get_port_parent_id(struct net_device *dev, struct netdev_phys_item_id *ppid, bool recurse) { const struct net_device_ops *ops = dev->netdev_ops; struct netdev_phys_item_id first = { }; struct net_device *lower_dev; struct list_head *iter; int err; if (ops->ndo_get_port_parent_id) { err = ops->ndo_get_port_parent_id(dev, ppid); if (err != -EOPNOTSUPP) return err; } err = devlink_compat_switch_id_get(dev, ppid); if (!recurse || err != -EOPNOTSUPP) return err; netdev_for_each_lower_dev(dev, lower_dev, iter) { err = dev_get_port_parent_id(lower_dev, ppid, true); if (err) break; if (!first.id_len) first = *ppid; else if (memcmp(&first, ppid, sizeof(*ppid))) return -EOPNOTSUPP; } return err; } EXPORT_SYMBOL(dev_get_port_parent_id); /** * netdev_port_same_parent_id - Indicate if two network devices have * the same port parent identifier * @a: first network device * @b: second network device */ bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b) { struct netdev_phys_item_id a_id = { }; struct netdev_phys_item_id b_id = { }; if (dev_get_port_parent_id(a, &a_id, true) || dev_get_port_parent_id(b, &b_id, true)) return false; return netdev_phys_item_id_same(&a_id, &b_id); } EXPORT_SYMBOL(netdev_port_same_parent_id); /** * dev_change_proto_down - set carrier according to proto_down. * * @dev: device * @proto_down: new value */ int dev_change_proto_down(struct net_device *dev, bool proto_down) { if (!(dev->priv_flags & IFF_CHANGE_PROTO_DOWN)) return -EOPNOTSUPP; if (!netif_device_present(dev)) return -ENODEV; if (proto_down) netif_carrier_off(dev); else netif_carrier_on(dev); dev->proto_down = proto_down; return 0; } /** * dev_change_proto_down_reason - proto down reason * * @dev: device * @mask: proto down mask * @value: proto down value */ void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask, u32 value) { int b; if (!mask) { dev->proto_down_reason = value; } else { for_each_set_bit(b, &mask, 32) { if (value & (1 << b)) dev->proto_down_reason |= BIT(b); else dev->proto_down_reason &= ~BIT(b); } } } struct bpf_xdp_link { struct bpf_link link; struct net_device *dev; /* protected by rtnl_lock, no refcnt held */ int flags; }; static enum bpf_xdp_mode dev_xdp_mode(struct net_device *dev, u32 flags) { if (flags & XDP_FLAGS_HW_MODE) return XDP_MODE_HW; if (flags & XDP_FLAGS_DRV_MODE) return XDP_MODE_DRV; if (flags & XDP_FLAGS_SKB_MODE) return XDP_MODE_SKB; return dev->netdev_ops->ndo_bpf ? XDP_MODE_DRV : XDP_MODE_SKB; } static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode) { switch (mode) { case XDP_MODE_SKB: return generic_xdp_install; case XDP_MODE_DRV: case XDP_MODE_HW: return dev->netdev_ops->ndo_bpf; default: return NULL; } } static struct bpf_xdp_link *dev_xdp_link(struct net_device *dev, enum bpf_xdp_mode mode) { return dev->xdp_state[mode].link; } static struct bpf_prog *dev_xdp_prog(struct net_device *dev, enum bpf_xdp_mode mode) { struct bpf_xdp_link *link = dev_xdp_link(dev, mode); if (link) return link->link.prog; return dev->xdp_state[mode].prog; } u8 dev_xdp_prog_count(struct net_device *dev) { u8 count = 0; int i; for (i = 0; i < __MAX_XDP_MODE; i++) if (dev->xdp_state[i].prog || dev->xdp_state[i].link) count++; return count; } EXPORT_SYMBOL_GPL(dev_xdp_prog_count); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode) { struct bpf_prog *prog = dev_xdp_prog(dev, mode); return prog ? prog->aux->id : 0; } static void dev_xdp_set_link(struct net_device *dev, enum bpf_xdp_mode mode, struct bpf_xdp_link *link) { dev->xdp_state[mode].link = link; dev->xdp_state[mode].prog = NULL; } static void dev_xdp_set_prog(struct net_device *dev, enum bpf_xdp_mode mode, struct bpf_prog *prog) { dev->xdp_state[mode].link = NULL; dev->xdp_state[mode].prog = prog; } static int dev_xdp_install(struct net_device *dev, enum bpf_xdp_mode mode, bpf_op_t bpf_op, struct netlink_ext_ack *extack, u32 flags, struct bpf_prog *prog) { struct netdev_bpf xdp; int err; memset(&xdp, 0, sizeof(xdp)); xdp.command = mode == XDP_MODE_HW ? XDP_SETUP_PROG_HW : XDP_SETUP_PROG; xdp.extack = extack; xdp.flags = flags; xdp.prog = prog; /* Drivers assume refcnt is already incremented (i.e, prog pointer is * "moved" into driver), so they don't increment it on their own, but * they do decrement refcnt when program is detached or replaced. * Given net_device also owns link/prog, we need to bump refcnt here * to prevent drivers from underflowing it. */ if (prog) bpf_prog_inc(prog); err = bpf_op(dev, &xdp); if (err) { if (prog) bpf_prog_put(prog); return err; } if (mode != XDP_MODE_HW) bpf_prog_change_xdp(dev_xdp_prog(dev, mode), prog); return 0; } static void dev_xdp_uninstall(struct net_device *dev) { struct bpf_xdp_link *link; struct bpf_prog *prog; enum bpf_xdp_mode mode; bpf_op_t bpf_op; ASSERT_RTNL(); for (mode = XDP_MODE_SKB; mode < __MAX_XDP_MODE; mode++) { prog = dev_xdp_prog(dev, mode); if (!prog) continue; bpf_op = dev_xdp_bpf_op(dev, mode); if (!bpf_op) continue; WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL)); /* auto-detach link from net device */ link = dev_xdp_link(dev, mode); if (link) link->dev = NULL; else bpf_prog_put(prog); dev_xdp_set_link(dev, mode, NULL); } } static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack, struct bpf_xdp_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog, u32 flags) { unsigned int num_modes = hweight32(flags & XDP_FLAGS_MODES); struct bpf_prog *cur_prog; struct net_device *upper; struct list_head *iter; enum bpf_xdp_mode mode; bpf_op_t bpf_op; int err; ASSERT_RTNL(); /* either link or prog attachment, never both */ if (link && (new_prog || old_prog)) return -EINVAL; /* link supports only XDP mode flags */ if (link && (flags & ~XDP_FLAGS_MODES)) { NL_SET_ERR_MSG(extack, "Invalid XDP flags for BPF link attachment"); return -EINVAL; } /* just one XDP mode bit should be set, zero defaults to drv/skb mode */ if (num_modes > 1) { NL_SET_ERR_MSG(extack, "Only one XDP mode flag can be set"); return -EINVAL; } /* avoid ambiguity if offload + drv/skb mode progs are both loaded */ if (!num_modes && dev_xdp_prog_count(dev) > 1) { NL_SET_ERR_MSG(extack, "More than one program loaded, unset mode is ambiguous"); return -EINVAL; } /* old_prog != NULL implies XDP_FLAGS_REPLACE is set */ if (old_prog && !(flags & XDP_FLAGS_REPLACE)) { NL_SET_ERR_MSG(extack, "XDP_FLAGS_REPLACE is not specified"); return -EINVAL; } mode = dev_xdp_mode(dev, flags); /* can't replace attached link */ if (dev_xdp_link(dev, mode)) { NL_SET_ERR_MSG(extack, "Can't replace active BPF XDP link"); return -EBUSY; } /* don't allow if an upper device already has a program */ netdev_for_each_upper_dev_rcu(dev, upper, iter) { if (dev_xdp_prog_count(upper) > 0) { NL_SET_ERR_MSG(extack, "Cannot attach when an upper device already has a program"); return -EEXIST; } } cur_prog = dev_xdp_prog(dev, mode); /* can't replace attached prog with link */ if (link && cur_prog) { NL_SET_ERR_MSG(extack, "Can't replace active XDP program with BPF link"); return -EBUSY; } if ((flags & XDP_FLAGS_REPLACE) && cur_prog != old_prog) { NL_SET_ERR_MSG(extack, "Active program does not match expected"); return -EEXIST; } /* put effective new program into new_prog */ if (link) new_prog = link->link.prog; if (new_prog) { bool offload = mode == XDP_MODE_HW; enum bpf_xdp_mode other_mode = mode == XDP_MODE_SKB ? XDP_MODE_DRV : XDP_MODE_SKB; if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && cur_prog) { NL_SET_ERR_MSG(extack, "XDP program already attached"); return -EBUSY; } if (!offload && dev_xdp_prog(dev, other_mode)) { NL_SET_ERR_MSG(extack, "Native and generic XDP can't be active at the same time"); return -EEXIST; } if (!offload && bpf_prog_is_dev_bound(new_prog->aux)) { NL_SET_ERR_MSG(extack, "Using device-bound program without HW_MODE flag is not supported"); return -EINVAL; } if (new_prog->expected_attach_type == BPF_XDP_DEVMAP) { NL_SET_ERR_MSG(extack, "BPF_XDP_DEVMAP programs can not be attached to a device"); return -EINVAL; } if (new_prog->expected_attach_type == BPF_XDP_CPUMAP) { NL_SET_ERR_MSG(extack, "BPF_XDP_CPUMAP programs can not be attached to a device"); return -EINVAL; } } /* don't call drivers if the effective program didn't change */ if (new_prog != cur_prog) { bpf_op = dev_xdp_bpf_op(dev, mode); if (!bpf_op) { NL_SET_ERR_MSG(extack, "Underlying driver does not support XDP in native mode"); return -EOPNOTSUPP; } err = dev_xdp_install(dev, mode, bpf_op, extack, flags, new_prog); if (err) return err; } if (link) dev_xdp_set_link(dev, mode, link); else dev_xdp_set_prog(dev, mode, new_prog); if (cur_prog) bpf_prog_put(cur_prog); return 0; } static int dev_xdp_attach_link(struct net_device *dev, struct netlink_ext_ack *extack, struct bpf_xdp_link *link) { return dev_xdp_attach(dev, extack, link, NULL, NULL, link->flags); } static int dev_xdp_detach_link(struct net_device *dev, struct netlink_ext_ack *extack, struct bpf_xdp_link *link) { enum bpf_xdp_mode mode; bpf_op_t bpf_op; ASSERT_RTNL(); mode = dev_xdp_mode(dev, link->flags); if (dev_xdp_link(dev, mode) != link) return -EINVAL; bpf_op = dev_xdp_bpf_op(dev, mode); WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL)); dev_xdp_set_link(dev, mode, NULL); return 0; } static void bpf_xdp_link_release(struct bpf_link *link) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); rtnl_lock(); /* if racing with net_device's tear down, xdp_link->dev might be * already NULL, in which case link was already auto-detached */ if (xdp_link->dev) { WARN_ON(dev_xdp_detach_link(xdp_link->dev, NULL, xdp_link)); xdp_link->dev = NULL; } rtnl_unlock(); } static int bpf_xdp_link_detach(struct bpf_link *link) { bpf_xdp_link_release(link); return 0; } static void bpf_xdp_link_dealloc(struct bpf_link *link) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); kfree(xdp_link); } static void bpf_xdp_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); u32 ifindex = 0; rtnl_lock(); if (xdp_link->dev) ifindex = xdp_link->dev->ifindex; rtnl_unlock(); seq_printf(seq, "ifindex:\t%u\n", ifindex); } static int bpf_xdp_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); u32 ifindex = 0; rtnl_lock(); if (xdp_link->dev) ifindex = xdp_link->dev->ifindex; rtnl_unlock(); info->xdp.ifindex = ifindex; return 0; } static int bpf_xdp_link_update(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); enum bpf_xdp_mode mode; bpf_op_t bpf_op; int err = 0; rtnl_lock(); /* link might have been auto-released already, so fail */ if (!xdp_link->dev) { err = -ENOLINK; goto out_unlock; } if (old_prog && link->prog != old_prog) { err = -EPERM; goto out_unlock; } old_prog = link->prog; if (old_prog->type != new_prog->type || old_prog->expected_attach_type != new_prog->expected_attach_type) { err = -EINVAL; goto out_unlock; } if (old_prog == new_prog) { /* no-op, don't disturb drivers */ bpf_prog_put(new_prog); goto out_unlock; } mode = dev_xdp_mode(xdp_link->dev, xdp_link->flags); bpf_op = dev_xdp_bpf_op(xdp_link->dev, mode); err = dev_xdp_install(xdp_link->dev, mode, bpf_op, NULL, xdp_link->flags, new_prog); if (err) goto out_unlock; old_prog = xchg(&link->prog, new_prog); bpf_prog_put(old_prog); out_unlock: rtnl_unlock(); return err; } static const struct bpf_link_ops bpf_xdp_link_lops = { .release = bpf_xdp_link_release, .dealloc = bpf_xdp_link_dealloc, .detach = bpf_xdp_link_detach, .show_fdinfo = bpf_xdp_link_show_fdinfo, .fill_link_info = bpf_xdp_link_fill_link_info, .update_prog = bpf_xdp_link_update, }; int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct net *net = current->nsproxy->net_ns; struct bpf_link_primer link_primer; struct bpf_xdp_link *link; struct net_device *dev; int err, fd; rtnl_lock(); dev = dev_get_by_index(net, attr->link_create.target_ifindex); if (!dev) { rtnl_unlock(); return -EINVAL; } link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; goto unlock; } bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog); link->dev = dev; link->flags = attr->link_create.flags; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); goto unlock; } err = dev_xdp_attach_link(dev, NULL, link); rtnl_unlock(); if (err) { link->dev = NULL; bpf_link_cleanup(&link_primer); goto out_put_dev; } fd = bpf_link_settle(&link_primer); /* link itself doesn't hold dev's refcnt to not complicate shutdown */ dev_put(dev); return fd; unlock: rtnl_unlock(); out_put_dev: dev_put(dev); return err; } /** * dev_change_xdp_fd - set or clear a bpf program for a device rx path * @dev: device * @extack: netlink extended ack * @fd: new program fd or negative value to clear * @expected_fd: old program fd that userspace expects to replace or clear * @flags: xdp-related flags * * Set or clear a bpf program for a device */ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, int expected_fd, u32 flags) { enum bpf_xdp_mode mode = dev_xdp_mode(dev, flags); struct bpf_prog *new_prog = NULL, *old_prog = NULL; int err; ASSERT_RTNL(); if (fd >= 0) { new_prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP, mode != XDP_MODE_SKB); if (IS_ERR(new_prog)) return PTR_ERR(new_prog); } if (expected_fd >= 0) { old_prog = bpf_prog_get_type_dev(expected_fd, BPF_PROG_TYPE_XDP, mode != XDP_MODE_SKB); if (IS_ERR(old_prog)) { err = PTR_ERR(old_prog); old_prog = NULL; goto err_out; } } err = dev_xdp_attach(dev, extack, NULL, new_prog, old_prog, flags); err_out: if (err && new_prog) bpf_prog_put(new_prog); if (old_prog) bpf_prog_put(old_prog); return err; } /** * dev_new_index - allocate an ifindex * @net: the applicable net namespace * * Returns a suitable unique value for a new device interface * number. The caller must hold the rtnl semaphore or the * dev_base_lock to be sure it remains unique. */ static int dev_new_index(struct net *net) { int ifindex = net->ifindex; for (;;) { if (++ifindex <= 0) ifindex = 1; if (!__dev_get_by_index(net, ifindex)) return net->ifindex = ifindex; } } /* Delayed registration/unregisteration */ LIST_HEAD(net_todo_list); DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); static void net_set_todo(struct net_device *dev) { list_add_tail(&dev->todo_list, &net_todo_list); atomic_inc(&dev_net(dev)->dev_unreg_count); } static netdev_features_t netdev_sync_upper_features(struct net_device *lower, struct net_device *upper, netdev_features_t features) { netdev_features_t upper_disables = NETIF_F_UPPER_DISABLES; netdev_features_t feature; int feature_bit; for_each_netdev_feature(upper_disables, feature_bit) { feature = __NETIF_F_BIT(feature_bit); if (!(upper->wanted_features & feature) && (features & feature)) { netdev_dbg(lower, "Dropping feature %pNF, upper dev %s has it off.\n", &feature, upper->name); features &= ~feature; } } return features; } static void netdev_sync_lower_features(struct net_device *upper, struct net_device *lower, netdev_features_t features) { netdev_features_t upper_disables = NETIF_F_UPPER_DISABLES; netdev_features_t feature; int feature_bit; for_each_netdev_feature(upper_disables, feature_bit) { feature = __NETIF_F_BIT(feature_bit); if (!(features & feature) && (lower->features & feature)) { netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n", &feature, lower->name); lower->wanted_features &= ~feature; __netdev_update_features(lower); if (unlikely(lower->features & feature)) netdev_WARN(upper, "failed to disable %pNF on %s!\n", &feature, lower->name); else netdev_features_change(lower); } } } static netdev_features_t netdev_fix_features(struct net_device *dev, netdev_features_t features) { /* Fix illegal checksum combinations */ if ((features & NETIF_F_HW_CSUM) && (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { netdev_warn(dev, "mixed HW and IP checksum settings.\n"); features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); } /* TSO requires that SG is present as well. */ if ((features & NETIF_F_ALL_TSO) && !(features & NETIF_F_SG)) { netdev_dbg(dev, "Dropping TSO features since no SG feature.\n"); features &= ~NETIF_F_ALL_TSO; } if ((features & NETIF_F_TSO) && !(features & NETIF_F_HW_CSUM) && !(features & NETIF_F_IP_CSUM)) { netdev_dbg(dev, "Dropping TSO features since no CSUM feature.\n"); features &= ~NETIF_F_TSO; features &= ~NETIF_F_TSO_ECN; } if ((features & NETIF_F_TSO6) && !(features & NETIF_F_HW_CSUM) && !(features & NETIF_F_IPV6_CSUM)) { netdev_dbg(dev, "Dropping TSO6 features since no CSUM feature.\n"); features &= ~NETIF_F_TSO6; } /* TSO with IPv4 ID mangling requires IPv4 TSO be enabled */ if ((features & NETIF_F_TSO_MANGLEID) && !(features & NETIF_F_TSO)) features &= ~NETIF_F_TSO_MANGLEID; /* TSO ECN requires that TSO is present as well. */ if ((features & NETIF_F_ALL_TSO) == NETIF_F_TSO_ECN) features &= ~NETIF_F_TSO_ECN; /* Software GSO depends on SG. */ if ((features & NETIF_F_GSO) && !(features & NETIF_F_SG)) { netdev_dbg(dev, "Dropping NETIF_F_GSO since no SG feature.\n"); features &= ~NETIF_F_GSO; } /* GSO partial features require GSO partial be set */ if ((features & dev->gso_partial_features) && !(features & NETIF_F_GSO_PARTIAL)) { netdev_dbg(dev, "Dropping partially supported GSO features since no GSO partial.\n"); features &= ~dev->gso_partial_features; } if (!(features & NETIF_F_RXCSUM)) { /* NETIF_F_GRO_HW implies doing RXCSUM since every packet * successfully merged by hardware must also have the * checksum verified by hardware. If the user does not * want to enable RXCSUM, logically, we should disable GRO_HW. */ if (features & NETIF_F_GRO_HW) { netdev_dbg(dev, "Dropping NETIF_F_GRO_HW since no RXCSUM feature.\n"); features &= ~NETIF_F_GRO_HW; } } /* LRO/HW-GRO features cannot be combined with RX-FCS */ if (features & NETIF_F_RXFCS) { if (features & NETIF_F_LRO) { netdev_dbg(dev, "Dropping LRO feature since RX-FCS is requested.\n"); features &= ~NETIF_F_LRO; } if (features & NETIF_F_GRO_HW) { netdev_dbg(dev, "Dropping HW-GRO feature since RX-FCS is requested.\n"); features &= ~NETIF_F_GRO_HW; } } if ((features & NETIF_F_GRO_HW) && (features & NETIF_F_LRO)) { netdev_dbg(dev, "Dropping LRO feature since HW-GRO is requested.\n"); features &= ~NETIF_F_LRO; } if (features & NETIF_F_HW_TLS_TX) { bool ip_csum = (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) == (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); bool hw_csum = features & NETIF_F_HW_CSUM; if (!ip_csum && !hw_csum) { netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n"); features &= ~NETIF_F_HW_TLS_TX; } } if ((features & NETIF_F_HW_TLS_RX) && !(features & NETIF_F_RXCSUM)) { netdev_dbg(dev, "Dropping TLS RX HW offload feature since no RXCSUM feature.\n"); features &= ~NETIF_F_HW_TLS_RX; } return features; } int __netdev_update_features(struct net_device *dev) { struct net_device *upper, *lower; netdev_features_t features; struct list_head *iter; int err = -1; ASSERT_RTNL(); features = netdev_get_wanted_features(dev); if (dev->netdev_ops->ndo_fix_features) features = dev->netdev_ops->ndo_fix_features(dev, features); /* driver might be less strict about feature dependencies */ features = netdev_fix_features(dev, features); /* some features can't be enabled if they're off on an upper device */ netdev_for_each_upper_dev_rcu(dev, upper, iter) features = netdev_sync_upper_features(dev, upper, features); if (dev->features == features) goto sync_lower; netdev_dbg(dev, "Features changed: %pNF -> %pNF\n", &dev->features, &features); if (dev->netdev_ops->ndo_set_features) err = dev->netdev_ops->ndo_set_features(dev, features); else err = 0; if (unlikely(err < 0)) { netdev_err(dev, "set_features() failed (%d); wanted %pNF, left %pNF\n", err, &features, &dev->features); /* return non-0 since some features might have changed and * it's better to fire a spurious notification than miss it */ return -1; } sync_lower: /* some features must be disabled on lower devices when disabled * on an upper device (think: bonding master or bridge) */ netdev_for_each_lower_dev(dev, lower, iter) netdev_sync_lower_features(dev, lower, features); if (!err) { netdev_features_t diff = features ^ dev->features; if (diff & NETIF_F_RX_UDP_TUNNEL_PORT) { /* udp_tunnel_{get,drop}_rx_info both need * NETIF_F_RX_UDP_TUNNEL_PORT enabled on the * device, or they won't do anything. * Thus we need to update dev->features * *before* calling udp_tunnel_get_rx_info, * but *after* calling udp_tunnel_drop_rx_info. */ if (features & NETIF_F_RX_UDP_TUNNEL_PORT) { dev->features = features; udp_tunnel_get_rx_info(dev); } else { udp_tunnel_drop_rx_info(dev); } } if (diff & NETIF_F_HW_VLAN_CTAG_FILTER) { if (features & NETIF_F_HW_VLAN_CTAG_FILTER) { dev->features = features; err |= vlan_get_rx_ctag_filter_info(dev); } else { vlan_drop_rx_ctag_filter_info(dev); } } if (diff & NETIF_F_HW_VLAN_STAG_FILTER) { if (features & NETIF_F_HW_VLAN_STAG_FILTER) { dev->features = features; err |= vlan_get_rx_stag_filter_info(dev); } else { vlan_drop_rx_stag_filter_info(dev); } } dev->features = features; } return err < 0 ? 0 : 1; } /** * netdev_update_features - recalculate device features * @dev: the device to check * * Recalculate dev->features set and send notifications if it * has changed. Should be called after driver or hardware dependent * conditions might have changed that influence the features. */ void netdev_update_features(struct net_device *dev) { if (__netdev_update_features(dev)) netdev_features_change(dev); } EXPORT_SYMBOL(netdev_update_features); /** * netdev_change_features - recalculate device features * @dev: the device to check * * Recalculate dev->features set and send notifications even * if they have not changed. Should be called instead of * netdev_update_features() if also dev->vlan_features might * have changed to allow the changes to be propagated to stacked * VLAN devices. */ void netdev_change_features(struct net_device *dev) { __netdev_update_features(dev); netdev_features_change(dev); } EXPORT_SYMBOL(netdev_change_features); /** * netif_stacked_transfer_operstate - transfer operstate * @rootdev: the root or lower level device to transfer state from * @dev: the device to transfer operstate to * * Transfer operational state from root to device. This is normally * called when a stacking relationship exists between the root * device and the device(a leaf device). */ void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev) { if (rootdev->operstate == IF_OPER_DORMANT) netif_dormant_on(dev); else netif_dormant_off(dev); if (rootdev->operstate == IF_OPER_TESTING) netif_testing_on(dev); else netif_testing_off(dev); if (netif_carrier_ok(rootdev)) netif_carrier_on(dev); else netif_carrier_off(dev); } EXPORT_SYMBOL(netif_stacked_transfer_operstate); static int netif_alloc_rx_queues(struct net_device *dev) { unsigned int i, count = dev->num_rx_queues; struct netdev_rx_queue *rx; size_t sz = count * sizeof(*rx); int err = 0; BUG_ON(count < 1); rx = kvzalloc(sz, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!rx) return -ENOMEM; dev->_rx = rx; for (i = 0; i < count; i++) { rx[i].dev = dev; /* XDP RX-queue setup */ err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i, 0); if (err < 0) goto err_rxq_info; } return 0; err_rxq_info: /* Rollback successful reg's and free other resources */ while (i--) xdp_rxq_info_unreg(&rx[i].xdp_rxq); kvfree(dev->_rx); dev->_rx = NULL; return err; } static void netif_free_rx_queues(struct net_device *dev) { unsigned int i, count = dev->num_rx_queues; /* netif_alloc_rx_queues alloc failed, resources have been unreg'ed */ if (!dev->_rx) return; for (i = 0; i < count; i++) xdp_rxq_info_unreg(&dev->_rx[i].xdp_rxq); kvfree(dev->_rx); } static void netdev_init_one_queue(struct net_device *dev, struct netdev_queue *queue, void *_unused) { /* Initialize queue lock */ spin_lock_init(&queue->_xmit_lock); netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); queue->xmit_lock_owner = -1; netdev_queue_numa_node_write(queue, NUMA_NO_NODE); queue->dev = dev; #ifdef CONFIG_BQL dql_init(&queue->dql, HZ); #endif } static void netif_free_tx_queues(struct net_device *dev) { kvfree(dev->_tx); } static int netif_alloc_netdev_queues(struct net_device *dev) { unsigned int count = dev->num_tx_queues; struct netdev_queue *tx; size_t sz = count * sizeof(*tx); if (count < 1 || count > 0xffff) return -EINVAL; tx = kvzalloc(sz, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!tx) return -ENOMEM; dev->_tx = tx; netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL); spin_lock_init(&dev->tx_global_lock); return 0; } void netif_tx_stop_all_queues(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); netif_tx_stop_queue(txq); } } EXPORT_SYMBOL(netif_tx_stop_all_queues); /** * register_netdevice() - register a network device * @dev: device to register * * Take a prepared network device structure and make it externally accessible. * A %NETDEV_REGISTER message is sent to the netdev notifier chain. * Callers must hold the rtnl lock - you may want register_netdev() * instead of this. */ int register_netdevice(struct net_device *dev) { int ret; struct net *net = dev_net(dev); BUILD_BUG_ON(sizeof(netdev_features_t) * BITS_PER_BYTE < NETDEV_FEATURE_COUNT); BUG_ON(dev_boot_phase); ASSERT_RTNL(); might_sleep(); /* When net_device's are persistent, this will be fatal. */ BUG_ON(dev->reg_state != NETREG_UNINITIALIZED); BUG_ON(!net); ret = ethtool_check_ops(dev->ethtool_ops); if (ret) return ret; spin_lock_init(&dev->addr_list_lock); netdev_set_addr_lockdep_class(dev); ret = dev_get_valid_name(net, dev, dev->name); if (ret < 0) goto out; ret = -ENOMEM; dev->name_node = netdev_name_node_head_alloc(dev); if (!dev->name_node) goto out; /* Init, if this function is available */ if (dev->netdev_ops->ndo_init) { ret = dev->netdev_ops->ndo_init(dev); if (ret) { if (ret > 0) ret = -EIO; goto err_free_name; } } if (((dev->hw_features | dev->features) & NETIF_F_HW_VLAN_CTAG_FILTER) && (!dev->netdev_ops->ndo_vlan_rx_add_vid || !dev->netdev_ops->ndo_vlan_rx_kill_vid)) { netdev_WARN(dev, "Buggy VLAN acceleration in driver!\n"); ret = -EINVAL; goto err_uninit; } ret = -EBUSY; if (!dev->ifindex) dev->ifindex = dev_new_index(net); else if (__dev_get_by_index(net, dev->ifindex)) goto err_uninit; /* Transfer changeable features to wanted_features and enable * software offloads (GSO and GRO). */ dev->hw_features |= (NETIF_F_SOFT_FEATURES | NETIF_F_SOFT_FEATURES_OFF); dev->features |= NETIF_F_SOFT_FEATURES; if (dev->udp_tunnel_nic_info) { dev->features |= NETIF_F_RX_UDP_TUNNEL_PORT; dev->hw_features |= NETIF_F_RX_UDP_TUNNEL_PORT; } dev->wanted_features = dev->features & dev->hw_features; if (!(dev->flags & IFF_LOOPBACK)) dev->hw_features |= NETIF_F_NOCACHE_COPY; /* If IPv4 TCP segmentation offload is supported we should also * allow the device to enable segmenting the frame with the option * of ignoring a static IP ID value. This doesn't enable the * feature itself but allows the user to enable it later. */ if (dev->hw_features & NETIF_F_TSO) dev->hw_features |= NETIF_F_TSO_MANGLEID; if (dev->vlan_features & NETIF_F_TSO) dev->vlan_features |= NETIF_F_TSO_MANGLEID; if (dev->mpls_features & NETIF_F_TSO) dev->mpls_features |= NETIF_F_TSO_MANGLEID; if (dev->hw_enc_features & NETIF_F_TSO) dev->hw_enc_features |= NETIF_F_TSO_MANGLEID; /* Make NETIF_F_HIGHDMA inheritable to VLAN devices. */ dev->vlan_features |= NETIF_F_HIGHDMA; /* Make NETIF_F_SG inheritable to tunnel devices. */ dev->hw_enc_features |= NETIF_F_SG | NETIF_F_GSO_PARTIAL; /* Make NETIF_F_SG inheritable to MPLS. */ dev->mpls_features |= NETIF_F_SG; ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev); ret = notifier_to_errno(ret); if (ret) goto err_uninit; ret = netdev_register_kobject(dev); write_lock(&dev_base_lock); dev->reg_state = ret ? NETREG_UNREGISTERED : NETREG_REGISTERED; write_unlock(&dev_base_lock); if (ret) goto err_uninit; __netdev_update_features(dev); /* * Default initial state at registry is that the * device is present. */ set_bit(__LINK_STATE_PRESENT, &dev->state); linkwatch_init_dev(dev); dev_init_scheduler(dev); netdev_hold(dev, &dev->dev_registered_tracker, GFP_KERNEL); list_netdevice(dev); add_device_randomness(dev->dev_addr, dev->addr_len); /* If the device has permanent device address, driver should * set dev_addr and also addr_assign_type should be set to * NET_ADDR_PERM (default value). */ if (dev->addr_assign_type == NET_ADDR_PERM) memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len); /* Notify protocols, that a new device appeared. */ ret = call_netdevice_notifiers(NETDEV_REGISTER, dev); ret = notifier_to_errno(ret); if (ret) { /* Expect explicit free_netdev() on failure */ dev->needs_free_netdev = false; unregister_netdevice_queue(dev, NULL); goto out; } /* * Prevent userspace races by waiting until the network * device is fully setup before sending notifications. */ if (!dev->rtnl_link_ops || dev->rtnl_link_state == RTNL_LINK_INITIALIZED) rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL); out: return ret; err_uninit: if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); if (dev->priv_destructor) dev->priv_destructor(dev); err_free_name: netdev_name_node_free(dev->name_node); goto out; } EXPORT_SYMBOL(register_netdevice); /** * init_dummy_netdev - init a dummy network device for NAPI * @dev: device to init * * This takes a network device structure and initialize the minimum * amount of fields so it can be used to schedule NAPI polls without * registering a full blown interface. This is to be used by drivers * that need to tie several hardware interfaces to a single NAPI * poll scheduler due to HW limitations. */ int init_dummy_netdev(struct net_device *dev) { /* Clear everything. Note we don't initialize spinlocks * are they aren't supposed to be taken by any of the * NAPI code and this dummy netdev is supposed to be * only ever used for NAPI polls */ memset(dev, 0, sizeof(struct net_device)); /* make sure we BUG if trying to hit standard * register/unregister code path */ dev->reg_state = NETREG_DUMMY; /* NAPI wants this */ INIT_LIST_HEAD(&dev->napi_list); /* a dummy interface is started by default */ set_bit(__LINK_STATE_PRESENT, &dev->state); set_bit(__LINK_STATE_START, &dev->state); /* napi_busy_loop stats accounting wants this */ dev_net_set(dev, &init_net); /* Note : We dont allocate pcpu_refcnt for dummy devices, * because users of this 'device' dont need to change * its refcount. */ return 0; } EXPORT_SYMBOL_GPL(init_dummy_netdev); /** * register_netdev - register a network device * @dev: device to register * * Take a completed network device structure and add it to the kernel * interfaces. A %NETDEV_REGISTER message is sent to the netdev notifier * chain. 0 is returned on success. A negative errno code is returned * on a failure to set up the device, or if the name is a duplicate. * * This is a wrapper around register_netdevice that takes the rtnl semaphore * and expands the device name if you passed a format string to * alloc_netdev. */ int register_netdev(struct net_device *dev) { int err; if (rtnl_lock_killable()) return -EINTR; err = register_netdevice(dev); rtnl_unlock(); return err; } EXPORT_SYMBOL(register_netdev); int netdev_refcnt_read(const struct net_device *dev) { #ifdef CONFIG_PCPU_DEV_REFCNT int i, refcnt = 0; for_each_possible_cpu(i) refcnt += *per_cpu_ptr(dev->pcpu_refcnt, i); return refcnt; #else return refcount_read(&dev->dev_refcnt); #endif } EXPORT_SYMBOL(netdev_refcnt_read); int netdev_unregister_timeout_secs __read_mostly = 10; #define WAIT_REFS_MIN_MSECS 1 #define WAIT_REFS_MAX_MSECS 250 /** * netdev_wait_allrefs_any - wait until all references are gone. * @list: list of net_devices to wait on * * This is called when unregistering network devices. * * Any protocol or device that holds a reference should register * for netdevice notification, and cleanup and put back the * reference if they receive an UNREGISTER event. * We can get stuck here if buggy protocols don't correctly * call dev_put. */ static struct net_device *netdev_wait_allrefs_any(struct list_head *list) { unsigned long rebroadcast_time, warning_time; struct net_device *dev; int wait = 0; rebroadcast_time = warning_time = jiffies; list_for_each_entry(dev, list, todo_list) if (netdev_refcnt_read(dev) == 1) return dev; while (true) { if (time_after(jiffies, rebroadcast_time + 1 * HZ)) { rtnl_lock(); /* Rebroadcast unregister notification */ list_for_each_entry(dev, list, todo_list) call_netdevice_notifiers(NETDEV_UNREGISTER, dev); __rtnl_unlock(); rcu_barrier(); rtnl_lock(); list_for_each_entry(dev, list, todo_list) if (test_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) { /* We must not have linkwatch events * pending on unregister. If this * happens, we simply run the queue * unscheduled, resulting in a noop * for this device. */ linkwatch_run_queue(); break; } __rtnl_unlock(); rebroadcast_time = jiffies; } rcu_barrier(); if (!wait) { wait = WAIT_REFS_MIN_MSECS; } else { msleep(wait); wait = min(wait << 1, WAIT_REFS_MAX_MSECS); } list_for_each_entry(dev, list, todo_list) if (netdev_refcnt_read(dev) == 1) return dev; if (time_after(jiffies, warning_time + READ_ONCE(netdev_unregister_timeout_secs) * HZ)) { list_for_each_entry(dev, list, todo_list) { pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n", dev->name, netdev_refcnt_read(dev)); ref_tracker_dir_print(&dev->refcnt_tracker, 10); } warning_time = jiffies; } } } /* The sequence is: * * rtnl_lock(); * ... * register_netdevice(x1); * register_netdevice(x2); * ... * unregister_netdevice(y1); * unregister_netdevice(y2); * ... * rtnl_unlock(); * free_netdev(y1); * free_netdev(y2); * * We are invoked by rtnl_unlock(). * This allows us to deal with problems: * 1) We can delete sysfs objects which invoke hotplug * without deadlocking with linkwatch via keventd. * 2) Since we run with the RTNL semaphore not held, we can sleep * safely in order to wait for the netdev refcnt to drop to zero. * * We must not return until all unregister events added during * the interval the lock was held have been completed. */ void netdev_run_todo(void) { struct net_device *dev, *tmp; struct list_head list; #ifdef CONFIG_LOCKDEP struct list_head unlink_list; list_replace_init(&net_unlink_list, &unlink_list); while (!list_empty(&unlink_list)) { struct net_device *dev = list_first_entry(&unlink_list, struct net_device, unlink_list); list_del_init(&dev->unlink_list); dev->nested_level = dev->lower_level - 1; } #endif /* Snapshot list, allow later requests */ list_replace_init(&net_todo_list, &list); __rtnl_unlock(); /* Wait for rcu callbacks to finish before next phase */ if (!list_empty(&list)) rcu_barrier(); list_for_each_entry_safe(dev, tmp, &list, todo_list) { if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) { netdev_WARN(dev, "run_todo but not unregistering\n"); list_del(&dev->todo_list); continue; } write_lock(&dev_base_lock); dev->reg_state = NETREG_UNREGISTERED; write_unlock(&dev_base_lock); linkwatch_forget_dev(dev); } while (!list_empty(&list)) { dev = netdev_wait_allrefs_any(&list); list_del(&dev->todo_list); /* paranoia */ BUG_ON(netdev_refcnt_read(dev) != 1); BUG_ON(!list_empty(&dev->ptype_all)); BUG_ON(!list_empty(&dev->ptype_specific)); WARN_ON(rcu_access_pointer(dev->ip_ptr)); WARN_ON(rcu_access_pointer(dev->ip6_ptr)); if (dev->priv_destructor) dev->priv_destructor(dev); if (dev->needs_free_netdev) free_netdev(dev); if (atomic_dec_and_test(&dev_net(dev)->dev_unreg_count)) wake_up(&netdev_unregistering_wq); /* Free network device */ kobject_put(&dev->dev.kobj); } } /* Convert net_device_stats to rtnl_link_stats64. rtnl_link_stats64 has * all the same fields in the same order as net_device_stats, with only * the type differing, but rtnl_link_stats64 may have additional fields * at the end for newer counters. */ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, const struct net_device_stats *netdev_stats) { size_t i, n = sizeof(*netdev_stats) / sizeof(atomic_long_t); const atomic_long_t *src = (atomic_long_t *)netdev_stats; u64 *dst = (u64 *)stats64; BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64)); for (i = 0; i < n; i++) dst[i] = (unsigned long)atomic_long_read(&src[i]); /* zero out counters that only exist in rtnl_link_stats64 */ memset((char *)stats64 + n * sizeof(u64), 0, sizeof(*stats64) - n * sizeof(u64)); } EXPORT_SYMBOL(netdev_stats_to_stats64); struct net_device_core_stats __percpu *netdev_core_stats_alloc(struct net_device *dev) { struct net_device_core_stats __percpu *p; p = alloc_percpu_gfp(struct net_device_core_stats, GFP_ATOMIC | __GFP_NOWARN); if (p && cmpxchg(&dev->core_stats, NULL, p)) free_percpu(p); /* This READ_ONCE() pairs with the cmpxchg() above */ return READ_ONCE(dev->core_stats); } EXPORT_SYMBOL(netdev_core_stats_alloc); /** * dev_get_stats - get network device statistics * @dev: device to get statistics from * @storage: place to store stats * * Get network statistics from device. Return @storage. * The device driver may provide its own method by setting * dev->netdev_ops->get_stats64 or dev->netdev_ops->get_stats; * otherwise the internal statistics structure is used. */ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, struct rtnl_link_stats64 *storage) { const struct net_device_ops *ops = dev->netdev_ops; const struct net_device_core_stats __percpu *p; if (ops->ndo_get_stats64) { memset(storage, 0, sizeof(*storage)); ops->ndo_get_stats64(dev, storage); } else if (ops->ndo_get_stats) { netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev)); } else { netdev_stats_to_stats64(storage, &dev->stats); } /* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */ p = READ_ONCE(dev->core_stats); if (p) { const struct net_device_core_stats *core_stats; int i; for_each_possible_cpu(i) { core_stats = per_cpu_ptr(p, i); storage->rx_dropped += READ_ONCE(core_stats->rx_dropped); storage->tx_dropped += READ_ONCE(core_stats->tx_dropped); storage->rx_nohandler += READ_ONCE(core_stats->rx_nohandler); storage->rx_otherhost_dropped += READ_ONCE(core_stats->rx_otherhost_dropped); } } return storage; } EXPORT_SYMBOL(dev_get_stats); /** * dev_fetch_sw_netstats - get per-cpu network device statistics * @s: place to store stats * @netstats: per-cpu network stats to read from * * Read per-cpu network statistics and populate the related fields in @s. */ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, const struct pcpu_sw_netstats __percpu *netstats) { int cpu; for_each_possible_cpu(cpu) { u64 rx_packets, rx_bytes, tx_packets, tx_bytes; const struct pcpu_sw_netstats *stats; unsigned int start; stats = per_cpu_ptr(netstats, cpu); do { start = u64_stats_fetch_begin_irq(&stats->syncp); rx_packets = u64_stats_read(&stats->rx_packets); rx_bytes = u64_stats_read(&stats->rx_bytes); tx_packets = u64_stats_read(&stats->tx_packets); tx_bytes = u64_stats_read(&stats->tx_bytes); } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); s->rx_packets += rx_packets; s->rx_bytes += rx_bytes; s->tx_packets += tx_packets; s->tx_bytes += tx_bytes; } } EXPORT_SYMBOL_GPL(dev_fetch_sw_netstats); /** * dev_get_tstats64 - ndo_get_stats64 implementation * @dev: device to get statistics from * @s: place to store stats * * Populate @s from dev->stats and dev->tstats. Can be used as * ndo_get_stats64() callback. */ void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s) { netdev_stats_to_stats64(s, &dev->stats); dev_fetch_sw_netstats(s, dev->tstats); } EXPORT_SYMBOL_GPL(dev_get_tstats64); struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) { struct netdev_queue *queue = dev_ingress_queue(dev); #ifdef CONFIG_NET_CLS_ACT if (queue) return queue; queue = kzalloc(sizeof(*queue), GFP_KERNEL); if (!queue) return NULL; netdev_init_one_queue(dev, queue, NULL); RCU_INIT_POINTER(queue->qdisc, &noop_qdisc); RCU_INIT_POINTER(queue->qdisc_sleeping, &noop_qdisc); rcu_assign_pointer(dev->ingress_queue, queue); #endif return queue; } static const struct ethtool_ops default_ethtool_ops; void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops) { if (dev->ethtool_ops == &default_ethtool_ops) dev->ethtool_ops = ops; } EXPORT_SYMBOL_GPL(netdev_set_default_ethtool_ops); void netdev_freemem(struct net_device *dev) { char *addr = (char *)dev - dev->padded; kvfree(addr); } /** * alloc_netdev_mqs - allocate network device * @sizeof_priv: size of private data to allocate space for * @name: device name format string * @name_assign_type: origin of device name * @setup: callback to initialize device * @txqs: the number of TX subqueues to allocate * @rxqs: the number of RX subqueues to allocate * * Allocates a struct net_device with private data area for driver use * and performs basic initialization. Also allocates subqueue structs * for each queue on the device. */ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *), unsigned int txqs, unsigned int rxqs) { struct net_device *dev; unsigned int alloc_size; struct net_device *p; BUG_ON(strlen(name) >= sizeof(dev->name)); if (txqs < 1) { pr_err("alloc_netdev: Unable to allocate device with zero queues\n"); return NULL; } if (rxqs < 1) { pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n"); return NULL; } alloc_size = sizeof(struct net_device); if (sizeof_priv) { /* ensure 32-byte alignment of private area */ alloc_size = ALIGN(alloc_size, NETDEV_ALIGN); alloc_size += sizeof_priv; } /* ensure 32-byte alignment of whole construct */ alloc_size += NETDEV_ALIGN - 1; p = kvzalloc(alloc_size, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!p) return NULL; dev = PTR_ALIGN(p, NETDEV_ALIGN); dev->padded = (char *)dev - (char *)p; ref_tracker_dir_init(&dev->refcnt_tracker, 128); #ifdef CONFIG_PCPU_DEV_REFCNT dev->pcpu_refcnt = alloc_percpu(int); if (!dev->pcpu_refcnt) goto free_dev; __dev_hold(dev); #else refcount_set(&dev->dev_refcnt, 1); #endif if (dev_addr_init(dev)) goto free_pcpu; dev_mc_init(dev); dev_uc_init(dev); dev_net_set(dev, &init_net); dev->gso_max_size = GSO_LEGACY_MAX_SIZE; dev->gso_max_segs = GSO_MAX_SEGS; dev->gro_max_size = GRO_LEGACY_MAX_SIZE; dev->tso_max_size = TSO_LEGACY_MAX_SIZE; dev->tso_max_segs = TSO_MAX_SEGS; dev->upper_level = 1; dev->lower_level = 1; #ifdef CONFIG_LOCKDEP dev->nested_level = 0; INIT_LIST_HEAD(&dev->unlink_list); #endif INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); INIT_LIST_HEAD(&dev->close_list); INIT_LIST_HEAD(&dev->link_watch_list); INIT_LIST_HEAD(&dev->adj_list.upper); INIT_LIST_HEAD(&dev->adj_list.lower); INIT_LIST_HEAD(&dev->ptype_all); INIT_LIST_HEAD(&dev->ptype_specific); INIT_LIST_HEAD(&dev->net_notifier_list); #ifdef CONFIG_NET_SCHED hash_init(dev->qdisc_hash); #endif dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; setup(dev); if (!dev->tx_queue_len) { dev->priv_flags |= IFF_NO_QUEUE; dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN; } dev->num_tx_queues = txqs; dev->real_num_tx_queues = txqs; if (netif_alloc_netdev_queues(dev)) goto free_all; dev->num_rx_queues = rxqs; dev->real_num_rx_queues = rxqs; if (netif_alloc_rx_queues(dev)) goto free_all; strcpy(dev->name, name); dev->name_assign_type = name_assign_type; dev->group = INIT_NETDEV_GROUP; if (!dev->ethtool_ops) dev->ethtool_ops = &default_ethtool_ops; nf_hook_netdev_init(dev); return dev; free_all: free_netdev(dev); return NULL; free_pcpu: #ifdef CONFIG_PCPU_DEV_REFCNT free_percpu(dev->pcpu_refcnt); free_dev: #endif netdev_freemem(dev); return NULL; } EXPORT_SYMBOL(alloc_netdev_mqs); /** * free_netdev - free network device * @dev: device * * This function does the last stage of destroying an allocated device * interface. The reference to the device object is released. If this * is the last reference then it will be freed.Must be called in process * context. */ void free_netdev(struct net_device *dev) { struct napi_struct *p, *n; might_sleep(); /* When called immediately after register_netdevice() failed the unwind * handling may still be dismantling the device. Handle that case by * deferring the free. */ if (dev->reg_state == NETREG_UNREGISTERING) { ASSERT_RTNL(); dev->needs_free_netdev = true; return; } netif_free_tx_queues(dev); netif_free_rx_queues(dev); kfree(rcu_dereference_protected(dev->ingress_queue, 1)); /* Flush device addresses */ dev_addr_flush(dev); list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) netif_napi_del(p); ref_tracker_dir_exit(&dev->refcnt_tracker); #ifdef CONFIG_PCPU_DEV_REFCNT free_percpu(dev->pcpu_refcnt); dev->pcpu_refcnt = NULL; #endif free_percpu(dev->core_stats); dev->core_stats = NULL; free_percpu(dev->xdp_bulkq); dev->xdp_bulkq = NULL; /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED) { netdev_freemem(dev); return; } BUG_ON(dev->reg_state != NETREG_UNREGISTERED); dev->reg_state = NETREG_RELEASED; /* will free via device release */ put_device(&dev->dev); } EXPORT_SYMBOL(free_netdev); /** * synchronize_net - Synchronize with packet receive processing * * Wait for packets currently being received to be done. * Does not block later packets from starting. */ void synchronize_net(void) { might_sleep(); if (rtnl_is_locked()) synchronize_rcu_expedited(); else synchronize_rcu(); } EXPORT_SYMBOL(synchronize_net); /** * unregister_netdevice_queue - remove device from the kernel * @dev: device * @head: list * * This function shuts down a device interface and removes it * from the kernel tables. * If head not NULL, device is queued to be unregistered later. * * Callers must hold the rtnl semaphore. You may want * unregister_netdev() instead of this. */ void unregister_netdevice_queue(struct net_device *dev, struct list_head *head) { ASSERT_RTNL(); if (head) { list_move_tail(&dev->unreg_list, head); } else { LIST_HEAD(single); list_add(&dev->unreg_list, &single); unregister_netdevice_many(&single); } } EXPORT_SYMBOL(unregister_netdevice_queue); /** * unregister_netdevice_many - unregister many devices * @head: list of devices * * Note: As most callers use a stack allocated list_head, * we force a list_del() to make sure stack wont be corrupted later. */ void unregister_netdevice_many(struct list_head *head) { struct net_device *dev, *tmp; LIST_HEAD(close_head); BUG_ON(dev_boot_phase); ASSERT_RTNL(); if (list_empty(head)) return; list_for_each_entry_safe(dev, tmp, head, unreg_list) { /* Some devices call without registering * for initialization unwind. Remove those * devices and proceed with the remaining. */ if (dev->reg_state == NETREG_UNINITIALIZED) { pr_debug("unregister_netdevice: device %s/%p never was registered\n", dev->name, dev); WARN_ON(1); list_del(&dev->unreg_list); continue; } dev->dismantle = true; BUG_ON(dev->reg_state != NETREG_REGISTERED); } /* If device is running, close it first. */ list_for_each_entry(dev, head, unreg_list) list_add_tail(&dev->close_list, &close_head); dev_close_many(&close_head, true); list_for_each_entry(dev, head, unreg_list) { /* And unlink it from device chain. */ write_lock(&dev_base_lock); unlist_netdevice(dev, false); dev->reg_state = NETREG_UNREGISTERING; write_unlock(&dev_base_lock); } flush_all_backlogs(); synchronize_net(); list_for_each_entry(dev, head, unreg_list) { struct sk_buff *skb = NULL; /* Shutdown queueing discipline. */ dev_shutdown(dev); dev_xdp_uninstall(dev); netdev_offload_xstats_disable_all(dev); /* Notify protocols, that we are about to destroy * this device. They should clean all the things. */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); if (!dev->rtnl_link_ops || dev->rtnl_link_state == RTNL_LINK_INITIALIZED) skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, GFP_KERNEL, NULL, 0); /* * Flush the unicast and multicast chains */ dev_uc_flush(dev); dev_mc_flush(dev); netdev_name_node_alt_flush(dev); netdev_name_node_free(dev->name_node); if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); if (skb) rtmsg_ifinfo_send(skb, dev, GFP_KERNEL); /* Notifier chain MUST detach us all upper devices. */ WARN_ON(netdev_has_any_upper_dev(dev)); WARN_ON(netdev_has_any_lower_dev(dev)); /* Remove entries from kobject tree */ netdev_unregister_kobject(dev); #ifdef CONFIG_XPS /* Remove XPS queueing entries */ netif_reset_xps_queues_gt(dev, 0); #endif } synchronize_net(); list_for_each_entry(dev, head, unreg_list) { netdev_put(dev, &dev->dev_registered_tracker); net_set_todo(dev); } list_del(head); } EXPORT_SYMBOL(unregister_netdevice_many); /** * unregister_netdev - remove device from the kernel * @dev: device * * This function shuts down a device interface and removes it * from the kernel tables. * * This is just a wrapper for unregister_netdevice that takes * the rtnl semaphore. In general you want to use this and not * unregister_netdevice. */ void unregister_netdev(struct net_device *dev) { rtnl_lock(); unregister_netdevice(dev); rtnl_unlock(); } EXPORT_SYMBOL(unregister_netdev); /** * __dev_change_net_namespace - move device to different nethost namespace * @dev: device * @net: network namespace * @pat: If not NULL name pattern to try if the current device name * is already taken in the destination network namespace. * @new_ifindex: If not zero, specifies device index in the target * namespace. * * This function shuts down a device interface and moves it * to a new network namespace. On success 0 is returned, on * a failure a netagive errno code is returned. * * Callers must hold the rtnl semaphore. */ int __dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat, int new_ifindex) { struct netdev_name_node *name_node; struct net *net_old = dev_net(dev); char new_name[IFNAMSIZ] = {}; int err, new_nsid; ASSERT_RTNL(); /* Don't allow namespace local devices to be moved. */ err = -EINVAL; if (dev->features & NETIF_F_NETNS_LOCAL) goto out; /* Ensure the device has been registrered */ if (dev->reg_state != NETREG_REGISTERED) goto out; /* Get out if there is nothing todo */ err = 0; if (net_eq(net_old, net)) goto out; /* Pick the destination device name, and ensure * we can use it in the destination network namespace. */ err = -EEXIST; if (netdev_name_in_use(net, dev->name)) { /* We get here if we can't use the current device name */ if (!pat) goto out; err = dev_prep_valid_name(net, dev, pat, new_name); if (err < 0) goto out; } /* Check that none of the altnames conflicts. */ err = -EEXIST; netdev_for_each_altname(dev, name_node) if (netdev_name_in_use(net, name_node->name)) goto out; /* Check that new_ifindex isn't used yet. */ err = -EBUSY; if (new_ifindex && __dev_get_by_index(net, new_ifindex)) goto out; /* * And now a mini version of register_netdevice unregister_netdevice. */ /* If device is running close it first. */ dev_close(dev); /* And unlink it from device chain */ unlist_netdevice(dev, true); synchronize_net(); /* Shutdown queueing discipline. */ dev_shutdown(dev); /* Notify protocols, that we are about to destroy * this device. They should clean all the things. * * Note that dev->reg_state stays at NETREG_REGISTERED. * This is wanted because this way 8021q and macvlan know * the device is just moving and can keep their slaves up. */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); rcu_barrier(); new_nsid = peernet2id_alloc(dev_net(dev), net, GFP_KERNEL); /* If there is an ifindex conflict assign a new one */ if (!new_ifindex) { if (__dev_get_by_index(net, dev->ifindex)) new_ifindex = dev_new_index(net); else new_ifindex = dev->ifindex; } rtmsg_ifinfo_newnet(RTM_DELLINK, dev, ~0U, GFP_KERNEL, &new_nsid, new_ifindex); /* * Flush the unicast and multicast chains */ dev_uc_flush(dev); dev_mc_flush(dev); /* Send a netdev-removed uevent to the old namespace */ kobject_uevent(&dev->dev.kobj, KOBJ_REMOVE); netdev_adjacent_del_links(dev); /* Move per-net netdevice notifiers that are following the netdevice */ move_netdevice_notifiers_dev_net(dev, net); /* Actually switch the network namespace */ dev_net_set(dev, net); dev->ifindex = new_ifindex; /* Send a netdev-add uevent to the new namespace */ kobject_uevent(&dev->dev.kobj, KOBJ_ADD); netdev_adjacent_add_links(dev); if (new_name[0]) /* Rename the netdev to prepared name */ strscpy(dev->name, new_name, IFNAMSIZ); /* Fixup kobjects */ err = device_rename(&dev->dev, dev->name); WARN_ON(err); /* Adapt owner in case owning user namespace of target network * namespace is different from the original one. */ err = netdev_change_owner(dev, net_old, net); WARN_ON(err); /* Add the device back in the hashes */ list_netdevice(dev); /* Notify protocols, that a new device appeared. */ call_netdevice_notifiers(NETDEV_REGISTER, dev); /* * Prevent userspace races by waiting until the network * device is fully setup before sending notifications. */ rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL); synchronize_net(); err = 0; out: return err; } EXPORT_SYMBOL_GPL(__dev_change_net_namespace); static int dev_cpu_dead(unsigned int oldcpu) { struct sk_buff **list_skb; struct sk_buff *skb; unsigned int cpu; struct softnet_data *sd, *oldsd, *remsd = NULL; local_irq_disable(); cpu = smp_processor_id(); sd = &per_cpu(softnet_data, cpu); oldsd = &per_cpu(softnet_data, oldcpu); /* Find end of our completion_queue. */ list_skb = &sd->completion_queue; while (*list_skb) list_skb = &(*list_skb)->next; /* Append completion queue from offline CPU. */ *list_skb = oldsd->completion_queue; oldsd->completion_queue = NULL; /* Append output queue from offline CPU. */ if (oldsd->output_queue) { *sd->output_queue_tailp = oldsd->output_queue; sd->output_queue_tailp = oldsd->output_queue_tailp; oldsd->output_queue = NULL; oldsd->output_queue_tailp = &oldsd->output_queue; } /* Append NAPI poll list from offline CPU, with one exception : * process_backlog() must be called by cpu owning percpu backlog. * We properly handle process_queue & input_pkt_queue later. */ while (!list_empty(&oldsd->poll_list)) { struct napi_struct *napi = list_first_entry(&oldsd->poll_list, struct napi_struct, poll_list); list_del_init(&napi->poll_list); if (napi->poll == process_backlog) napi->state = 0; else ____napi_schedule(sd, napi); } raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_enable(); #ifdef CONFIG_RPS remsd = oldsd->rps_ipi_list; oldsd->rps_ipi_list = NULL; #endif /* send out pending IPI's on offline CPU */ net_rps_send_ipi(remsd); /* Process offline CPU's input_pkt_queue */ while ((skb = __skb_dequeue(&oldsd->process_queue))) { netif_rx(skb); input_queue_head_incr(oldsd); } while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) { netif_rx(skb); input_queue_head_incr(oldsd); } return 0; } /** * netdev_increment_features - increment feature set by one * @all: current feature set * @one: new feature set * @mask: mask feature set * * Computes a new feature set after adding a device with feature set * @one to the master device with current feature set @all. Will not * enable anything that is off in @mask. Returns the new feature set. */ netdev_features_t netdev_increment_features(netdev_features_t all, netdev_features_t one, netdev_features_t mask) { if (mask & NETIF_F_HW_CSUM) mask |= NETIF_F_CSUM_MASK; mask |= NETIF_F_VLAN_CHALLENGED; all |= one & (NETIF_F_ONE_FOR_ALL | NETIF_F_CSUM_MASK) & mask; all &= one | ~NETIF_F_ALL_FOR_ALL; /* If one device supports hw checksumming, set for all. */ if (all & NETIF_F_HW_CSUM) all &= ~(NETIF_F_CSUM_MASK & ~NETIF_F_HW_CSUM); return all; } EXPORT_SYMBOL(netdev_increment_features); static struct hlist_head * __net_init netdev_create_hash(void) { int i; struct hlist_head *hash; hash = kmalloc_array(NETDEV_HASHENTRIES, sizeof(*hash), GFP_KERNEL); if (hash != NULL) for (i = 0; i < NETDEV_HASHENTRIES; i++) INIT_HLIST_HEAD(&hash[i]); return hash; } /* Initialize per network namespace state */ static int __net_init netdev_init(struct net *net) { BUILD_BUG_ON(GRO_HASH_BUCKETS > 8 * sizeof_field(struct napi_struct, gro_bitmask)); INIT_LIST_HEAD(&net->dev_base_head); net->dev_name_head = netdev_create_hash(); if (net->dev_name_head == NULL) goto err_name; net->dev_index_head = netdev_create_hash(); if (net->dev_index_head == NULL) goto err_idx; RAW_INIT_NOTIFIER_HEAD(&net->netdev_chain); return 0; err_idx: kfree(net->dev_name_head); err_name: return -ENOMEM; } /** * netdev_drivername - network driver for the device * @dev: network device * * Determine network driver for device. */ const char *netdev_drivername(const struct net_device *dev) { const struct device_driver *driver; const struct device *parent; const char *empty = ""; parent = dev->dev.parent; if (!parent) return empty; driver = parent->driver; if (driver && driver->name) return driver->name; return empty; } static void __netdev_printk(const char *level, const struct net_device *dev, struct va_format *vaf) { if (dev && dev->dev.parent) { dev_printk_emit(level[1] - '0', dev->dev.parent, "%s %s %s%s: %pV", dev_driver_string(dev->dev.parent), dev_name(dev->dev.parent), netdev_name(dev), netdev_reg_state(dev), vaf); } else if (dev) { printk("%s%s%s: %pV", level, netdev_name(dev), netdev_reg_state(dev), vaf); } else { printk("%s(NULL net_device): %pV", level, vaf); } } void netdev_printk(const char *level, const struct net_device *dev, const char *format, ...) { struct va_format vaf; va_list args; va_start(args, format); vaf.fmt = format; vaf.va = &args; __netdev_printk(level, dev, &vaf); va_end(args); } EXPORT_SYMBOL(netdev_printk); #define define_netdev_printk_level(func, level) \ void func(const struct net_device *dev, const char *fmt, ...) \ { \ struct va_format vaf; \ va_list args; \ \ va_start(args, fmt); \ \ vaf.fmt = fmt; \ vaf.va = &args; \ \ __netdev_printk(level, dev, &vaf); \ \ va_end(args); \ } \ EXPORT_SYMBOL(func); define_netdev_printk_level(netdev_emerg, KERN_EMERG); define_netdev_printk_level(netdev_alert, KERN_ALERT); define_netdev_printk_level(netdev_crit, KERN_CRIT); define_netdev_printk_level(netdev_err, KERN_ERR); define_netdev_printk_level(netdev_warn, KERN_WARNING); define_netdev_printk_level(netdev_notice, KERN_NOTICE); define_netdev_printk_level(netdev_info, KERN_INFO); static void __net_exit netdev_exit(struct net *net) { kfree(net->dev_name_head); kfree(net->dev_index_head); if (net != &init_net) WARN_ON_ONCE(!list_empty(&net->dev_base_head)); } static struct pernet_operations __net_initdata netdev_net_ops = { .init = netdev_init, .exit = netdev_exit, }; static void __net_exit default_device_exit_net(struct net *net) { struct netdev_name_node *name_node, *tmp; struct net_device *dev, *aux; /* * Push all migratable network devices back to the * initial network namespace */ ASSERT_RTNL(); for_each_netdev_safe(net, dev, aux) { int err; char fb_name[IFNAMSIZ]; /* Ignore unmoveable devices (i.e. loopback) */ if (dev->features & NETIF_F_NETNS_LOCAL) continue; /* Leave virtual devices for the generic cleanup */ if (dev->rtnl_link_ops && !dev->rtnl_link_ops->netns_refund) continue; /* Push remaining network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); if (netdev_name_in_use(&init_net, fb_name)) snprintf(fb_name, IFNAMSIZ, "dev%%d"); netdev_for_each_altname_safe(dev, name_node, tmp) if (netdev_name_in_use(&init_net, name_node->name)) { netdev_name_node_del(name_node); synchronize_rcu(); __netdev_name_node_alt_destroy(name_node); } err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { pr_emerg("%s: failed to move %s to init_net: %d\n", __func__, dev->name, err); BUG(); } } } static void __net_exit default_device_exit_batch(struct list_head *net_list) { /* At exit all network devices most be removed from a network * namespace. Do this in the reverse order of registration. * Do this across as many network namespaces as possible to * improve batching efficiency. */ struct net_device *dev; struct net *net; LIST_HEAD(dev_kill_list); rtnl_lock(); list_for_each_entry(net, net_list, exit_list) { default_device_exit_net(net); cond_resched(); } list_for_each_entry(net, net_list, exit_list) { for_each_netdev_reverse(net, dev) { if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) dev->rtnl_link_ops->dellink(dev, &dev_kill_list); else unregister_netdevice_queue(dev, &dev_kill_list); } } unregister_netdevice_many(&dev_kill_list); rtnl_unlock(); } static struct pernet_operations __net_initdata default_device_ops = { .exit_batch = default_device_exit_batch, }; /* * Initialize the DEV module. At boot time this walks the device list and * unhooks any devices that fail to initialise (normally hardware not * present) and leaves us with a valid list of present and active devices. * */ /* * This is called single threaded during boot, so no need * to take the rtnl semaphore. */ static int __init net_dev_init(void) { int i, rc = -ENOMEM; BUG_ON(!dev_boot_phase); if (dev_proc_init()) goto out; if (netdev_kobject_init()) goto out; INIT_LIST_HEAD(&ptype_all); for (i = 0; i < PTYPE_HASH_SIZE; i++) INIT_LIST_HEAD(&ptype_base[i]); if (register_pernet_subsys(&netdev_net_ops)) goto out; /* * Initialise the packet receive queues. */ for_each_possible_cpu(i) { struct work_struct *flush = per_cpu_ptr(&flush_works, i); struct softnet_data *sd = &per_cpu(softnet_data, i); INIT_WORK(flush, flush_backlog); skb_queue_head_init(&sd->input_pkt_queue); skb_queue_head_init(&sd->process_queue); #ifdef CONFIG_XFRM_OFFLOAD skb_queue_head_init(&sd->xfrm_backlog); #endif INIT_LIST_HEAD(&sd->poll_list); sd->output_queue_tailp = &sd->output_queue; #ifdef CONFIG_RPS INIT_CSD(&sd->csd, rps_trigger_softirq, sd); sd->cpu = i; #endif INIT_CSD(&sd->defer_csd, trigger_rx_softirq, sd); spin_lock_init(&sd->defer_lock); init_gro_hash(&sd->backlog); sd->backlog.poll = process_backlog; sd->backlog.weight = weight_p; } dev_boot_phase = 0; /* The loopback device is special if any other network devices * is present in a network namespace the loopback device must * be present. Since we now dynamically allocate and free the * loopback device ensure this invariant is maintained by * keeping the loopback device as the first device on the * list of network devices. Ensuring the loopback devices * is the first device that appears and the last network device * that disappears. */ if (register_pernet_device(&loopback_net_ops)) goto out; if (register_pernet_device(&default_device_ops)) goto out; open_softirq(NET_TX_SOFTIRQ, net_tx_action); open_softirq(NET_RX_SOFTIRQ, net_rx_action); rc = cpuhp_setup_state_nocalls(CPUHP_NET_DEV_DEAD, "net/dev:dead", NULL, dev_cpu_dead); WARN_ON(rc < 0); rc = 0; out: return rc; } subsys_initcall(net_dev_init); |
| 6 10 10 1 1 10 10 10 1 7 7 6 1222 1221 151 151 151 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/core/dst_cache.c - dst entry cache * * Copyright (c) 2016 Paolo Abeni <pabeni@redhat.com> */ #include <linux/kernel.h> #include <linux/percpu.h> #include <net/dst_cache.h> #include <net/route.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ip6_fib.h> #endif #include <uapi/linux/in.h> struct dst_cache_pcpu { unsigned long refresh_ts; struct dst_entry *dst; u32 cookie; union { struct in_addr in_saddr; struct in6_addr in6_saddr; }; }; static void dst_cache_per_cpu_dst_set(struct dst_cache_pcpu *dst_cache, struct dst_entry *dst, u32 cookie) { dst_release(dst_cache->dst); if (dst) dst_hold(dst); dst_cache->cookie = cookie; dst_cache->dst = dst; } static struct dst_entry *dst_cache_per_cpu_get(struct dst_cache *dst_cache, struct dst_cache_pcpu *idst) { struct dst_entry *dst; dst = idst->dst; if (!dst) goto fail; /* the cache already hold a dst reference; it can't go away */ dst_hold(dst); if (unlikely(!time_after(idst->refresh_ts, dst_cache->reset_ts) || (dst->obsolete && !dst->ops->check(dst, idst->cookie)))) { dst_cache_per_cpu_dst_set(idst, NULL, 0); dst_release(dst); goto fail; } return dst; fail: idst->refresh_ts = jiffies; return NULL; } struct dst_entry *dst_cache_get(struct dst_cache *dst_cache) { if (!dst_cache->cache) return NULL; return dst_cache_per_cpu_get(dst_cache, this_cpu_ptr(dst_cache->cache)); } EXPORT_SYMBOL_GPL(dst_cache_get); struct rtable *dst_cache_get_ip4(struct dst_cache *dst_cache, __be32 *saddr) { struct dst_cache_pcpu *idst; struct dst_entry *dst; if (!dst_cache->cache) return NULL; idst = this_cpu_ptr(dst_cache->cache); dst = dst_cache_per_cpu_get(dst_cache, idst); if (!dst) return NULL; *saddr = idst->in_saddr.s_addr; return container_of(dst, struct rtable, dst); } EXPORT_SYMBOL_GPL(dst_cache_get_ip4); void dst_cache_set_ip4(struct dst_cache *dst_cache, struct dst_entry *dst, __be32 saddr) { struct dst_cache_pcpu *idst; if (!dst_cache->cache) return; idst = this_cpu_ptr(dst_cache->cache); dst_cache_per_cpu_dst_set(idst, dst, 0); idst->in_saddr.s_addr = saddr; } EXPORT_SYMBOL_GPL(dst_cache_set_ip4); #if IS_ENABLED(CONFIG_IPV6) void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst, const struct in6_addr *saddr) { struct dst_cache_pcpu *idst; if (!dst_cache->cache) return; idst = this_cpu_ptr(dst_cache->cache); dst_cache_per_cpu_dst_set(this_cpu_ptr(dst_cache->cache), dst, rt6_get_cookie((struct rt6_info *)dst)); idst->in6_saddr = *saddr; } EXPORT_SYMBOL_GPL(dst_cache_set_ip6); struct dst_entry *dst_cache_get_ip6(struct dst_cache *dst_cache, struct in6_addr *saddr) { struct dst_cache_pcpu *idst; struct dst_entry *dst; if (!dst_cache->cache) return NULL; idst = this_cpu_ptr(dst_cache->cache); dst = dst_cache_per_cpu_get(dst_cache, idst); if (!dst) return NULL; *saddr = idst->in6_saddr; return dst; } EXPORT_SYMBOL_GPL(dst_cache_get_ip6); #endif int dst_cache_init(struct dst_cache *dst_cache, gfp_t gfp) { dst_cache->cache = alloc_percpu_gfp(struct dst_cache_pcpu, gfp | __GFP_ZERO); if (!dst_cache->cache) return -ENOMEM; dst_cache_reset(dst_cache); return 0; } EXPORT_SYMBOL_GPL(dst_cache_init); void dst_cache_destroy(struct dst_cache *dst_cache) { int i; if (!dst_cache->cache) return; for_each_possible_cpu(i) dst_release(per_cpu_ptr(dst_cache->cache, i)->dst); free_percpu(dst_cache->cache); } EXPORT_SYMBOL_GPL(dst_cache_destroy); void dst_cache_reset_now(struct dst_cache *dst_cache) { int i; if (!dst_cache->cache) return; dst_cache->reset_ts = jiffies; for_each_possible_cpu(i) { struct dst_cache_pcpu *idst = per_cpu_ptr(dst_cache->cache, i); struct dst_entry *dst = idst->dst; idst->cookie = 0; idst->dst = NULL; dst_release(dst); } } EXPORT_SYMBOL_GPL(dst_cache_reset_now); |
| 1803 2327 2326 2236 272 124 248 128 123 1 3 120 2327 266 2327 324 323 324 324 178 183 322 5 229 215 325 200 325 339 339 325 121 178 178 169 121 145 5 173 173 648 645 645 2749 2748 645 645 2133 2133 1804 1805 1804 1803 124 124 192 17 177 169 169 173 173 583 583 2133 1502 1501 1501 2 2 1 320 320 320 1 1 169 169 173 173 583 583 2132 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/core/dev_addr_lists.c - Functions for handling net device lists * Copyright (c) 2010 Jiri Pirko <jpirko@redhat.com> * * This file contains functions for working with unicast, multicast and device * addresses lists. */ #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/export.h> #include <linux/list.h> #include "dev.h" /* * General list handling functions */ static int __hw_addr_insert(struct netdev_hw_addr_list *list, struct netdev_hw_addr *new, int addr_len) { struct rb_node **ins_point = &list->tree.rb_node, *parent = NULL; struct netdev_hw_addr *ha; while (*ins_point) { int diff; ha = rb_entry(*ins_point, struct netdev_hw_addr, node); diff = memcmp(new->addr, ha->addr, addr_len); if (diff == 0) diff = memcmp(&new->type, &ha->type, sizeof(new->type)); parent = *ins_point; if (diff < 0) ins_point = &parent->rb_left; else if (diff > 0) ins_point = &parent->rb_right; else return -EEXIST; } rb_link_node_rcu(&new->node, parent, ins_point); rb_insert_color(&new->node, &list->tree); return 0; } static struct netdev_hw_addr* __hw_addr_create(const unsigned char *addr, int addr_len, unsigned char addr_type, bool global, bool sync) { struct netdev_hw_addr *ha; int alloc_size; alloc_size = sizeof(*ha); if (alloc_size < L1_CACHE_BYTES) alloc_size = L1_CACHE_BYTES; ha = kmalloc(alloc_size, GFP_ATOMIC); if (!ha) return NULL; memcpy(ha->addr, addr, addr_len); ha->type = addr_type; ha->refcount = 1; ha->global_use = global; ha->synced = sync ? 1 : 0; ha->sync_cnt = 0; return ha; } static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type, bool global, bool sync, int sync_count, bool exclusive) { struct rb_node **ins_point = &list->tree.rb_node, *parent = NULL; struct netdev_hw_addr *ha; if (addr_len > MAX_ADDR_LEN) return -EINVAL; while (*ins_point) { int diff; ha = rb_entry(*ins_point, struct netdev_hw_addr, node); diff = memcmp(addr, ha->addr, addr_len); if (diff == 0) diff = memcmp(&addr_type, &ha->type, sizeof(addr_type)); parent = *ins_point; if (diff < 0) { ins_point = &parent->rb_left; } else if (diff > 0) { ins_point = &parent->rb_right; } else { if (exclusive) return -EEXIST; if (global) { /* check if addr is already used as global */ if (ha->global_use) return 0; else ha->global_use = true; } if (sync) { if (ha->synced && sync_count) return -EEXIST; else ha->synced++; } ha->refcount++; return 0; } } ha = __hw_addr_create(addr, addr_len, addr_type, global, sync); if (!ha) return -ENOMEM; rb_link_node(&ha->node, parent, ins_point); rb_insert_color(&ha->node, &list->tree); list_add_tail_rcu(&ha->list, &list->list); list->count++; return 0; } static int __hw_addr_add(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type) { return __hw_addr_add_ex(list, addr, addr_len, addr_type, false, false, 0, false); } static int __hw_addr_del_entry(struct netdev_hw_addr_list *list, struct netdev_hw_addr *ha, bool global, bool sync) { if (global && !ha->global_use) return -ENOENT; if (sync && !ha->synced) return -ENOENT; if (global) ha->global_use = false; if (sync) ha->synced--; if (--ha->refcount) return 0; rb_erase(&ha->node, &list->tree); list_del_rcu(&ha->list); kfree_rcu(ha, rcu_head); list->count--; return 0; } static struct netdev_hw_addr *__hw_addr_lookup(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type) { struct rb_node *node; node = list->tree.rb_node; while (node) { struct netdev_hw_addr *ha = rb_entry(node, struct netdev_hw_addr, node); int diff = memcmp(addr, ha->addr, addr_len); if (diff == 0 && addr_type) diff = memcmp(&addr_type, &ha->type, sizeof(addr_type)); if (diff < 0) node = node->rb_left; else if (diff > 0) node = node->rb_right; else return ha; } return NULL; } static int __hw_addr_del_ex(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type, bool global, bool sync) { struct netdev_hw_addr *ha = __hw_addr_lookup(list, addr, addr_len, addr_type); if (!ha) return -ENOENT; return __hw_addr_del_entry(list, ha, global, sync); } static int __hw_addr_del(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type) { return __hw_addr_del_ex(list, addr, addr_len, addr_type, false, false); } static int __hw_addr_sync_one(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr *ha, int addr_len) { int err; err = __hw_addr_add_ex(to_list, ha->addr, addr_len, ha->type, false, true, ha->sync_cnt, false); if (err && err != -EEXIST) return err; if (!err) { ha->sync_cnt++; ha->refcount++; } return 0; } static void __hw_addr_unsync_one(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, struct netdev_hw_addr *ha, int addr_len) { int err; err = __hw_addr_del_ex(to_list, ha->addr, addr_len, ha->type, false, true); if (err) return; ha->sync_cnt--; /* address on from list is not marked synced */ __hw_addr_del_entry(from_list, ha, false, false); } static int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len) { int err = 0; struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &from_list->list, list) { if (ha->sync_cnt == ha->refcount) { __hw_addr_unsync_one(to_list, from_list, ha, addr_len); } else { err = __hw_addr_sync_one(to_list, ha, addr_len); if (err) break; } } return err; } /* This function only works where there is a strict 1-1 relationship * between source and destionation of they synch. If you ever need to * sync addresses to more then 1 destination, you need to use * __hw_addr_sync_multiple(). */ int __hw_addr_sync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len) { int err = 0; struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &from_list->list, list) { if (!ha->sync_cnt) { err = __hw_addr_sync_one(to_list, ha, addr_len); if (err) break; } else if (ha->refcount == 1) __hw_addr_unsync_one(to_list, from_list, ha, addr_len); } return err; } EXPORT_SYMBOL(__hw_addr_sync); void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len) { struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &from_list->list, list) { if (ha->sync_cnt) __hw_addr_unsync_one(to_list, from_list, ha, addr_len); } } EXPORT_SYMBOL(__hw_addr_unsync); /** * __hw_addr_sync_dev - Synchonize device's multicast list * @list: address list to syncronize * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed * * This function is intended to be called from the ndo_set_rx_mode * function of devices that require explicit address add/remove * notifications. The unsync function may be NULL in which case * the addresses requiring removal will simply be removed without * any notification to the device. **/ int __hw_addr_sync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *), int (*unsync)(struct net_device *, const unsigned char *)) { struct netdev_hw_addr *ha, *tmp; int err; /* first go through and flush out any stale entries */ list_for_each_entry_safe(ha, tmp, &list->list, list) { if (!ha->sync_cnt || ha->refcount != 1) continue; /* if unsync is defined and fails defer unsyncing address */ if (unsync && unsync(dev, ha->addr)) continue; ha->sync_cnt--; __hw_addr_del_entry(list, ha, false, false); } /* go through and sync new entries to the list */ list_for_each_entry_safe(ha, tmp, &list->list, list) { if (ha->sync_cnt) continue; err = sync(dev, ha->addr); if (err) return err; ha->sync_cnt++; ha->refcount++; } return 0; } EXPORT_SYMBOL(__hw_addr_sync_dev); /** * __hw_addr_ref_sync_dev - Synchronize device's multicast address list taking * into account references * @list: address list to synchronize * @dev: device to sync * @sync: function to call if address or reference on it should be added * @unsync: function to call if address or some reference on it should removed * * This function is intended to be called from the ndo_set_rx_mode * function of devices that require explicit address or references on it * add/remove notifications. The unsync function may be NULL in which case * the addresses or references on it requiring removal will simply be * removed without any notification to the device. That is responsibility of * the driver to identify and distribute address or references on it between * internal address tables. **/ int __hw_addr_ref_sync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *, int), int (*unsync)(struct net_device *, const unsigned char *, int)) { struct netdev_hw_addr *ha, *tmp; int err, ref_cnt; /* first go through and flush out any unsynced/stale entries */ list_for_each_entry_safe(ha, tmp, &list->list, list) { /* sync if address is not used */ if ((ha->sync_cnt << 1) <= ha->refcount) continue; /* if fails defer unsyncing address */ ref_cnt = ha->refcount - ha->sync_cnt; if (unsync && unsync(dev, ha->addr, ref_cnt)) continue; ha->refcount = (ref_cnt << 1) + 1; ha->sync_cnt = ref_cnt; __hw_addr_del_entry(list, ha, false, false); } /* go through and sync updated/new entries to the list */ list_for_each_entry_safe(ha, tmp, &list->list, list) { /* sync if address added or reused */ if ((ha->sync_cnt << 1) >= ha->refcount) continue; ref_cnt = ha->refcount - ha->sync_cnt; err = sync(dev, ha->addr, ref_cnt); if (err) return err; ha->refcount = ref_cnt << 1; ha->sync_cnt = ref_cnt; } return 0; } EXPORT_SYMBOL(__hw_addr_ref_sync_dev); /** * __hw_addr_ref_unsync_dev - Remove synchronized addresses and references on * it from device * @list: address list to remove synchronized addresses (references on it) from * @dev: device to sync * @unsync: function to call if address and references on it should be removed * * Remove all addresses that were added to the device by * __hw_addr_ref_sync_dev(). This function is intended to be called from the * ndo_stop or ndo_open functions on devices that require explicit address (or * references on it) add/remove notifications. If the unsync function pointer * is NULL then this function can be used to just reset the sync_cnt for the * addresses in the list. **/ void __hw_addr_ref_unsync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *, int)) { struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &list->list, list) { if (!ha->sync_cnt) continue; /* if fails defer unsyncing address */ if (unsync && unsync(dev, ha->addr, ha->sync_cnt)) continue; ha->refcount -= ha->sync_cnt - 1; ha->sync_cnt = 0; __hw_addr_del_entry(list, ha, false, false); } } EXPORT_SYMBOL(__hw_addr_ref_unsync_dev); /** * __hw_addr_unsync_dev - Remove synchronized addresses from device * @list: address list to remove synchronized addresses from * @dev: device to sync * @unsync: function to call if address should be removed * * Remove all addresses that were added to the device by __hw_addr_sync_dev(). * This function is intended to be called from the ndo_stop or ndo_open * functions on devices that require explicit address add/remove * notifications. If the unsync function pointer is NULL then this function * can be used to just reset the sync_cnt for the addresses in the list. **/ void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *)) { struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &list->list, list) { if (!ha->sync_cnt) continue; /* if unsync is defined and fails defer unsyncing address */ if (unsync && unsync(dev, ha->addr)) continue; ha->sync_cnt--; __hw_addr_del_entry(list, ha, false, false); } } EXPORT_SYMBOL(__hw_addr_unsync_dev); static void __hw_addr_flush(struct netdev_hw_addr_list *list) { struct netdev_hw_addr *ha, *tmp; list->tree = RB_ROOT; list_for_each_entry_safe(ha, tmp, &list->list, list) { list_del_rcu(&ha->list); kfree_rcu(ha, rcu_head); } list->count = 0; } void __hw_addr_init(struct netdev_hw_addr_list *list) { INIT_LIST_HEAD(&list->list); list->count = 0; list->tree = RB_ROOT; } EXPORT_SYMBOL(__hw_addr_init); /* * Device addresses handling functions */ /* Check that netdev->dev_addr is not written to directly as this would * break the rbtree layout. All changes should go thru dev_addr_set() and co. * Remove this check in mid-2024. */ void dev_addr_check(struct net_device *dev) { if (!memcmp(dev->dev_addr, dev->dev_addr_shadow, MAX_ADDR_LEN)) return; netdev_warn(dev, "Current addr: %*ph\n", MAX_ADDR_LEN, dev->dev_addr); netdev_warn(dev, "Expected addr: %*ph\n", MAX_ADDR_LEN, dev->dev_addr_shadow); netdev_WARN(dev, "Incorrect netdev->dev_addr\n"); } /** * dev_addr_flush - Flush device address list * @dev: device * * Flush device address list and reset ->dev_addr. * * The caller must hold the rtnl_mutex. */ void dev_addr_flush(struct net_device *dev) { /* rtnl_mutex must be held here */ dev_addr_check(dev); __hw_addr_flush(&dev->dev_addrs); dev->dev_addr = NULL; } /** * dev_addr_init - Init device address list * @dev: device * * Init device address list and create the first element, * used by ->dev_addr. * * The caller must hold the rtnl_mutex. */ int dev_addr_init(struct net_device *dev) { unsigned char addr[MAX_ADDR_LEN]; struct netdev_hw_addr *ha; int err; /* rtnl_mutex must be held here */ __hw_addr_init(&dev->dev_addrs); memset(addr, 0, sizeof(addr)); err = __hw_addr_add(&dev->dev_addrs, addr, sizeof(addr), NETDEV_HW_ADDR_T_LAN); if (!err) { /* * Get the first (previously created) address from the list * and set dev_addr pointer to this location. */ ha = list_first_entry(&dev->dev_addrs.list, struct netdev_hw_addr, list); dev->dev_addr = ha->addr; } return err; } void dev_addr_mod(struct net_device *dev, unsigned int offset, const void *addr, size_t len) { struct netdev_hw_addr *ha; dev_addr_check(dev); ha = container_of(dev->dev_addr, struct netdev_hw_addr, addr[0]); rb_erase(&ha->node, &dev->dev_addrs.tree); memcpy(&ha->addr[offset], addr, len); memcpy(&dev->dev_addr_shadow[offset], addr, len); WARN_ON(__hw_addr_insert(&dev->dev_addrs, ha, dev->addr_len)); } EXPORT_SYMBOL(dev_addr_mod); /** * dev_addr_add - Add a device address * @dev: device * @addr: address to add * @addr_type: address type * * Add a device address to the device or increase the reference count if * it already exists. * * The caller must hold the rtnl_mutex. */ int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type) { int err; ASSERT_RTNL(); err = dev_pre_changeaddr_notify(dev, addr, NULL); if (err) return err; err = __hw_addr_add(&dev->dev_addrs, addr, dev->addr_len, addr_type); if (!err) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return err; } EXPORT_SYMBOL(dev_addr_add); /** * dev_addr_del - Release a device address. * @dev: device * @addr: address to delete * @addr_type: address type * * Release reference to a device address and remove it from the device * if the reference count drops to zero. * * The caller must hold the rtnl_mutex. */ int dev_addr_del(struct net_device *dev, const unsigned char *addr, unsigned char addr_type) { int err; struct netdev_hw_addr *ha; ASSERT_RTNL(); /* * We can not remove the first address from the list because * dev->dev_addr points to that. */ ha = list_first_entry(&dev->dev_addrs.list, struct netdev_hw_addr, list); if (!memcmp(ha->addr, addr, dev->addr_len) && ha->type == addr_type && ha->refcount == 1) return -ENOENT; err = __hw_addr_del(&dev->dev_addrs, addr, dev->addr_len, addr_type); if (!err) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return err; } EXPORT_SYMBOL(dev_addr_del); /* * Unicast list handling functions */ /** * dev_uc_add_excl - Add a global secondary unicast address * @dev: device * @addr: address to add */ int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr) { int err; netif_addr_lock_bh(dev); err = __hw_addr_add_ex(&dev->uc, addr, dev->addr_len, NETDEV_HW_ADDR_T_UNICAST, true, false, 0, true); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_uc_add_excl); /** * dev_uc_add - Add a secondary unicast address * @dev: device * @addr: address to add * * Add a secondary unicast address to the device or increase * the reference count if it already exists. */ int dev_uc_add(struct net_device *dev, const unsigned char *addr) { int err; netif_addr_lock_bh(dev); err = __hw_addr_add(&dev->uc, addr, dev->addr_len, NETDEV_HW_ADDR_T_UNICAST); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_uc_add); /** * dev_uc_del - Release secondary unicast address. * @dev: device * @addr: address to delete * * Release reference to a secondary unicast address and remove it * from the device if the reference count drops to zero. */ int dev_uc_del(struct net_device *dev, const unsigned char *addr) { int err; netif_addr_lock_bh(dev); err = __hw_addr_del(&dev->uc, addr, dev->addr_len, NETDEV_HW_ADDR_T_UNICAST); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_uc_del); /** * dev_uc_sync - Synchronize device's unicast list to another device * @to: destination device * @from: source device * * Add newly added addresses to the destination device and release * addresses that have no users left. The source device must be * locked by netif_addr_lock_bh. * * This function is intended to be called from the dev->set_rx_mode * function of layered software devices. This function assumes that * addresses will only ever be synced to the @to devices and no other. */ int dev_uc_sync(struct net_device *to, struct net_device *from) { int err = 0; if (to->addr_len != from->addr_len) return -EINVAL; netif_addr_lock(to); err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_uc_sync); /** * dev_uc_sync_multiple - Synchronize device's unicast list to another * device, but allow for multiple calls to sync to multiple devices. * @to: destination device * @from: source device * * Add newly added addresses to the destination device and release * addresses that have been deleted from the source. The source device * must be locked by netif_addr_lock_bh. * * This function is intended to be called from the dev->set_rx_mode * function of layered software devices. It allows for a single source * device to be synced to multiple destination devices. */ int dev_uc_sync_multiple(struct net_device *to, struct net_device *from) { int err = 0; if (to->addr_len != from->addr_len) return -EINVAL; netif_addr_lock(to); err = __hw_addr_sync_multiple(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_uc_sync_multiple); /** * dev_uc_unsync - Remove synchronized addresses from the destination device * @to: destination device * @from: source device * * Remove all addresses that were added to the destination device by * dev_uc_sync(). This function is intended to be called from the * dev->stop function of layered software devices. */ void dev_uc_unsync(struct net_device *to, struct net_device *from) { if (to->addr_len != from->addr_len) return; /* netif_addr_lock_bh() uses lockdep subclass 0, this is okay for two * reasons: * 1) This is always called without any addr_list_lock, so as the * outermost one here, it must be 0. * 2) This is called by some callers after unlinking the upper device, * so the dev->lower_level becomes 1 again. * Therefore, the subclass for 'from' is 0, for 'to' is either 1 or * larger. */ netif_addr_lock_bh(from); netif_addr_lock(to); __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); netif_addr_unlock_bh(from); } EXPORT_SYMBOL(dev_uc_unsync); /** * dev_uc_flush - Flush unicast addresses * @dev: device * * Flush unicast addresses. */ void dev_uc_flush(struct net_device *dev) { netif_addr_lock_bh(dev); __hw_addr_flush(&dev->uc); netif_addr_unlock_bh(dev); } EXPORT_SYMBOL(dev_uc_flush); /** * dev_uc_init - Init unicast address list * @dev: device * * Init unicast address list. */ void dev_uc_init(struct net_device *dev) { __hw_addr_init(&dev->uc); } EXPORT_SYMBOL(dev_uc_init); /* * Multicast list handling functions */ /** * dev_mc_add_excl - Add a global secondary multicast address * @dev: device * @addr: address to add */ int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr) { int err; netif_addr_lock_bh(dev); err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, NETDEV_HW_ADDR_T_MULTICAST, true, false, 0, true); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_mc_add_excl); static int __dev_mc_add(struct net_device *dev, const unsigned char *addr, bool global) { int err; netif_addr_lock_bh(dev); err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, NETDEV_HW_ADDR_T_MULTICAST, global, false, 0, false); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } /** * dev_mc_add - Add a multicast address * @dev: device * @addr: address to add * * Add a multicast address to the device or increase * the reference count if it already exists. */ int dev_mc_add(struct net_device *dev, const unsigned char *addr) { return __dev_mc_add(dev, addr, false); } EXPORT_SYMBOL(dev_mc_add); /** * dev_mc_add_global - Add a global multicast address * @dev: device * @addr: address to add * * Add a global multicast address to the device. */ int dev_mc_add_global(struct net_device *dev, const unsigned char *addr) { return __dev_mc_add(dev, addr, true); } EXPORT_SYMBOL(dev_mc_add_global); static int __dev_mc_del(struct net_device *dev, const unsigned char *addr, bool global) { int err; netif_addr_lock_bh(dev); err = __hw_addr_del_ex(&dev->mc, addr, dev->addr_len, NETDEV_HW_ADDR_T_MULTICAST, global, false); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); return err; } /** * dev_mc_del - Delete a multicast address. * @dev: device * @addr: address to delete * * Release reference to a multicast address and remove it * from the device if the reference count drops to zero. */ int dev_mc_del(struct net_device *dev, const unsigned char *addr) { return __dev_mc_del(dev, addr, false); } EXPORT_SYMBOL(dev_mc_del); /** * dev_mc_del_global - Delete a global multicast address. * @dev: device * @addr: address to delete * * Release reference to a multicast address and remove it * from the device if the reference count drops to zero. */ int dev_mc_del_global(struct net_device *dev, const unsigned char *addr) { return __dev_mc_del(dev, addr, true); } EXPORT_SYMBOL(dev_mc_del_global); /** * dev_mc_sync - Synchronize device's multicast list to another device * @to: destination device * @from: source device * * Add newly added addresses to the destination device and release * addresses that have no users left. The source device must be * locked by netif_addr_lock_bh. * * This function is intended to be called from the ndo_set_rx_mode * function of layered software devices. */ int dev_mc_sync(struct net_device *to, struct net_device *from) { int err = 0; if (to->addr_len != from->addr_len) return -EINVAL; netif_addr_lock(to); err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_mc_sync); /** * dev_mc_sync_multiple - Synchronize device's multicast list to another * device, but allow for multiple calls to sync to multiple devices. * @to: destination device * @from: source device * * Add newly added addresses to the destination device and release * addresses that have no users left. The source device must be * locked by netif_addr_lock_bh. * * This function is intended to be called from the ndo_set_rx_mode * function of layered software devices. It allows for a single * source device to be synced to multiple destination devices. */ int dev_mc_sync_multiple(struct net_device *to, struct net_device *from) { int err = 0; if (to->addr_len != from->addr_len) return -EINVAL; netif_addr_lock(to); err = __hw_addr_sync_multiple(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_mc_sync_multiple); /** * dev_mc_unsync - Remove synchronized addresses from the destination device * @to: destination device * @from: source device * * Remove all addresses that were added to the destination device by * dev_mc_sync(). This function is intended to be called from the * dev->stop function of layered software devices. */ void dev_mc_unsync(struct net_device *to, struct net_device *from) { if (to->addr_len != from->addr_len) return; /* See the above comments inside dev_uc_unsync(). */ netif_addr_lock_bh(from); netif_addr_lock(to); __hw_addr_unsync(&to->mc, &from->mc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); netif_addr_unlock_bh(from); } EXPORT_SYMBOL(dev_mc_unsync); /** * dev_mc_flush - Flush multicast addresses * @dev: device * * Flush multicast addresses. */ void dev_mc_flush(struct net_device *dev) { netif_addr_lock_bh(dev); __hw_addr_flush(&dev->mc); netif_addr_unlock_bh(dev); } EXPORT_SYMBOL(dev_mc_flush); /** * dev_mc_init - Init multicast address list * @dev: device * * Init multicast address list. */ void dev_mc_init(struct net_device *dev) { __hw_addr_init(&dev->mc); } EXPORT_SYMBOL(dev_mc_init); |
| 7107 3050 6315 1444 389 999 1330 142 264 4081 2883 74 74 74 306 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RCULIST_H #define _LINUX_RCULIST_H #ifdef __KERNEL__ /* * RCU-protected list version */ #include <linux/list.h> #include <linux/rcupdate.h> /* * INIT_LIST_HEAD_RCU - Initialize a list_head visible to RCU readers * @list: list to be initialized * * You should instead use INIT_LIST_HEAD() for normal initialization and * cleanup tasks, when readers have no access to the list being initialized. * However, if the list being initialized is visible to readers, you * need to keep the compiler from being too mischievous. */ static inline void INIT_LIST_HEAD_RCU(struct list_head *list) { WRITE_ONCE(list->next, list); WRITE_ONCE(list->prev, list); } /* * return the ->next pointer of a list_head in an rcu safe * way, we must not access it directly */ #define list_next_rcu(list) (*((struct list_head __rcu **)(&(list)->next))) /** * list_tail_rcu - returns the prev pointer of the head of the list * @head: the head of the list * * Note: This should only be used with the list header, and even then * only if list_del() and similar primitives are not also used on the * list header. */ #define list_tail_rcu(head) (*((struct list_head __rcu **)(&(head)->prev))) /* * Check during list traversal that we are within an RCU reader */ #define check_arg_count_one(dummy) #ifdef CONFIG_PROVE_RCU_LIST #define __list_check_rcu(dummy, cond, extra...) \ ({ \ check_arg_count_one(extra); \ RCU_LOCKDEP_WARN(!(cond) && !rcu_read_lock_any_held(), \ "RCU-list traversed in non-reader section!"); \ }) #define __list_check_srcu(cond) \ ({ \ RCU_LOCKDEP_WARN(!(cond), \ "RCU-list traversed without holding the required lock!");\ }) #else #define __list_check_rcu(dummy, cond, extra...) \ ({ check_arg_count_one(extra); }) #define __list_check_srcu(cond) ({ }) #endif /* * Insert a new entry between two known consecutive entries. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_add_rcu(struct list_head *new, struct list_head *prev, struct list_head *next) { if (!__list_add_valid(new, prev, next)) return; new->next = next; new->prev = prev; rcu_assign_pointer(list_next_rcu(prev), new); next->prev = new; } /** * list_add_rcu - add a new entry to rcu-protected list * @new: new entry to be added * @head: list head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_add_rcu() * or list_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). */ static inline void list_add_rcu(struct list_head *new, struct list_head *head) { __list_add_rcu(new, head, head->next); } /** * list_add_tail_rcu - add a new entry to rcu-protected list * @new: new entry to be added * @head: list head to add it before * * Insert a new entry before the specified head. * This is useful for implementing queues. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_add_tail_rcu() * or list_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). */ static inline void list_add_tail_rcu(struct list_head *new, struct list_head *head) { __list_add_rcu(new, head->prev, head); } /** * list_del_rcu - deletes entry from list without re-initialization * @entry: the element to delete from the list. * * Note: list_empty() on entry does not return true after this, * the entry is in an undefined state. 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 list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_del_rcu() * or list_add_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). * * Note that the caller is not permitted to immediately free * the newly deleted entry. Instead, either synchronize_rcu() * or call_rcu() must be used to defer freeing until an RCU * grace period has elapsed. */ static inline void list_del_rcu(struct list_head *entry) { __list_del_entry(entry); entry->prev = LIST_POISON2; } /** * hlist_del_init_rcu - deletes entry from hash list with re-initialization * @n: the element to delete from the hash list. * * Note: list_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_add_head_rcu() or * hlist_del_rcu(), running on this same list. However, it is * perfectly legal to run concurrently with the _rcu list-traversal * primitives, such as hlist_for_each_entry_rcu(). */ static inline void hlist_del_init_rcu(struct hlist_node *n) { if (!hlist_unhashed(n)) { __hlist_del(n); WRITE_ONCE(n->pprev, NULL); } } /** * list_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * The @old entry will be replaced with the @new entry atomically. * Note: @old should not be empty. */ static inline void list_replace_rcu(struct list_head *old, struct list_head *new) { new->next = old->next; new->prev = old->prev; rcu_assign_pointer(list_next_rcu(new->prev), new); new->next->prev = new; old->prev = LIST_POISON2; } /** * __list_splice_init_rcu - join an RCU-protected list into an existing list. * @list: the RCU-protected list to splice * @prev: points to the last element of the existing list * @next: points to the first element of the existing list * @sync: synchronize_rcu, synchronize_rcu_expedited, ... * * The list pointed to by @prev and @next can be RCU-read traversed * concurrently with this function. * * Note that this function blocks. * * Important note: the caller must take whatever action is necessary to prevent * any other updates to the existing list. In principle, it is possible to * modify the list as soon as sync() begins execution. If this sort of thing * becomes necessary, an alternative version based on call_rcu() could be * created. But only if -really- needed -- there is no shortage of RCU API * members. */ static inline void __list_splice_init_rcu(struct list_head *list, struct list_head *prev, struct list_head *next, void (*sync)(void)) { struct list_head *first = list->next; struct list_head *last = list->prev; /* * "first" and "last" tracking list, so initialize it. RCU readers * have access to this list, so we must use INIT_LIST_HEAD_RCU() * instead of INIT_LIST_HEAD(). */ INIT_LIST_HEAD_RCU(list); /* * At this point, the list body still points to the source list. * Wait for any readers to finish using the list before splicing * the list body into the new list. Any new readers will see * an empty list. */ sync(); ASSERT_EXCLUSIVE_ACCESS(*first); ASSERT_EXCLUSIVE_ACCESS(*last); /* * Readers are finished with the source list, so perform splice. * The order is important if the new list is global and accessible * to concurrent RCU readers. Note that RCU readers are not * permitted to traverse the prev pointers without excluding * this function. */ last->next = next; rcu_assign_pointer(list_next_rcu(prev), first); first->prev = prev; next->prev = last; } /** * list_splice_init_rcu - splice an RCU-protected list into an existing list, * designed for stacks. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_init_rcu(struct list_head *list, struct list_head *head, void (*sync)(void)) { if (!list_empty(list)) __list_splice_init_rcu(list, head, head->next, sync); } /** * list_splice_tail_init_rcu - splice an RCU-protected list into an existing * list, designed for queues. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_tail_init_rcu(struct list_head *list, struct list_head *head, void (*sync)(void)) { if (!list_empty(list)) __list_splice_init_rcu(list, head->prev, head, sync); } /** * list_entry_rcu - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_entry_rcu(ptr, type, member) \ container_of(READ_ONCE(ptr), type, member) /* * Where are list_empty_rcu() and list_first_entry_rcu()? * * They do not exist because they would lead to subtle race conditions: * * if (!list_empty_rcu(mylist)) { * struct foo *bar = list_first_entry_rcu(mylist, struct foo, list_member); * do_something(bar); * } * * The list might be non-empty when list_empty_rcu() checks it, but it * might have become empty by the time that list_first_entry_rcu() rereads * the ->next pointer, which would result in a SEGV. * * When not using RCU, it is OK for list_first_entry() to re-read that * pointer because both functions should be protected by some lock that * blocks writers. * * When using RCU, list_empty() uses READ_ONCE() to fetch the * RCU-protected ->next pointer and then compares it to the address of the * list head. However, it neither dereferences this pointer nor provides * this pointer to its caller. Thus, READ_ONCE() suffices (that is, * rcu_dereference() is not needed), which means that list_empty() can be * used anywhere you would want to use list_empty_rcu(). Just don't * expect anything useful to happen if you do a subsequent lockless * call to list_first_entry_rcu()!!! * * See list_first_or_null_rcu for an alternative. */ /** * list_first_or_null_rcu - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the list is empty, it returns NULL. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_first_or_null_rcu(ptr, type, member) \ ({ \ struct list_head *__ptr = (ptr); \ struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__ptr != __next) ? list_entry_rcu(__next, type, member) : NULL; \ }) /** * list_next_or_null_rcu - get the first element from a list * @head: the head for the list. * @ptr: the list head to take the next element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the ptr is at the end of the list, NULL is returned. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_next_or_null_rcu(head, ptr, type, member) \ ({ \ struct list_head *__head = (head); \ struct list_head *__ptr = (ptr); \ struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__next != __head) ? list_entry_rcu(__next, type, \ member) : NULL; \ }) /** * list_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define list_for_each_entry_rcu(pos, head, member, cond...) \ for (__list_check_rcu(dummy, ## cond, 0), \ pos = list_entry_rcu((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_srcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * @cond: lockdep expression for the lock required to traverse the list. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by srcu_read_lock(). * The lockdep expression srcu_read_lock_held() can be passed as the * cond argument from read side. */ #define list_for_each_entry_srcu(pos, head, member, cond) \ for (__list_check_srcu(cond), \ pos = list_entry_rcu((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_entry_lockless - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * This primitive may safely run concurrently with the _rcu * list-mutation primitives such as list_add_rcu(), but requires some * implicit RCU read-side guarding. One example is running within a special * exception-time environment where preemption is disabled and where lockdep * cannot be invoked. Another example is when items are added to the list, * but never deleted. */ #define list_entry_lockless(ptr, type, member) \ container_of((typeof(ptr))READ_ONCE(ptr), type, member) /** * list_for_each_entry_lockless - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_struct within the struct. * * This primitive may safely run concurrently with the _rcu * list-mutation primitives such as list_add_rcu(), but requires some * implicit RCU read-side guarding. One example is running within a special * exception-time environment where preemption is disabled and where lockdep * cannot be invoked. Another example is when items are added to the list, * but never deleted. */ #define list_for_each_entry_lockless(pos, head, member) \ for (pos = list_entry_lockless((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_lockless(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_continue_rcu - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after * the current position which must have been in the list when the RCU read * lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. * * This iterator is similar to list_for_each_entry_from_rcu() except * this starts after the given position and that one starts at the given * position. */ #define list_for_each_entry_continue_rcu(pos, head, member) \ for (pos = list_entry_rcu(pos->member.next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_from_rcu - iterate over a list from current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_node within the struct. * * Iterate over the tail of a list starting from a given position, * which must have been in the list when the RCU read lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. * * This iterator is similar to list_for_each_entry_continue_rcu() except * this starts from the given position and that one starts from the position * after the given position. */ #define list_for_each_entry_from_rcu(pos, head, member) \ for (; &(pos)->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*(pos)), member)) /** * hlist_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * * Note: list_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_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry(). */ static inline void hlist_del_rcu(struct hlist_node *n) { __hlist_del(n); WRITE_ONCE(n->pprev, LIST_POISON2); } /** * hlist_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * The @old entry will be replaced with the @new entry atomically. */ static inline void hlist_replace_rcu(struct hlist_node *old, struct hlist_node *new) { struct hlist_node *next = old->next; new->next = next; WRITE_ONCE(new->pprev, old->pprev); rcu_assign_pointer(*(struct hlist_node __rcu **)new->pprev, new); if (next) WRITE_ONCE(new->next->pprev, &new->next); WRITE_ONCE(old->pprev, LIST_POISON2); } /** * hlists_swap_heads_rcu - swap the lists the hlist heads point to * @left: The hlist head on the left * @right: The hlist head on the right * * The lists start out as [@left ][node1 ... ] and * [@right ][node2 ... ] * The lists end up as [@left ][node2 ... ] * [@right ][node1 ... ] */ static inline void hlists_swap_heads_rcu(struct hlist_head *left, struct hlist_head *right) { struct hlist_node *node1 = left->first; struct hlist_node *node2 = right->first; rcu_assign_pointer(left->first, node2); rcu_assign_pointer(right->first, node1); WRITE_ONCE(node2->pprev, &left->first); WRITE_ONCE(node1->pprev, &right->first); } /* * return the first or the next element in an RCU protected hlist */ #define hlist_first_rcu(head) (*((struct hlist_node __rcu **)(&(head)->first))) #define hlist_next_rcu(node) (*((struct hlist_node __rcu **)(&(node)->next))) #define hlist_pprev_rcu(node) (*((struct hlist_node __rcu **)((node)->pprev))) /** * hlist_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, * 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_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_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_add_head_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; n->next = first; WRITE_ONCE(n->pprev, &h->first); rcu_assign_pointer(hlist_first_rcu(h), n); if (first) WRITE_ONCE(first->pprev, &n->next); } /** * hlist_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, * 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_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_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_add_tail_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *i, *last = NULL; /* Note: write side code, so rcu accessors are not needed. */ for (i = h->first; i; i = i->next) last = i; if (last) { n->next = last->next; WRITE_ONCE(n->pprev, &last->next); rcu_assign_pointer(hlist_next_rcu(last), n); } else { hlist_add_head_rcu(n, h); } } /** * hlist_add_before_rcu * @n: the new element to add to the hash list. * @next: the existing element to add the new element before. * * Description: * Adds the specified element to the specified hlist * before the specified node 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_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ static inline void hlist_add_before_rcu(struct hlist_node *n, struct hlist_node *next) { WRITE_ONCE(n->pprev, next->pprev); n->next = next; rcu_assign_pointer(hlist_pprev_rcu(n), n); WRITE_ONCE(next->pprev, &n->next); } /** * hlist_add_behind_rcu * @n: the new element to add to the hash list. * @prev: the existing element to add the new element after. * * Description: * Adds the specified element to the specified hlist * after the specified node 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_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ static inline void hlist_add_behind_rcu(struct hlist_node *n, struct hlist_node *prev) { n->next = prev->next; WRITE_ONCE(n->pprev, &prev->next); rcu_assign_pointer(hlist_next_rcu(prev), n); if (n->next) WRITE_ONCE(n->next->pprev, &n->next); } #define __hlist_for_each_rcu(pos, head) \ for (pos = rcu_dereference(hlist_first_rcu(head)); \ pos; \ pos = rcu_dereference(hlist_next_rcu(pos))) /** * hlist_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu(pos, head, member, cond...) \ for (__list_check_rcu(dummy, ## cond, 0), \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_srcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @cond: lockdep expression for the lock required to traverse the list. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by srcu_read_lock(). * The lockdep expression srcu_read_lock_held() can be passed as the * cond argument from read side. */ #define hlist_for_each_entry_srcu(pos, head, member, cond) \ for (__list_check_srcu(cond), \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_notrace - iterate over rcu list of given type (for tracing) * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). * * This is the same as hlist_for_each_entry_rcu() except that it does * not do any RCU debugging or tracing. */ #define hlist_for_each_entry_rcu_notrace(pos, head, member) \ for (pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_bh - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu_bh(pos, head, member) \ for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu(pos, member) \ for (pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu_bh - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu_bh(pos, member) \ for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_from_rcu - iterate over a hlist continuing from current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_from_rcu(pos, member) \ for (; pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) #endif /* __KERNEL__ */ #endif |
| 669 56 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/sys.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/export.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/utsname.h> #include <linux/mman.h> #include <linux/reboot.h> #include <linux/prctl.h> #include <linux/highuid.h> #include <linux/fs.h> #include <linux/kmod.h> #include <linux/perf_event.h> #include <linux/resource.h> #include <linux/kernel.h> #include <linux/workqueue.h> #include <linux/capability.h> #include <linux/device.h> #include <linux/key.h> #include <linux/times.h> #include <linux/posix-timers.h> #include <linux/security.h> #include <linux/random.h> #include <linux/suspend.h> #include <linux/tty.h> #include <linux/signal.h> #include <linux/cn_proc.h> #include <linux/getcpu.h> #include <linux/task_io_accounting_ops.h> #include <linux/seccomp.h> #include <linux/cpu.h> #include <linux/personality.h> #include <linux/ptrace.h> #include <linux/fs_struct.h> #include <linux/file.h> #include <linux/mount.h> #include <linux/gfp.h> #include <linux/syscore_ops.h> #include <linux/version.h> #include <linux/ctype.h> #include <linux/syscall_user_dispatch.h> #include <linux/compat.h> #include <linux/syscalls.h> #include <linux/kprobes.h> #include <linux/user_namespace.h> #include <linux/time_namespace.h> #include <linux/binfmts.h> #include <linux/sched.h> #include <linux/sched/autogroup.h> #include <linux/sched/loadavg.h> #include <linux/sched/stat.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/task.h> #include <linux/sched/cputime.h> #include <linux/rcupdate.h> #include <linux/uidgid.h> #include <linux/cred.h> #include <linux/nospec.h> #include <linux/kmsg_dump.h> /* Move somewhere else to avoid recompiling? */ #include <generated/utsrelease.h> #include <linux/uaccess.h> #include <asm/io.h> #include <asm/unistd.h> #include "uid16.h" #include <trace/hooks/sys.h> #ifndef SET_UNALIGN_CTL # define SET_UNALIGN_CTL(a, b) (-EINVAL) #endif #ifndef GET_UNALIGN_CTL # define GET_UNALIGN_CTL(a, b) (-EINVAL) #endif #ifndef SET_FPEMU_CTL # define SET_FPEMU_CTL(a, b) (-EINVAL) #endif #ifndef GET_FPEMU_CTL # define GET_FPEMU_CTL(a, b) (-EINVAL) #endif #ifndef SET_FPEXC_CTL # define SET_FPEXC_CTL(a, b) (-EINVAL) #endif #ifndef GET_FPEXC_CTL # define GET_FPEXC_CTL(a, b) (-EINVAL) #endif #ifndef GET_ENDIAN # define GET_ENDIAN(a, b) (-EINVAL) #endif #ifndef SET_ENDIAN # define SET_ENDIAN(a, b) (-EINVAL) #endif #ifndef GET_TSC_CTL # define GET_TSC_CTL(a) (-EINVAL) #endif #ifndef SET_TSC_CTL # define SET_TSC_CTL(a) (-EINVAL) #endif #ifndef GET_FP_MODE # define GET_FP_MODE(a) (-EINVAL) #endif #ifndef SET_FP_MODE # define SET_FP_MODE(a,b) (-EINVAL) #endif #ifndef SVE_SET_VL # define SVE_SET_VL(a) (-EINVAL) #endif #ifndef SVE_GET_VL # define SVE_GET_VL() (-EINVAL) #endif #ifndef SME_SET_VL # define SME_SET_VL(a) (-EINVAL) #endif #ifndef SME_GET_VL # define SME_GET_VL() (-EINVAL) #endif #ifndef PAC_RESET_KEYS # define PAC_RESET_KEYS(a, b) (-EINVAL) #endif #ifndef PAC_SET_ENABLED_KEYS # define PAC_SET_ENABLED_KEYS(a, b, c) (-EINVAL) #endif #ifndef PAC_GET_ENABLED_KEYS # define PAC_GET_ENABLED_KEYS(a) (-EINVAL) #endif #ifndef SET_TAGGED_ADDR_CTRL # define SET_TAGGED_ADDR_CTRL(a) (-EINVAL) #endif #ifndef GET_TAGGED_ADDR_CTRL # define GET_TAGGED_ADDR_CTRL() (-EINVAL) #endif /* * this is where the system-wide overflow UID and GID are defined, for * architectures that now have 32-bit UID/GID but didn't in the past */ int overflowuid = DEFAULT_OVERFLOWUID; int overflowgid = DEFAULT_OVERFLOWGID; EXPORT_SYMBOL(overflowuid); EXPORT_SYMBOL(overflowgid); /* * the same as above, but for filesystems which can only store a 16-bit * UID and GID. as such, this is needed on all architectures */ int fs_overflowuid = DEFAULT_FS_OVERFLOWUID; int fs_overflowgid = DEFAULT_FS_OVERFLOWGID; EXPORT_SYMBOL(fs_overflowuid); EXPORT_SYMBOL(fs_overflowgid); /* * Returns true if current's euid is same as p's uid or euid, * or has CAP_SYS_NICE to p's user_ns. * * Called with rcu_read_lock, creds are safe */ static bool set_one_prio_perm(struct task_struct *p) { const struct cred *cred = current_cred(), *pcred = __task_cred(p); if (uid_eq(pcred->uid, cred->euid) || uid_eq(pcred->euid, cred->euid)) return true; if (ns_capable(pcred->user_ns, CAP_SYS_NICE)) return true; return false; } /* * set the priority of a task * - the caller must hold the RCU read lock */ static int set_one_prio(struct task_struct *p, int niceval, int error) { int no_nice; if (!set_one_prio_perm(p)) { error = -EPERM; goto out; } if (niceval < task_nice(p) && !can_nice(p, niceval)) { error = -EACCES; goto out; } no_nice = security_task_setnice(p, niceval); if (no_nice) { error = no_nice; goto out; } if (error == -ESRCH) error = 0; set_user_nice(p, niceval); out: return error; } SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) { struct task_struct *g, *p; struct user_struct *user; const struct cred *cred = current_cred(); int error = -EINVAL; struct pid *pgrp; kuid_t uid; if (which > PRIO_USER || which < PRIO_PROCESS) goto out; /* normalize: avoid signed division (rounding problems) */ error = -ESRCH; if (niceval < MIN_NICE) niceval = MIN_NICE; if (niceval > MAX_NICE) niceval = MAX_NICE; rcu_read_lock(); switch (which) { case PRIO_PROCESS: if (who) p = find_task_by_vpid(who); else p = current; if (p) error = set_one_prio(p, niceval, error); break; case PRIO_PGRP: if (who) pgrp = find_vpid(who); else pgrp = task_pgrp(current); read_lock(&tasklist_lock); do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { error = set_one_prio(p, niceval, error); } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); read_unlock(&tasklist_lock); break; case PRIO_USER: uid = make_kuid(cred->user_ns, who); user = cred->user; if (!who) uid = cred->uid; else if (!uid_eq(uid, cred->uid)) { user = find_user(uid); if (!user) goto out_unlock; /* No processes for this user */ } for_each_process_thread(g, p) { if (uid_eq(task_uid(p), uid) && task_pid_vnr(p)) error = set_one_prio(p, niceval, error); } if (!uid_eq(uid, cred->uid)) free_uid(user); /* For find_user() */ break; } out_unlock: rcu_read_unlock(); out: return error; } /* * Ugh. To avoid negative return values, "getpriority()" will * not return the normal nice-value, but a negated value that * has been offset by 20 (ie it returns 40..1 instead of -20..19) * to stay compatible. */ SYSCALL_DEFINE2(getpriority, int, which, int, who) { struct task_struct *g, *p; struct user_struct *user; const struct cred *cred = current_cred(); long niceval, retval = -ESRCH; struct pid *pgrp; kuid_t uid; if (which > PRIO_USER || which < PRIO_PROCESS) return -EINVAL; rcu_read_lock(); switch (which) { case PRIO_PROCESS: if (who) p = find_task_by_vpid(who); else p = current; if (p) { niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } break; case PRIO_PGRP: if (who) pgrp = find_vpid(who); else pgrp = task_pgrp(current); read_lock(&tasklist_lock); do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); read_unlock(&tasklist_lock); break; case PRIO_USER: uid = make_kuid(cred->user_ns, who); user = cred->user; if (!who) uid = cred->uid; else if (!uid_eq(uid, cred->uid)) { user = find_user(uid); if (!user) goto out_unlock; /* No processes for this user */ } for_each_process_thread(g, p) { if (uid_eq(task_uid(p), uid) && task_pid_vnr(p)) { niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } } if (!uid_eq(uid, cred->uid)) free_uid(user); /* for find_user() */ break; } out_unlock: rcu_read_unlock(); return retval; } /* * Unprivileged users may change the real gid to the effective gid * or vice versa. (BSD-style) * * If you set the real gid at all, or set the effective gid to a value not * equal to the real gid, then the saved gid is set to the new effective gid. * * This makes it possible for a setgid program to completely drop its * privileges, which is often a useful assertion to make when you are doing * a security audit over a program. * * The general idea is that a program which uses just setregid() will be * 100% compatible with BSD. A program which uses just setgid() will be * 100% compatible with POSIX with saved IDs. * * SMP: There are not races, the GIDs are checked only by filesystem * operations (as far as semantic preservation is concerned). */ #ifdef CONFIG_MULTIUSER long __sys_setregid(gid_t rgid, gid_t egid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kgid_t krgid, kegid; krgid = make_kgid(ns, rgid); kegid = make_kgid(ns, egid); if ((rgid != (gid_t) -1) && !gid_valid(krgid)) return -EINVAL; if ((egid != (gid_t) -1) && !gid_valid(kegid)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); retval = -EPERM; if (rgid != (gid_t) -1) { if (gid_eq(old->gid, krgid) || gid_eq(old->egid, krgid) || ns_capable_setid(old->user_ns, CAP_SETGID)) new->gid = krgid; else goto error; } if (egid != (gid_t) -1) { if (gid_eq(old->gid, kegid) || gid_eq(old->egid, kegid) || gid_eq(old->sgid, kegid) || ns_capable_setid(old->user_ns, CAP_SETGID)) new->egid = kegid; else goto error; } if (rgid != (gid_t) -1 || (egid != (gid_t) -1 && !gid_eq(kegid, old->gid))) new->sgid = new->egid; new->fsgid = new->egid; retval = security_task_fix_setgid(new, old, LSM_SETID_RE); if (retval < 0) goto error; return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid) { return __sys_setregid(rgid, egid); } /* * setgid() is implemented like SysV w/ SAVED_IDS * * SMP: Same implicit races as above. */ long __sys_setgid(gid_t gid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kgid_t kgid; kgid = make_kgid(ns, gid); if (!gid_valid(kgid)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); retval = -EPERM; if (ns_capable_setid(old->user_ns, CAP_SETGID)) new->gid = new->egid = new->sgid = new->fsgid = kgid; else if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->sgid)) new->egid = new->fsgid = kgid; else goto error; retval = security_task_fix_setgid(new, old, LSM_SETID_ID); if (retval < 0) goto error; return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE1(setgid, gid_t, gid) { return __sys_setgid(gid); } /* * change the user struct in a credentials set to match the new UID */ static int set_user(struct cred *new) { struct user_struct *new_user; new_user = alloc_uid(new->uid); if (!new_user) return -EAGAIN; free_uid(new->user); new->user = new_user; return 0; } static void flag_nproc_exceeded(struct cred *new) { if (new->ucounts == current_ucounts()) return; /* * We don't fail in case of NPROC limit excess here because too many * poorly written programs don't check set*uid() return code, assuming * it never fails if called by root. We may still enforce NPROC limit * for programs doing set*uid()+execve() by harmlessly deferring the * failure to the execve() stage. */ if (is_rlimit_overlimit(new->ucounts, UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC)) && new->user != INIT_USER) current->flags |= PF_NPROC_EXCEEDED; else current->flags &= ~PF_NPROC_EXCEEDED; } /* * Unprivileged users may change the real uid to the effective uid * or vice versa. (BSD-style) * * If you set the real uid at all, or set the effective uid to a value not * equal to the real uid, then the saved uid is set to the new effective uid. * * This makes it possible for a setuid program to completely drop its * privileges, which is often a useful assertion to make when you are doing * a security audit over a program. * * The general idea is that a program which uses just setreuid() will be * 100% compatible with BSD. A program which uses just setuid() will be * 100% compatible with POSIX with saved IDs. */ long __sys_setreuid(uid_t ruid, uid_t euid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kuid_t kruid, keuid; kruid = make_kuid(ns, ruid); keuid = make_kuid(ns, euid); if ((ruid != (uid_t) -1) && !uid_valid(kruid)) return -EINVAL; if ((euid != (uid_t) -1) && !uid_valid(keuid)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); retval = -EPERM; if (ruid != (uid_t) -1) { new->uid = kruid; if (!uid_eq(old->uid, kruid) && !uid_eq(old->euid, kruid) && !ns_capable_setid(old->user_ns, CAP_SETUID)) goto error; } if (euid != (uid_t) -1) { new->euid = keuid; if (!uid_eq(old->uid, keuid) && !uid_eq(old->euid, keuid) && !uid_eq(old->suid, keuid) && !ns_capable_setid(old->user_ns, CAP_SETUID)) goto error; } if (!uid_eq(new->uid, old->uid)) { retval = set_user(new); if (retval < 0) goto error; } if (ruid != (uid_t) -1 || (euid != (uid_t) -1 && !uid_eq(keuid, old->uid))) new->suid = new->euid; new->fsuid = new->euid; retval = security_task_fix_setuid(new, old, LSM_SETID_RE); if (retval < 0) goto error; retval = set_cred_ucounts(new); if (retval < 0) goto error; flag_nproc_exceeded(new); return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid) { return __sys_setreuid(ruid, euid); } /* * setuid() is implemented like SysV with SAVED_IDS * * Note that SAVED_ID's is deficient in that a setuid root program * like sendmail, for example, cannot set its uid to be a normal * user and then switch back, because if you're root, setuid() sets * the saved uid too. If you don't like this, blame the bright people * in the POSIX committee and/or USG. Note that the BSD-style setreuid() * will allow a root program to temporarily drop privileges and be able to * regain them by swapping the real and effective uid. */ long __sys_setuid(uid_t uid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kuid_t kuid; kuid = make_kuid(ns, uid); if (!uid_valid(kuid)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); retval = -EPERM; if (ns_capable_setid(old->user_ns, CAP_SETUID)) { new->suid = new->uid = kuid; if (!uid_eq(kuid, old->uid)) { retval = set_user(new); if (retval < 0) goto error; } } else if (!uid_eq(kuid, old->uid) && !uid_eq(kuid, new->suid)) { goto error; } new->fsuid = new->euid = kuid; retval = security_task_fix_setuid(new, old, LSM_SETID_ID); if (retval < 0) goto error; retval = set_cred_ucounts(new); if (retval < 0) goto error; flag_nproc_exceeded(new); return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE1(setuid, uid_t, uid) { return __sys_setuid(uid); } /* * This function implements a generic ability to update ruid, euid, * and suid. This allows you to implement the 4.4 compatible seteuid(). */ long __sys_setresuid(uid_t ruid, uid_t euid, uid_t suid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kuid_t kruid, keuid, ksuid; bool ruid_new, euid_new, suid_new; kruid = make_kuid(ns, ruid); keuid = make_kuid(ns, euid); ksuid = make_kuid(ns, suid); if ((ruid != (uid_t) -1) && !uid_valid(kruid)) return -EINVAL; if ((euid != (uid_t) -1) && !uid_valid(keuid)) return -EINVAL; if ((suid != (uid_t) -1) && !uid_valid(ksuid)) return -EINVAL; old = current_cred(); /* check for no-op */ if ((ruid == (uid_t) -1 || uid_eq(kruid, old->uid)) && (euid == (uid_t) -1 || (uid_eq(keuid, old->euid) && uid_eq(keuid, old->fsuid))) && (suid == (uid_t) -1 || uid_eq(ksuid, old->suid))) return 0; ruid_new = ruid != (uid_t) -1 && !uid_eq(kruid, old->uid) && !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid); euid_new = euid != (uid_t) -1 && !uid_eq(keuid, old->uid) && !uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid); suid_new = suid != (uid_t) -1 && !uid_eq(ksuid, old->uid) && !uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid); if ((ruid_new || euid_new || suid_new) && !ns_capable_setid(old->user_ns, CAP_SETUID)) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (ruid != (uid_t) -1) { new->uid = kruid; if (!uid_eq(kruid, old->uid)) { retval = set_user(new); if (retval < 0) goto error; } } if (euid != (uid_t) -1) new->euid = keuid; if (suid != (uid_t) -1) new->suid = ksuid; new->fsuid = new->euid; retval = security_task_fix_setuid(new, old, LSM_SETID_RES); if (retval < 0) goto error; retval = set_cred_ucounts(new); if (retval < 0) goto error; flag_nproc_exceeded(new); return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid) { return __sys_setresuid(ruid, euid, suid); } SYSCALL_DEFINE3(getresuid, uid_t __user *, ruidp, uid_t __user *, euidp, uid_t __user *, suidp) { const struct cred *cred = current_cred(); int retval; uid_t ruid, euid, suid; ruid = from_kuid_munged(cred->user_ns, cred->uid); euid = from_kuid_munged(cred->user_ns, cred->euid); suid = from_kuid_munged(cred->user_ns, cred->suid); retval = put_user(ruid, ruidp); if (!retval) { retval = put_user(euid, euidp); if (!retval) return put_user(suid, suidp); } return retval; } /* * Same as above, but for rgid, egid, sgid. */ long __sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kgid_t krgid, kegid, ksgid; bool rgid_new, egid_new, sgid_new; krgid = make_kgid(ns, rgid); kegid = make_kgid(ns, egid); ksgid = make_kgid(ns, sgid); if ((rgid != (gid_t) -1) && !gid_valid(krgid)) return -EINVAL; if ((egid != (gid_t) -1) && !gid_valid(kegid)) return -EINVAL; if ((sgid != (gid_t) -1) && !gid_valid(ksgid)) return -EINVAL; old = current_cred(); /* check for no-op */ if ((rgid == (gid_t) -1 || gid_eq(krgid, old->gid)) && (egid == (gid_t) -1 || (gid_eq(kegid, old->egid) && gid_eq(kegid, old->fsgid))) && (sgid == (gid_t) -1 || gid_eq(ksgid, old->sgid))) return 0; rgid_new = rgid != (gid_t) -1 && !gid_eq(krgid, old->gid) && !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid); egid_new = egid != (gid_t) -1 && !gid_eq(kegid, old->gid) && !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid); sgid_new = sgid != (gid_t) -1 && !gid_eq(ksgid, old->gid) && !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid); if ((rgid_new || egid_new || sgid_new) && !ns_capable_setid(old->user_ns, CAP_SETGID)) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (rgid != (gid_t) -1) new->gid = krgid; if (egid != (gid_t) -1) new->egid = kegid; if (sgid != (gid_t) -1) new->sgid = ksgid; new->fsgid = new->egid; retval = security_task_fix_setgid(new, old, LSM_SETID_RES); if (retval < 0) goto error; return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid) { return __sys_setresgid(rgid, egid, sgid); } SYSCALL_DEFINE3(getresgid, gid_t __user *, rgidp, gid_t __user *, egidp, gid_t __user *, sgidp) { const struct cred *cred = current_cred(); int retval; gid_t rgid, egid, sgid; rgid = from_kgid_munged(cred->user_ns, cred->gid); egid = from_kgid_munged(cred->user_ns, cred->egid); sgid = from_kgid_munged(cred->user_ns, cred->sgid); retval = put_user(rgid, rgidp); if (!retval) { retval = put_user(egid, egidp); if (!retval) retval = put_user(sgid, sgidp); } return retval; } /* * "setfsuid()" sets the fsuid - the uid used for filesystem checks. This * is used for "access()" and for the NFS daemon (letting nfsd stay at * whatever uid it wants to). It normally shadows "euid", except when * explicitly set by setfsuid() or for access.. */ long __sys_setfsuid(uid_t uid) { const struct cred *old; struct cred *new; uid_t old_fsuid; kuid_t kuid; old = current_cred(); old_fsuid = from_kuid_munged(old->user_ns, old->fsuid); kuid = make_kuid(old->user_ns, uid); if (!uid_valid(kuid)) return old_fsuid; new = prepare_creds(); if (!new) return old_fsuid; if (uid_eq(kuid, old->uid) || uid_eq(kuid, old->euid) || uid_eq(kuid, old->suid) || uid_eq(kuid, old->fsuid) || ns_capable_setid(old->user_ns, CAP_SETUID)) { if (!uid_eq(kuid, old->fsuid)) { new->fsuid = kuid; if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0) goto change_okay; } } abort_creds(new); return old_fsuid; change_okay: commit_creds(new); return old_fsuid; } SYSCALL_DEFINE1(setfsuid, uid_t, uid) { return __sys_setfsuid(uid); } /* * Samma pÃ¥ svenska.. */ long __sys_setfsgid(gid_t gid) { const struct cred *old; struct cred *new; gid_t old_fsgid; kgid_t kgid; old = current_cred(); old_fsgid = from_kgid_munged(old->user_ns, old->fsgid); kgid = make_kgid(old->user_ns, gid); if (!gid_valid(kgid)) return old_fsgid; new = prepare_creds(); if (!new) return old_fsgid; if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->egid) || gid_eq(kgid, old->sgid) || gid_eq(kgid, old->fsgid) || ns_capable_setid(old->user_ns, CAP_SETGID)) { if (!gid_eq(kgid, old->fsgid)) { new->fsgid = kgid; if (security_task_fix_setgid(new,old,LSM_SETID_FS) == 0) goto change_okay; } } abort_creds(new); return old_fsgid; change_okay: commit_creds(new); return old_fsgid; } SYSCALL_DEFINE1(setfsgid, gid_t, gid) { return __sys_setfsgid(gid); } #endif /* CONFIG_MULTIUSER */ /** * sys_getpid - return the thread group id of the current process * * Note, despite the name, this returns the tgid not the pid. The tgid and * the pid are identical unless CLONE_THREAD was specified on clone() in * which case the tgid is the same in all threads of the same group. * * This is SMP safe as current->tgid does not change. */ SYSCALL_DEFINE0(getpid) { return task_tgid_vnr(current); } /* Thread ID - the internal kernel "pid" */ SYSCALL_DEFINE0(gettid) { return task_pid_vnr(current); } /* * Accessing ->real_parent is not SMP-safe, it could * change from under us. However, we can use a stale * value of ->real_parent under rcu_read_lock(), see * release_task()->call_rcu(delayed_put_task_struct). */ SYSCALL_DEFINE0(getppid) { int pid; rcu_read_lock(); pid = task_tgid_vnr(rcu_dereference(current->real_parent)); rcu_read_unlock(); return pid; } SYSCALL_DEFINE0(getuid) { /* Only we change this so SMP safe */ return from_kuid_munged(current_user_ns(), current_uid()); } SYSCALL_DEFINE0(geteuid) { /* Only we change this so SMP safe */ return from_kuid_munged(current_user_ns(), current_euid()); } SYSCALL_DEFINE0(getgid) { /* Only we change this so SMP safe */ return from_kgid_munged(current_user_ns(), current_gid()); } SYSCALL_DEFINE0(getegid) { /* Only we change this so SMP safe */ return from_kgid_munged(current_user_ns(), current_egid()); } static void do_sys_times(struct tms *tms) { u64 tgutime, tgstime, cutime, cstime; thread_group_cputime_adjusted(current, &tgutime, &tgstime); cutime = current->signal->cutime; cstime = current->signal->cstime; tms->tms_utime = nsec_to_clock_t(tgutime); tms->tms_stime = nsec_to_clock_t(tgstime); tms->tms_cutime = nsec_to_clock_t(cutime); tms->tms_cstime = nsec_to_clock_t(cstime); } SYSCALL_DEFINE1(times, struct tms __user *, tbuf) { if (tbuf) { struct tms tmp; do_sys_times(&tmp); if (copy_to_user(tbuf, &tmp, sizeof(struct tms))) return -EFAULT; } force_successful_syscall_return(); return (long) jiffies_64_to_clock_t(get_jiffies_64()); } #ifdef CONFIG_COMPAT static compat_clock_t clock_t_to_compat_clock_t(clock_t x) { return compat_jiffies_to_clock_t(clock_t_to_jiffies(x)); } COMPAT_SYSCALL_DEFINE1(times, struct compat_tms __user *, tbuf) { if (tbuf) { struct tms tms; struct compat_tms tmp; do_sys_times(&tms); /* Convert our struct tms to the compat version. */ tmp.tms_utime = clock_t_to_compat_clock_t(tms.tms_utime); tmp.tms_stime = clock_t_to_compat_clock_t(tms.tms_stime); tmp.tms_cutime = clock_t_to_compat_clock_t(tms.tms_cutime); tmp.tms_cstime = clock_t_to_compat_clock_t(tms.tms_cstime); if (copy_to_user(tbuf, &tmp, sizeof(tmp))) return -EFAULT; } force_successful_syscall_return(); return compat_jiffies_to_clock_t(jiffies); } #endif /* * This needs some heavy checking ... * I just haven't the stomach for it. I also don't fully * understand sessions/pgrp etc. Let somebody who does explain it. * * OK, I think I have the protection semantics right.... this is really * only important on a multi-user system anyway, to make sure one user * can't send a signal to a process owned by another. -TYT, 12/12/91 * * !PF_FORKNOEXEC check to conform completely to POSIX. */ SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid) { struct task_struct *p; struct task_struct *group_leader = current->group_leader; struct pid *pgrp; int err; if (!pid) pid = task_pid_vnr(group_leader); if (!pgid) pgid = pid; if (pgid < 0) return -EINVAL; rcu_read_lock(); /* From this point forward we keep holding onto the tasklist lock * so that our parent does not change from under us. -DaveM */ write_lock_irq(&tasklist_lock); err = -ESRCH; p = find_task_by_vpid(pid); if (!p) goto out; err = -EINVAL; if (!thread_group_leader(p)) goto out; if (same_thread_group(p->real_parent, group_leader)) { err = -EPERM; if (task_session(p) != task_session(group_leader)) goto out; err = -EACCES; if (!(p->flags & PF_FORKNOEXEC)) goto out; } else { err = -ESRCH; if (p != group_leader) goto out; } err = -EPERM; if (p->signal->leader) goto out; pgrp = task_pid(p); if (pgid != pid) { struct task_struct *g; pgrp = find_vpid(pgid); g = pid_task(pgrp, PIDTYPE_PGID); if (!g || task_session(g) != task_session(group_leader)) goto out; } err = security_task_setpgid(p, pgid); if (err) goto out; if (task_pgrp(p) != pgrp) change_pid(p, PIDTYPE_PGID, pgrp); err = 0; out: /* All paths lead to here, thus we are safe. -DaveM */ write_unlock_irq(&tasklist_lock); rcu_read_unlock(); return err; } static int do_getpgid(pid_t pid) { struct task_struct *p; struct pid *grp; int retval; rcu_read_lock(); if (!pid) grp = task_pgrp(current); else { retval = -ESRCH; p = find_task_by_vpid(pid); if (!p) goto out; grp = task_pgrp(p); if (!grp) goto out; retval = security_task_getpgid(p); if (retval) goto out; } retval = pid_vnr(grp); out: rcu_read_unlock(); return retval; } SYSCALL_DEFINE1(getpgid, pid_t, pid) { return do_getpgid(pid); } #ifdef __ARCH_WANT_SYS_GETPGRP SYSCALL_DEFINE0(getpgrp) { return do_getpgid(0); } #endif SYSCALL_DEFINE1(getsid, pid_t, pid) { struct task_struct *p; struct pid *sid; int retval; rcu_read_lock(); if (!pid) sid = task_session(current); else { retval = -ESRCH; p = find_task_by_vpid(pid); if (!p) goto out; sid = task_session(p); if (!sid) goto out; retval = security_task_getsid(p); if (retval) goto out; } retval = pid_vnr(sid); out: rcu_read_unlock(); return retval; } static void set_special_pids(struct pid *pid) { struct task_struct *curr = current->group_leader; if (task_session(curr) != pid) change_pid(curr, PIDTYPE_SID, pid); if (task_pgrp(curr) != pid) change_pid(curr, PIDTYPE_PGID, pid); } int ksys_setsid(void) { struct task_struct *group_leader = current->group_leader; struct pid *sid = task_pid(group_leader); pid_t session = pid_vnr(sid); int err = -EPERM; write_lock_irq(&tasklist_lock); /* Fail if I am already a session leader */ if (group_leader->signal->leader) goto out; /* Fail if a process group id already exists that equals the * proposed session id. */ if (pid_task(sid, PIDTYPE_PGID)) goto out; group_leader->signal->leader = 1; set_special_pids(sid); proc_clear_tty(group_leader); err = session; out: write_unlock_irq(&tasklist_lock); if (err > 0) { proc_sid_connector(group_leader); sched_autogroup_create_attach(group_leader); } return err; } SYSCALL_DEFINE0(setsid) { return ksys_setsid(); } DECLARE_RWSEM(uts_sem); #ifdef COMPAT_UTS_MACHINE #define override_architecture(name) \ (personality(current->personality) == PER_LINUX32 && \ copy_to_user(name->machine, COMPAT_UTS_MACHINE, \ sizeof(COMPAT_UTS_MACHINE))) #else #define override_architecture(name) 0 #endif /* * Work around broken programs that cannot handle "Linux 3.0". * Instead we map 3.x to 2.6.40+x, so e.g. 3.0 would be 2.6.40 * And we map 4.x and later versions to 2.6.60+x, so 4.0/5.0/6.0/... would be * 2.6.60. */ static int override_release(char __user *release, size_t len) { int ret = 0; if (current->personality & UNAME26) { const char *rest = UTS_RELEASE; char buf[65] = { 0 }; int ndots = 0; unsigned v; size_t copy; while (*rest) { if (*rest == '.' && ++ndots >= 3) break; if (!isdigit(*rest) && *rest != '.') break; rest++; } v = LINUX_VERSION_PATCHLEVEL + 60; copy = clamp_t(size_t, len, 1, sizeof(buf)); copy = scnprintf(buf, copy, "2.6.%u%s", v, rest); ret = copy_to_user(release, buf, copy + 1); } return ret; } SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name) { struct new_utsname tmp; down_read(&uts_sem); memcpy(&tmp, utsname(), sizeof(tmp)); up_read(&uts_sem); if (copy_to_user(name, &tmp, sizeof(tmp))) return -EFAULT; if (override_release(name->release, sizeof(name->release))) return -EFAULT; if (override_architecture(name)) return -EFAULT; return 0; } #ifdef __ARCH_WANT_SYS_OLD_UNAME /* * Old cruft */ SYSCALL_DEFINE1(uname, struct old_utsname __user *, name) { struct old_utsname tmp; if (!name) return -EFAULT; down_read(&uts_sem); memcpy(&tmp, utsname(), sizeof(tmp)); up_read(&uts_sem); if (copy_to_user(name, &tmp, sizeof(tmp))) return -EFAULT; if (override_release(name->release, sizeof(name->release))) return -EFAULT; if (override_architecture(name)) return -EFAULT; return 0; } SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name) { struct oldold_utsname tmp; if (!name) return -EFAULT; memset(&tmp, 0, sizeof(tmp)); down_read(&uts_sem); memcpy(&tmp.sysname, &utsname()->sysname, __OLD_UTS_LEN); memcpy(&tmp.nodename, &utsname()->nodename, __OLD_UTS_LEN); memcpy(&tmp.release, &utsname()->release, __OLD_UTS_LEN); memcpy(&tmp.version, &utsname()->version, __OLD_UTS_LEN); memcpy(&tmp.machine, &utsname()->machine, __OLD_UTS_LEN); up_read(&uts_sem); if (copy_to_user(name, &tmp, sizeof(tmp))) return -EFAULT; if (override_architecture(name)) return -EFAULT; if (override_release(name->release, sizeof(name->release))) return -EFAULT; return 0; } #endif SYSCALL_DEFINE2(sethostname, char __user *, name, int, len) { int errno; char tmp[__NEW_UTS_LEN]; if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; if (len < 0 || len > __NEW_UTS_LEN) return -EINVAL; errno = -EFAULT; if (!copy_from_user(tmp, name, len)) { struct new_utsname *u; add_device_randomness(tmp, len); down_write(&uts_sem); u = utsname(); memcpy(u->nodename, tmp, len); memset(u->nodename + len, 0, sizeof(u->nodename) - len); errno = 0; uts_proc_notify(UTS_PROC_HOSTNAME); up_write(&uts_sem); } return errno; } #ifdef __ARCH_WANT_SYS_GETHOSTNAME SYSCALL_DEFINE2(gethostname, char __user *, name, int, len) { int i; struct new_utsname *u; char tmp[__NEW_UTS_LEN + 1]; if (len < 0) return -EINVAL; down_read(&uts_sem); u = utsname(); i = 1 + strlen(u->nodename); if (i > len) i = len; memcpy(tmp, u->nodename, i); up_read(&uts_sem); if (copy_to_user(name, tmp, i)) return -EFAULT; return 0; } #endif /* * Only setdomainname; getdomainname can be implemented by calling * uname() */ SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len) { int errno; char tmp[__NEW_UTS_LEN]; if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; if (len < 0 || len > __NEW_UTS_LEN) return -EINVAL; errno = -EFAULT; if (!copy_from_user(tmp, name, len)) { struct new_utsname *u; add_device_randomness(tmp, len); down_write(&uts_sem); u = utsname(); memcpy(u->domainname, tmp, len); memset(u->domainname + len, 0, sizeof(u->domainname) - len); errno = 0; uts_proc_notify(UTS_PROC_DOMAINNAME); up_write(&uts_sem); } return errno; } /* make sure you are allowed to change @tsk limits before calling this */ static int do_prlimit(struct task_struct *tsk, unsigned int resource, struct rlimit *new_rlim, struct rlimit *old_rlim) { struct rlimit *rlim; int retval = 0; if (resource >= RLIM_NLIMITS) return -EINVAL; resource = array_index_nospec(resource, RLIM_NLIMITS); if (new_rlim) { if (new_rlim->rlim_cur > new_rlim->rlim_max) return -EINVAL; if (resource == RLIMIT_NOFILE && new_rlim->rlim_max > sysctl_nr_open) return -EPERM; } /* Holding a refcount on tsk protects tsk->signal from disappearing. */ rlim = tsk->signal->rlim + resource; task_lock(tsk->group_leader); if (new_rlim) { /* * Keep the capable check against init_user_ns until cgroups can * contain all limits. */ if (new_rlim->rlim_max > rlim->rlim_max && !capable(CAP_SYS_RESOURCE)) retval = -EPERM; if (!retval) retval = security_task_setrlimit(tsk, resource, new_rlim); } if (!retval) { if (old_rlim) *old_rlim = *rlim; if (new_rlim) *rlim = *new_rlim; } task_unlock(tsk->group_leader); /* * RLIMIT_CPU handling. Arm the posix CPU timer if the limit is not * infinite. In case of RLIM_INFINITY the posix CPU timer code * ignores the rlimit. */ if (!retval && new_rlim && resource == RLIMIT_CPU && new_rlim->rlim_cur != RLIM_INFINITY && IS_ENABLED(CONFIG_POSIX_TIMERS)) { /* * update_rlimit_cpu can fail if the task is exiting, but there * may be other tasks in the thread group that are not exiting, * and they need their cpu timers adjusted. * * The group_leader is the last task to be released, so if we * cannot update_rlimit_cpu on it, then the entire process is * exiting and we do not need to update at all. */ update_rlimit_cpu(tsk->group_leader, new_rlim->rlim_cur); } return retval; } SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim) { struct rlimit value; int ret; ret = do_prlimit(current, resource, NULL, &value); if (!ret) ret = copy_to_user(rlim, &value, sizeof(*rlim)) ? -EFAULT : 0; return ret; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct compat_rlimit __user *, rlim) { struct rlimit r; struct compat_rlimit r32; if (copy_from_user(&r32, rlim, sizeof(struct compat_rlimit))) return -EFAULT; if (r32.rlim_cur == COMPAT_RLIM_INFINITY) r.rlim_cur = RLIM_INFINITY; else r.rlim_cur = r32.rlim_cur; if (r32.rlim_max == COMPAT_RLIM_INFINITY) r.rlim_max = RLIM_INFINITY; else r.rlim_max = r32.rlim_max; return do_prlimit(current, resource, &r, NULL); } COMPAT_SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct compat_rlimit __user *, rlim) { struct rlimit r; int ret; ret = do_prlimit(current, resource, NULL, &r); if (!ret) { struct compat_rlimit r32; if (r.rlim_cur > COMPAT_RLIM_INFINITY) r32.rlim_cur = COMPAT_RLIM_INFINITY; else r32.rlim_cur = r.rlim_cur; if (r.rlim_max > COMPAT_RLIM_INFINITY) r32.rlim_max = COMPAT_RLIM_INFINITY; else r32.rlim_max = r.rlim_max; if (copy_to_user(rlim, &r32, sizeof(struct compat_rlimit))) return -EFAULT; } return ret; } #endif #ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT /* * Back compatibility for getrlimit. Needed for some apps. */ SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, struct rlimit __user *, rlim) { struct rlimit x; if (resource >= RLIM_NLIMITS) return -EINVAL; resource = array_index_nospec(resource, RLIM_NLIMITS); task_lock(current->group_leader); x = current->signal->rlim[resource]; task_unlock(current->group_leader); if (x.rlim_cur > 0x7FFFFFFF) x.rlim_cur = 0x7FFFFFFF; if (x.rlim_max > 0x7FFFFFFF) x.rlim_max = 0x7FFFFFFF; return copy_to_user(rlim, &x, sizeof(x)) ? -EFAULT : 0; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, struct compat_rlimit __user *, rlim) { struct rlimit r; if (resource >= RLIM_NLIMITS) return -EINVAL; resource = array_index_nospec(resource, RLIM_NLIMITS); task_lock(current->group_leader); r = current->signal->rlim[resource]; task_unlock(current->group_leader); if (r.rlim_cur > 0x7FFFFFFF) r.rlim_cur = 0x7FFFFFFF; if (r.rlim_max > 0x7FFFFFFF) r.rlim_max = 0x7FFFFFFF; if (put_user(r.rlim_cur, &rlim->rlim_cur) || put_user(r.rlim_max, &rlim->rlim_max)) return -EFAULT; return 0; } #endif #endif static inline bool rlim64_is_infinity(__u64 rlim64) { #if BITS_PER_LONG < 64 return rlim64 >= ULONG_MAX; #else return rlim64 == RLIM64_INFINITY; #endif } static void rlim_to_rlim64(const struct rlimit *rlim, struct rlimit64 *rlim64) { if (rlim->rlim_cur == RLIM_INFINITY) rlim64->rlim_cur = RLIM64_INFINITY; else rlim64->rlim_cur = rlim->rlim_cur; if (rlim->rlim_max == RLIM_INFINITY) rlim64->rlim_max = RLIM64_INFINITY; else rlim64->rlim_max = rlim->rlim_max; } static void rlim64_to_rlim(const struct rlimit64 *rlim64, struct rlimit *rlim) { if (rlim64_is_infinity(rlim64->rlim_cur)) rlim->rlim_cur = RLIM_INFINITY; else rlim->rlim_cur = (unsigned long)rlim64->rlim_cur; if (rlim64_is_infinity(rlim64->rlim_max)) rlim->rlim_max = RLIM_INFINITY; else rlim->rlim_max = (unsigned long)rlim64->rlim_max; } /* rcu lock must be held */ static int check_prlimit_permission(struct task_struct *task, unsigned int flags) { const struct cred *cred = current_cred(), *tcred; bool id_match; if (current == task) return 0; tcred = __task_cred(task); id_match = (uid_eq(cred->uid, tcred->euid) && uid_eq(cred->uid, tcred->suid) && uid_eq(cred->uid, tcred->uid) && gid_eq(cred->gid, tcred->egid) && gid_eq(cred->gid, tcred->sgid) && gid_eq(cred->gid, tcred->gid)); if (!id_match && !ns_capable(tcred->user_ns, CAP_SYS_RESOURCE)) return -EPERM; return security_task_prlimit(cred, tcred, flags); } SYSCALL_DEFINE4(prlimit64, pid_t, pid, unsigned int, resource, const struct rlimit64 __user *, new_rlim, struct rlimit64 __user *, old_rlim) { struct rlimit64 old64, new64; struct rlimit old, new; struct task_struct *tsk; unsigned int checkflags = 0; int ret; if (old_rlim) checkflags |= LSM_PRLIMIT_READ; if (new_rlim) { if (copy_from_user(&new64, new_rlim, sizeof(new64))) return -EFAULT; rlim64_to_rlim(&new64, &new); checkflags |= LSM_PRLIMIT_WRITE; } rcu_read_lock(); tsk = pid ? find_task_by_vpid(pid) : current; if (!tsk) { rcu_read_unlock(); return -ESRCH; } ret = check_prlimit_permission(tsk, checkflags); if (ret) { rcu_read_unlock(); return ret; } get_task_struct(tsk); rcu_read_unlock(); ret = do_prlimit(tsk, resource, new_rlim ? &new : NULL, old_rlim ? &old : NULL); if (!ret && old_rlim) { rlim_to_rlim64(&old, &old64); if (copy_to_user(old_rlim, &old64, sizeof(old64))) ret = -EFAULT; } put_task_struct(tsk); return ret; } SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim) { struct rlimit new_rlim; if (copy_from_user(&new_rlim, rlim, sizeof(*rlim))) return -EFAULT; return do_prlimit(current, resource, &new_rlim, NULL); } /* * It would make sense to put struct rusage in the task_struct, * except that would make the task_struct be *really big*. After * task_struct gets moved into malloc'ed memory, it would * make sense to do this. It will make moving the rest of the information * a lot simpler! (Which we're not doing right now because we're not * measuring them yet). * * When sampling multiple threads for RUSAGE_SELF, under SMP we might have * races with threads incrementing their own counters. But since word * reads are atomic, we either get new values or old values and we don't * care which for the sums. We always take the siglock to protect reading * the c* fields from p->signal from races with exit.c updating those * fields when reaping, so a sample either gets all the additions of a * given child after it's reaped, or none so this sample is before reaping. * * Locking: * We need to take the siglock for CHILDEREN, SELF and BOTH * for the cases current multithreaded, non-current single threaded * non-current multithreaded. Thread traversal is now safe with * the siglock held. * Strictly speaking, we donot need to take the siglock if we are current and * single threaded, as no one else can take our signal_struct away, no one * else can reap the children to update signal->c* counters, and no one else * can race with the signal-> fields. If we do not take any lock, the * signal-> fields could be read out of order while another thread was just * exiting. So we should place a read memory barrier when we avoid the lock. * On the writer side, write memory barrier is implied in __exit_signal * as __exit_signal releases the siglock spinlock after updating the signal-> * fields. But we don't do this yet to keep things simple. * */ static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r) { r->ru_nvcsw += t->nvcsw; r->ru_nivcsw += t->nivcsw; r->ru_minflt += t->min_flt; r->ru_majflt += t->maj_flt; r->ru_inblock += task_io_get_inblock(t); r->ru_oublock += task_io_get_oublock(t); } void getrusage(struct task_struct *p, int who, struct rusage *r) { struct task_struct *t; unsigned long flags; u64 tgutime, tgstime, utime, stime; unsigned long maxrss; struct mm_struct *mm; struct signal_struct *sig = p->signal; unsigned int seq = 0; retry: memset(r, 0, sizeof(*r)); utime = stime = 0; maxrss = 0; if (who == RUSAGE_THREAD) { task_cputime_adjusted(current, &utime, &stime); accumulate_thread_rusage(p, r); maxrss = sig->maxrss; goto out_thread; } flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq); switch (who) { case RUSAGE_BOTH: case RUSAGE_CHILDREN: utime = sig->cutime; stime = sig->cstime; r->ru_nvcsw = sig->cnvcsw; r->ru_nivcsw = sig->cnivcsw; r->ru_minflt = sig->cmin_flt; r->ru_majflt = sig->cmaj_flt; r->ru_inblock = sig->cinblock; r->ru_oublock = sig->coublock; maxrss = sig->cmaxrss; if (who == RUSAGE_CHILDREN) break; fallthrough; case RUSAGE_SELF: r->ru_nvcsw += sig->nvcsw; r->ru_nivcsw += sig->nivcsw; r->ru_minflt += sig->min_flt; r->ru_majflt += sig->maj_flt; r->ru_inblock += sig->inblock; r->ru_oublock += sig->oublock; if (maxrss < sig->maxrss) maxrss = sig->maxrss; rcu_read_lock(); __for_each_thread(sig, t) accumulate_thread_rusage(t, r); rcu_read_unlock(); break; default: BUG(); } if (need_seqretry(&sig->stats_lock, seq)) { seq = 1; goto retry; } done_seqretry_irqrestore(&sig->stats_lock, seq, flags); if (who == RUSAGE_CHILDREN) goto out_children; thread_group_cputime_adjusted(p, &tgutime, &tgstime); utime += tgutime; stime += tgstime; out_thread: mm = get_task_mm(p); if (mm) { setmax_mm_hiwater_rss(&maxrss, mm); mmput(mm); } out_children: r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */ r->ru_utime = ns_to_kernel_old_timeval(utime); r->ru_stime = ns_to_kernel_old_timeval(stime); } SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru) { struct rusage r; if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN && who != RUSAGE_THREAD) return -EINVAL; getrusage(current, who, &r); return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(getrusage, int, who, struct compat_rusage __user *, ru) { struct rusage r; if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN && who != RUSAGE_THREAD) return -EINVAL; getrusage(current, who, &r); return put_compat_rusage(&r, ru); } #endif SYSCALL_DEFINE1(umask, int, mask) { mask = xchg(¤t->fs->umask, mask & S_IRWXUGO); return mask; } static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) { struct fd exe; struct inode *inode; int err; exe = fdget(fd); if (!exe.file) return -EBADF; inode = file_inode(exe.file); /* * Because the original mm->exe_file points to executable file, make * sure that this one is executable as well, to avoid breaking an * overall picture. */ err = -EACCES; if (!S_ISREG(inode->i_mode) || path_noexec(&exe.file->f_path)) goto exit; err = file_permission(exe.file, MAY_EXEC); if (err) goto exit; err = replace_mm_exe_file(mm, exe.file); exit: fdput(exe); return err; } /* * Check arithmetic relations of passed addresses. * * WARNING: we don't require any capability here so be very careful * in what is allowed for modification from userspace. */ static int validate_prctl_map_addr(struct prctl_mm_map *prctl_map) { unsigned long mmap_max_addr = TASK_SIZE; int error = -EINVAL, i; static const unsigned char offsets[] = { offsetof(struct prctl_mm_map, start_code), offsetof(struct prctl_mm_map, end_code), offsetof(struct prctl_mm_map, start_data), offsetof(struct prctl_mm_map, end_data), offsetof(struct prctl_mm_map, start_brk), offsetof(struct prctl_mm_map, brk), offsetof(struct prctl_mm_map, start_stack), offsetof(struct prctl_mm_map, arg_start), offsetof(struct prctl_mm_map, arg_end), offsetof(struct prctl_mm_map, env_start), offsetof(struct prctl_mm_map, env_end), }; /* * Make sure the members are not somewhere outside * of allowed address space. */ for (i = 0; i < ARRAY_SIZE(offsets); i++) { u64 val = *(u64 *)((char *)prctl_map + offsets[i]); if ((unsigned long)val >= mmap_max_addr || (unsigned long)val < mmap_min_addr) goto out; } /* * Make sure the pairs are ordered. */ #define __prctl_check_order(__m1, __op, __m2) \ ((unsigned long)prctl_map->__m1 __op \ (unsigned long)prctl_map->__m2) ? 0 : -EINVAL error = __prctl_check_order(start_code, <, end_code); error |= __prctl_check_order(start_data,<=, end_data); error |= __prctl_check_order(start_brk, <=, brk); error |= __prctl_check_order(arg_start, <=, arg_end); error |= __prctl_check_order(env_start, <=, env_end); if (error) goto out; #undef __prctl_check_order error = -EINVAL; /* * Neither we should allow to override limits if they set. */ if (check_data_rlimit(rlimit(RLIMIT_DATA), prctl_map->brk, prctl_map->start_brk, prctl_map->end_data, prctl_map->start_data)) goto out; error = 0; out: return error; } #ifdef CONFIG_CHECKPOINT_RESTORE static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data_size) { struct prctl_mm_map prctl_map = { .exe_fd = (u32)-1, }; unsigned long user_auxv[AT_VECTOR_SIZE]; struct mm_struct *mm = current->mm; int error; BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv)); BUILD_BUG_ON(sizeof(struct prctl_mm_map) > 256); if (opt == PR_SET_MM_MAP_SIZE) return put_user((unsigned int)sizeof(prctl_map), (unsigned int __user *)addr); if (data_size != sizeof(prctl_map)) return -EINVAL; if (copy_from_user(&prctl_map, addr, sizeof(prctl_map))) return -EFAULT; error = validate_prctl_map_addr(&prctl_map); if (error) return error; if (prctl_map.auxv_size) { /* * Someone is trying to cheat the auxv vector. */ if (!prctl_map.auxv || prctl_map.auxv_size > sizeof(mm->saved_auxv)) return -EINVAL; memset(user_auxv, 0, sizeof(user_auxv)); if (copy_from_user(user_auxv, (const void __user *)prctl_map.auxv, prctl_map.auxv_size)) return -EFAULT; /* Last entry must be AT_NULL as specification requires */ user_auxv[AT_VECTOR_SIZE - 2] = AT_NULL; user_auxv[AT_VECTOR_SIZE - 1] = AT_NULL; } if (prctl_map.exe_fd != (u32)-1) { /* * Check if the current user is checkpoint/restore capable. * At the time of this writing, it checks for CAP_SYS_ADMIN * or CAP_CHECKPOINT_RESTORE. * Note that a user with access to ptrace can masquerade an * arbitrary program as any executable, even setuid ones. * This may have implications in the tomoyo subsystem. */ if (!checkpoint_restore_ns_capable(current_user_ns())) return -EPERM; error = prctl_set_mm_exe_file(mm, prctl_map.exe_fd); if (error) return error; } /* * arg_lock protects concurrent updates but we still need mmap_lock for * read to exclude races with sys_brk. */ mmap_read_lock(mm); /* * We don't validate if these members are pointing to * real present VMAs because application may have correspond * VMAs already unmapped and kernel uses these members for statistics * output in procfs mostly, except * * - @start_brk/@brk which are used in do_brk_flags but kernel lookups * for VMAs when updating these members so anything wrong written * here cause kernel to swear at userspace program but won't lead * to any problem in kernel itself */ spin_lock(&mm->arg_lock); mm->start_code = prctl_map.start_code; mm->end_code = prctl_map.end_code; mm->start_data = prctl_map.start_data; mm->end_data = prctl_map.end_data; mm->start_brk = prctl_map.start_brk; mm->brk = prctl_map.brk; mm->start_stack = prctl_map.start_stack; mm->arg_start = prctl_map.arg_start; mm->arg_end = prctl_map.arg_end; mm->env_start = prctl_map.env_start; mm->env_end = prctl_map.env_end; spin_unlock(&mm->arg_lock); /* * Note this update of @saved_auxv is lockless thus * if someone reads this member in procfs while we're * updating -- it may get partly updated results. It's * known and acceptable trade off: we leave it as is to * not introduce additional locks here making the kernel * more complex. */ if (prctl_map.auxv_size) memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv)); mmap_read_unlock(mm); return 0; } #endif /* CONFIG_CHECKPOINT_RESTORE */ static int prctl_set_auxv(struct mm_struct *mm, unsigned long addr, unsigned long len) { /* * This doesn't move the auxiliary vector itself since it's pinned to * mm_struct, but it permits filling the vector with new values. It's * up to the caller to provide sane values here, otherwise userspace * tools which use this vector might be unhappy. */ unsigned long user_auxv[AT_VECTOR_SIZE] = {}; if (len > sizeof(user_auxv)) return -EINVAL; if (copy_from_user(user_auxv, (const void __user *)addr, len)) return -EFAULT; /* Make sure the last entry is always AT_NULL */ user_auxv[AT_VECTOR_SIZE - 2] = 0; user_auxv[AT_VECTOR_SIZE - 1] = 0; BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv)); task_lock(current); memcpy(mm->saved_auxv, user_auxv, len); task_unlock(current); return 0; } static int prctl_set_mm(int opt, unsigned long addr, unsigned long arg4, unsigned long arg5) { struct mm_struct *mm = current->mm; struct prctl_mm_map prctl_map = { .auxv = NULL, .auxv_size = 0, .exe_fd = -1, }; struct vm_area_struct *vma; int error; if (arg5 || (arg4 && (opt != PR_SET_MM_AUXV && opt != PR_SET_MM_MAP && opt != PR_SET_MM_MAP_SIZE))) return -EINVAL; #ifdef CONFIG_CHECKPOINT_RESTORE if (opt == PR_SET_MM_MAP || opt == PR_SET_MM_MAP_SIZE) return prctl_set_mm_map(opt, (const void __user *)addr, arg4); #endif if (!capable(CAP_SYS_RESOURCE)) return -EPERM; if (opt == PR_SET_MM_EXE_FILE) return prctl_set_mm_exe_file(mm, (unsigned int)addr); if (opt == PR_SET_MM_AUXV) return prctl_set_auxv(mm, addr, arg4); if (addr >= TASK_SIZE || addr < mmap_min_addr) return -EINVAL; error = -EINVAL; /* * arg_lock protects concurrent updates of arg boundaries, we need * mmap_lock for a) concurrent sys_brk, b) finding VMA for addr * validation. */ mmap_read_lock(mm); vma = find_vma(mm, addr); spin_lock(&mm->arg_lock); prctl_map.start_code = mm->start_code; prctl_map.end_code = mm->end_code; prctl_map.start_data = mm->start_data; prctl_map.end_data = mm->end_data; prctl_map.start_brk = mm->start_brk; prctl_map.brk = mm->brk; prctl_map.start_stack = mm->start_stack; prctl_map.arg_start = mm->arg_start; prctl_map.arg_end = mm->arg_end; prctl_map.env_start = mm->env_start; prctl_map.env_end = mm->env_end; switch (opt) { case PR_SET_MM_START_CODE: prctl_map.start_code = addr; break; case PR_SET_MM_END_CODE: prctl_map.end_code = addr; break; case PR_SET_MM_START_DATA: prctl_map.start_data = addr; break; case PR_SET_MM_END_DATA: prctl_map.end_data = addr; break; case PR_SET_MM_START_STACK: prctl_map.start_stack = addr; break; case PR_SET_MM_START_BRK: prctl_map.start_brk = addr; break; case PR_SET_MM_BRK: prctl_map.brk = addr; break; case PR_SET_MM_ARG_START: prctl_map.arg_start = addr; break; case PR_SET_MM_ARG_END: prctl_map.arg_end = addr; break; case PR_SET_MM_ENV_START: prctl_map.env_start = addr; break; case PR_SET_MM_ENV_END: prctl_map.env_end = addr; break; default: goto out; } error = validate_prctl_map_addr(&prctl_map); if (error) goto out; switch (opt) { /* * If command line arguments and environment * are placed somewhere else on stack, we can * set them up here, ARG_START/END to setup * command line arguments and ENV_START/END * for environment. */ case PR_SET_MM_START_STACK: case PR_SET_MM_ARG_START: case PR_SET_MM_ARG_END: case PR_SET_MM_ENV_START: case PR_SET_MM_ENV_END: if (!vma) { error = -EFAULT; goto out; } } mm->start_code = prctl_map.start_code; mm->end_code = prctl_map.end_code; mm->start_data = prctl_map.start_data; mm->end_data = prctl_map.end_data; mm->start_brk = prctl_map.start_brk; mm->brk = prctl_map.brk; mm->start_stack = prctl_map.start_stack; mm->arg_start = prctl_map.arg_start; mm->arg_end = prctl_map.arg_end; mm->env_start = prctl_map.env_start; mm->env_end = prctl_map.env_end; error = 0; out: spin_unlock(&mm->arg_lock); mmap_read_unlock(mm); return error; } #ifdef CONFIG_CHECKPOINT_RESTORE static int prctl_get_tid_address(struct task_struct *me, int __user * __user *tid_addr) { return put_user(me->clear_child_tid, tid_addr); } #else static int prctl_get_tid_address(struct task_struct *me, int __user * __user *tid_addr) { return -EINVAL; } #endif static int propagate_has_child_subreaper(struct task_struct *p, void *data) { /* * If task has has_child_subreaper - all its descendants * already have these flag too and new descendants will * inherit it on fork, skip them. * * If we've found child_reaper - skip descendants in * it's subtree as they will never get out pidns. */ if (p->signal->has_child_subreaper || is_child_reaper(task_pid(p))) return 0; p->signal->has_child_subreaper = 1; return 1; } int __weak arch_prctl_spec_ctrl_get(struct task_struct *t, unsigned long which) { return -EINVAL; } int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which, unsigned long ctrl) { return -EINVAL; } #define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LOCAL_THROTTLE) #ifdef CONFIG_ANON_VMA_NAME #define ANON_VMA_NAME_MAX_LEN 80 #define ANON_VMA_NAME_INVALID_CHARS "\\`$[]" static inline bool is_valid_name_char(char ch) { /* printable ascii characters, excluding ANON_VMA_NAME_INVALID_CHARS */ return ch > 0x1f && ch < 0x7f && !strchr(ANON_VMA_NAME_INVALID_CHARS, ch); } static int prctl_set_vma(unsigned long opt, unsigned long addr, unsigned long size, unsigned long arg) { struct mm_struct *mm = current->mm; const char __user *uname; struct anon_vma_name *anon_name = NULL; bool bypass = false; int error; switch (opt) { case PR_SET_VMA_ANON_NAME: uname = (const char __user *)arg; if (uname) { char *name, *pch; name = strndup_user(uname, ANON_VMA_NAME_MAX_LEN); if (IS_ERR(name)) return PTR_ERR(name); for (pch = name; *pch != '\0'; pch++) { if (!is_valid_name_char(*pch)) { kfree(name); return -EINVAL; } } /* anon_vma has its own copy */ anon_name = anon_vma_name_alloc(name); kfree(name); if (!anon_name) return -ENOMEM; } trace_android_rvh_pr_set_vma_name_bypass(mm, addr, size, anon_name, &error, &bypass); if (bypass) return error; mmap_write_lock(mm); error = madvise_set_anon_name(mm, addr, size, anon_name); mmap_write_unlock(mm); anon_vma_name_put(anon_name); break; default: error = -EINVAL; } return error; } #else /* CONFIG_ANON_VMA_NAME */ static int prctl_set_vma(unsigned long opt, unsigned long start, unsigned long size, unsigned long arg) { return -EINVAL; } #endif /* CONFIG_ANON_VMA_NAME */ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { struct task_struct *me = current; unsigned char comm[sizeof(me->comm)]; long error; error = security_task_prctl(option, arg2, arg3, arg4, arg5); if (error != -ENOSYS) return error; error = 0; switch (option) { case PR_SET_PDEATHSIG: if (!valid_signal(arg2)) { error = -EINVAL; break; } me->pdeath_signal = arg2; break; case PR_GET_PDEATHSIG: error = put_user(me->pdeath_signal, (int __user *)arg2); break; case PR_GET_DUMPABLE: error = get_dumpable(me->mm); break; case PR_SET_DUMPABLE: if (arg2 != SUID_DUMP_DISABLE && arg2 != SUID_DUMP_USER) { error = -EINVAL; break; } set_dumpable(me->mm, arg2); break; case PR_SET_UNALIGN: error = SET_UNALIGN_CTL(me, arg2); break; case PR_GET_UNALIGN: error = GET_UNALIGN_CTL(me, arg2); break; case PR_SET_FPEMU: error = SET_FPEMU_CTL(me, arg2); break; case PR_GET_FPEMU: error = GET_FPEMU_CTL(me, arg2); break; case PR_SET_FPEXC: error = SET_FPEXC_CTL(me, arg2); break; case PR_GET_FPEXC: error = GET_FPEXC_CTL(me, arg2); break; case PR_GET_TIMING: error = PR_TIMING_STATISTICAL; break; case PR_SET_TIMING: if (arg2 != PR_TIMING_STATISTICAL) error = -EINVAL; break; case PR_SET_NAME: comm[sizeof(me->comm) - 1] = 0; if (strncpy_from_user(comm, (char __user *)arg2, sizeof(me->comm) - 1) < 0) return -EFAULT; set_task_comm(me, comm); proc_comm_connector(me); break; case PR_GET_NAME: get_task_comm(comm, me); if (copy_to_user((char __user *)arg2, comm, sizeof(comm))) return -EFAULT; break; case PR_GET_ENDIAN: error = GET_ENDIAN(me, arg2); break; case PR_SET_ENDIAN: error = SET_ENDIAN(me, arg2); break; case PR_GET_SECCOMP: error = prctl_get_seccomp(); break; case PR_SET_SECCOMP: error = prctl_set_seccomp(arg2, (char __user *)arg3); break; case PR_GET_TSC: error = GET_TSC_CTL(arg2); break; case PR_SET_TSC: error = SET_TSC_CTL(arg2); break; case PR_TASK_PERF_EVENTS_DISABLE: error = perf_event_task_disable(); break; case PR_TASK_PERF_EVENTS_ENABLE: error = perf_event_task_enable(); break; case PR_GET_TIMERSLACK: if (current->timer_slack_ns > ULONG_MAX) error = ULONG_MAX; else error = current->timer_slack_ns; break; case PR_SET_TIMERSLACK: if (task_is_realtime(current)) break; if (arg2 <= 0) current->timer_slack_ns = current->default_timer_slack_ns; else current->timer_slack_ns = arg2; break; case PR_MCE_KILL: if (arg4 | arg5) return -EINVAL; switch (arg2) { case PR_MCE_KILL_CLEAR: if (arg3 != 0) return -EINVAL; current->flags &= ~PF_MCE_PROCESS; break; case PR_MCE_KILL_SET: current->flags |= PF_MCE_PROCESS; if (arg3 == PR_MCE_KILL_EARLY) current->flags |= PF_MCE_EARLY; else if (arg3 == PR_MCE_KILL_LATE) current->flags &= ~PF_MCE_EARLY; else if (arg3 == PR_MCE_KILL_DEFAULT) current->flags &= ~(PF_MCE_EARLY|PF_MCE_PROCESS); else return -EINVAL; break; default: return -EINVAL; } break; case PR_MCE_KILL_GET: if (arg2 | arg3 | arg4 | arg5) return -EINVAL; if (current->flags & PF_MCE_PROCESS) error = (current->flags & PF_MCE_EARLY) ? PR_MCE_KILL_EARLY : PR_MCE_KILL_LATE; else error = PR_MCE_KILL_DEFAULT; break; case PR_SET_MM: error = prctl_set_mm(arg2, arg3, arg4, arg5); break; case PR_GET_TID_ADDRESS: error = prctl_get_tid_address(me, (int __user * __user *)arg2); break; case PR_SET_CHILD_SUBREAPER: me->signal->is_child_subreaper = !!arg2; if (!arg2) break; walk_process_tree(me, propagate_has_child_subreaper, NULL); break; case PR_GET_CHILD_SUBREAPER: error = put_user(me->signal->is_child_subreaper, (int __user *)arg2); break; case PR_SET_NO_NEW_PRIVS: if (arg2 != 1 || arg3 || arg4 || arg5) return -EINVAL; task_set_no_new_privs(current); break; case PR_GET_NO_NEW_PRIVS: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; return task_no_new_privs(current) ? 1 : 0; case PR_GET_THP_DISABLE: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; error = !!test_bit(MMF_DISABLE_THP, &me->mm->flags); break; case PR_SET_THP_DISABLE: if (arg3 || arg4 || arg5) return -EINVAL; if (mmap_write_lock_killable(me->mm)) return -EINTR; if (arg2) set_bit(MMF_DISABLE_THP, &me->mm->flags); else clear_bit(MMF_DISABLE_THP, &me->mm->flags); mmap_write_unlock(me->mm); break; case PR_MPX_ENABLE_MANAGEMENT: case PR_MPX_DISABLE_MANAGEMENT: /* No longer implemented: */ return -EINVAL; case PR_SET_FP_MODE: error = SET_FP_MODE(me, arg2); break; case PR_GET_FP_MODE: error = GET_FP_MODE(me); break; case PR_SVE_SET_VL: error = SVE_SET_VL(arg2); break; case PR_SVE_GET_VL: error = SVE_GET_VL(); break; case PR_SME_SET_VL: error = SME_SET_VL(arg2); break; case PR_SME_GET_VL: error = SME_GET_VL(); break; case PR_GET_SPECULATION_CTRL: if (arg3 || arg4 || arg5) return -EINVAL; error = arch_prctl_spec_ctrl_get(me, arg2); break; case PR_SET_SPECULATION_CTRL: if (arg4 || arg5) return -EINVAL; error = arch_prctl_spec_ctrl_set(me, arg2, arg3); break; case PR_PAC_RESET_KEYS: if (arg3 || arg4 || arg5) return -EINVAL; error = PAC_RESET_KEYS(me, arg2); break; case PR_PAC_SET_ENABLED_KEYS: if (arg4 || arg5) return -EINVAL; error = PAC_SET_ENABLED_KEYS(me, arg2, arg3); break; case PR_PAC_GET_ENABLED_KEYS: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; error = PAC_GET_ENABLED_KEYS(me); break; case PR_SET_TAGGED_ADDR_CTRL: if (arg3 || arg4 || arg5) return -EINVAL; error = SET_TAGGED_ADDR_CTRL(arg2); break; case PR_GET_TAGGED_ADDR_CTRL: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; error = GET_TAGGED_ADDR_CTRL(); break; case PR_SET_IO_FLUSHER: if (!capable(CAP_SYS_RESOURCE)) return -EPERM; if (arg3 || arg4 || arg5) return -EINVAL; if (arg2 == 1) current->flags |= PR_IO_FLUSHER; else if (!arg2) current->flags &= ~PR_IO_FLUSHER; else return -EINVAL; break; case PR_GET_IO_FLUSHER: if (!capable(CAP_SYS_RESOURCE)) return -EPERM; if (arg2 || arg3 || arg4 || arg5) return -EINVAL; error = (current->flags & PR_IO_FLUSHER) == PR_IO_FLUSHER; break; case PR_SET_SYSCALL_USER_DISPATCH: error = set_syscall_user_dispatch(arg2, arg3, arg4, (char __user *) arg5); break; #ifdef CONFIG_SCHED_CORE case PR_SCHED_CORE: error = sched_core_share_pid(arg2, arg3, arg4, arg5); break; #endif case PR_SET_VMA: error = prctl_set_vma(arg2, arg3, arg4, arg5); break; default: error = -EINVAL; break; } trace_android_vh_syscall_prctl_finished(option, me); return error; } SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep, struct getcpu_cache __user *, unused) { int err = 0; int cpu = raw_smp_processor_id(); if (cpup) err |= put_user(cpu, cpup); if (nodep) err |= put_user(cpu_to_node(cpu), nodep); return err ? -EFAULT : 0; } /** * do_sysinfo - fill in sysinfo struct * @info: pointer to buffer to fill */ static int do_sysinfo(struct sysinfo *info) { unsigned long mem_total, sav_total; unsigned int mem_unit, bitcount; struct timespec64 tp; memset(info, 0, sizeof(struct sysinfo)); ktime_get_boottime_ts64(&tp); timens_add_boottime(&tp); info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0); get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT); info->procs = nr_threads; si_meminfo(info); si_swapinfo(info); /* * If the sum of all the available memory (i.e. ram + swap) * is less than can be stored in a 32 bit unsigned long then * we can be binary compatible with 2.2.x kernels. If not, * well, in that case 2.2.x was broken anyways... * * -Erik Andersen <andersee@debian.org> */ mem_total = info->totalram + info->totalswap; if (mem_total < info->totalram || mem_total < info->totalswap) goto out; bitcount = 0; mem_unit = info->mem_unit; while (mem_unit > 1) { bitcount++; mem_unit >>= 1; sav_total = mem_total; mem_total <<= 1; if (mem_total < sav_total) goto out; } /* * If mem_total did not overflow, multiply all memory values by * info->mem_unit and set it to 1. This leaves things compatible * with 2.2.x, and also retains compatibility with earlier 2.4.x * kernels... */ info->mem_unit = 1; info->totalram <<= bitcount; info->freeram <<= bitcount; info->sharedram <<= bitcount; info->bufferram <<= bitcount; info->totalswap <<= bitcount; info->freeswap <<= bitcount; info->totalhigh <<= bitcount; info->freehigh <<= bitcount; out: return 0; } SYSCALL_DEFINE1(sysinfo, struct sysinfo __user *, info) { struct sysinfo val; do_sysinfo(&val); if (copy_to_user(info, &val, sizeof(struct sysinfo))) return -EFAULT; return 0; } #ifdef CONFIG_COMPAT struct compat_sysinfo { s32 uptime; u32 loads[3]; u32 totalram; u32 freeram; u32 sharedram; u32 bufferram; u32 totalswap; u32 freeswap; u16 procs; u16 pad; u32 totalhigh; u32 freehigh; u32 mem_unit; char _f[20-2*sizeof(u32)-sizeof(int)]; }; COMPAT_SYSCALL_DEFINE1(sysinfo, struct compat_sysinfo __user *, info) { struct sysinfo s; struct compat_sysinfo s_32; do_sysinfo(&s); /* Check to see if any memory value is too large for 32-bit and scale * down if needed */ if (upper_32_bits(s.totalram) || upper_32_bits(s.totalswap)) { int bitcount = 0; while (s.mem_unit < PAGE_SIZE) { s.mem_unit <<= 1; bitcount++; } s.totalram >>= bitcount; s.freeram >>= bitcount; s.sharedram >>= bitcount; s.bufferram >>= bitcount; s.totalswap >>= bitcount; s.freeswap >>= bitcount; s.totalhigh >>= bitcount; s.freehigh >>= bitcount; } memset(&s_32, 0, sizeof(s_32)); s_32.uptime = s.uptime; s_32.loads[0] = s.loads[0]; s_32.loads[1] = s.loads[1]; s_32.loads[2] = s.loads[2]; s_32.totalram = s.totalram; s_32.freeram = s.freeram; s_32.sharedram = s.sharedram; s_32.bufferram = s.bufferram; s_32.totalswap = s.totalswap; s_32.freeswap = s.freeswap; s_32.procs = s.procs; s_32.totalhigh = s.totalhigh; s_32.freehigh = s.freehigh; s_32.mem_unit = s.mem_unit; if (copy_to_user(info, &s_32, sizeof(s_32))) return -EFAULT; return 0; } #endif /* CONFIG_COMPAT */ |
| 5 5 5 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Module kallsyms support * * Copyright (C) 2010 Rusty Russell */ #include <linux/module.h> #include <linux/kallsyms.h> #include <linux/buildid.h> #include <linux/bsearch.h> #include "internal.h" /* Lookup exported symbol in given range of kernel_symbols */ static const struct kernel_symbol *lookup_exported_symbol(const char *name, const struct kernel_symbol *start, const struct kernel_symbol *stop) { return bsearch(name, start, stop - start, sizeof(struct kernel_symbol), cmp_name); } static int is_exported(const char *name, unsigned long value, const struct module *mod) { const struct kernel_symbol *ks; if (!mod) ks = lookup_exported_symbol(name, __start___ksymtab, __stop___ksymtab); else ks = lookup_exported_symbol(name, mod->syms, mod->syms + mod->num_syms); return ks && kernel_symbol_value(ks) == value; } /* As per nm */ static char elf_type(const Elf_Sym *sym, const struct load_info *info) { const Elf_Shdr *sechdrs = info->sechdrs; if (ELF_ST_BIND(sym->st_info) == STB_WEAK) { if (ELF_ST_TYPE(sym->st_info) == STT_OBJECT) return 'v'; else return 'w'; } if (sym->st_shndx == SHN_UNDEF) return 'U'; if (sym->st_shndx == SHN_ABS || sym->st_shndx == info->index.pcpu) return 'a'; if (sym->st_shndx >= SHN_LORESERVE) return '?'; if (sechdrs[sym->st_shndx].sh_flags & SHF_EXECINSTR) return 't'; if (sechdrs[sym->st_shndx].sh_flags & SHF_ALLOC && sechdrs[sym->st_shndx].sh_type != SHT_NOBITS) { if (!(sechdrs[sym->st_shndx].sh_flags & SHF_WRITE)) return 'r'; else if (sechdrs[sym->st_shndx].sh_flags & ARCH_SHF_SMALL) return 'g'; else return 'd'; } if (sechdrs[sym->st_shndx].sh_type == SHT_NOBITS) { if (sechdrs[sym->st_shndx].sh_flags & ARCH_SHF_SMALL) return 's'; else return 'b'; } if (strstarts(info->secstrings + sechdrs[sym->st_shndx].sh_name, ".debug")) { return 'n'; } return '?'; } static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs, unsigned int shnum, unsigned int pcpundx) { const Elf_Shdr *sec; if (src->st_shndx == SHN_UNDEF || src->st_shndx >= shnum || !src->st_name) return false; #ifdef CONFIG_KALLSYMS_ALL if (src->st_shndx == pcpundx) return true; #endif sec = sechdrs + src->st_shndx; if (!(sec->sh_flags & SHF_ALLOC) #ifndef CONFIG_KALLSYMS_ALL || !(sec->sh_flags & SHF_EXECINSTR) #endif || (sec->sh_entsize & INIT_OFFSET_MASK)) return false; return true; } /* * We only allocate and copy the strings needed by the parts of symtab * we keep. This is simple, but has the effect of making multiple * copies of duplicates. We could be more sophisticated, see * linux-kernel thread starting with * <73defb5e4bca04a6431392cc341112b1@localhost>. */ void layout_symtab(struct module *mod, struct load_info *info) { Elf_Shdr *symsect = info->sechdrs + info->index.sym; Elf_Shdr *strsect = info->sechdrs + info->index.str; const Elf_Sym *src; unsigned int i, nsrc, ndst, strtab_size = 0; /* Put symbol section at end of init part of module. */ symsect->sh_flags |= SHF_ALLOC; symsect->sh_entsize = module_get_offset(mod, &mod->init_layout.size, symsect, info->index.sym) | INIT_OFFSET_MASK; pr_debug("\t%s\n", info->secstrings + symsect->sh_name); src = (void *)info->hdr + symsect->sh_offset; nsrc = symsect->sh_size / sizeof(*src); /* Compute total space required for the core symbols' strtab. */ for (ndst = i = 0; i < nsrc; i++) { if (i == 0 || is_livepatch_module(mod) || is_core_symbol(src + i, info->sechdrs, info->hdr->e_shnum, info->index.pcpu)) { strtab_size += strlen(&info->strtab[src[i].st_name]) + 1; ndst++; } } /* Append room for core symbols at end of core part. */ info->symoffs = ALIGN(mod->data_layout.size, symsect->sh_addralign ?: 1); info->stroffs = mod->data_layout.size = info->symoffs + ndst * sizeof(Elf_Sym); mod->data_layout.size += strtab_size; /* Note add_kallsyms() computes strtab_size as core_typeoffs - stroffs */ info->core_typeoffs = mod->data_layout.size; mod->data_layout.size += ndst * sizeof(char); mod->data_layout.size = strict_align(mod->data_layout.size); /* Put string table section at end of init part of module. */ strsect->sh_flags |= SHF_ALLOC; strsect->sh_entsize = module_get_offset(mod, &mod->init_layout.size, strsect, info->index.str) | INIT_OFFSET_MASK; pr_debug("\t%s\n", info->secstrings + strsect->sh_name); /* We'll tack temporary mod_kallsyms on the end. */ mod->init_layout.size = ALIGN(mod->init_layout.size, __alignof__(struct mod_kallsyms)); info->mod_kallsyms_init_off = mod->init_layout.size; mod->init_layout.size += sizeof(struct mod_kallsyms); info->init_typeoffs = mod->init_layout.size; mod->init_layout.size += nsrc * sizeof(char); mod->init_layout.size = strict_align(mod->init_layout.size); } /* * We use the full symtab and strtab which layout_symtab arranged to * be appended to the init section. Later we switch to the cut-down * core-only ones. */ void add_kallsyms(struct module *mod, const struct load_info *info) { unsigned int i, ndst; const Elf_Sym *src; Elf_Sym *dst; char *s; Elf_Shdr *symsec = &info->sechdrs[info->index.sym]; unsigned long strtab_size; /* Set up to point into init section. */ mod->kallsyms = (void __rcu *)mod->init_layout.base + info->mod_kallsyms_init_off; rcu_read_lock(); /* The following is safe since this pointer cannot change */ rcu_dereference(mod->kallsyms)->symtab = (void *)symsec->sh_addr; rcu_dereference(mod->kallsyms)->num_symtab = symsec->sh_size / sizeof(Elf_Sym); /* Make sure we get permanent strtab: don't use info->strtab. */ rcu_dereference(mod->kallsyms)->strtab = (void *)info->sechdrs[info->index.str].sh_addr; rcu_dereference(mod->kallsyms)->typetab = mod->init_layout.base + info->init_typeoffs; /* * Now populate the cut down core kallsyms for after init * and set types up while we still have access to sections. */ mod->core_kallsyms.symtab = dst = mod->data_layout.base + info->symoffs; mod->core_kallsyms.strtab = s = mod->data_layout.base + info->stroffs; mod->core_kallsyms.typetab = mod->data_layout.base + info->core_typeoffs; strtab_size = info->core_typeoffs - info->stroffs; src = rcu_dereference(mod->kallsyms)->symtab; for (ndst = i = 0; i < rcu_dereference(mod->kallsyms)->num_symtab; i++) { rcu_dereference(mod->kallsyms)->typetab[i] = elf_type(src + i, info); if (i == 0 || is_livepatch_module(mod) || is_core_symbol(src + i, info->sechdrs, info->hdr->e_shnum, info->index.pcpu)) { ssize_t ret; mod->core_kallsyms.typetab[ndst] = rcu_dereference(mod->kallsyms)->typetab[i]; dst[ndst] = src[i]; dst[ndst++].st_name = s - mod->core_kallsyms.strtab; ret = strscpy(s, &rcu_dereference(mod->kallsyms)->strtab[src[i].st_name], strtab_size); if (ret < 0) break; s += ret + 1; strtab_size -= ret + 1; } } rcu_read_unlock(); mod->core_kallsyms.num_symtab = ndst; } #if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) void init_build_id(struct module *mod, const struct load_info *info) { const Elf_Shdr *sechdr; unsigned int i; for (i = 0; i < info->hdr->e_shnum; i++) { sechdr = &info->sechdrs[i]; if (!sect_empty(sechdr) && sechdr->sh_type == SHT_NOTE && !build_id_parse_buf((void *)sechdr->sh_addr, mod->build_id, sechdr->sh_size)) break; } } #else void init_build_id(struct module *mod, const struct load_info *info) { } #endif /* * This ignores the intensely annoying "mapping symbols" found * in ARM ELF files: $a, $t and $d. */ static inline int is_arm_mapping_symbol(const char *str) { if (str[0] == '.' && str[1] == 'L') return true; return str[0] == '$' && strchr("axtd", str[1]) && (str[2] == '\0' || str[2] == '.'); } static const char *kallsyms_symbol_name(struct mod_kallsyms *kallsyms, unsigned int symnum) { return kallsyms->strtab + kallsyms->symtab[symnum].st_name; } /* * Given a module and address, find the corresponding symbol and return its name * while providing its size and offset if needed. */ static const char *find_kallsyms_symbol(struct module *mod, unsigned long addr, unsigned long *size, unsigned long *offset) { unsigned int i, best = 0; unsigned long nextval, bestval; struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms); /* At worse, next value is at end of module */ if (within_module_init(addr, mod)) nextval = (unsigned long)mod->init_layout.base + mod->init_layout.text_size; else nextval = (unsigned long)mod->core_layout.base + mod->core_layout.text_size; bestval = kallsyms_symbol_value(&kallsyms->symtab[best]); /* * Scan for closest preceding symbol, and next symbol. (ELF * starts real symbols at 1). */ for (i = 1; i < kallsyms->num_symtab; i++) { const Elf_Sym *sym = &kallsyms->symtab[i]; unsigned long thisval = kallsyms_symbol_value(sym); if (sym->st_shndx == SHN_UNDEF) continue; /* * We ignore unnamed symbols: they're uninformative * and inserted at a whim. */ if (*kallsyms_symbol_name(kallsyms, i) == '\0' || is_arm_mapping_symbol(kallsyms_symbol_name(kallsyms, i))) continue; if (thisval <= addr && thisval > bestval) { best = i; bestval = thisval; } if (thisval > addr && thisval < nextval) nextval = thisval; } if (!best) return NULL; if (size) *size = nextval - bestval; if (offset) *offset = addr - bestval; return kallsyms_symbol_name(kallsyms, best); } void * __weak dereference_module_function_descriptor(struct module *mod, void *ptr) { return ptr; } /* * For kallsyms to ask for address resolution. NULL means not found. Careful * not to lock to avoid deadlock on oopses, simply disable preemption. */ const char *module_address_lookup(unsigned long addr, unsigned long *size, unsigned long *offset, char **modname, const unsigned char **modbuildid, char *namebuf) { const char *ret = NULL; struct module *mod; preempt_disable(); mod = __module_address(addr); if (mod) { if (modname) *modname = mod->name; if (modbuildid) { #if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) *modbuildid = mod->build_id; #else *modbuildid = NULL; #endif } ret = find_kallsyms_symbol(mod, addr, size, offset); } /* Make a copy in here where it's safe */ if (ret) { strncpy(namebuf, ret, KSYM_NAME_LEN - 1); ret = namebuf; } preempt_enable(); return ret; } int lookup_module_symbol_name(unsigned long addr, char *symname) { struct module *mod; preempt_disable(); list_for_each_entry_rcu(mod, &modules, list) { if (mod->state == MODULE_STATE_UNFORMED) continue; if (within_module(addr, mod)) { const char *sym; sym = find_kallsyms_symbol(mod, addr, NULL, NULL); if (!sym) goto out; strscpy(symname, sym, KSYM_NAME_LEN); preempt_enable(); return 0; } } out: preempt_enable(); return -ERANGE; } int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name) { struct module *mod; preempt_disable(); list_for_each_entry_rcu(mod, &modules, list) { if (mod->state == MODULE_STATE_UNFORMED) continue; if (within_module(addr, mod)) { const char *sym; sym = find_kallsyms_symbol(mod, addr, size, offset); if (!sym) goto out; if (modname) strscpy(modname, mod->name, MODULE_NAME_LEN); if (name) strscpy(name, sym, KSYM_NAME_LEN); preempt_enable(); return 0; } } out: preempt_enable(); return -ERANGE; } int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *name, char *module_name, int *exported) { struct module *mod; preempt_disable(); list_for_each_entry_rcu(mod, &modules, list) { struct mod_kallsyms *kallsyms; if (mod->state == MODULE_STATE_UNFORMED) continue; kallsyms = rcu_dereference_sched(mod->kallsyms); if (symnum < kallsyms->num_symtab) { const Elf_Sym *sym = &kallsyms->symtab[symnum]; *value = kallsyms_symbol_value(sym); *type = kallsyms->typetab[symnum]; strscpy(name, kallsyms_symbol_name(kallsyms, symnum), KSYM_NAME_LEN); strscpy(module_name, mod->name, MODULE_NAME_LEN); *exported = is_exported(name, *value, mod); preempt_enable(); return 0; } symnum -= kallsyms->num_symtab; } preempt_enable(); return -ERANGE; } /* Given a module and name of symbol, find and return the symbol's value */ unsigned long find_kallsyms_symbol_value(struct module *mod, const char *name) { unsigned int i; struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms); for (i = 0; i < kallsyms->num_symtab; i++) { const Elf_Sym *sym = &kallsyms->symtab[i]; if (strcmp(name, kallsyms_symbol_name(kallsyms, i)) == 0 && sym->st_shndx != SHN_UNDEF) return kallsyms_symbol_value(sym); } return 0; } static unsigned long __module_kallsyms_lookup_name(const char *name) { struct module *mod; char *colon; colon = strnchr(name, MODULE_NAME_LEN, ':'); if (colon) { mod = find_module_all(name, colon - name, false); if (mod) return find_kallsyms_symbol_value(mod, colon + 1); return 0; } list_for_each_entry_rcu(mod, &modules, list) { unsigned long ret; if (mod->state == MODULE_STATE_UNFORMED) continue; ret = find_kallsyms_symbol_value(mod, name); if (ret) return ret; } return 0; } /* Look for this name: can be of form module:name. */ unsigned long module_kallsyms_lookup_name(const char *name) { unsigned long ret; /* Don't lock: we're in enough trouble already. */ preempt_disable(); ret = __module_kallsyms_lookup_name(name); preempt_enable(); return ret; } int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, unsigned long), void *data) { struct module *mod; unsigned int i; int ret = 0; mutex_lock(&module_mutex); list_for_each_entry(mod, &modules, list) { struct mod_kallsyms *kallsyms; if (mod->state == MODULE_STATE_UNFORMED) continue; /* Use rcu_dereference_sched() to remain compliant with the sparse tool */ preempt_disable(); kallsyms = rcu_dereference_sched(mod->kallsyms); preempt_enable(); for (i = 0; i < kallsyms->num_symtab; i++) { const Elf_Sym *sym = &kallsyms->symtab[i]; if (sym->st_shndx == SHN_UNDEF) continue; ret = fn(data, kallsyms_symbol_name(kallsyms, i), mod, kallsyms_symbol_value(sym)); if (ret != 0) goto out; } } out: mutex_unlock(&module_mutex); return ret; } |
| 58 58 58 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2020 Christoph Hellwig. * * Support for "universal" pointers that can point to either kernel or userspace * memory. */ #ifndef _LINUX_SOCKPTR_H #define _LINUX_SOCKPTR_H #include <linux/slab.h> #include <linux/uaccess.h> typedef struct { union { void *kernel; void __user *user; }; bool is_kernel : 1; } sockptr_t; static inline bool sockptr_is_kernel(sockptr_t sockptr) { return sockptr.is_kernel; } static inline sockptr_t KERNEL_SOCKPTR(void *p) { return (sockptr_t) { .kernel = p, .is_kernel = true }; } static inline sockptr_t USER_SOCKPTR(void __user *p) { return (sockptr_t) { .user = p }; } static inline bool sockptr_is_null(sockptr_t sockptr) { if (sockptr_is_kernel(sockptr)) return !sockptr.kernel; return !sockptr.user; } static inline int copy_from_sockptr_offset(void *dst, sockptr_t src, size_t offset, size_t size) { if (!sockptr_is_kernel(src)) return copy_from_user(dst, src.user + offset, size); memcpy(dst, src.kernel + offset, size); return 0; } /* Deprecated. * This is unsafe, unless caller checked user provided optlen. * Prefer copy_safe_from_sockptr() instead. */ static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) { return copy_from_sockptr_offset(dst, src, 0, size); } /** * copy_safe_from_sockptr: copy a struct from sockptr * @dst: Destination address, in kernel space. This buffer must be @ksize * bytes long. * @ksize: Size of @dst struct. * @optval: Source address. (in user or kernel space) * @optlen: Size of @optval data. * * Returns: * * -EINVAL: @optlen < @ksize * * -EFAULT: access to userspace failed. * * 0 : @ksize bytes were copied */ static inline int copy_safe_from_sockptr(void *dst, size_t ksize, sockptr_t optval, unsigned int optlen) { if (optlen < ksize) return -EINVAL; if (copy_from_sockptr(dst, optval, ksize)) return -EFAULT; return 0; } static inline int copy_to_sockptr_offset(sockptr_t dst, size_t offset, const void *src, size_t size) { if (!sockptr_is_kernel(dst)) return copy_to_user(dst.user + offset, src, size); memcpy(dst.kernel + offset, src, size); return 0; } static inline int copy_to_sockptr(sockptr_t dst, const void *src, size_t size) { return copy_to_sockptr_offset(dst, 0, src, size); } static inline void *memdup_sockptr(sockptr_t src, size_t len) { void *p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_sockptr(p, src, len)) { kfree(p); return ERR_PTR(-EFAULT); } return p; } static inline void *memdup_sockptr_nul(sockptr_t src, size_t len) { char *p = kmalloc_track_caller(len + 1, GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_sockptr(p, src, len)) { kfree(p); return ERR_PTR(-EFAULT); } p[len] = '\0'; return p; } static inline long strncpy_from_sockptr(char *dst, sockptr_t src, size_t count) { if (sockptr_is_kernel(src)) { size_t len = min(strnlen(src.kernel, count - 1) + 1, count); memcpy(dst, src.kernel, len); return len; } return strncpy_from_user(dst, src.user, count); } static inline int check_zeroed_sockptr(sockptr_t src, size_t offset, size_t size) { if (!sockptr_is_kernel(src)) return check_zeroed_user(src.user + offset, size); return memchr_inv(src.kernel + offset, 0, size) == NULL; } #endif /* _LINUX_SOCKPTR_H */ |
| 2 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 | /* * Update: The Berkeley copyright was changed, and the change * is retroactive to all "true" BSD software (ie everything * from UCB as opposed to other peoples code that just carried * the same license). The new copyright doesn't clash with the * GPL, so the module-only restriction has been removed.. */ /* Because this code is derived from the 4.3BSD compress source: * * Copyright (c) 1985, 1986 The Regents of the University of California. * All rights reserved. * * This code is derived from software contributed to Berkeley by * James A. Woods, derived from original work by Spencer Thomas * and Joseph Orost. * * 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. All advertising materials mentioning features or use of this software * must display the following acknowledgement: * This product includes software developed by the University of * California, Berkeley and its contributors. * 4. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS 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 REGENTS 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. */ /* * This version is for use with contiguous buffers on Linux-derived systems. * * ==FILEVERSION 20000226== * * NOTE TO MAINTAINERS: * If you modify this file at all, please set the number above to the * date of the modification as YYMMDD (year month day). * bsd_comp.c is shipped with a PPP distribution as well as with * the kernel; if everyone increases the FILEVERSION number above, * then scripts can do the right thing when deciding whether to * install a new bsd_comp.c file. Don't change the format of that * line otherwise, so the installation script can recognize it. * * From: bsd_comp.c,v 1.3 1994/12/08 01:59:58 paulus Exp */ #include <linux/module.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/string.h> #include <linux/ppp_defs.h> #undef PACKETPTR #define PACKETPTR 1 #include <linux/ppp-comp.h> #undef PACKETPTR #include <asm/byteorder.h> /* * PPP "BSD compress" compression * The differences between this compression and the classic BSD LZW * source are obvious from the requirement that the classic code worked * with files while this handles arbitrarily long streams that * are broken into packets. They are: * * When the code size expands, a block of junk is not emitted by * the compressor and not expected by the decompressor. * * New codes are not necessarily assigned every time an old * code is output by the compressor. This is because a packet * end forces a code to be emitted, but does not imply that a * new sequence has been seen. * * The compression ratio is checked at the first end of a packet * after the appropriate gap. Besides simplifying and speeding * things up, this makes it more likely that the transmitter * and receiver will agree when the dictionary is cleared when * compression is not going well. */ /* * Macros to extract protocol version and number of bits * from the third byte of the BSD Compress CCP configuration option. */ #define BSD_VERSION(x) ((x) >> 5) #define BSD_NBITS(x) ((x) & 0x1F) #define BSD_CURRENT_VERSION 1 /* * A dictionary for doing BSD compress. */ struct bsd_dict { union { /* hash value */ unsigned long fcode; struct { #if defined(__LITTLE_ENDIAN) /* Little endian order */ unsigned short prefix; /* preceding code */ unsigned char suffix; /* last character of new code */ unsigned char pad; #elif defined(__BIG_ENDIAN) /* Big endian order */ unsigned char pad; unsigned char suffix; /* last character of new code */ unsigned short prefix; /* preceding code */ #else #error Endianness not defined... #endif } hs; } f; unsigned short codem1; /* output of hash table -1 */ unsigned short cptr; /* map code to hash table entry */ }; struct bsd_db { int totlen; /* length of this structure */ unsigned int hsize; /* size of the hash table */ unsigned char hshift; /* used in hash function */ unsigned char n_bits; /* current bits/code */ unsigned char maxbits; /* maximum bits/code */ unsigned char debug; /* non-zero if debug desired */ unsigned char unit; /* ppp unit number */ unsigned short seqno; /* sequence # of next packet */ unsigned int mru; /* size of receive (decompress) bufr */ unsigned int maxmaxcode; /* largest valid code */ unsigned int max_ent; /* largest code in use */ unsigned int in_count; /* uncompressed bytes, aged */ unsigned int bytes_out; /* compressed bytes, aged */ unsigned int ratio; /* recent compression ratio */ unsigned int checkpoint; /* when to next check the ratio */ unsigned int clear_count; /* times dictionary cleared */ unsigned int incomp_count; /* incompressible packets */ unsigned int incomp_bytes; /* incompressible bytes */ unsigned int uncomp_count; /* uncompressed packets */ unsigned int uncomp_bytes; /* uncompressed bytes */ unsigned int comp_count; /* compressed packets */ unsigned int comp_bytes; /* compressed bytes */ unsigned short *lens; /* array of lengths of codes */ struct bsd_dict *dict; /* dictionary */ }; #define BSD_OVHD 2 /* BSD compress overhead/packet */ #define MIN_BSD_BITS 9 #define BSD_INIT_BITS MIN_BSD_BITS #define MAX_BSD_BITS 15 static void bsd_free (void *state); static void *bsd_alloc(unsigned char *options, int opt_len, int decomp); static void *bsd_comp_alloc (unsigned char *options, int opt_len); static void *bsd_decomp_alloc (unsigned char *options, int opt_len); static int bsd_init (void *db, unsigned char *options, int opt_len, int unit, int debug, int decomp); static int bsd_comp_init (void *state, unsigned char *options, int opt_len, int unit, int opthdr, int debug); static int bsd_decomp_init (void *state, unsigned char *options, int opt_len, int unit, int opthdr, int mru, int debug); static void bsd_reset (void *state); static void bsd_comp_stats (void *state, struct compstat *stats); static int bsd_compress (void *state, unsigned char *rptr, unsigned char *obuf, int isize, int osize); static void bsd_incomp (void *state, unsigned char *ibuf, int icnt); static int bsd_decompress (void *state, unsigned char *ibuf, int isize, unsigned char *obuf, int osize); /* These are in ppp_generic.c */ extern int ppp_register_compressor (struct compressor *cp); extern void ppp_unregister_compressor (struct compressor *cp); /* * the next two codes should not be changed lightly, as they must not * lie within the contiguous general code space. */ #define CLEAR 256 /* table clear output code */ #define FIRST 257 /* first free entry */ #define LAST 255 #define MAXCODE(b) ((1 << (b)) - 1) #define BADCODEM1 MAXCODE(MAX_BSD_BITS) #define BSD_HASH(prefix,suffix,hshift) ((((unsigned long)(suffix))<<(hshift)) \ ^ (unsigned long)(prefix)) #define BSD_KEY(prefix,suffix) ((((unsigned long)(suffix)) << 16) \ + (unsigned long)(prefix)) #define CHECK_GAP 10000 /* Ratio check interval */ #define RATIO_SCALE_LOG 8 #define RATIO_SCALE (1<<RATIO_SCALE_LOG) #define RATIO_MAX (0x7fffffff>>RATIO_SCALE_LOG) /* * clear the dictionary */ static void bsd_clear(struct bsd_db *db) { db->clear_count++; db->max_ent = FIRST-1; db->n_bits = BSD_INIT_BITS; db->bytes_out = 0; db->in_count = 0; db->ratio = 0; db->checkpoint = CHECK_GAP; } /* * If the dictionary is full, then see if it is time to reset it. * * Compute the compression ratio using fixed-point arithmetic * with 8 fractional bits. * * Since we have an infinite stream instead of a single file, * watch only the local compression ratio. * * Since both peers must reset the dictionary at the same time even in * the absence of CLEAR codes (while packets are incompressible), they * must compute the same ratio. */ static int bsd_check (struct bsd_db *db) /* 1=output CLEAR */ { unsigned int new_ratio; if (db->in_count >= db->checkpoint) { /* age the ratio by limiting the size of the counts */ if (db->in_count >= RATIO_MAX || db->bytes_out >= RATIO_MAX) { db->in_count -= (db->in_count >> 2); db->bytes_out -= (db->bytes_out >> 2); } db->checkpoint = db->in_count + CHECK_GAP; if (db->max_ent >= db->maxmaxcode) { /* Reset the dictionary only if the ratio is worse, * or if it looks as if it has been poisoned * by incompressible data. * * This does not overflow, because * db->in_count <= RATIO_MAX. */ new_ratio = db->in_count << RATIO_SCALE_LOG; if (db->bytes_out != 0) { new_ratio /= db->bytes_out; } if (new_ratio < db->ratio || new_ratio < 1 * RATIO_SCALE) { bsd_clear (db); return 1; } db->ratio = new_ratio; } } return 0; } /* * Return statistics. */ static void bsd_comp_stats (void *state, struct compstat *stats) { struct bsd_db *db = (struct bsd_db *) state; stats->unc_bytes = db->uncomp_bytes; stats->unc_packets = db->uncomp_count; stats->comp_bytes = db->comp_bytes; stats->comp_packets = db->comp_count; stats->inc_bytes = db->incomp_bytes; stats->inc_packets = db->incomp_count; stats->in_count = db->in_count; stats->bytes_out = db->bytes_out; } /* * Reset state, as on a CCP ResetReq. */ static void bsd_reset (void *state) { struct bsd_db *db = (struct bsd_db *) state; bsd_clear(db); db->seqno = 0; db->clear_count = 0; } /* * Release the compression structure */ static void bsd_free (void *state) { struct bsd_db *db = state; if (!db) return; /* * Release the dictionary */ vfree(db->dict); db->dict = NULL; /* * Release the string buffer */ vfree(db->lens); db->lens = NULL; /* * Finally release the structure itself. */ kfree(db); } /* * Allocate space for a (de) compressor. */ static void *bsd_alloc (unsigned char *options, int opt_len, int decomp) { int bits; unsigned int hsize, hshift, maxmaxcode; struct bsd_db *db; if (opt_len != 3 || options[0] != CI_BSD_COMPRESS || options[1] != 3 || BSD_VERSION(options[2]) != BSD_CURRENT_VERSION) { return NULL; } bits = BSD_NBITS(options[2]); switch (bits) { case 9: /* needs 82152 for both directions */ case 10: /* needs 84144 */ case 11: /* needs 88240 */ case 12: /* needs 96432 */ hsize = 5003; hshift = 4; break; case 13: /* needs 176784 */ hsize = 9001; hshift = 5; break; case 14: /* needs 353744 */ hsize = 18013; hshift = 6; break; case 15: /* needs 691440 */ hsize = 35023; hshift = 7; break; case 16: /* needs 1366160--far too much, */ /* hsize = 69001; */ /* and 69001 is too big for cptr */ /* hshift = 8; */ /* in struct bsd_db */ /* break; */ default: return NULL; } /* * Allocate the main control structure for this instance. */ maxmaxcode = MAXCODE(bits); db = kzalloc(sizeof (struct bsd_db), GFP_KERNEL); if (!db) { return NULL; } /* * Allocate space for the dictionary. This may be more than one page in * length. */ db->dict = vmalloc(array_size(hsize, sizeof(struct bsd_dict))); if (!db->dict) { bsd_free (db); return NULL; } /* * If this is the compression buffer then there is no length data. */ if (!decomp) { db->lens = NULL; } /* * For decompression, the length information is needed as well. */ else { db->lens = vmalloc(array_size(sizeof(db->lens[0]), (maxmaxcode + 1))); if (!db->lens) { bsd_free (db); return NULL; } } /* * Initialize the data information for the compression code */ db->totlen = sizeof (struct bsd_db) + (sizeof (struct bsd_dict) * hsize); db->hsize = hsize; db->hshift = hshift; db->maxmaxcode = maxmaxcode; db->maxbits = bits; return (void *) db; } static void *bsd_comp_alloc (unsigned char *options, int opt_len) { return bsd_alloc (options, opt_len, 0); } static void *bsd_decomp_alloc (unsigned char *options, int opt_len) { return bsd_alloc (options, opt_len, 1); } /* * Initialize the database. */ static int bsd_init (void *state, unsigned char *options, int opt_len, int unit, int debug, int decomp) { struct bsd_db *db = state; int indx; if ((opt_len != 3) || (options[0] != CI_BSD_COMPRESS) || (options[1] != 3) || (BSD_VERSION(options[2]) != BSD_CURRENT_VERSION) || (BSD_NBITS(options[2]) != db->maxbits) || (decomp && db->lens == NULL)) { return 0; } if (decomp) { indx = LAST; do { db->lens[indx] = 1; } while (indx-- > 0); } indx = db->hsize; while (indx-- != 0) { db->dict[indx].codem1 = BADCODEM1; db->dict[indx].cptr = 0; } db->unit = unit; db->mru = 0; #ifndef DEBUG if (debug) #endif db->debug = 1; bsd_reset(db); return 1; } static int bsd_comp_init (void *state, unsigned char *options, int opt_len, int unit, int opthdr, int debug) { return bsd_init (state, options, opt_len, unit, debug, 0); } static int bsd_decomp_init (void *state, unsigned char *options, int opt_len, int unit, int opthdr, int mru, int debug) { return bsd_init (state, options, opt_len, unit, debug, 1); } /* * Obtain pointers to the various structures in the compression tables */ #define dict_ptrx(p,idx) &(p->dict[idx]) #define lens_ptrx(p,idx) &(p->lens[idx]) #ifdef DEBUG static unsigned short *lens_ptr(struct bsd_db *db, int idx) { if ((unsigned int) idx > (unsigned int) db->maxmaxcode) { printk ("<9>ppp: lens_ptr(%d) > max\n", idx); idx = 0; } return lens_ptrx (db, idx); } static struct bsd_dict *dict_ptr(struct bsd_db *db, int idx) { if ((unsigned int) idx >= (unsigned int) db->hsize) { printk ("<9>ppp: dict_ptr(%d) > max\n", idx); idx = 0; } return dict_ptrx (db, idx); } #else #define lens_ptr(db,idx) lens_ptrx(db,idx) #define dict_ptr(db,idx) dict_ptrx(db,idx) #endif /* * compress a packet * * The result of this function is the size of the compressed * packet. A zero is returned if the packet was not compressed * for some reason, such as the size being larger than uncompressed. * * One change from the BSD compress command is that when the * code size expands, we do not output a bunch of padding. */ static int bsd_compress (void *state, unsigned char *rptr, unsigned char *obuf, int isize, int osize) { struct bsd_db *db; int hshift; unsigned int max_ent; unsigned int n_bits; unsigned int bitno; unsigned long accm; int ent; unsigned long fcode; struct bsd_dict *dictp; unsigned char c; int hval; int disp; int ilen; int mxcode; unsigned char *wptr; int olen; #define PUTBYTE(v) \ { \ ++olen; \ if (wptr) \ { \ *wptr++ = (unsigned char) (v); \ if (olen >= osize) \ { \ wptr = NULL; \ } \ } \ } #define OUTPUT(ent) \ { \ bitno -= n_bits; \ accm |= ((ent) << bitno); \ do \ { \ PUTBYTE(accm >> 24); \ accm <<= 8; \ bitno += 8; \ } \ while (bitno <= 24); \ } /* * If the protocol is not in the range we're interested in, * just return without compressing the packet. If it is, * the protocol becomes the first byte to compress. */ ent = PPP_PROTOCOL(rptr); if (ent < 0x21 || ent > 0xf9) { return 0; } db = (struct bsd_db *) state; hshift = db->hshift; max_ent = db->max_ent; n_bits = db->n_bits; bitno = 32; accm = 0; mxcode = MAXCODE (n_bits); /* Initialize the output pointers */ wptr = obuf; olen = PPP_HDRLEN + BSD_OVHD; if (osize > isize) { osize = isize; } /* This is the PPP header information */ if (wptr) { *wptr++ = PPP_ADDRESS(rptr); *wptr++ = PPP_CONTROL(rptr); *wptr++ = 0; *wptr++ = PPP_COMP; *wptr++ = db->seqno >> 8; *wptr++ = db->seqno; } /* Skip the input header */ rptr += PPP_HDRLEN; isize -= PPP_HDRLEN; ilen = ++isize; /* Low byte of protocol is counted as input */ while (--ilen > 0) { c = *rptr++; fcode = BSD_KEY (ent, c); hval = BSD_HASH (ent, c, hshift); dictp = dict_ptr (db, hval); /* Validate and then check the entry. */ if (dictp->codem1 >= max_ent) { goto nomatch; } if (dictp->f.fcode == fcode) { ent = dictp->codem1 + 1; continue; /* found (prefix,suffix) */ } /* continue probing until a match or invalid entry */ disp = (hval == 0) ? 1 : hval; do { hval += disp; if (hval >= db->hsize) { hval -= db->hsize; } dictp = dict_ptr (db, hval); if (dictp->codem1 >= max_ent) { goto nomatch; } } while (dictp->f.fcode != fcode); ent = dictp->codem1 + 1; /* finally found (prefix,suffix) */ continue; nomatch: OUTPUT(ent); /* output the prefix */ /* code -> hashtable */ if (max_ent < db->maxmaxcode) { struct bsd_dict *dictp2; struct bsd_dict *dictp3; int indx; /* expand code size if needed */ if (max_ent >= mxcode) { db->n_bits = ++n_bits; mxcode = MAXCODE (n_bits); } /* Invalidate old hash table entry using * this code, and then take it over. */ dictp2 = dict_ptr (db, max_ent + 1); indx = dictp2->cptr; dictp3 = dict_ptr (db, indx); if (dictp3->codem1 == max_ent) { dictp3->codem1 = BADCODEM1; } dictp2->cptr = hval; dictp->codem1 = max_ent; dictp->f.fcode = fcode; db->max_ent = ++max_ent; if (db->lens) { unsigned short *len1 = lens_ptr (db, max_ent); unsigned short *len2 = lens_ptr (db, ent); *len1 = *len2 + 1; } } ent = c; } OUTPUT(ent); /* output the last code */ db->bytes_out += olen - PPP_HDRLEN - BSD_OVHD; db->uncomp_bytes += isize; db->in_count += isize; ++db->uncomp_count; ++db->seqno; if (bitno < 32) { ++db->bytes_out; /* must be set before calling bsd_check */ } /* * Generate the clear command if needed */ if (bsd_check(db)) { OUTPUT (CLEAR); } /* * Pad dribble bits of last code with ones. * Do not emit a completely useless byte of ones. */ if (bitno != 32) { PUTBYTE((accm | (0xff << (bitno-8))) >> 24); } /* * Increase code size if we would have without the packet * boundary because the decompressor will do so. */ if (max_ent >= mxcode && max_ent < db->maxmaxcode) { db->n_bits++; } /* If output length is too large then this is an incomplete frame. */ if (wptr == NULL) { ++db->incomp_count; db->incomp_bytes += isize; olen = 0; } else /* Count the number of compressed frames */ { ++db->comp_count; db->comp_bytes += olen; } /* Return the resulting output length */ return olen; #undef OUTPUT #undef PUTBYTE } /* * Update the "BSD Compress" dictionary on the receiver for * incompressible data by pretending to compress the incoming data. */ static void bsd_incomp (void *state, unsigned char *ibuf, int icnt) { (void) bsd_compress (state, ibuf, (char *) 0, icnt, 0); } /* * Decompress "BSD Compress". * * Because of patent problems, we return DECOMP_ERROR for errors * found by inspecting the input data and for system problems, but * DECOMP_FATALERROR for any errors which could possibly be said to * be being detected "after" decompression. For DECOMP_ERROR, * we can issue a CCP reset-request; for DECOMP_FATALERROR, we may be * infringing a patent of Motorola's if we do, so we take CCP down * instead. * * Given that the frame has the correct sequence number and a good FCS, * errors such as invalid codes in the input most likely indicate a * bug, so we return DECOMP_FATALERROR for them in order to turn off * compression, even though they are detected by inspecting the input. */ static int bsd_decompress (void *state, unsigned char *ibuf, int isize, unsigned char *obuf, int osize) { struct bsd_db *db; unsigned int max_ent; unsigned long accm; unsigned int bitno; /* 1st valid bit in accm */ unsigned int n_bits; unsigned int tgtbitno; /* bitno when we have a code */ struct bsd_dict *dictp; int explen; int seq; unsigned int incode; unsigned int oldcode; unsigned int finchar; unsigned char *p; unsigned char *wptr; int adrs; int ctrl; int ilen; int codelen; int extra; db = (struct bsd_db *) state; max_ent = db->max_ent; accm = 0; bitno = 32; /* 1st valid bit in accm */ n_bits = db->n_bits; tgtbitno = 32 - n_bits; /* bitno when we have a code */ /* * Save the address/control from the PPP header * and then get the sequence number. */ adrs = PPP_ADDRESS (ibuf); ctrl = PPP_CONTROL (ibuf); seq = (ibuf[4] << 8) + ibuf[5]; ibuf += (PPP_HDRLEN + 2); ilen = isize - (PPP_HDRLEN + 2); /* * Check the sequence number and give up if it differs from * the value we're expecting. */ if (seq != db->seqno) { if (db->debug) { printk("bsd_decomp%d: bad sequence # %d, expected %d\n", db->unit, seq, db->seqno - 1); } return DECOMP_ERROR; } ++db->seqno; db->bytes_out += ilen; /* * Fill in the ppp header, but not the last byte of the protocol * (that comes from the decompressed data). */ wptr = obuf; *wptr++ = adrs; *wptr++ = ctrl; *wptr++ = 0; oldcode = CLEAR; explen = 3; /* * Keep the checkpoint correctly so that incompressible packets * clear the dictionary at the proper times. */ for (;;) { if (ilen-- <= 0) { db->in_count += (explen - 3); /* don't count the header */ break; } /* * Accumulate bytes until we have a complete code. * Then get the next code, relying on the 32-bit, * unsigned accm to mask the result. */ bitno -= 8; accm |= *ibuf++ << bitno; if (tgtbitno < bitno) { continue; } incode = accm >> tgtbitno; accm <<= n_bits; bitno += n_bits; /* * The dictionary must only be cleared at the end of a packet. */ if (incode == CLEAR) { if (ilen > 0) { if (db->debug) { printk("bsd_decomp%d: bad CLEAR\n", db->unit); } return DECOMP_FATALERROR; /* probably a bug */ } bsd_clear(db); break; } if ((incode > max_ent + 2) || (incode > db->maxmaxcode) || (incode > max_ent && oldcode == CLEAR)) { if (db->debug) { printk("bsd_decomp%d: bad code 0x%x oldcode=0x%x ", db->unit, incode, oldcode); printk("max_ent=0x%x explen=%d seqno=%d\n", max_ent, explen, db->seqno); } return DECOMP_FATALERROR; /* probably a bug */ } /* Special case for KwKwK string. */ if (incode > max_ent) { finchar = oldcode; extra = 1; } else { finchar = incode; extra = 0; } codelen = *(lens_ptr (db, finchar)); explen += codelen + extra; if (explen > osize) { if (db->debug) { printk("bsd_decomp%d: ran out of mru\n", db->unit); #ifdef DEBUG printk(" len=%d, finchar=0x%x, codelen=%d, explen=%d\n", ilen, finchar, codelen, explen); #endif } return DECOMP_FATALERROR; } /* * Decode this code and install it in the decompressed buffer. */ wptr += codelen; p = wptr; while (finchar > LAST) { struct bsd_dict *dictp2 = dict_ptr (db, finchar); dictp = dict_ptr (db, dictp2->cptr); #ifdef DEBUG if (--codelen <= 0 || dictp->codem1 != finchar-1) { if (codelen <= 0) { printk("bsd_decomp%d: fell off end of chain ", db->unit); printk("0x%x at 0x%x by 0x%x, max_ent=0x%x\n", incode, finchar, dictp2->cptr, max_ent); } else { if (dictp->codem1 != finchar-1) { printk("bsd_decomp%d: bad code chain 0x%x " "finchar=0x%x ", db->unit, incode, finchar); printk("oldcode=0x%x cptr=0x%x codem1=0x%x\n", oldcode, dictp2->cptr, dictp->codem1); } } return DECOMP_FATALERROR; } #endif *--p = dictp->f.hs.suffix; finchar = dictp->f.hs.prefix; } *--p = finchar; #ifdef DEBUG if (--codelen != 0) { printk("bsd_decomp%d: short by %d after code 0x%x, max_ent=0x%x\n", db->unit, codelen, incode, max_ent); } #endif if (extra) /* the KwKwK case again */ { *wptr++ = finchar; } /* * If not first code in a packet, and * if not out of code space, then allocate a new code. * * Keep the hash table correct so it can be used * with uncompressed packets. */ if (oldcode != CLEAR && max_ent < db->maxmaxcode) { struct bsd_dict *dictp2, *dictp3; unsigned short *lens1, *lens2; unsigned long fcode; int hval, disp, indx; fcode = BSD_KEY(oldcode,finchar); hval = BSD_HASH(oldcode,finchar,db->hshift); dictp = dict_ptr (db, hval); /* look for a free hash table entry */ if (dictp->codem1 < max_ent) { disp = (hval == 0) ? 1 : hval; do { hval += disp; if (hval >= db->hsize) { hval -= db->hsize; } dictp = dict_ptr (db, hval); } while (dictp->codem1 < max_ent); } /* * Invalidate previous hash table entry * assigned this code, and then take it over */ dictp2 = dict_ptr (db, max_ent + 1); indx = dictp2->cptr; dictp3 = dict_ptr (db, indx); if (dictp3->codem1 == max_ent) { dictp3->codem1 = BADCODEM1; } dictp2->cptr = hval; dictp->codem1 = max_ent; dictp->f.fcode = fcode; db->max_ent = ++max_ent; /* Update the length of this string. */ lens1 = lens_ptr (db, max_ent); lens2 = lens_ptr (db, oldcode); *lens1 = *lens2 + 1; /* Expand code size if needed. */ if (max_ent >= MAXCODE(n_bits) && max_ent < db->maxmaxcode) { db->n_bits = ++n_bits; tgtbitno = 32-n_bits; } } oldcode = incode; } ++db->comp_count; ++db->uncomp_count; db->comp_bytes += isize - BSD_OVHD - PPP_HDRLEN; db->uncomp_bytes += explen; if (bsd_check(db)) { if (db->debug) { printk("bsd_decomp%d: peer should have cleared dictionary on %d\n", db->unit, db->seqno - 1); } } return explen; } /************************************************************* * Table of addresses for the BSD compression module *************************************************************/ static struct compressor ppp_bsd_compress = { .compress_proto = CI_BSD_COMPRESS, .comp_alloc = bsd_comp_alloc, .comp_free = bsd_free, .comp_init = bsd_comp_init, .comp_reset = bsd_reset, .compress = bsd_compress, .comp_stat = bsd_comp_stats, .decomp_alloc = bsd_decomp_alloc, .decomp_free = bsd_free, .decomp_init = bsd_decomp_init, .decomp_reset = bsd_reset, .decompress = bsd_decompress, .incomp = bsd_incomp, .decomp_stat = bsd_comp_stats, .owner = THIS_MODULE }; /************************************************************* * Module support routines *************************************************************/ static int __init bsdcomp_init(void) { int answer = ppp_register_compressor(&ppp_bsd_compress); if (answer == 0) printk(KERN_INFO "PPP BSD Compression module registered\n"); return answer; } static void __exit bsdcomp_cleanup(void) { ppp_unregister_compressor(&ppp_bsd_compress); } module_init(bsdcomp_init); module_exit(bsdcomp_cleanup); MODULE_LICENSE("Dual BSD/GPL"); MODULE_ALIAS("ppp-compress-" __stringify(CI_BSD_COMPRESS)); |
| 3326 3326 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 | /* Copyright 2011, Siemens AG * written by Alexander Smirnov <alex.bluesman.smirnov@gmail.com> */ /* Based on patches from Jon Smirl <jonsmirl@gmail.com> * Copyright (c) 2011 Jon Smirl <jonsmirl@gmail.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 * as published by the Free Software Foundation. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. */ /* Jon's code is based on 6lowpan implementation for Contiki which is: * Copyright (c) 2008, Swedish Institute of Computer Science. * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of the Institute nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE INSTITUTE AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE INSTITUTE OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. */ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/ieee802154.h> #include <linux/if_arp.h> #include <net/ipv6.h> #include "6lowpan_i.h" static int open_count; static const struct header_ops lowpan_header_ops = { .create = lowpan_header_create, }; static int lowpan_dev_init(struct net_device *ldev) { netdev_lockdep_set_classes(ldev); return 0; } static int lowpan_open(struct net_device *dev) { if (!open_count) lowpan_rx_init(); open_count++; return 0; } static int lowpan_stop(struct net_device *dev) { open_count--; if (!open_count) lowpan_rx_exit(); return 0; } static int lowpan_neigh_construct(struct net_device *dev, struct neighbour *n) { struct lowpan_802154_neigh *neigh = lowpan_802154_neigh(neighbour_priv(n)); /* default no short_addr is available for a neighbour */ neigh->short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC); return 0; } static int lowpan_get_iflink(const struct net_device *dev) { return lowpan_802154_dev(dev)->wdev->ifindex; } static const struct net_device_ops lowpan_netdev_ops = { .ndo_init = lowpan_dev_init, .ndo_start_xmit = lowpan_xmit, .ndo_open = lowpan_open, .ndo_stop = lowpan_stop, .ndo_neigh_construct = lowpan_neigh_construct, .ndo_get_iflink = lowpan_get_iflink, }; static void lowpan_setup(struct net_device *ldev) { memset(ldev->broadcast, 0xff, IEEE802154_ADDR_LEN); /* We need an ipv6hdr as minimum len when calling xmit */ ldev->hard_header_len = sizeof(struct ipv6hdr); ldev->flags = IFF_BROADCAST | IFF_MULTICAST; ldev->priv_flags |= IFF_NO_QUEUE; ldev->netdev_ops = &lowpan_netdev_ops; ldev->header_ops = &lowpan_header_ops; ldev->needs_free_netdev = true; ldev->features |= NETIF_F_NETNS_LOCAL; } static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != IEEE802154_ADDR_LEN) return -EINVAL; } return 0; } static int lowpan_newlink(struct net *src_net, struct net_device *ldev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net_device *wdev; int ret; ASSERT_RTNL(); pr_debug("adding new link\n"); if (!tb[IFLA_LINK]) return -EINVAL; /* find and hold wpan device */ wdev = dev_get_by_index(dev_net(ldev), nla_get_u32(tb[IFLA_LINK])); if (!wdev) return -ENODEV; if (wdev->type != ARPHRD_IEEE802154) { dev_put(wdev); return -EINVAL; } if (wdev->ieee802154_ptr->lowpan_dev) { dev_put(wdev); return -EBUSY; } lowpan_802154_dev(ldev)->wdev = wdev; /* Set the lowpan hardware address to the wpan hardware address. */ __dev_addr_set(ldev, wdev->dev_addr, IEEE802154_ADDR_LEN); /* We need headroom for possible wpan_dev_hard_header call and tailroom * for encryption/fcs handling. The lowpan interface will replace * the IPv6 header with 6LoWPAN header. At worst case the 6LoWPAN * header has LOWPAN_IPHC_MAX_HEADER_LEN more bytes than the IPv6 * header. */ ldev->needed_headroom = LOWPAN_IPHC_MAX_HEADER_LEN + wdev->needed_headroom; ldev->needed_tailroom = wdev->needed_tailroom; ldev->neigh_priv_len = sizeof(struct lowpan_802154_neigh); ret = lowpan_register_netdevice(ldev, LOWPAN_LLTYPE_IEEE802154); if (ret < 0) { dev_put(wdev); return ret; } wdev->ieee802154_ptr->lowpan_dev = ldev; return 0; } static void lowpan_dellink(struct net_device *ldev, struct list_head *head) { struct net_device *wdev = lowpan_802154_dev(ldev)->wdev; ASSERT_RTNL(); wdev->ieee802154_ptr->lowpan_dev = NULL; lowpan_unregister_netdevice(ldev); dev_put(wdev); } static struct rtnl_link_ops lowpan_link_ops __read_mostly = { .kind = "lowpan", .priv_size = LOWPAN_PRIV_SIZE(sizeof(struct lowpan_802154_dev)), .setup = lowpan_setup, .newlink = lowpan_newlink, .dellink = lowpan_dellink, .validate = lowpan_validate, }; static inline int __init lowpan_netlink_init(void) { return rtnl_link_register(&lowpan_link_ops); } static inline void lowpan_netlink_fini(void) { rtnl_link_unregister(&lowpan_link_ops); } static int lowpan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *ndev = netdev_notifier_info_to_dev(ptr); struct wpan_dev *wpan_dev; if (ndev->type != ARPHRD_IEEE802154) return NOTIFY_DONE; wpan_dev = ndev->ieee802154_ptr; if (!wpan_dev) return NOTIFY_DONE; switch (event) { case NETDEV_UNREGISTER: /* Check if wpan interface is unregistered that we * also delete possible lowpan interfaces which belongs * to the wpan interface. */ if (wpan_dev->lowpan_dev) lowpan_dellink(wpan_dev->lowpan_dev, NULL); break; default: return NOTIFY_DONE; } return NOTIFY_OK; } static struct notifier_block lowpan_dev_notifier = { .notifier_call = lowpan_device_event, }; static int __init lowpan_init_module(void) { int err = 0; err = lowpan_net_frag_init(); if (err < 0) goto out; err = lowpan_netlink_init(); if (err < 0) goto out_frag; err = register_netdevice_notifier(&lowpan_dev_notifier); if (err < 0) goto out_pack; return 0; out_pack: lowpan_netlink_fini(); out_frag: lowpan_net_frag_exit(); out: return err; } static void __exit lowpan_cleanup_module(void) { lowpan_netlink_fini(); lowpan_net_frag_exit(); unregister_netdevice_notifier(&lowpan_dev_notifier); } module_init(lowpan_init_module); module_exit(lowpan_cleanup_module); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("lowpan"); |
| 367 373 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* auditfilter.c -- filtering of audit events * * Copyright 2003-2004 Red Hat, Inc. * Copyright 2005 Hewlett-Packard Development Company, L.P. * Copyright 2005 IBM Corporation */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/audit.h> #include <linux/kthread.h> #include <linux/mutex.h> #include <linux/fs.h> #include <linux/namei.h> #include <linux/netlink.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/security.h> #include <net/net_namespace.h> #include <net/sock.h> #include "audit.h" /* * Locking model: * * audit_filter_mutex: * Synchronizes writes and blocking reads of audit's filterlist * data. Rcu is used to traverse the filterlist and access * contents of structs audit_entry, audit_watch and opaque * LSM rules during filtering. If modified, these structures * must be copied and replace their counterparts in the filterlist. * An audit_parent struct is not accessed during filtering, so may * be written directly provided audit_filter_mutex is held. */ /* Audit filter lists, defined in <linux/audit.h> */ struct list_head audit_filter_list[AUDIT_NR_FILTERS] = { LIST_HEAD_INIT(audit_filter_list[0]), LIST_HEAD_INIT(audit_filter_list[1]), LIST_HEAD_INIT(audit_filter_list[2]), LIST_HEAD_INIT(audit_filter_list[3]), LIST_HEAD_INIT(audit_filter_list[4]), LIST_HEAD_INIT(audit_filter_list[5]), LIST_HEAD_INIT(audit_filter_list[6]), LIST_HEAD_INIT(audit_filter_list[7]), #if AUDIT_NR_FILTERS != 8 #error Fix audit_filter_list initialiser #endif }; static struct list_head audit_rules_list[AUDIT_NR_FILTERS] = { LIST_HEAD_INIT(audit_rules_list[0]), LIST_HEAD_INIT(audit_rules_list[1]), LIST_HEAD_INIT(audit_rules_list[2]), LIST_HEAD_INIT(audit_rules_list[3]), LIST_HEAD_INIT(audit_rules_list[4]), LIST_HEAD_INIT(audit_rules_list[5]), LIST_HEAD_INIT(audit_rules_list[6]), LIST_HEAD_INIT(audit_rules_list[7]), }; DEFINE_MUTEX(audit_filter_mutex); static void audit_free_lsm_field(struct audit_field *f) { switch (f->type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: kfree(f->lsm_str); security_audit_rule_free(f->lsm_rule); } } static inline void audit_free_rule(struct audit_entry *e) { int i; struct audit_krule *erule = &e->rule; /* some rules don't have associated watches */ if (erule->watch) audit_put_watch(erule->watch); if (erule->fields) for (i = 0; i < erule->field_count; i++) audit_free_lsm_field(&erule->fields[i]); kfree(erule->fields); kfree(erule->filterkey); kfree(e); } void audit_free_rule_rcu(struct rcu_head *head) { struct audit_entry *e = container_of(head, struct audit_entry, rcu); audit_free_rule(e); } /* Initialize an audit filterlist entry. */ static inline struct audit_entry *audit_init_entry(u32 field_count) { struct audit_entry *entry; struct audit_field *fields; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (unlikely(!entry)) return NULL; fields = kcalloc(field_count, sizeof(*fields), GFP_KERNEL); if (unlikely(!fields)) { kfree(entry); return NULL; } entry->rule.fields = fields; return entry; } /* Unpack a filter field's string representation from user-space * buffer. */ char *audit_unpack_string(void **bufp, size_t *remain, size_t len) { char *str; if (!*bufp || (len == 0) || (len > *remain)) return ERR_PTR(-EINVAL); /* Of the currently implemented string fields, PATH_MAX * defines the longest valid length. */ if (len > PATH_MAX) return ERR_PTR(-ENAMETOOLONG); str = kmalloc(len + 1, GFP_KERNEL); if (unlikely(!str)) return ERR_PTR(-ENOMEM); memcpy(str, *bufp, len); str[len] = 0; *bufp += len; *remain -= len; return str; } /* Translate an inode field to kernel representation. */ static inline int audit_to_inode(struct audit_krule *krule, struct audit_field *f) { if ((krule->listnr != AUDIT_FILTER_EXIT && krule->listnr != AUDIT_FILTER_URING_EXIT) || krule->inode_f || krule->watch || krule->tree || (f->op != Audit_equal && f->op != Audit_not_equal)) return -EINVAL; krule->inode_f = f; return 0; } static __u32 *classes[AUDIT_SYSCALL_CLASSES]; int __init audit_register_class(int class, unsigned *list) { __u32 *p = kcalloc(AUDIT_BITMASK_SIZE, sizeof(__u32), GFP_KERNEL); if (!p) return -ENOMEM; while (*list != ~0U) { unsigned n = *list++; if (n >= AUDIT_BITMASK_SIZE * 32 - AUDIT_SYSCALL_CLASSES) { kfree(p); return -EINVAL; } p[AUDIT_WORD(n)] |= AUDIT_BIT(n); } if (class >= AUDIT_SYSCALL_CLASSES || classes[class]) { kfree(p); return -EINVAL; } classes[class] = p; return 0; } int audit_match_class(int class, unsigned syscall) { if (unlikely(syscall >= AUDIT_BITMASK_SIZE * 32)) return 0; if (unlikely(class >= AUDIT_SYSCALL_CLASSES || !classes[class])) return 0; return classes[class][AUDIT_WORD(syscall)] & AUDIT_BIT(syscall); } #ifdef CONFIG_AUDITSYSCALL static inline int audit_match_class_bits(int class, u32 *mask) { int i; if (classes[class]) { for (i = 0; i < AUDIT_BITMASK_SIZE; i++) if (mask[i] & classes[class][i]) return 0; } return 1; } static int audit_match_signal(struct audit_entry *entry) { struct audit_field *arch = entry->rule.arch_f; if (!arch) { /* When arch is unspecified, we must check both masks on biarch * as syscall number alone is ambiguous. */ return (audit_match_class_bits(AUDIT_CLASS_SIGNAL, entry->rule.mask) && audit_match_class_bits(AUDIT_CLASS_SIGNAL_32, entry->rule.mask)); } switch(audit_classify_arch(arch->val)) { case 0: /* native */ return (audit_match_class_bits(AUDIT_CLASS_SIGNAL, entry->rule.mask)); case 1: /* 32bit on biarch */ return (audit_match_class_bits(AUDIT_CLASS_SIGNAL_32, entry->rule.mask)); default: return 1; } } #endif /* Common user-space to kernel rule translation. */ static inline struct audit_entry *audit_to_entry_common(struct audit_rule_data *rule) { unsigned listnr; struct audit_entry *entry; int i, err; err = -EINVAL; listnr = rule->flags & ~AUDIT_FILTER_PREPEND; switch(listnr) { default: goto exit_err; #ifdef CONFIG_AUDITSYSCALL case AUDIT_FILTER_ENTRY: pr_err("AUDIT_FILTER_ENTRY is deprecated\n"); goto exit_err; case AUDIT_FILTER_EXIT: case AUDIT_FILTER_URING_EXIT: case AUDIT_FILTER_TASK: #endif case AUDIT_FILTER_USER: case AUDIT_FILTER_EXCLUDE: case AUDIT_FILTER_FS: ; } if (unlikely(rule->action == AUDIT_POSSIBLE)) { pr_err("AUDIT_POSSIBLE is deprecated\n"); goto exit_err; } if (rule->action != AUDIT_NEVER && rule->action != AUDIT_ALWAYS) goto exit_err; if (rule->field_count > AUDIT_MAX_FIELDS) goto exit_err; err = -ENOMEM; entry = audit_init_entry(rule->field_count); if (!entry) goto exit_err; entry->rule.flags = rule->flags & AUDIT_FILTER_PREPEND; entry->rule.listnr = listnr; entry->rule.action = rule->action; entry->rule.field_count = rule->field_count; for (i = 0; i < AUDIT_BITMASK_SIZE; i++) entry->rule.mask[i] = rule->mask[i]; for (i = 0; i < AUDIT_SYSCALL_CLASSES; i++) { int bit = AUDIT_BITMASK_SIZE * 32 - i - 1; __u32 *p = &entry->rule.mask[AUDIT_WORD(bit)]; __u32 *class; if (!(*p & AUDIT_BIT(bit))) continue; *p &= ~AUDIT_BIT(bit); class = classes[i]; if (class) { int j; for (j = 0; j < AUDIT_BITMASK_SIZE; j++) entry->rule.mask[j] |= class[j]; } } return entry; exit_err: return ERR_PTR(err); } static u32 audit_ops[] = { [Audit_equal] = AUDIT_EQUAL, [Audit_not_equal] = AUDIT_NOT_EQUAL, [Audit_bitmask] = AUDIT_BIT_MASK, [Audit_bittest] = AUDIT_BIT_TEST, [Audit_lt] = AUDIT_LESS_THAN, [Audit_gt] = AUDIT_GREATER_THAN, [Audit_le] = AUDIT_LESS_THAN_OR_EQUAL, [Audit_ge] = AUDIT_GREATER_THAN_OR_EQUAL, }; static u32 audit_to_op(u32 op) { u32 n; for (n = Audit_equal; n < Audit_bad && audit_ops[n] != op; n++) ; return n; } /* check if an audit field is valid */ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f) { switch (f->type) { case AUDIT_MSGTYPE: if (entry->rule.listnr != AUDIT_FILTER_EXCLUDE && entry->rule.listnr != AUDIT_FILTER_USER) return -EINVAL; break; case AUDIT_FSTYPE: if (entry->rule.listnr != AUDIT_FILTER_FS) return -EINVAL; break; case AUDIT_PERM: if (entry->rule.listnr == AUDIT_FILTER_URING_EXIT) return -EINVAL; break; } switch (entry->rule.listnr) { case AUDIT_FILTER_FS: switch(f->type) { case AUDIT_FSTYPE: case AUDIT_FILTERKEY: break; default: return -EINVAL; } } /* Check for valid field type and op */ switch (f->type) { case AUDIT_ARG0: case AUDIT_ARG1: case AUDIT_ARG2: case AUDIT_ARG3: case AUDIT_PERS: /* <uapi/linux/personality.h> */ case AUDIT_DEVMINOR: /* all ops are valid */ break; case AUDIT_UID: case AUDIT_EUID: case AUDIT_SUID: case AUDIT_FSUID: case AUDIT_LOGINUID: case AUDIT_OBJ_UID: case AUDIT_GID: case AUDIT_EGID: case AUDIT_SGID: case AUDIT_FSGID: case AUDIT_OBJ_GID: case AUDIT_PID: case AUDIT_MSGTYPE: case AUDIT_PPID: case AUDIT_DEVMAJOR: case AUDIT_EXIT: case AUDIT_SUCCESS: case AUDIT_INODE: case AUDIT_SESSIONID: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: case AUDIT_SADDR_FAM: /* bit ops are only useful on syscall args */ if (f->op == Audit_bitmask || f->op == Audit_bittest) return -EINVAL; break; case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_WATCH: case AUDIT_DIR: case AUDIT_FILTERKEY: case AUDIT_LOGINUID_SET: case AUDIT_ARCH: case AUDIT_FSTYPE: case AUDIT_PERM: case AUDIT_FILETYPE: case AUDIT_FIELD_COMPARE: case AUDIT_EXE: /* only equal and not equal valid ops */ if (f->op != Audit_not_equal && f->op != Audit_equal) return -EINVAL; break; default: /* field not recognized */ return -EINVAL; } /* Check for select valid field values */ switch (f->type) { case AUDIT_LOGINUID_SET: if ((f->val != 0) && (f->val != 1)) return -EINVAL; break; case AUDIT_PERM: if (f->val & ~15) return -EINVAL; break; case AUDIT_FILETYPE: if (f->val & ~S_IFMT) return -EINVAL; break; case AUDIT_FIELD_COMPARE: if (f->val > AUDIT_MAX_FIELD_COMPARE) return -EINVAL; break; case AUDIT_SADDR_FAM: if (f->val >= AF_MAX) return -EINVAL; break; default: break; } return 0; } /* Translate struct audit_rule_data to kernel's rule representation. */ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, size_t datasz) { int err = 0; struct audit_entry *entry; void *bufp; size_t remain = datasz - sizeof(struct audit_rule_data); int i; char *str; struct audit_fsnotify_mark *audit_mark; entry = audit_to_entry_common(data); if (IS_ERR(entry)) goto exit_nofree; bufp = data->buf; for (i = 0; i < data->field_count; i++) { struct audit_field *f = &entry->rule.fields[i]; u32 f_val; err = -EINVAL; f->op = audit_to_op(data->fieldflags[i]); if (f->op == Audit_bad) goto exit_free; f->type = data->fields[i]; f_val = data->values[i]; /* Support legacy tests for a valid loginuid */ if ((f->type == AUDIT_LOGINUID) && (f_val == AUDIT_UID_UNSET)) { f->type = AUDIT_LOGINUID_SET; f_val = 0; entry->rule.pflags |= AUDIT_LOGINUID_LEGACY; } err = audit_field_valid(entry, f); if (err) goto exit_free; err = -EINVAL; switch (f->type) { case AUDIT_LOGINUID: case AUDIT_UID: case AUDIT_EUID: case AUDIT_SUID: case AUDIT_FSUID: case AUDIT_OBJ_UID: f->uid = make_kuid(current_user_ns(), f_val); if (!uid_valid(f->uid)) goto exit_free; break; case AUDIT_GID: case AUDIT_EGID: case AUDIT_SGID: case AUDIT_FSGID: case AUDIT_OBJ_GID: f->gid = make_kgid(current_user_ns(), f_val); if (!gid_valid(f->gid)) goto exit_free; break; case AUDIT_ARCH: f->val = f_val; entry->rule.arch_f = f; break; case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } entry->rule.buflen += f_val; f->lsm_str = str; err = security_audit_rule_init(f->type, f->op, str, (void **)&f->lsm_rule, GFP_KERNEL); /* Keep currently invalid fields around in case they * become valid after a policy reload. */ if (err == -EINVAL) { pr_warn("audit rule for LSM \'%s\' is invalid\n", str); err = 0; } else if (err) goto exit_free; break; case AUDIT_WATCH: str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } err = audit_to_watch(&entry->rule, str, f_val, f->op); if (err) { kfree(str); goto exit_free; } entry->rule.buflen += f_val; break; case AUDIT_DIR: str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } err = audit_make_tree(&entry->rule, str, f->op); kfree(str); if (err) goto exit_free; entry->rule.buflen += f_val; break; case AUDIT_INODE: f->val = f_val; err = audit_to_inode(&entry->rule, f); if (err) goto exit_free; break; case AUDIT_FILTERKEY: if (entry->rule.filterkey || f_val > AUDIT_MAX_KEY_LEN) goto exit_free; str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } entry->rule.buflen += f_val; entry->rule.filterkey = str; break; case AUDIT_EXE: if (entry->rule.exe || f_val > PATH_MAX) goto exit_free; str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } audit_mark = audit_alloc_mark(&entry->rule, str, f_val); if (IS_ERR(audit_mark)) { kfree(str); err = PTR_ERR(audit_mark); goto exit_free; } entry->rule.buflen += f_val; entry->rule.exe = audit_mark; break; default: f->val = f_val; break; } } if (entry->rule.inode_f && entry->rule.inode_f->op == Audit_not_equal) entry->rule.inode_f = NULL; exit_nofree: return entry; exit_free: if (entry->rule.tree) audit_put_tree(entry->rule.tree); /* that's the temporary one */ if (entry->rule.exe) audit_remove_mark(entry->rule.exe); /* that's the template one */ audit_free_rule(entry); return ERR_PTR(err); } /* Pack a filter field's string representation into data block. */ static inline size_t audit_pack_string(void **bufp, const char *str) { size_t len = strlen(str); memcpy(*bufp, str, len); *bufp += len; return len; } /* Translate kernel rule representation to struct audit_rule_data. */ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule) { struct audit_rule_data *data; void *bufp; int i; data = kmalloc(struct_size(data, buf, krule->buflen), GFP_KERNEL); if (unlikely(!data)) return NULL; memset(data, 0, sizeof(*data)); data->flags = krule->flags | krule->listnr; data->action = krule->action; data->field_count = krule->field_count; bufp = data->buf; for (i = 0; i < data->field_count; i++) { struct audit_field *f = &krule->fields[i]; data->fields[i] = f->type; data->fieldflags[i] = audit_ops[f->op]; switch(f->type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: data->buflen += data->values[i] = audit_pack_string(&bufp, f->lsm_str); break; case AUDIT_WATCH: data->buflen += data->values[i] = audit_pack_string(&bufp, audit_watch_path(krule->watch)); break; case AUDIT_DIR: data->buflen += data->values[i] = audit_pack_string(&bufp, audit_tree_path(krule->tree)); break; case AUDIT_FILTERKEY: data->buflen += data->values[i] = audit_pack_string(&bufp, krule->filterkey); break; case AUDIT_EXE: data->buflen += data->values[i] = audit_pack_string(&bufp, audit_mark_path(krule->exe)); break; case AUDIT_LOGINUID_SET: if (krule->pflags & AUDIT_LOGINUID_LEGACY && !f->val) { data->fields[i] = AUDIT_LOGINUID; data->values[i] = AUDIT_UID_UNSET; break; } fallthrough; /* if set */ default: data->values[i] = f->val; } } for (i = 0; i < AUDIT_BITMASK_SIZE; i++) data->mask[i] = krule->mask[i]; return data; } /* Compare two rules in kernel format. Considered success if rules * don't match. */ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b) { int i; if (a->flags != b->flags || a->pflags != b->pflags || a->listnr != b->listnr || a->action != b->action || a->field_count != b->field_count) return 1; for (i = 0; i < a->field_count; i++) { if (a->fields[i].type != b->fields[i].type || a->fields[i].op != b->fields[i].op) return 1; switch(a->fields[i].type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: if (strcmp(a->fields[i].lsm_str, b->fields[i].lsm_str)) return 1; break; case AUDIT_WATCH: if (strcmp(audit_watch_path(a->watch), audit_watch_path(b->watch))) return 1; break; case AUDIT_DIR: if (strcmp(audit_tree_path(a->tree), audit_tree_path(b->tree))) return 1; break; case AUDIT_FILTERKEY: /* both filterkeys exist based on above type compare */ if (strcmp(a->filterkey, b->filterkey)) return 1; break; case AUDIT_EXE: /* both paths exist based on above type compare */ if (strcmp(audit_mark_path(a->exe), audit_mark_path(b->exe))) return 1; break; case AUDIT_UID: case AUDIT_EUID: case AUDIT_SUID: case AUDIT_FSUID: case AUDIT_LOGINUID: case AUDIT_OBJ_UID: if (!uid_eq(a->fields[i].uid, b->fields[i].uid)) return 1; break; case AUDIT_GID: case AUDIT_EGID: case AUDIT_SGID: case AUDIT_FSGID: case AUDIT_OBJ_GID: if (!gid_eq(a->fields[i].gid, b->fields[i].gid)) return 1; break; default: if (a->fields[i].val != b->fields[i].val) return 1; } } for (i = 0; i < AUDIT_BITMASK_SIZE; i++) if (a->mask[i] != b->mask[i]) return 1; return 0; } /* Duplicate LSM field information. The lsm_rule is opaque, so must be * re-initialized. */ static inline int audit_dupe_lsm_field(struct audit_field *df, struct audit_field *sf) { int ret = 0; char *lsm_str; /* our own copy of lsm_str */ lsm_str = kstrdup(sf->lsm_str, GFP_KERNEL); if (unlikely(!lsm_str)) return -ENOMEM; df->lsm_str = lsm_str; /* our own (refreshed) copy of lsm_rule */ ret = security_audit_rule_init(df->type, df->op, df->lsm_str, (void **)&df->lsm_rule, GFP_KERNEL); /* Keep currently invalid fields around in case they * become valid after a policy reload. */ if (ret == -EINVAL) { pr_warn("audit rule for LSM \'%s\' is invalid\n", df->lsm_str); ret = 0; } return ret; } /* Duplicate an audit rule. This will be a deep copy with the exception * of the watch - that pointer is carried over. The LSM specific fields * will be updated in the copy. The point is to be able to replace the old * rule with the new rule in the filterlist, then free the old rule. * The rlist element is undefined; list manipulations are handled apart from * the initial copy. */ struct audit_entry *audit_dupe_rule(struct audit_krule *old) { u32 fcount = old->field_count; struct audit_entry *entry; struct audit_krule *new; char *fk; int i, err = 0; entry = audit_init_entry(fcount); if (unlikely(!entry)) return ERR_PTR(-ENOMEM); new = &entry->rule; new->flags = old->flags; new->pflags = old->pflags; new->listnr = old->listnr; new->action = old->action; for (i = 0; i < AUDIT_BITMASK_SIZE; i++) new->mask[i] = old->mask[i]; new->prio = old->prio; new->buflen = old->buflen; new->inode_f = old->inode_f; new->field_count = old->field_count; /* * note that we are OK with not refcounting here; audit_match_tree() * never dereferences tree and we can't get false positives there * since we'd have to have rule gone from the list *and* removed * before the chunks found by lookup had been allocated, i.e. before * the beginning of list scan. */ new->tree = old->tree; memcpy(new->fields, old->fields, sizeof(struct audit_field) * fcount); /* deep copy this information, updating the lsm_rule fields, because * the originals will all be freed when the old rule is freed. */ for (i = 0; i < fcount; i++) { switch (new->fields[i].type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: err = audit_dupe_lsm_field(&new->fields[i], &old->fields[i]); break; case AUDIT_FILTERKEY: fk = kstrdup(old->filterkey, GFP_KERNEL); if (unlikely(!fk)) err = -ENOMEM; else new->filterkey = fk; break; case AUDIT_EXE: err = audit_dupe_exe(new, old); break; } if (err) { if (new->exe) audit_remove_mark(new->exe); audit_free_rule(entry); return ERR_PTR(err); } } if (old->watch) { audit_get_watch(old->watch); new->watch = old->watch; } return entry; } /* Find an existing audit rule. * Caller must hold audit_filter_mutex to prevent stale rule data. */ static struct audit_entry *audit_find_rule(struct audit_entry *entry, struct list_head **p) { struct audit_entry *e, *found = NULL; struct list_head *list; int h; if (entry->rule.inode_f) { h = audit_hash_ino(entry->rule.inode_f->val); *p = list = &audit_inode_hash[h]; } else if (entry->rule.watch) { /* we don't know the inode number, so must walk entire hash */ for (h = 0; h < AUDIT_INODE_BUCKETS; h++) { list = &audit_inode_hash[h]; list_for_each_entry(e, list, list) if (!audit_compare_rule(&entry->rule, &e->rule)) { found = e; goto out; } } goto out; } else { *p = list = &audit_filter_list[entry->rule.listnr]; } list_for_each_entry(e, list, list) if (!audit_compare_rule(&entry->rule, &e->rule)) { found = e; goto out; } out: return found; } static u64 prio_low = ~0ULL/2; static u64 prio_high = ~0ULL/2 - 1; /* Add rule to given filterlist if not a duplicate. */ static inline int audit_add_rule(struct audit_entry *entry) { struct audit_entry *e; struct audit_watch *watch = entry->rule.watch; struct audit_tree *tree = entry->rule.tree; struct list_head *list; int err = 0; #ifdef CONFIG_AUDITSYSCALL int dont_count = 0; /* If any of these, don't count towards total */ switch(entry->rule.listnr) { case AUDIT_FILTER_USER: case AUDIT_FILTER_EXCLUDE: case AUDIT_FILTER_FS: dont_count = 1; } #endif mutex_lock(&audit_filter_mutex); e = audit_find_rule(entry, &list); if (e) { mutex_unlock(&audit_filter_mutex); err = -EEXIST; /* normally audit_add_tree_rule() will free it on failure */ if (tree) audit_put_tree(tree); return err; } if (watch) { /* audit_filter_mutex is dropped and re-taken during this call */ err = audit_add_watch(&entry->rule, &list); if (err) { mutex_unlock(&audit_filter_mutex); /* * normally audit_add_tree_rule() will free it * on failure */ if (tree) audit_put_tree(tree); return err; } } if (tree) { err = audit_add_tree_rule(&entry->rule); if (err) { mutex_unlock(&audit_filter_mutex); return err; } } entry->rule.prio = ~0ULL; if (entry->rule.listnr == AUDIT_FILTER_EXIT || entry->rule.listnr == AUDIT_FILTER_URING_EXIT) { if (entry->rule.flags & AUDIT_FILTER_PREPEND) entry->rule.prio = ++prio_high; else entry->rule.prio = --prio_low; } if (entry->rule.flags & AUDIT_FILTER_PREPEND) { list_add(&entry->rule.list, &audit_rules_list[entry->rule.listnr]); list_add_rcu(&entry->list, list); entry->rule.flags &= ~AUDIT_FILTER_PREPEND; } else { list_add_tail(&entry->rule.list, &audit_rules_list[entry->rule.listnr]); list_add_tail_rcu(&entry->list, list); } #ifdef CONFIG_AUDITSYSCALL if (!dont_count) audit_n_rules++; if (!audit_match_signal(entry)) audit_signals++; #endif mutex_unlock(&audit_filter_mutex); return err; } /* Remove an existing rule from filterlist. */ int audit_del_rule(struct audit_entry *entry) { struct audit_entry *e; struct audit_tree *tree = entry->rule.tree; struct list_head *list; int ret = 0; #ifdef CONFIG_AUDITSYSCALL int dont_count = 0; /* If any of these, don't count towards total */ switch(entry->rule.listnr) { case AUDIT_FILTER_USER: case AUDIT_FILTER_EXCLUDE: case AUDIT_FILTER_FS: dont_count = 1; } #endif mutex_lock(&audit_filter_mutex); e = audit_find_rule(entry, &list); if (!e) { ret = -ENOENT; goto out; } if (e->rule.watch) audit_remove_watch_rule(&e->rule); if (e->rule.tree) audit_remove_tree_rule(&e->rule); if (e->rule.exe) audit_remove_mark_rule(&e->rule); #ifdef CONFIG_AUDITSYSCALL if (!dont_count) audit_n_rules--; if (!audit_match_signal(entry)) audit_signals--; #endif list_del_rcu(&e->list); list_del(&e->rule.list); call_rcu(&e->rcu, audit_free_rule_rcu); out: mutex_unlock(&audit_filter_mutex); if (tree) audit_put_tree(tree); /* that's the temporary one */ return ret; } /* List rules using struct audit_rule_data. */ static void audit_list_rules(int seq, struct sk_buff_head *q) { struct sk_buff *skb; struct audit_krule *r; int i; /* This is a blocking read, so use audit_filter_mutex instead of rcu * iterator to sync with list writers. */ for (i=0; i<AUDIT_NR_FILTERS; i++) { list_for_each_entry(r, &audit_rules_list[i], list) { struct audit_rule_data *data; data = audit_krule_to_data(r); if (unlikely(!data)) break; skb = audit_make_reply(seq, AUDIT_LIST_RULES, 0, 1, data, struct_size(data, buf, data->buflen)); if (skb) skb_queue_tail(q, skb); kfree(data); } } skb = audit_make_reply(seq, AUDIT_LIST_RULES, 1, 1, NULL, 0); if (skb) skb_queue_tail(q, skb); } /* Log rule additions and removals */ static void audit_log_rule_change(char *action, struct audit_krule *rule, int res) { struct audit_buffer *ab; if (!audit_enabled) return; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_CONFIG_CHANGE); if (!ab) return; audit_log_session_info(ab); audit_log_task_context(ab); audit_log_format(ab, " op=%s", action); audit_log_key(ab, rule->filterkey); audit_log_format(ab, " list=%d res=%d", rule->listnr, res); audit_log_end(ab); } /** * audit_rule_change - apply all rules to the specified message type * @type: audit message type * @seq: netlink audit message sequence (serial) number * @data: payload data * @datasz: size of payload data */ int audit_rule_change(int type, int seq, void *data, size_t datasz) { int err = 0; struct audit_entry *entry; switch (type) { case AUDIT_ADD_RULE: entry = audit_data_to_entry(data, datasz); if (IS_ERR(entry)) return PTR_ERR(entry); err = audit_add_rule(entry); audit_log_rule_change("add_rule", &entry->rule, !err); break; case AUDIT_DEL_RULE: entry = audit_data_to_entry(data, datasz); if (IS_ERR(entry)) return PTR_ERR(entry); err = audit_del_rule(entry); audit_log_rule_change("remove_rule", &entry->rule, !err); break; default: WARN_ON(1); return -EINVAL; } if (err || type == AUDIT_DEL_RULE) { if (entry->rule.exe) audit_remove_mark(entry->rule.exe); audit_free_rule(entry); } return err; } /** * audit_list_rules_send - list the audit rules * @request_skb: skb of request we are replying to (used to target the reply) * @seq: netlink audit message sequence (serial) number */ int audit_list_rules_send(struct sk_buff *request_skb, int seq) { struct task_struct *tsk; struct audit_netlink_list *dest; /* We can't just spew out the rules here because we might fill * the available socket buffer space and deadlock waiting for * auditctl to read from it... which isn't ever going to * happen if we're actually running in the context of auditctl * trying to _send_ the stuff */ dest = kmalloc(sizeof(*dest), GFP_KERNEL); if (!dest) return -ENOMEM; dest->net = get_net(sock_net(NETLINK_CB(request_skb).sk)); dest->portid = NETLINK_CB(request_skb).portid; skb_queue_head_init(&dest->q); mutex_lock(&audit_filter_mutex); audit_list_rules(seq, &dest->q); mutex_unlock(&audit_filter_mutex); tsk = kthread_run(audit_send_list_thread, dest, "audit_send_list"); if (IS_ERR(tsk)) { skb_queue_purge(&dest->q); put_net(dest->net); kfree(dest); return PTR_ERR(tsk); } return 0; } int audit_comparator(u32 left, u32 op, u32 right) { switch (op) { case Audit_equal: return (left == right); case Audit_not_equal: return (left != right); case Audit_lt: return (left < right); case Audit_le: return (left <= right); case Audit_gt: return (left > right); case Audit_ge: return (left >= right); case Audit_bitmask: return (left & right); case Audit_bittest: return ((left & right) == right); default: return 0; } } int audit_uid_comparator(kuid_t left, u32 op, kuid_t right) { switch (op) { case Audit_equal: return uid_eq(left, right); case Audit_not_equal: return !uid_eq(left, right); case Audit_lt: return uid_lt(left, right); case Audit_le: return uid_lte(left, right); case Audit_gt: return uid_gt(left, right); case Audit_ge: return uid_gte(left, right); case Audit_bitmask: case Audit_bittest: default: return 0; } } int audit_gid_comparator(kgid_t left, u32 op, kgid_t right) { switch (op) { case Audit_equal: return gid_eq(left, right); case Audit_not_equal: return !gid_eq(left, right); case Audit_lt: return gid_lt(left, right); case Audit_le: return gid_lte(left, right); case Audit_gt: return gid_gt(left, right); case Audit_ge: return gid_gte(left, right); case Audit_bitmask: case Audit_bittest: default: return 0; } } /** * parent_len - find the length of the parent portion of a pathname * @path: pathname of which to determine length */ int parent_len(const char *path) { int plen; const char *p; plen = strlen(path); if (plen == 0) return plen; /* disregard trailing slashes */ p = path + plen - 1; while ((*p == '/') && (p > path)) p--; /* walk backward until we find the next slash or hit beginning */ while ((*p != '/') && (p > path)) p--; /* did we find a slash? Then increment to include it in path */ if (*p == '/') p++; return p - path; } /** * audit_compare_dname_path - compare given dentry name with last component in * given path. Return of 0 indicates a match. * @dname: dentry name that we're comparing * @path: full pathname that we're comparing * @parentlen: length of the parent if known. Passing in AUDIT_NAME_FULL * here indicates that we must compute this value. */ int audit_compare_dname_path(const struct qstr *dname, const char *path, int parentlen) { int dlen, pathlen; const char *p; dlen = dname->len; pathlen = strlen(path); if (pathlen < dlen) return 1; parentlen = parentlen == AUDIT_NAME_FULL ? parent_len(path) : parentlen; if (pathlen - parentlen != dlen) return 1; p = path + parentlen; return strncmp(p, dname->name, dlen); } int audit_filter(int msgtype, unsigned int listtype) { struct audit_entry *e; int ret = 1; /* Audit by default */ rcu_read_lock(); list_for_each_entry_rcu(e, &audit_filter_list[listtype], list) { int i, result = 0; for (i = 0; i < e->rule.field_count; i++) { struct audit_field *f = &e->rule.fields[i]; pid_t pid; u32 sid; switch (f->type) { case AUDIT_PID: pid = task_pid_nr(current); result = audit_comparator(pid, f->op, f->val); break; case AUDIT_UID: result = audit_uid_comparator(current_uid(), f->op, f->uid); break; case AUDIT_GID: result = audit_gid_comparator(current_gid(), f->op, f->gid); break; case AUDIT_LOGINUID: result = audit_uid_comparator(audit_get_loginuid(current), f->op, f->uid); break; case AUDIT_LOGINUID_SET: result = audit_comparator(audit_loginuid_set(current), f->op, f->val); break; case AUDIT_MSGTYPE: result = audit_comparator(msgtype, f->op, f->val); break; case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: if (f->lsm_rule) { security_current_getsecid_subj(&sid); result = security_audit_rule_match(sid, f->type, f->op, f->lsm_rule); } break; case AUDIT_EXE: result = audit_exe_compare(current, e->rule.exe); if (f->op == Audit_not_equal) result = !result; break; default: goto unlock_and_return; } if (result < 0) /* error */ goto unlock_and_return; if (!result) break; } if (result > 0) { if (e->rule.action == AUDIT_NEVER || listtype == AUDIT_FILTER_EXCLUDE) ret = 0; break; } } unlock_and_return: rcu_read_unlock(); return ret; } static int update_lsm_rule(struct audit_krule *r) { struct audit_entry *entry = container_of(r, struct audit_entry, rule); struct audit_entry *nentry; int err = 0; if (!security_audit_rule_known(r)) return 0; nentry = audit_dupe_rule(r); if (entry->rule.exe) audit_remove_mark(entry->rule.exe); if (IS_ERR(nentry)) { /* save the first error encountered for the * return value */ err = PTR_ERR(nentry); audit_panic("error updating LSM filters"); if (r->watch) list_del(&r->rlist); list_del_rcu(&entry->list); list_del(&r->list); } else { if (r->watch || r->tree) list_replace_init(&r->rlist, &nentry->rule.rlist); list_replace_rcu(&entry->list, &nentry->list); list_replace(&r->list, &nentry->rule.list); } call_rcu(&entry->rcu, audit_free_rule_rcu); return err; } /* This function will re-initialize the lsm_rule field of all applicable rules. * It will traverse the filter lists serarching for rules that contain LSM * specific filter fields. When such a rule is found, it is copied, the * LSM field is re-initialized, and the old rule is replaced with the * updated rule. */ int audit_update_lsm_rules(void) { struct audit_krule *r, *n; int i, err = 0; /* audit_filter_mutex synchronizes the writers */ mutex_lock(&audit_filter_mutex); for (i = 0; i < AUDIT_NR_FILTERS; i++) { list_for_each_entry_safe(r, n, &audit_rules_list[i], list) { int res = update_lsm_rule(r); if (!err) err = res; } } mutex_unlock(&audit_filter_mutex); return err; } |
| 4 6 6 1 4 3 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPV6 GSO/GRO offload support * Linux INET6 implementation * * UDPv6 GSO support */ #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/indirect_call_wrapper.h> #include <net/protocol.h> #include <net/ipv6.h> #include <net/udp.h> #include <net/ip6_checksum.h> #include "ip6_offload.h" #include <net/gro.h> static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int mss; unsigned int unfrag_ip6hlen, unfrag_len; struct frag_hdr *fptr; u8 *packet_start, *prevhdr; u8 nexthdr; u8 frag_hdr_sz = sizeof(struct frag_hdr); __wsum csum; int tnl_hlen; int err; if (skb->encapsulation && skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM)) segs = skb_udp_tunnel_segment(skb, features, true); else { const struct ipv6hdr *ipv6h; struct udphdr *uh; 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, true); 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); ipv6h = ipv6_hdr(skb); uh->check = 0; csum = skb_checksum(skb, 0, skb->len, 0); uh->check = udp_v6_check(skb->len, &ipv6h->saddr, &ipv6h->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; /* Check if there is enough headroom to insert fragment header. */ tnl_hlen = skb_tnl_header_len(skb); if (skb->mac_header < (tnl_hlen + frag_hdr_sz)) { if (gso_pskb_expand_head(skb, tnl_hlen + frag_hdr_sz)) goto out; } /* Find the unfragmentable header and shift it left by frag_hdr_sz * bytes to insert fragment header. */ err = ip6_find_1stfragopt(skb, &prevhdr); if (err < 0) return ERR_PTR(err); unfrag_ip6hlen = err; nexthdr = *prevhdr; *prevhdr = NEXTHDR_FRAGMENT; unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) + unfrag_ip6hlen + tnl_hlen; packet_start = (u8 *) skb->head + SKB_GSO_CB(skb)->mac_offset; memmove(packet_start-frag_hdr_sz, packet_start, unfrag_len); SKB_GSO_CB(skb)->mac_offset -= frag_hdr_sz; skb->mac_header -= frag_hdr_sz; skb->network_header -= frag_hdr_sz; fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); fptr->nexthdr = nexthdr; fptr->reserved = 0; fptr->identification = ipv6_proxy_select_ident(dev_net(skb->dev), skb); /* Fragment the skb. ipv6 header and the remaining fields of the * fragment header are updated in ipv6_gso_segment() */ segs = skb_segment(skb, features); } out: return segs; } static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport) { const struct ipv6hdr *iph = skb_gro_network_header(skb); return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport, &iph->daddr, dport, inet6_iif(skb), inet6_sdif(skb), &udp_table, NULL); } INDIRECT_CALLABLE_SCOPE struct sk_buff *udp6_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, ip6_gro_compute_pseudo)) goto flush; else if (uh->check) skb_gro_checksum_try_convert(skb, IPPROTO_UDP, ip6_gro_compute_pseudo); skip: NAPI_GRO_CB(skb)->is_ipv6 = 1; if (static_branch_unlikely(&udpv6_encap_needed_key)) sk = udp6_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; } INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff) { const struct ipv6hdr *ipv6h = ipv6_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_v6_check(skb->len - nhoff, &ipv6h->saddr, &ipv6h->daddr, 0); return udp_gro_complete(skb, nhoff, udp6_lib_lookup_skb); } static const struct net_offload udpv6_offload = { .callbacks = { .gso_segment = udp6_ufo_fragment, .gro_receive = udp6_gro_receive, .gro_complete = udp6_gro_complete, }, }; int udpv6_offload_init(void) { return inet6_add_offload(&udpv6_offload, IPPROTO_UDP); } int udpv6_offload_exit(void) { return inet6_del_offload(&udpv6_offload, IPPROTO_UDP); } |
| 966 964 2 965 631 631 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2009 Red Hat, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/numa_balancing.h> #include <linux/highmem.h> #include <linux/hugetlb.h> #include <linux/mmu_notifier.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/shrinker.h> #include <linux/mm_inline.h> #include <linux/swapops.h> #include <linux/backing-dev.h> #include <linux/dax.h> #include <linux/khugepaged.h> #include <linux/freezer.h> #include <linux/pfn_t.h> #include <linux/mman.h> #include <linux/memremap.h> #include <linux/pagemap.h> #include <linux/debugfs.h> #include <linux/migrate.h> #include <linux/hashtable.h> #include <linux/userfaultfd_k.h> #include <linux/page_idle.h> #include <linux/shmem_fs.h> #include <linux/oom.h> #include <linux/numa.h> #include <linux/page_owner.h> #include <linux/sched/sysctl.h> #include <linux/memory-tiers.h> #include <linux/compat.h> #include <asm/tlb.h> #include <asm/pgalloc.h> #include "internal.h" #include "swap.h" #define CREATE_TRACE_POINTS #include <trace/events/thp.h> /* * By default, transparent hugepage support is disabled in order to avoid * risking an increased memory footprint for applications that are not * guaranteed to benefit from it. When transparent hugepage support is * enabled, it is for all mappings, and khugepaged scans all mappings. * Defrag is invoked by khugepaged hugepage allocations and by page faults * for all hugepage allocations. */ unsigned long transparent_hugepage_flags __read_mostly = #ifdef CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS (1<<TRANSPARENT_HUGEPAGE_FLAG)| #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE_MADVISE (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)| #endif (1<<TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG)| (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)| (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); static struct shrinker deferred_split_shrinker; static atomic_t huge_zero_refcount; struct page *huge_zero_page __read_mostly; unsigned long huge_zero_pfn __read_mostly = ~0UL; bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags, bool smaps, bool in_pf, bool enforce_sysfs) { if (!vma->vm_mm) /* vdso */ return false; /* * Explicitly disabled through madvise or prctl, or some * architectures may disable THP for some mappings, for * example, s390 kvm. * */ if ((vm_flags & VM_NOHUGEPAGE) || test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) return false; /* * If the hardware/firmware marked hugepage support disabled. */ if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_NEVER_DAX)) return false; /* khugepaged doesn't collapse DAX vma, but page fault is fine. */ if (vma_is_dax(vma)) return in_pf; /* * Special VMA and hugetlb VMA. * Must be checked after dax since some dax mappings may have * VM_MIXEDMAP set. */ if (vm_flags & VM_NO_KHUGEPAGED) return false; /* * Check alignment for file vma and size for both file and anon vma. * * Skip the check for page fault. Huge fault does the check in fault * handlers. And this check is not suitable for huge PUD fault. */ if (!in_pf && !transhuge_vma_suitable(vma, (vma->vm_end - HPAGE_PMD_SIZE))) return false; /* * Enabled via shmem mount options or sysfs settings. * Must be done before hugepage flags check since shmem has its * own flags. */ if (!in_pf && shmem_file(vma->vm_file)) return shmem_huge_enabled(vma, !enforce_sysfs); /* Enforce sysfs THP requirements as necessary */ if (enforce_sysfs && (!hugepage_flags_enabled() || (!(vm_flags & VM_HUGEPAGE) && !hugepage_flags_always()))) return false; /* Only regular file is valid */ if (!in_pf && file_thp_enabled(vma)) return true; if (!vma_is_anonymous(vma)) return false; if (vma_is_temporary_stack(vma)) return false; /* * THPeligible bit of smaps should show 1 for proper VMAs even * though anon_vma is not initialized yet. * * Allow page fault since anon_vma may be not initialized until * the first page fault. */ if (!vma->anon_vma) return (smaps || in_pf); return true; } static bool get_huge_zero_page(void) { struct page *zero_page; retry: if (likely(atomic_inc_not_zero(&huge_zero_refcount))) return true; zero_page = alloc_pages((GFP_TRANSHUGE | __GFP_ZERO) & ~__GFP_MOVABLE, HPAGE_PMD_ORDER); if (!zero_page) { count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED); return false; } preempt_disable(); if (cmpxchg(&huge_zero_page, NULL, zero_page)) { preempt_enable(); __free_pages(zero_page, compound_order(zero_page)); goto retry; } WRITE_ONCE(huge_zero_pfn, page_to_pfn(zero_page)); /* We take additional reference here. It will be put back by shrinker */ atomic_set(&huge_zero_refcount, 2); preempt_enable(); count_vm_event(THP_ZERO_PAGE_ALLOC); return true; } static void put_huge_zero_page(void) { /* * Counter should never go to zero here. Only shrinker can put * last reference. */ BUG_ON(atomic_dec_and_test(&huge_zero_refcount)); } struct page *mm_get_huge_zero_page(struct mm_struct *mm) { if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) return READ_ONCE(huge_zero_page); if (!get_huge_zero_page()) return NULL; if (test_and_set_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) put_huge_zero_page(); return READ_ONCE(huge_zero_page); } void mm_put_huge_zero_page(struct mm_struct *mm) { if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) put_huge_zero_page(); } static unsigned long shrink_huge_zero_page_count(struct shrinker *shrink, struct shrink_control *sc) { /* we can free zero page only if last reference remains */ return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0; } static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, struct shrink_control *sc) { if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { struct page *zero_page = xchg(&huge_zero_page, NULL); BUG_ON(zero_page == NULL); WRITE_ONCE(huge_zero_pfn, ~0UL); __free_pages(zero_page, compound_order(zero_page)); return HPAGE_PMD_NR; } return 0; } static struct shrinker huge_zero_page_shrinker = { .count_objects = shrink_huge_zero_page_count, .scan_objects = shrink_huge_zero_page_scan, .seeks = DEFAULT_SEEKS, }; #ifdef CONFIG_SYSFS static ssize_t enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { const char *output; if (test_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags)) output = "[always] madvise never"; else if (test_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags)) output = "always [madvise] never"; else output = "always madvise [never]"; return sysfs_emit(buf, "%s\n", output); } static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { ssize_t ret = count; if (sysfs_streq(buf, "always")) { clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); } else if (sysfs_streq(buf, "madvise")) { clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); } else if (sysfs_streq(buf, "never")) { clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); } else ret = -EINVAL; if (ret > 0) { int err = start_stop_khugepaged(); if (err) ret = err; } return ret; } static struct kobj_attribute enabled_attr = __ATTR_RW(enabled); ssize_t single_hugepage_flag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf, enum transparent_hugepage_flag flag) { return sysfs_emit(buf, "%d\n", !!test_bit(flag, &transparent_hugepage_flags)); } ssize_t single_hugepage_flag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count, enum transparent_hugepage_flag flag) { unsigned long value; int ret; ret = kstrtoul(buf, 10, &value); if (ret < 0) return ret; if (value > 1) return -EINVAL; if (value) set_bit(flag, &transparent_hugepage_flags); else clear_bit(flag, &transparent_hugepage_flags); return count; } static ssize_t defrag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { const char *output; if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) output = "[always] defer defer+madvise madvise never"; else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) output = "always [defer] defer+madvise madvise never"; else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags)) output = "always defer [defer+madvise] madvise never"; else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) output = "always defer defer+madvise [madvise] never"; else output = "always defer defer+madvise madvise [never]"; return sysfs_emit(buf, "%s\n", output); } static ssize_t defrag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { if (sysfs_streq(buf, "always")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); } else if (sysfs_streq(buf, "defer+madvise")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); } else if (sysfs_streq(buf, "defer")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); } else if (sysfs_streq(buf, "madvise")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); } else if (sysfs_streq(buf, "never")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); } else return -EINVAL; return count; } static struct kobj_attribute defrag_attr = __ATTR_RW(defrag); static ssize_t use_zero_page_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return single_hugepage_flag_show(kobj, attr, buf, TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); } static ssize_t use_zero_page_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { return single_hugepage_flag_store(kobj, attr, buf, count, TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); } static struct kobj_attribute use_zero_page_attr = __ATTR_RW(use_zero_page); static ssize_t hpage_pmd_size_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", HPAGE_PMD_SIZE); } static struct kobj_attribute hpage_pmd_size_attr = __ATTR_RO(hpage_pmd_size); static struct attribute *hugepage_attr[] = { &enabled_attr.attr, &defrag_attr.attr, &use_zero_page_attr.attr, &hpage_pmd_size_attr.attr, #ifdef CONFIG_SHMEM &shmem_enabled_attr.attr, #endif NULL, }; static const struct attribute_group hugepage_attr_group = { .attrs = hugepage_attr, }; static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj) { int err; *hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj); if (unlikely(!*hugepage_kobj)) { pr_err("failed to create transparent hugepage kobject\n"); return -ENOMEM; } err = sysfs_create_group(*hugepage_kobj, &hugepage_attr_group); if (err) { pr_err("failed to register transparent hugepage group\n"); goto delete_obj; } err = sysfs_create_group(*hugepage_kobj, &khugepaged_attr_group); if (err) { pr_err("failed to register transparent hugepage group\n"); goto remove_hp_group; } return 0; remove_hp_group: sysfs_remove_group(*hugepage_kobj, &hugepage_attr_group); delete_obj: kobject_put(*hugepage_kobj); return err; } static void __init hugepage_exit_sysfs(struct kobject *hugepage_kobj) { sysfs_remove_group(hugepage_kobj, &khugepaged_attr_group); sysfs_remove_group(hugepage_kobj, &hugepage_attr_group); kobject_put(hugepage_kobj); } #else static inline int hugepage_init_sysfs(struct kobject **hugepage_kobj) { return 0; } static inline void hugepage_exit_sysfs(struct kobject *hugepage_kobj) { } #endif /* CONFIG_SYSFS */ static int __init hugepage_init(void) { int err; struct kobject *hugepage_kobj; if (!has_transparent_hugepage()) { /* * Hardware doesn't support hugepages, hence disable * DAX PMD support. */ transparent_hugepage_flags = 1 << TRANSPARENT_HUGEPAGE_NEVER_DAX; return -EINVAL; } /* * hugepages can't be allocated by the buddy allocator */ MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER >= MAX_ORDER); /* * we use page->mapping and page->index in second tail page * as list_head: assuming THP order >= 2 */ MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER < 2); err = hugepage_init_sysfs(&hugepage_kobj); if (err) goto err_sysfs; err = khugepaged_init(); if (err) goto err_slab; err = register_shrinker(&huge_zero_page_shrinker, "thp-zero"); if (err) goto err_hzp_shrinker; err = register_shrinker(&deferred_split_shrinker, "thp-deferred_split"); if (err) goto err_split_shrinker; /* * By default disable transparent hugepages on smaller systems, * where the extra memory used could hurt more than TLB overhead * is likely to save. The admin can still enable it through /sys. */ if (totalram_pages() < (512 << (20 - PAGE_SHIFT))) { transparent_hugepage_flags = 0; return 0; } err = start_stop_khugepaged(); if (err) goto err_khugepaged; return 0; err_khugepaged: unregister_shrinker(&deferred_split_shrinker); err_split_shrinker: unregister_shrinker(&huge_zero_page_shrinker); err_hzp_shrinker: khugepaged_destroy(); err_slab: hugepage_exit_sysfs(hugepage_kobj); err_sysfs: return err; } subsys_initcall(hugepage_init); static int __init setup_transparent_hugepage(char *str) { int ret = 0; if (!str) goto out; if (!strcmp(str, "always")) { set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); ret = 1; } else if (!strcmp(str, "madvise")) { clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); ret = 1; } else if (!strcmp(str, "never")) { clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); ret = 1; } out: if (!ret) pr_warn("transparent_hugepage= cannot parse, ignored\n"); return ret; } __setup("transparent_hugepage=", setup_transparent_hugepage); pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) { if (likely(vma->vm_flags & VM_WRITE)) pmd = pmd_mkwrite(pmd); return pmd; } #ifdef CONFIG_MEMCG static inline struct deferred_split *get_deferred_split_queue(struct page *page) { struct mem_cgroup *memcg = page_memcg(compound_head(page)); struct pglist_data *pgdat = NODE_DATA(page_to_nid(page)); if (memcg) return &memcg->deferred_split_queue; else return &pgdat->deferred_split_queue; } #else static inline struct deferred_split *get_deferred_split_queue(struct page *page) { struct pglist_data *pgdat = NODE_DATA(page_to_nid(page)); return &pgdat->deferred_split_queue; } #endif void prep_transhuge_page(struct page *page) { /* * we use page->mapping and page->index in second tail page * as list_head: assuming THP order >= 2 */ INIT_LIST_HEAD(page_deferred_list(page)); set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR); } static inline bool is_transparent_hugepage(struct page *page) { if (!PageCompound(page)) return false; page = compound_head(page); return is_huge_zero_page(page) || page[1].compound_dtor == TRANSHUGE_PAGE_DTOR; } static unsigned long __thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, loff_t off, unsigned long flags, unsigned long size) { loff_t off_end = off + len; loff_t off_align = round_up(off, size); unsigned long len_pad, ret; if (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall()) return 0; if (off_end <= off_align || (off_end - off_align) < size) return 0; len_pad = len + size; if (len_pad < len || (off + len_pad) < off) return 0; ret = current->mm->get_unmapped_area(filp, addr, len_pad, off >> PAGE_SHIFT, flags); /* * The failure might be due to length padding. The caller will retry * without the padding. */ if (IS_ERR_VALUE(ret)) return 0; /* * Do not try to align to THP boundary if allocation at the address * hint succeeds. */ if (ret == addr) return addr; ret += (off - ret) & (size - 1); return ret; } unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { unsigned long ret; loff_t off = (loff_t)pgoff << PAGE_SHIFT; ret = __thp_get_unmapped_area(filp, addr, len, off, flags, PMD_SIZE); if (ret) return ret; return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags); } EXPORT_SYMBOL_GPL(thp_get_unmapped_area); static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page, gfp_t gfp) { struct vm_area_struct *vma = vmf->vma; pgtable_t pgtable; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; vm_fault_t ret = 0; VM_BUG_ON_PAGE(!PageCompound(page), page); if (mem_cgroup_charge(page_folio(page), vma->vm_mm, gfp)) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); count_vm_event(THP_FAULT_FALLBACK_CHARGE); return VM_FAULT_FALLBACK; } cgroup_throttle_swaprate(page, gfp); pgtable = pte_alloc_one(vma->vm_mm); if (unlikely(!pgtable)) { ret = VM_FAULT_OOM; goto release; } clear_huge_page(page, vmf->address, HPAGE_PMD_NR); /* * The memory barrier inside __SetPageUptodate makes sure that * clear_huge_page writes become visible before the set_pmd_at() * write. */ __SetPageUptodate(page); vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) { goto unlock_release; } else { pmd_t entry; ret = check_stable_address_space(vma->vm_mm); if (ret) goto unlock_release; /* Deliver the page fault to userland */ if (userfaultfd_missing(vma)) { spin_unlock(vmf->ptl); put_page(page); pte_free(vma->vm_mm, pgtable); ret = handle_userfault(vmf, VM_UFFD_MISSING); VM_BUG_ON(ret & VM_FAULT_FALLBACK); return ret; } entry = mk_huge_pmd(page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); page_add_new_anon_rmap(page, vma, haddr); lru_cache_add_inactive_or_unevictable(page, vma); pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR); mm_inc_nr_ptes(vma->vm_mm); spin_unlock(vmf->ptl); count_vm_event(THP_FAULT_ALLOC); count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC); } return 0; unlock_release: spin_unlock(vmf->ptl); release: if (pgtable) pte_free(vma->vm_mm, pgtable); put_page(page); return ret; } /* * always: directly stall for all thp allocations * defer: wake kswapd and fail if not immediately available * defer+madvise: wake kswapd and directly stall for MADV_HUGEPAGE, otherwise * fail if not immediately available * madvise: directly stall for MADV_HUGEPAGE, otherwise fail if not immediately * available * never: never stall for any thp allocation */ gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma) { const bool vma_madvised = vma && (vma->vm_flags & VM_HUGEPAGE); /* Always do synchronous compaction */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY); /* Kick kcompactd and fail quickly */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM; /* Synchronous compaction if madvised, otherwise kick kcompactd */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : __GFP_KSWAPD_RECLAIM); /* Only do synchronous compaction if madvised */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : 0); return GFP_TRANSHUGE_LIGHT; } /* Caller must hold page table lock. */ static void set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, struct page *zero_page) { pmd_t entry; if (!pmd_none(*pmd)) return; entry = mk_pmd(zero_page, vma->vm_page_prot); entry = pmd_mkhuge(entry); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, haddr, pmd, entry); mm_inc_nr_ptes(mm); } vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; gfp_t gfp; struct folio *folio; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; if (!transhuge_vma_suitable(vma, haddr)) return VM_FAULT_FALLBACK; if (unlikely(anon_vma_prepare(vma))) return VM_FAULT_OOM; khugepaged_enter_vma(vma, vma->vm_flags); if (!(vmf->flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(vma->vm_mm) && transparent_hugepage_use_zero_page()) { pgtable_t pgtable; struct page *zero_page; vm_fault_t ret; pgtable = pte_alloc_one(vma->vm_mm); if (unlikely(!pgtable)) return VM_FAULT_OOM; zero_page = mm_get_huge_zero_page(vma->vm_mm); if (unlikely(!zero_page)) { pte_free(vma->vm_mm, pgtable); count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; } vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); ret = 0; if (pmd_none(*vmf->pmd)) { ret = check_stable_address_space(vma->vm_mm); if (ret) { spin_unlock(vmf->ptl); pte_free(vma->vm_mm, pgtable); } else if (userfaultfd_missing(vma)) { spin_unlock(vmf->ptl); pte_free(vma->vm_mm, pgtable); ret = handle_userfault(vmf, VM_UFFD_MISSING); VM_BUG_ON(ret & VM_FAULT_FALLBACK); } else { set_huge_zero_page(pgtable, vma->vm_mm, vma, haddr, vmf->pmd, zero_page); update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); spin_unlock(vmf->ptl); } } else { spin_unlock(vmf->ptl); pte_free(vma->vm_mm, pgtable); } return ret; } gfp = vma_thp_gfp_mask(vma); folio = vma_alloc_folio(gfp, HPAGE_PMD_ORDER, vma, haddr, true); if (unlikely(!folio)) { count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; } return __do_huge_pmd_anonymous_page(vmf, &folio->page, gfp); } static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, pfn_t pfn, pgprot_t prot, bool write, pgtable_t pgtable) { struct mm_struct *mm = vma->vm_mm; pmd_t entry; spinlock_t *ptl; ptl = pmd_lock(mm, pmd); if (!pmd_none(*pmd)) { if (write) { if (pmd_pfn(*pmd) != pfn_t_to_pfn(pfn)) { WARN_ON_ONCE(!is_huge_zero_pmd(*pmd)); goto out_unlock; } entry = pmd_mkyoung(*pmd); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); if (pmdp_set_access_flags(vma, addr, pmd, entry, 1)) update_mmu_cache_pmd(vma, addr, pmd); } goto out_unlock; } entry = pmd_mkhuge(pfn_t_pmd(pfn, prot)); if (pfn_t_devmap(pfn)) entry = pmd_mkdevmap(entry); if (write) { entry = pmd_mkyoung(pmd_mkdirty(entry)); entry = maybe_pmd_mkwrite(entry, vma); } if (pgtable) { pgtable_trans_huge_deposit(mm, pmd, pgtable); mm_inc_nr_ptes(mm); pgtable = NULL; } set_pmd_at(mm, addr, pmd, entry); update_mmu_cache_pmd(vma, addr, pmd); out_unlock: spin_unlock(ptl); if (pgtable) pte_free(mm, pgtable); } /** * vmf_insert_pfn_pmd_prot - 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 and * also consult the vmf_insert_mixed_prot() documentation when * @pgprot != @vmf->vma->vm_page_prot. * * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn, pgprot_t pgprot, bool write) { unsigned long addr = vmf->address & PMD_MASK; struct vm_area_struct *vma = vmf->vma; pgtable_t pgtable = NULL; /* * If we had pmd_special, we could avoid all these restrictions, * but we need to be consistent with PTEs and architectures that * can't support a 'special' bit. */ BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) && !pfn_t_devmap(pfn)); BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == (VM_PFNMAP|VM_MIXEDMAP)); BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; if (arch_needs_pgtable_deposit()) { pgtable = pte_alloc_one(vma->vm_mm); if (!pgtable) return VM_FAULT_OOM; } track_pfn_insert(vma, &pgprot, pfn); insert_pfn_pmd(vma, addr, vmf->pmd, pfn, pgprot, write, pgtable); return VM_FAULT_NOPAGE; } EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd_prot); #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma) { if (likely(vma->vm_flags & VM_WRITE)) pud = pud_mkwrite(pud); return pud; } static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, pfn_t pfn, pgprot_t prot, bool write) { struct mm_struct *mm = vma->vm_mm; pud_t entry; spinlock_t *ptl; ptl = pud_lock(mm, pud); if (!pud_none(*pud)) { if (write) { if (pud_pfn(*pud) != pfn_t_to_pfn(pfn)) { WARN_ON_ONCE(!is_huge_zero_pud(*pud)); goto out_unlock; } entry = pud_mkyoung(*pud); entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma); if (pudp_set_access_flags(vma, addr, pud, entry, 1)) update_mmu_cache_pud(vma, addr, pud); } goto out_unlock; } entry = pud_mkhuge(pfn_t_pud(pfn, prot)); if (pfn_t_devmap(pfn)) entry = pud_mkdevmap(entry); if (write) { entry = pud_mkyoung(pud_mkdirty(entry)); entry = maybe_pud_mkwrite(entry, vma); } set_pud_at(mm, addr, pud, entry); update_mmu_cache_pud(vma, addr, pud); out_unlock: spin_unlock(ptl); } /** * vmf_insert_pfn_pud_prot - 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 and * also consult the vmf_insert_mixed_prot() documentation when * @pgprot != @vmf->vma->vm_page_prot. * * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn_pud_prot(struct vm_fault *vmf, pfn_t pfn, pgprot_t pgprot, bool write) { unsigned long addr = vmf->address & PUD_MASK; struct vm_area_struct *vma = vmf->vma; /* * If we had pud_special, we could avoid all these restrictions, * but we need to be consistent with PTEs and architectures that * can't support a 'special' bit. */ BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) && !pfn_t_devmap(pfn)); BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == (VM_PFNMAP|VM_MIXEDMAP)); BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; track_pfn_insert(vma, &pgprot, pfn); insert_pfn_pud(vma, addr, vmf->pud, pfn, pgprot, write); return VM_FAULT_NOPAGE; } EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud_prot); #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ static void touch_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, bool write) { pmd_t _pmd; _pmd = pmd_mkyoung(*pmd); if (write) _pmd = pmd_mkdirty(_pmd); if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK, pmd, _pmd, write)) update_mmu_cache_pmd(vma, addr, pmd); } struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap) { unsigned long pfn = pmd_pfn(*pmd); struct mm_struct *mm = vma->vm_mm; struct page *page; assert_spin_locked(pmd_lockptr(mm, pmd)); /* FOLL_GET and FOLL_PIN are mutually exclusive. */ if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) return NULL; if (flags & FOLL_WRITE && !pmd_write(*pmd)) return NULL; if (pmd_present(*pmd) && pmd_devmap(*pmd)) /* pass */; else return NULL; if (flags & FOLL_TOUCH) touch_pmd(vma, addr, pmd, flags & FOLL_WRITE); /* * device mapped pages can only be returned if the * caller will manage the page reference count. */ if (!(flags & (FOLL_GET | FOLL_PIN))) return ERR_PTR(-EEXIST); pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT; *pgmap = get_dev_pagemap(pfn, *pgmap); if (!*pgmap) return ERR_PTR(-EFAULT); page = pfn_to_page(pfn); if (!try_grab_page(page, flags)) page = ERR_PTR(-ENOMEM); return page; } 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) { spinlock_t *dst_ptl, *src_ptl; struct page *src_page; pmd_t pmd; pgtable_t pgtable = NULL; int ret = -ENOMEM; /* Skip if can be re-fill on fault */ if (!vma_is_anonymous(dst_vma)) return 0; pgtable = pte_alloc_one(dst_mm); if (unlikely(!pgtable)) goto out; dst_ptl = pmd_lock(dst_mm, dst_pmd); src_ptl = pmd_lockptr(src_mm, src_pmd); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); ret = -EAGAIN; pmd = *src_pmd; #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION if (unlikely(is_swap_pmd(pmd))) { swp_entry_t entry = pmd_to_swp_entry(pmd); VM_BUG_ON(!is_pmd_migration_entry(pmd)); if (!is_readable_migration_entry(entry)) { entry = make_readable_migration_entry( swp_offset(entry)); pmd = swp_entry_to_pmd(entry); if (pmd_swp_soft_dirty(*src_pmd)) pmd = pmd_swp_mksoft_dirty(pmd); if (pmd_swp_uffd_wp(*src_pmd)) pmd = pmd_swp_mkuffd_wp(pmd); set_pmd_at(src_mm, addr, src_pmd, pmd); } add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); mm_inc_nr_ptes(dst_mm); pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); if (!userfaultfd_wp(dst_vma)) pmd = pmd_swp_clear_uffd_wp(pmd); set_pmd_at(dst_mm, addr, dst_pmd, pmd); ret = 0; goto out_unlock; } #endif if (unlikely(!pmd_trans_huge(pmd))) { pte_free(dst_mm, pgtable); goto out_unlock; } /* * When page table lock is held, the huge zero pmd should not be * under splitting since we don't split the page itself, only pmd to * a page table. */ if (is_huge_zero_pmd(pmd)) { /* * get_huge_zero_page() will never allocate a new page here, * since we already have a zero page to copy. It just takes a * reference. */ mm_get_huge_zero_page(dst_mm); goto out_zero_page; } src_page = pmd_page(pmd); VM_BUG_ON_PAGE(!PageHead(src_page), src_page); get_page(src_page); if (unlikely(page_try_dup_anon_rmap(src_page, true, src_vma))) { /* Page maybe pinned: split and retry the fault on PTEs. */ put_page(src_page); pte_free(dst_mm, pgtable); spin_unlock(src_ptl); spin_unlock(dst_ptl); __split_huge_pmd(src_vma, src_pmd, addr, false, NULL); return -EAGAIN; } add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); out_zero_page: mm_inc_nr_ptes(dst_mm); pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); pmdp_set_wrprotect(src_mm, addr, src_pmd); if (!userfaultfd_wp(dst_vma)) pmd = pmd_clear_uffd_wp(pmd); pmd = pmd_mkold(pmd_wrprotect(pmd)); set_pmd_at(dst_mm, addr, dst_pmd, pmd); ret = 0; out_unlock: spin_unlock(src_ptl); spin_unlock(dst_ptl); out: return ret; } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static void touch_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, bool write) { pud_t _pud; _pud = pud_mkyoung(*pud); if (write) _pud = pud_mkdirty(_pud); if (pudp_set_access_flags(vma, addr & HPAGE_PUD_MASK, pud, _pud, write)) update_mmu_cache_pud(vma, addr, pud); } struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap) { unsigned long pfn = pud_pfn(*pud); struct mm_struct *mm = vma->vm_mm; struct page *page; assert_spin_locked(pud_lockptr(mm, pud)); if (flags & FOLL_WRITE && !pud_write(*pud)) return NULL; /* FOLL_GET and FOLL_PIN are mutually exclusive. */ if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) return NULL; if (pud_present(*pud) && pud_devmap(*pud)) /* pass */; else return NULL; if (flags & FOLL_TOUCH) touch_pud(vma, addr, pud, flags & FOLL_WRITE); /* * device mapped pages can only be returned if the * caller will manage the page reference count. * * At least one of FOLL_GET | FOLL_PIN must be set, so assert that here: */ if (!(flags & (FOLL_GET | FOLL_PIN))) return ERR_PTR(-EEXIST); pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT; *pgmap = get_dev_pagemap(pfn, *pgmap); if (!*pgmap) return ERR_PTR(-EFAULT); page = pfn_to_page(pfn); if (!try_grab_page(page, flags)) page = ERR_PTR(-ENOMEM); return page; } 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) { spinlock_t *dst_ptl, *src_ptl; pud_t pud; int ret; dst_ptl = pud_lock(dst_mm, dst_pud); src_ptl = pud_lockptr(src_mm, src_pud); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); ret = -EAGAIN; pud = *src_pud; if (unlikely(!pud_trans_huge(pud) && !pud_devmap(pud))) goto out_unlock; /* * When page table lock is held, the huge zero pud should not be * under splitting since we don't split the page itself, only pud to * a page table. */ if (is_huge_zero_pud(pud)) { /* No huge zero pud yet */ } /* * TODO: once we support anonymous pages, use page_try_dup_anon_rmap() * and split if duplicating fails. */ pudp_set_wrprotect(src_mm, addr, src_pud); pud = pud_mkold(pud_wrprotect(pud)); set_pud_at(dst_mm, addr, dst_pud, pud); ret = 0; out_unlock: spin_unlock(src_ptl); spin_unlock(dst_ptl); return ret; } void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) { bool write = vmf->flags & FAULT_FLAG_WRITE; vmf->ptl = pud_lock(vmf->vma->vm_mm, vmf->pud); if (unlikely(!pud_same(*vmf->pud, orig_pud))) goto unlock; touch_pud(vmf->vma, vmf->address, vmf->pud, write); unlock: spin_unlock(vmf->ptl); } #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ void huge_pmd_set_accessed(struct vm_fault *vmf) { bool write = vmf->flags & FAULT_FLAG_WRITE; vmf->ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); if (unlikely(!pmd_same(*vmf->pmd, vmf->orig_pmd))) goto unlock; touch_pmd(vmf->vma, vmf->address, vmf->pmd, write); unlock: spin_unlock(vmf->ptl); } vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) { const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; struct vm_area_struct *vma = vmf->vma; struct folio *folio; struct page *page; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; pmd_t orig_pmd = vmf->orig_pmd; vmf->ptl = pmd_lockptr(vma->vm_mm, vmf->pmd); VM_BUG_ON_VMA(!vma->anon_vma, vma); VM_BUG_ON(unshare && (vmf->flags & FAULT_FLAG_WRITE)); VM_BUG_ON(!unshare && !(vmf->flags & FAULT_FLAG_WRITE)); if (is_huge_zero_pmd(orig_pmd)) goto fallback; spin_lock(vmf->ptl); if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) { spin_unlock(vmf->ptl); return 0; } page = pmd_page(orig_pmd); folio = page_folio(page); VM_BUG_ON_PAGE(!PageHead(page), page); /* Early check when only holding the PT lock. */ if (PageAnonExclusive(page)) goto reuse; if (!folio_trylock(folio)) { folio_get(folio); spin_unlock(vmf->ptl); folio_lock(folio); spin_lock(vmf->ptl); if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) { spin_unlock(vmf->ptl); folio_unlock(folio); folio_put(folio); return 0; } folio_put(folio); } /* Recheck after temporarily dropping the PT lock. */ if (PageAnonExclusive(page)) { folio_unlock(folio); goto reuse; } /* * See do_wp_page(): we can only reuse the folio exclusively if * there are no additional references. Note that we always drain * the LRU pagevecs immediately after adding a THP. */ if (folio_ref_count(folio) > 1 + folio_test_swapcache(folio) * folio_nr_pages(folio)) goto unlock_fallback; if (folio_test_swapcache(folio)) folio_free_swap(folio); if (folio_ref_count(folio) == 1) { pmd_t entry; page_move_anon_rmap(page, vma); SetPageAnonExclusive(page); folio_unlock(folio); reuse: if (unlikely(unshare)) { spin_unlock(vmf->ptl); return 0; } entry = pmd_mkyoung(orig_pmd); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry, 1)) update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); spin_unlock(vmf->ptl); return VM_FAULT_WRITE; } unlock_fallback: folio_unlock(folio); spin_unlock(vmf->ptl); fallback: __split_huge_pmd(vma, vmf->pmd, vmf->address, false, NULL); return VM_FAULT_FALLBACK; } /* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */ static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page, struct vm_area_struct *vma, unsigned int flags) { /* If the pmd is writable, we can write to the page. */ if (pmd_write(pmd)) return true; /* Maybe FOLL_FORCE is set to override it? */ if (!(flags & FOLL_FORCE)) return false; /* But FOLL_FORCE has no effect on shared mappings */ if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) return false; /* ... or read-only private ones */ if (!(vma->vm_flags & VM_MAYWRITE)) return false; /* ... or already writable ones that just need to take a write fault */ if (vma->vm_flags & VM_WRITE) return false; /* * See can_change_pte_writable(): we broke COW and could map the page * writable if we have an exclusive anonymous page ... */ if (!page || !PageAnon(page) || !PageAnonExclusive(page)) return false; /* ... and a write-fault isn't required for other reasons. */ if (vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd)) return false; return !userfaultfd_huge_pmd_wp(vma, pmd); } struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags) { struct mm_struct *mm = vma->vm_mm; struct page *page; assert_spin_locked(pmd_lockptr(mm, pmd)); page = pmd_page(*pmd); VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page); if ((flags & FOLL_WRITE) && !can_follow_write_pmd(*pmd, page, vma, flags)) return NULL; /* Avoid dumping huge zero page */ if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd)) return ERR_PTR(-EFAULT); /* Full NUMA hinting faults to serialise migration in fault paths */ if (pmd_protnone(*pmd) && !gup_can_follow_protnone(flags)) return NULL; if (!pmd_write(*pmd) && gup_must_unshare(flags, page)) return ERR_PTR(-EMLINK); VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && !PageAnonExclusive(page), page); if (!try_grab_page(page, flags)) return ERR_PTR(-ENOMEM); if (flags & FOLL_TOUCH) touch_pmd(vma, addr, pmd, flags & FOLL_WRITE); page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page); return page; } /* NUMA hinting page fault entry point for trans huge pmds */ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; pmd_t oldpmd = vmf->orig_pmd; pmd_t pmd; struct page *page; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; int page_nid = NUMA_NO_NODE; int target_nid, last_cpupid = (-1 & LAST_CPUPID_MASK); bool migrated = false; bool was_writable = pmd_savedwrite(oldpmd); int flags = 0; vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { spin_unlock(vmf->ptl); return 0; } pmd = pmd_modify(oldpmd, vma->vm_page_prot); page = vm_normal_page_pmd(vma, haddr, pmd); if (!page) goto out_map; /* See similar comment in do_numa_page for explanation */ if (!was_writable) flags |= TNF_NO_GROUP; page_nid = page_to_nid(page); /* * For memory tiering mode, cpupid of slow memory page is used * to record page access time. So use default value. */ if (node_is_toptier(page_nid)) last_cpupid = page_cpupid_last(page); target_nid = numa_migrate_prep(page, vma, haddr, page_nid, &flags); if (target_nid == NUMA_NO_NODE) { put_page(page); goto out_map; } spin_unlock(vmf->ptl); migrated = migrate_misplaced_page(page, vma, target_nid); if (migrated) { flags |= TNF_MIGRATED; page_nid = target_nid; task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, flags); return 0; } flags |= TNF_MIGRATE_FAIL; vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { spin_unlock(vmf->ptl); return 0; } out_map: /* Restore the PMD */ pmd = pmd_modify(oldpmd, vma->vm_page_prot); pmd = pmd_mkyoung(pmd); if (was_writable) pmd = pmd_mkwrite(pmd); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd); update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); spin_unlock(vmf->ptl); if (page_nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, flags); return 0; } /* * Return true if we do MADV_FREE successfully on entire pmd page. * Otherwise, return false. */ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long next) { spinlock_t *ptl; pmd_t orig_pmd; struct page *page; struct mm_struct *mm = tlb->mm; bool ret = false; tlb_change_page_size(tlb, HPAGE_PMD_SIZE); ptl = pmd_trans_huge_lock(pmd, vma); if (!ptl) goto out_unlocked; orig_pmd = *pmd; if (is_huge_zero_pmd(orig_pmd)) goto out; if (unlikely(!pmd_present(orig_pmd))) { VM_BUG_ON(thp_migration_supported() && !is_pmd_migration_entry(orig_pmd)); goto out; } page = pmd_page(orig_pmd); /* * If other processes are mapping this page, we couldn't discard * the page unless they all do MADV_FREE so let's skip the page. */ if (total_mapcount(page) != 1) goto out; if (!trylock_page(page)) goto out; /* * If user want to discard part-pages of THP, split it so MADV_FREE * will deactivate only them. */ if (next - addr != HPAGE_PMD_SIZE) { get_page(page); spin_unlock(ptl); split_huge_page(page); unlock_page(page); put_page(page); goto out_unlocked; } if (PageDirty(page)) ClearPageDirty(page); unlock_page(page); if (pmd_young(orig_pmd) || pmd_dirty(orig_pmd)) { pmdp_invalidate(vma, addr, pmd); orig_pmd = pmd_mkold(orig_pmd); orig_pmd = pmd_mkclean(orig_pmd); set_pmd_at(mm, addr, pmd, orig_pmd); tlb_remove_pmd_tlb_entry(tlb, pmd, addr); } mark_page_lazyfree(page); ret = true; out: spin_unlock(ptl); out_unlocked: return ret; } static inline void zap_deposited_table(struct mm_struct *mm, pmd_t *pmd) { pgtable_t pgtable; pgtable = pgtable_trans_huge_withdraw(mm, pmd); pte_free(mm, pgtable); mm_dec_nr_ptes(mm); } int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr) { pmd_t orig_pmd; spinlock_t *ptl; tlb_change_page_size(tlb, HPAGE_PMD_SIZE); ptl = __pmd_trans_huge_lock(pmd, vma); if (!ptl) return 0; /* * For architectures like ppc64 we look at deposited pgtable * when calling pmdp_huge_get_and_clear. So do the * pgtable_trans_huge_withdraw after finishing pmdp related * operations. */ orig_pmd = pmdp_huge_get_and_clear_full(vma, addr, pmd, tlb->fullmm); tlb_remove_pmd_tlb_entry(tlb, pmd, addr); if (vma_is_special_huge(vma)) { if (arch_needs_pgtable_deposit()) zap_deposited_table(tlb->mm, pmd); spin_unlock(ptl); } else if (is_huge_zero_pmd(orig_pmd)) { zap_deposited_table(tlb->mm, pmd); spin_unlock(ptl); } else { struct page *page = NULL; int flush_needed = 1; if (pmd_present(orig_pmd)) { page = pmd_page(orig_pmd); page_remove_rmap(page, vma, true); VM_BUG_ON_PAGE(page_mapcount(page) < 0, page); VM_BUG_ON_PAGE(!PageHead(page), page); } else if (thp_migration_supported()) { swp_entry_t entry; VM_BUG_ON(!is_pmd_migration_entry(orig_pmd)); entry = pmd_to_swp_entry(orig_pmd); page = pfn_swap_entry_to_page(entry); flush_needed = 0; } else WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!"); if (PageAnon(page)) { zap_deposited_table(tlb->mm, pmd); add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR); } else { if (arch_needs_pgtable_deposit()) zap_deposited_table(tlb->mm, pmd); add_mm_counter(tlb->mm, mm_counter_file(page), -HPAGE_PMD_NR); } spin_unlock(ptl); if (flush_needed) tlb_remove_page_size(tlb, page, HPAGE_PMD_SIZE); } return 1; } #ifndef pmd_move_must_withdraw static inline int pmd_move_must_withdraw(spinlock_t *new_pmd_ptl, spinlock_t *old_pmd_ptl, struct vm_area_struct *vma) { /* * With split pmd lock we also need to move preallocated * PTE page table if new_pmd is on different PMD page table. * * We also don't deposit and withdraw tables for file pages. */ return (new_pmd_ptl != old_pmd_ptl) && vma_is_anonymous(vma); } #endif static pmd_t move_soft_dirty_pmd(pmd_t pmd) { #ifdef CONFIG_MEM_SOFT_DIRTY if (unlikely(is_pmd_migration_entry(pmd))) pmd = pmd_swp_mksoft_dirty(pmd); else if (pmd_present(pmd)) pmd = pmd_mksoft_dirty(pmd); #endif return pmd; } 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) { spinlock_t *old_ptl, *new_ptl; pmd_t pmd; struct mm_struct *mm = vma->vm_mm; bool force_flush = false; /* * The destination pmd shouldn't be established, free_pgtables() * should have release it. */ if (WARN_ON(!pmd_none(*new_pmd))) { VM_BUG_ON(pmd_trans_huge(*new_pmd)); return false; } /* * We don't have to worry about the ordering of src and dst * ptlocks because exclusive mmap_lock prevents deadlock. */ old_ptl = __pmd_trans_huge_lock(old_pmd, vma); if (old_ptl) { new_ptl = pmd_lockptr(mm, new_pmd); if (new_ptl != old_ptl) spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd); if (pmd_present(pmd)) force_flush = true; VM_BUG_ON(!pmd_none(*new_pmd)); if (pmd_move_must_withdraw(new_ptl, old_ptl, vma)) { pgtable_t pgtable; pgtable = pgtable_trans_huge_withdraw(mm, old_pmd); pgtable_trans_huge_deposit(mm, new_pmd, pgtable); } pmd = move_soft_dirty_pmd(pmd); set_pmd_at(mm, new_addr, new_pmd, pmd); if (force_flush) flush_pmd_tlb_range(vma, old_addr, old_addr + PMD_SIZE); if (new_ptl != old_ptl) spin_unlock(new_ptl); spin_unlock(old_ptl); return true; } return false; } /* * Returns * - 0 if PMD could not be locked * - 1 if PMD was locked but protections unchanged and TLB flush unnecessary * or if prot_numa but THP migration is not supported * - HPAGE_PMD_NR if protections changed and TLB flush necessary */ 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) { struct mm_struct *mm = vma->vm_mm; spinlock_t *ptl; pmd_t oldpmd, entry; bool preserve_write; int ret; bool prot_numa = cp_flags & MM_CP_PROT_NUMA; bool uffd_wp = cp_flags & MM_CP_UFFD_WP; bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; tlb_change_page_size(tlb, HPAGE_PMD_SIZE); if (prot_numa && !thp_migration_supported()) return 1; ptl = __pmd_trans_huge_lock(pmd, vma); if (!ptl) return 0; preserve_write = prot_numa && pmd_write(*pmd); ret = 1; #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION if (is_swap_pmd(*pmd)) { swp_entry_t entry = pmd_to_swp_entry(*pmd); struct page *page = pfn_swap_entry_to_page(entry); pmd_t newpmd; VM_BUG_ON(!is_pmd_migration_entry(*pmd)); if (is_writable_migration_entry(entry)) { /* * A protection check is difficult so * just be safe and disable write */ if (PageAnon(page)) entry = make_readable_exclusive_migration_entry(swp_offset(entry)); else entry = make_readable_migration_entry(swp_offset(entry)); newpmd = swp_entry_to_pmd(entry); if (pmd_swp_soft_dirty(*pmd)) newpmd = pmd_swp_mksoft_dirty(newpmd); if (pmd_swp_uffd_wp(*pmd)) newpmd = pmd_swp_mkuffd_wp(newpmd); } else { newpmd = *pmd; } if (uffd_wp) newpmd = pmd_swp_mkuffd_wp(newpmd); else if (uffd_wp_resolve) newpmd = pmd_swp_clear_uffd_wp(newpmd); if (!pmd_same(*pmd, newpmd)) set_pmd_at(mm, addr, pmd, newpmd); goto unlock; } #endif if (prot_numa) { struct page *page; bool toptier; /* * Avoid trapping faults against the zero page. The read-only * data is likely to be read-cached on the local CPU and * local/remote hits to the zero page are not interesting. */ if (is_huge_zero_pmd(*pmd)) goto unlock; if (pmd_protnone(*pmd)) goto unlock; page = pmd_page(*pmd); toptier = node_is_toptier(page_to_nid(page)); /* * Skip scanning top tier node if normal numa * balancing is disabled */ if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) && toptier) goto unlock; if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING && !toptier) xchg_page_access_time(page, jiffies_to_msecs(jiffies)); } /* * In case prot_numa, we are under mmap_read_lock(mm). It's critical * to not clear pmd intermittently to avoid race with MADV_DONTNEED * which is also under mmap_read_lock(mm): * * CPU0: CPU1: * change_huge_pmd(prot_numa=1) * pmdp_huge_get_and_clear_notify() * madvise_dontneed() * zap_pmd_range() * pmd_trans_huge(*pmd) == 0 (without ptl) * // skip the pmd * set_pmd_at(); * // pmd is re-established * * The race makes MADV_DONTNEED miss the huge pmd and don't clear it * which may break userspace. * * pmdp_invalidate_ad() is required to make sure we don't miss * dirty/young flags set by hardware. */ oldpmd = pmdp_invalidate_ad(vma, addr, pmd); entry = pmd_modify(oldpmd, newprot); if (preserve_write) entry = pmd_mk_savedwrite(entry); if (uffd_wp) { entry = pmd_wrprotect(entry); entry = pmd_mkuffd_wp(entry); } else if (uffd_wp_resolve) { /* * Leave the write bit to be handled by PF interrupt * handler, then things like COW could be properly * handled. */ entry = pmd_clear_uffd_wp(entry); } ret = HPAGE_PMD_NR; set_pmd_at(mm, addr, pmd, entry); if (huge_pmd_needs_flush(oldpmd, entry)) tlb_flush_pmd_range(tlb, addr, HPAGE_PMD_SIZE); BUG_ON(vma_is_anonymous(vma) && !preserve_write && pmd_write(entry)); unlock: spin_unlock(ptl); return ret; } #ifdef CONFIG_USERFAULTFD /* * The PT lock for src_pmd and dst_vma/src_vma (for reading) are locked by * the caller, but it must return after releasing the page_table_lock. * Just move the page from src_pmd to dst_pmd if possible. * Return zero if succeeded in moving the page, -EAGAIN if it needs to be * repeated by the caller, or other errors in case of failure. */ 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) { pmd_t _dst_pmd, src_pmdval; struct page *src_page; struct folio *src_folio; struct anon_vma *src_anon_vma; spinlock_t *src_ptl, *dst_ptl; pgtable_t src_pgtable; struct mmu_notifier_range range; int err = 0; src_pmdval = *src_pmd; src_ptl = pmd_lockptr(mm, src_pmd); lockdep_assert_held(src_ptl); vma_assert_locked(src_vma); vma_assert_locked(dst_vma); /* Sanity checks before the operation */ if (WARN_ON_ONCE(!pmd_none(dst_pmdval)) || WARN_ON_ONCE(src_addr & ~HPAGE_PMD_MASK) || WARN_ON_ONCE(dst_addr & ~HPAGE_PMD_MASK)) { spin_unlock(src_ptl); return -EINVAL; } if (!pmd_trans_huge(src_pmdval)) { spin_unlock(src_ptl); if (is_pmd_migration_entry(src_pmdval)) { pmd_migration_entry_wait(mm, &src_pmdval); return -EAGAIN; } return -ENOENT; } src_page = pmd_page(src_pmdval); if (!is_huge_zero_pmd(src_pmdval)) { if (unlikely(!PageAnonExclusive(src_page))) { spin_unlock(src_ptl); return -EBUSY; } src_folio = page_folio(src_page); folio_get(src_folio); } else src_folio = NULL; spin_unlock(src_ptl); flush_cache_range(src_vma, src_addr, src_addr + HPAGE_PMD_SIZE); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, src_vma, mm, src_addr, src_addr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); if (src_folio) { folio_lock(src_folio); /* * split_huge_page walks the anon_vma chain without the page * lock. Serialize against it with the anon_vma lock, the page * lock is not enough. */ src_anon_vma = folio_get_anon_vma(src_folio); if (!src_anon_vma) { err = -EAGAIN; goto unlock_folio; } anon_vma_lock_write(src_anon_vma); } else src_anon_vma = NULL; dst_ptl = pmd_lockptr(mm, dst_pmd); double_pt_lock(src_ptl, dst_ptl); if (unlikely(!pmd_same(*src_pmd, src_pmdval) || !pmd_same(*dst_pmd, dst_pmdval))) { err = -EAGAIN; goto unlock_ptls; } if (src_folio) { if (folio_maybe_dma_pinned(src_folio) || !PageAnonExclusive(&src_folio->page)) { err = -EBUSY; goto unlock_ptls; } if (WARN_ON_ONCE(!folio_test_head(src_folio)) || WARN_ON_ONCE(!folio_test_anon(src_folio))) { err = -EBUSY; goto unlock_ptls; } src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd); /* Folio got pinned from under us. Put it back and fail the move. */ if (folio_maybe_dma_pinned(src_folio)) { set_pmd_at(mm, src_addr, src_pmd, src_pmdval); err = -EBUSY; goto unlock_ptls; } page_move_anon_rmap(&src_folio->page, dst_vma); WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr)); _dst_pmd = mk_huge_pmd(&src_folio->page, dst_vma->vm_page_prot); /* Follow mremap() behavior and treat the entry dirty after the move */ _dst_pmd = pmd_mkwrite(pmd_mkdirty(_dst_pmd)); } else { src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd); _dst_pmd = mk_huge_pmd(src_page, dst_vma->vm_page_prot); } set_pmd_at(mm, dst_addr, dst_pmd, _dst_pmd); src_pgtable = pgtable_trans_huge_withdraw(mm, src_pmd); pgtable_trans_huge_deposit(mm, dst_pmd, src_pgtable); unlock_ptls: double_pt_unlock(src_ptl, dst_ptl); if (src_anon_vma) { anon_vma_unlock_write(src_anon_vma); put_anon_vma(src_anon_vma); } unlock_folio: /* unblock rmap walks */ if (src_folio) folio_unlock(src_folio); mmu_notifier_invalidate_range_end(&range); if (src_folio) folio_put(src_folio); return err; } #endif /* CONFIG_USERFAULTFD */ /* * Returns page table lock pointer if a given pmd maps a thp, NULL otherwise. * * Note that if it returns page table lock pointer, this routine returns without * unlocking page table lock. So callers must unlock it. */ spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { spinlock_t *ptl; ptl = pmd_lock(vma->vm_mm, pmd); if (likely(is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd))) return ptl; spin_unlock(ptl); return NULL; } EXPORT_SYMBOL_GPL(__pmd_trans_huge_lock); /* * Returns page table lock pointer if a given pud maps a thp, NULL otherwise. * * Note that if it returns page table lock pointer, this routine returns without * unlocking page table lock. So callers must unlock it. */ spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma) { spinlock_t *ptl; ptl = pud_lock(vma->vm_mm, pud); if (likely(pud_trans_huge(*pud) || pud_devmap(*pud))) return ptl; spin_unlock(ptl); return NULL; } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr) { spinlock_t *ptl; ptl = __pud_trans_huge_lock(pud, vma); if (!ptl) return 0; pudp_huge_get_and_clear_full(tlb->mm, addr, pud, tlb->fullmm); tlb_remove_pud_tlb_entry(tlb, pud, addr); if (vma_is_special_huge(vma)) { spin_unlock(ptl); /* No zero page support yet */ } else { /* No support for anonymous PUD pages yet */ BUG(); } return 1; } static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud, unsigned long haddr) { VM_BUG_ON(haddr & ~HPAGE_PUD_MASK); VM_BUG_ON_VMA(vma->vm_start > haddr, vma); VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma); VM_BUG_ON(!pud_trans_huge(*pud) && !pud_devmap(*pud)); count_vm_event(THP_SPLIT_PUD); pudp_huge_clear_flush_notify(vma, haddr, pud); } void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, unsigned long address) { spinlock_t *ptl; struct mmu_notifier_range range; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, address & HPAGE_PUD_MASK, (address & HPAGE_PUD_MASK) + HPAGE_PUD_SIZE); mmu_notifier_invalidate_range_start(&range); ptl = pud_lock(vma->vm_mm, pud); if (unlikely(!pud_trans_huge(*pud) && !pud_devmap(*pud))) goto out; __split_huge_pud_locked(vma, pud, range.start); out: spin_unlock(ptl); /* * No need to double call mmu_notifier->invalidate_range() callback as * the above pudp_huge_clear_flush_notify() did already call it. */ mmu_notifier_invalidate_range_only_end(&range); } #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd) { struct mm_struct *mm = vma->vm_mm; pgtable_t pgtable; pmd_t _pmd, old_pmd; int i; /* * Leave pmd empty until pte is filled note that it is fine to delay * notification until mmu_notifier_invalidate_range_end() as we are * replacing a zero pmd write protected page with a zero pte write * protected page. * * See Documentation/mm/mmu_notifier.rst */ old_pmd = pmdp_huge_clear_flush(vma, haddr, pmd); pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { pte_t *pte, entry; entry = pfn_pte(my_zero_pfn(haddr), vma->vm_page_prot); entry = pte_mkspecial(entry); if (pmd_uffd_wp(old_pmd)) entry = pte_mkuffd_wp(entry); pte = pte_offset_map(&_pmd, haddr); VM_BUG_ON(!pte_none(*pte)); set_pte_at(mm, haddr, pte, entry); pte_unmap(pte); } smp_wmb(); /* make pte visible before pmd */ pmd_populate(mm, pmd, pgtable); } static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, unsigned long haddr, bool freeze) { struct mm_struct *mm = vma->vm_mm; struct page *page; pgtable_t pgtable; pmd_t old_pmd, _pmd; bool young, write, soft_dirty, pmd_migration = false, uffd_wp = false; bool anon_exclusive = false, dirty = false; unsigned long addr; int i; VM_BUG_ON(haddr & ~HPAGE_PMD_MASK); VM_BUG_ON_VMA(vma->vm_start > haddr, vma); VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PMD_SIZE, vma); VM_BUG_ON(!is_pmd_migration_entry(*pmd) && !pmd_trans_huge(*pmd) && !pmd_devmap(*pmd)); count_vm_event(THP_SPLIT_PMD); if (!vma_is_anonymous(vma)) { old_pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd); /* * We are going to unmap this huge page. So * just go ahead and zap it */ if (arch_needs_pgtable_deposit()) zap_deposited_table(mm, pmd); if (vma_is_special_huge(vma)) return; if (unlikely(is_pmd_migration_entry(old_pmd))) { swp_entry_t entry; entry = pmd_to_swp_entry(old_pmd); page = pfn_swap_entry_to_page(entry); } else { page = pmd_page(old_pmd); if (!PageDirty(page) && pmd_dirty(old_pmd)) set_page_dirty(page); if (!PageReferenced(page) && pmd_young(old_pmd)) SetPageReferenced(page); page_remove_rmap(page, vma, true); put_page(page); } add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR); return; } if (is_huge_zero_pmd(*pmd)) { /* * FIXME: Do we want to invalidate secondary mmu by calling * mmu_notifier_invalidate_range() see comments below inside * __split_huge_pmd() ? * * We are going from a zero huge page write protected to zero * small page also write protected so it does not seems useful * to invalidate secondary mmu at this time. */ return __split_huge_zero_page_pmd(vma, haddr, pmd); } pmd_migration = is_pmd_migration_entry(*pmd); if (unlikely(pmd_migration)) { swp_entry_t entry; old_pmd = *pmd; entry = pmd_to_swp_entry(old_pmd); page = pfn_swap_entry_to_page(entry); write = is_writable_migration_entry(entry); if (PageAnon(page)) anon_exclusive = is_readable_exclusive_migration_entry(entry); young = is_migration_entry_young(entry); dirty = is_migration_entry_dirty(entry); soft_dirty = pmd_swp_soft_dirty(old_pmd); uffd_wp = pmd_swp_uffd_wp(old_pmd); } else { /* * Up to this point the pmd is present and huge and userland has * the whole access to the hugepage during the split (which * happens in place). If we overwrite the pmd with the not-huge * version pointing to the pte here (which of course we could if * all CPUs were bug free), userland could trigger a small page * size TLB miss on the small sized TLB while the hugepage TLB * entry is still established in the huge TLB. Some CPU doesn't * like that. See * http://support.amd.com/TechDocs/41322_10h_Rev_Gd.pdf, Erratum * 383 on page 105. Intel should be safe but is also warns that * it's only safe if the permission and cache attributes of the * two entries loaded in the two TLB is identical (which should * be the case here). But it is generally safer to never allow * small and huge TLB entries for the same virtual address to be * loaded simultaneously. So instead of doing "pmd_populate(); * flush_pmd_tlb_range();" we first mark the current pmd * notpresent (atomically because here the pmd_trans_huge must * remain set at all times on the pmd until the split is * complete for this pmd), then we flush the SMP TLB and finally * we write the non-huge version of the pmd entry with * pmd_populate. */ old_pmd = pmdp_invalidate(vma, haddr, pmd); page = pmd_page(old_pmd); if (pmd_dirty(old_pmd)) { dirty = true; SetPageDirty(page); } write = pmd_write(old_pmd); young = pmd_young(old_pmd); soft_dirty = pmd_soft_dirty(old_pmd); uffd_wp = pmd_uffd_wp(old_pmd); VM_BUG_ON_PAGE(!page_count(page), page); page_ref_add(page, HPAGE_PMD_NR - 1); /* * Without "freeze", we'll simply split the PMD, propagating the * PageAnonExclusive() flag for each PTE by setting it for * each subpage -- no need to (temporarily) clear. * * With "freeze" we want to replace mapped pages by * migration entries right away. This is only possible if we * managed to clear PageAnonExclusive() -- see * set_pmd_migration_entry(). * * In case we cannot clear PageAnonExclusive(), split the PMD * only and let try_to_migrate_one() fail later. * * See page_try_share_anon_rmap(): invalidate PMD first. */ anon_exclusive = PageAnon(page) && PageAnonExclusive(page); if (freeze && anon_exclusive && page_try_share_anon_rmap(page)) freeze = false; } /* * Withdraw the table only after we mark the pmd entry invalid. * This's critical for some architectures (Power). */ pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) { pte_t entry, *pte; /* * Note that NUMA hinting access restrictions are not * transferred to avoid any possibility of altering * permissions across VMAs. */ if (freeze || pmd_migration) { swp_entry_t swp_entry; if (write) swp_entry = make_writable_migration_entry( page_to_pfn(page + i)); else if (anon_exclusive) swp_entry = make_readable_exclusive_migration_entry( page_to_pfn(page + i)); else swp_entry = make_readable_migration_entry( page_to_pfn(page + i)); if (young) swp_entry = make_migration_entry_young(swp_entry); if (dirty) swp_entry = make_migration_entry_dirty(swp_entry); entry = swp_entry_to_pte(swp_entry); if (soft_dirty) entry = pte_swp_mksoft_dirty(entry); if (uffd_wp) entry = pte_swp_mkuffd_wp(entry); } else { entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot)); entry = maybe_mkwrite(entry, vma); if (anon_exclusive) SetPageAnonExclusive(page + i); if (!write) entry = pte_wrprotect(entry); if (!young) entry = pte_mkold(entry); /* * NOTE: we don't do pte_mkdirty when dirty==true * because it breaks sparc64 which can sigsegv * random process. Need to revisit when we figure * out what is special with sparc64. */ if (soft_dirty) entry = pte_mksoft_dirty(entry); if (uffd_wp) entry = pte_mkuffd_wp(entry); } pte = pte_offset_map(&_pmd, addr); BUG_ON(!pte_none(*pte)); set_pte_at(mm, addr, pte, entry); if (!pmd_migration) atomic_inc(&page[i]._mapcount); pte_unmap(pte); } if (!pmd_migration) { /* * Set PG_double_map before dropping compound_mapcount to avoid * false-negative page_mapped(). */ if (compound_mapcount(page) > 1 && !TestSetPageDoubleMap(page)) { for (i = 0; i < HPAGE_PMD_NR; i++) atomic_inc(&page[i]._mapcount); } lock_page_memcg(page); if (atomic_add_negative(-1, compound_mapcount_ptr(page))) { /* Last compound_mapcount is gone. */ __mod_lruvec_page_state(page, NR_ANON_THPS, -HPAGE_PMD_NR); if (TestClearPageDoubleMap(page)) { /* No need in mapcount reference anymore */ for (i = 0; i < HPAGE_PMD_NR; i++) atomic_dec(&page[i]._mapcount); } } unlock_page_memcg(page); /* Above is effectively page_remove_rmap(page, vma, true) */ munlock_vma_page(page, vma, true); } smp_wmb(); /* make pte visible before pmd */ pmd_populate(mm, pmd, pgtable); if (freeze) { for (i = 0; i < HPAGE_PMD_NR; i++) { page_remove_rmap(page + i, vma, false); put_page(page + i); } } } void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long address, bool freeze, struct folio *folio) { spinlock_t *ptl; struct mmu_notifier_range range; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, address & HPAGE_PMD_MASK, (address & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); ptl = pmd_lock(vma->vm_mm, pmd); /* * If caller asks to setup a migration entry, we need a folio to check * pmd against. Otherwise we can end up replacing wrong folio. */ VM_BUG_ON(freeze && !folio); VM_WARN_ON_ONCE(folio && !folio_test_locked(folio)); if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || is_pmd_migration_entry(*pmd)) { /* * It's safe to call pmd_page when folio is set because it's * guaranteed that pmd is present. */ if (folio && folio != page_folio(pmd_page(*pmd))) goto out; __split_huge_pmd_locked(vma, pmd, range.start, freeze); } out: spin_unlock(ptl); /* * No need to double call mmu_notifier->invalidate_range() callback. * They are 3 cases to consider inside __split_huge_pmd_locked(): * 1) pmdp_huge_clear_flush_notify() call invalidate_range() obvious * 2) __split_huge_zero_page_pmd() read only zero page and any write * fault will trigger a flush_notify before pointing to a new page * (it is fine if the secondary mmu keeps pointing to the old zero * page in the meantime) * 3) Split a huge pmd into pte pointing to the same page. No need * to invalidate secondary tlb entry they are all still valid. * any further changes to individual pte will notify. So no need * to call mmu_notifier->invalidate_range() */ mmu_notifier_invalidate_range_only_end(&range); } void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct folio *folio) { pmd_t *pmd = mm_find_pmd(vma->vm_mm, address); if (!pmd) return; __split_huge_pmd(vma, pmd, address, freeze, folio); } static inline void split_huge_pmd_if_needed(struct vm_area_struct *vma, unsigned long address) { /* * If the new address isn't hpage aligned and it could previously * contain an hugepage: check if we need to split an huge pmd. */ if (!IS_ALIGNED(address, HPAGE_PMD_SIZE) && range_in_vma(vma, ALIGN_DOWN(address, HPAGE_PMD_SIZE), ALIGN(address, HPAGE_PMD_SIZE))) split_huge_pmd_address(vma, address, false, NULL); } void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, long adjust_next) { /* Check if we need to split start first. */ split_huge_pmd_if_needed(vma, start); /* Check if we need to split end next. */ split_huge_pmd_if_needed(vma, end); /* * If we're also updating the next vma vm_start, * check if we need to split it. */ if (adjust_next > 0) { struct vm_area_struct *next = find_vma(vma->vm_mm, vma->vm_end); unsigned long nstart = next->vm_start; nstart += adjust_next; split_huge_pmd_if_needed(next, nstart); } } static void unmap_folio(struct folio *folio) { enum ttu_flags ttu_flags = TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | TTU_SYNC; VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); /* * Anon pages need migration entries to preserve them, but file * pages can simply be left unmapped, then faulted back on demand. * If that is ever changed (perhaps for mlock), update remap_page(). */ if (folio_test_anon(folio)) try_to_migrate(folio, ttu_flags); else try_to_unmap(folio, ttu_flags | TTU_IGNORE_MLOCK); } static void remap_page(struct folio *folio, unsigned long nr) { int i = 0; /* If unmap_folio() uses try_to_migrate() on file, remove this check */ if (!folio_test_anon(folio)) return; for (;;) { remove_migration_ptes(folio, folio, true); i += folio_nr_pages(folio); if (i >= nr) break; folio = folio_next(folio); } } static void lru_add_page_tail(struct page *head, struct page *tail, struct lruvec *lruvec, struct list_head *list) { VM_BUG_ON_PAGE(!PageHead(head), head); VM_BUG_ON_PAGE(PageCompound(tail), head); VM_BUG_ON_PAGE(PageLRU(tail), head); lockdep_assert_held(&lruvec->lru_lock); if (list) { /* page reclaim is reclaiming a huge page */ VM_WARN_ON(PageLRU(head)); get_page(tail); list_add_tail(&tail->lru, list); } else { /* head is still on lru (and we have it frozen) */ VM_WARN_ON(!PageLRU(head)); if (PageUnevictable(tail)) tail->mlock_count = 0; else list_add_tail(&tail->lru, &head->lru); SetPageLRU(tail); } } static void __split_huge_page_tail(struct page *head, int tail, struct lruvec *lruvec, struct list_head *list) { struct page *page_tail = head + tail; VM_BUG_ON_PAGE(atomic_read(&page_tail->_mapcount) != -1, page_tail); /* * Clone page flags before unfreezing refcount. * * After successful get_page_unless_zero() might follow flags change, * for example lock_page() which set PG_waiters. * * Note that for mapped sub-pages of an anonymous THP, * PG_anon_exclusive has been cleared in unmap_folio() and is stored in * the migration entry instead from where remap_page() will restore it. * We can still have PG_anon_exclusive set on effectively unmapped and * unreferenced sub-pages of an anonymous THP: we can simply drop * PG_anon_exclusive (-> PG_mappedtodisk) for these here. */ page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; page_tail->flags |= (head->flags & ((1L << PG_referenced) | (1L << PG_swapbacked) | (1L << PG_swapcache) | (1L << PG_mlocked) | (1L << PG_uptodate) | (1L << PG_active) | (1L << PG_workingset) | (1L << PG_locked) | (1L << PG_unevictable) | #ifdef CONFIG_64BIT (1L << PG_arch_2) | #endif (1L << PG_dirty) | LRU_GEN_MASK | LRU_REFS_MASK)); /* ->mapping in first tail page is compound_mapcount */ VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING, page_tail); page_tail->mapping = head->mapping; page_tail->index = head->index + tail; /* * page->private should not be set in tail pages with the exception * of swap cache pages that store the swp_entry_t in tail pages. * Fix up and warn once if private is unexpectedly set. */ if (!folio_test_swapcache(page_folio(head))) { VM_WARN_ON_ONCE_PAGE(page_tail->private != 0, page_tail); page_tail->private = 0; } /* Page flags must be visible before we make the page non-compound. */ smp_wmb(); /* * Clear PageTail before unfreezing page refcount. * * After successful get_page_unless_zero() might follow put_page() * which needs correct compound_head(). */ clear_compound_head(page_tail); /* Finally unfreeze refcount. Additional reference from page cache. */ page_ref_unfreeze(page_tail, 1 + (!PageAnon(head) || PageSwapCache(head))); if (page_is_young(head)) set_page_young(page_tail); if (page_is_idle(head)) set_page_idle(page_tail); page_cpupid_xchg_last(page_tail, page_cpupid_last(head)); /* * always add to the tail because some iterators expect new * pages to show after the currently processed elements - e.g. * migrate_pages */ lru_add_page_tail(head, page_tail, lruvec, list); } static void __split_huge_page(struct page *page, struct list_head *list, pgoff_t end) { struct folio *folio = page_folio(page); struct page *head = &folio->page; struct lruvec *lruvec; struct address_space *swap_cache = NULL; unsigned long offset = 0; unsigned int nr = thp_nr_pages(head); int i; /* complete memcg works before add pages to LRU */ split_page_memcg(head, nr); if (PageAnon(head) && PageSwapCache(head)) { swp_entry_t entry = { .val = page_private(head) }; offset = swp_offset(entry); swap_cache = swap_address_space(entry); xa_lock(&swap_cache->i_pages); } /* lock lru list/PageCompound, ref frozen by page_ref_freeze */ lruvec = folio_lruvec_lock(folio); ClearPageHasHWPoisoned(head); for (i = nr - 1; i >= 1; i--) { __split_huge_page_tail(head, i, lruvec, list); /* Some pages can be beyond EOF: drop them from page cache */ if (head[i].index >= end) { struct folio *tail = page_folio(head + i); if (shmem_mapping(head->mapping)) shmem_uncharge(head->mapping->host, 1); else if (folio_test_clear_dirty(tail)) folio_account_cleaned(tail, inode_to_wb(folio->mapping->host)); __filemap_remove_folio(tail, NULL); folio_put(tail); } else if (!PageAnon(page)) { __xa_store(&head->mapping->i_pages, head[i].index, head + i, 0); } else if (swap_cache) { __xa_store(&swap_cache->i_pages, offset + i, head + i, 0); } } ClearPageCompound(head); unlock_page_lruvec(lruvec); /* Caller disabled irqs, so they are still disabled here */ split_page_owner(head, nr); /* See comment in __split_huge_page_tail() */ if (PageAnon(head)) { /* Additional pin to swap cache */ if (PageSwapCache(head)) { page_ref_add(head, 2); xa_unlock(&swap_cache->i_pages); } else { page_ref_inc(head); } } else { /* Additional pin to page cache */ page_ref_add(head, 2); xa_unlock(&head->mapping->i_pages); } local_irq_enable(); remap_page(folio, nr); if (PageSwapCache(head)) { swp_entry_t entry = { .val = page_private(head) }; split_swap_cluster(entry); } for (i = 0; i < nr; i++) { struct page *subpage = head + i; if (subpage == page) continue; unlock_page(subpage); /* * Subpages may be freed if there wasn't any mapping * like if add_to_swap() is running on a lru page that * had its mapping zapped. And freeing these pages * requires taking the lru_lock so we do the put_page * of the tail pages after the split is complete. */ free_page_and_swap_cache(subpage); } } /* Racy check whether the huge page can be split */ bool can_split_folio(struct folio *folio, int *pextra_pins) { int extra_pins; /* Additional pins from page cache */ if (folio_test_anon(folio)) extra_pins = folio_test_swapcache(folio) ? folio_nr_pages(folio) : 0; else extra_pins = folio_nr_pages(folio); if (pextra_pins) *pextra_pins = extra_pins; return folio_mapcount(folio) == folio_ref_count(folio) - extra_pins - 1; } /* * This function splits huge page into normal pages. @page can point to any * subpage of huge page to split. Split doesn't change the position of @page. * * Only caller must hold pin on the @page, otherwise split fails with -EBUSY. * The huge page must be locked. * * If @list is null, tail pages will be added to LRU list, otherwise, to @list. * * Both head page and tail pages will inherit mapping, flags, and so on from * the hugepage. * * GUP pin and PG_locked transferred to @page. Rest subpages can be freed if * they are not mapped. * * Returns 0 if the hugepage is split successfully. * Returns -EBUSY if the page is pinned or if anon_vma disappeared from under * us. */ int split_huge_page_to_list(struct page *page, struct list_head *list) { struct folio *folio = page_folio(page); struct deferred_split *ds_queue = get_deferred_split_queue(&folio->page); XA_STATE(xas, &folio->mapping->i_pages, folio->index); struct anon_vma *anon_vma = NULL; struct address_space *mapping = NULL; int extra_pins, ret; pgoff_t end; bool is_hzp; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); is_hzp = is_huge_zero_page(&folio->page); if (is_hzp) { pr_warn_ratelimited("Called split_huge_page for huge zero page\n"); return -EBUSY; } if (folio_test_writeback(folio)) return -EBUSY; if (folio_test_anon(folio)) { /* * The caller does not necessarily hold an mmap_lock that would * prevent the anon_vma disappearing so we first we take a * reference to it and then lock the anon_vma for write. This * is similar to folio_lock_anon_vma_read except the write lock * is taken to serialise against parallel split or collapse * operations. */ anon_vma = folio_get_anon_vma(folio); if (!anon_vma) { ret = -EBUSY; goto out; } end = -1; mapping = NULL; anon_vma_lock_write(anon_vma); } else { gfp_t gfp; mapping = folio->mapping; /* Truncated ? */ if (!mapping) { ret = -EBUSY; goto out; } gfp = current_gfp_context(mapping_gfp_mask(mapping) & GFP_RECLAIM_MASK); if (!filemap_release_folio(folio, gfp)) { ret = -EBUSY; goto out; } xas_split_alloc(&xas, folio, folio_order(folio), gfp); if (xas_error(&xas)) { ret = xas_error(&xas); goto out; } anon_vma = NULL; i_mmap_lock_read(mapping); /* *__split_huge_page() may need to trim off pages beyond EOF: * but on 32-bit, i_size_read() takes an irq-unsafe seqlock, * which cannot be nested inside the page tree lock. So note * end now: i_size itself may be changed at any moment, but * folio lock is good enough to serialize the trimming. */ end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); if (shmem_mapping(mapping)) end = shmem_fallocend(mapping->host, end); } /* * Racy check if we can split the page, before unmap_folio() will * split PMDs */ if (!can_split_folio(folio, &extra_pins)) { ret = -EAGAIN; goto out_unlock; } unmap_folio(folio); /* block interrupt reentry in xa_lock and spinlock */ local_irq_disable(); if (mapping) { /* * Check if the folio is present in page cache. * We assume all tail are present too, if folio is there. */ xas_lock(&xas); xas_reset(&xas); if (xas_load(&xas) != folio) goto fail; } /* Prevent deferred_split_scan() touching ->_refcount */ spin_lock(&ds_queue->split_queue_lock); if (folio_ref_freeze(folio, 1 + extra_pins)) { if (!list_empty(page_deferred_list(&folio->page))) { ds_queue->split_queue_len--; list_del(page_deferred_list(&folio->page)); } spin_unlock(&ds_queue->split_queue_lock); if (mapping) { int nr = folio_nr_pages(folio); xas_split(&xas, folio, folio_order(folio)); if (folio_test_pmd_mappable(folio)) { if (folio_test_swapbacked(folio)) { __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, -nr); } else { __lruvec_stat_mod_folio(folio, NR_FILE_THPS, -nr); filemap_nr_thps_dec(mapping); } } } __split_huge_page(page, list, end); ret = 0; } else { spin_unlock(&ds_queue->split_queue_lock); fail: if (mapping) xas_unlock(&xas); local_irq_enable(); remap_page(folio, folio_nr_pages(folio)); ret = -EAGAIN; } out_unlock: if (anon_vma) { anon_vma_unlock_write(anon_vma); put_anon_vma(anon_vma); } if (mapping) i_mmap_unlock_read(mapping); out: xas_destroy(&xas); count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED); return ret; } void free_transhuge_page(struct page *page) { struct deferred_split *ds_queue = get_deferred_split_queue(page); unsigned long flags; spin_lock_irqsave(&ds_queue->split_queue_lock, flags); if (!list_empty(page_deferred_list(page))) { ds_queue->split_queue_len--; list_del(page_deferred_list(page)); } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); free_compound_page(page); } void deferred_split_huge_page(struct page *page) { struct deferred_split *ds_queue = get_deferred_split_queue(page); #ifdef CONFIG_MEMCG struct mem_cgroup *memcg = page_memcg(compound_head(page)); #endif unsigned long flags; VM_BUG_ON_PAGE(!PageTransHuge(page), page); /* * The try_to_unmap() in page reclaim path might reach here too, * this may cause a race condition to corrupt deferred split queue. * And, if page reclaim is already handling the same page, it is * unnecessary to handle it again in shrinker. * * Check PageSwapCache to determine if the page is being * handled by page reclaim since THP swap would add the page into * swap cache before calling try_to_unmap(). */ if (PageSwapCache(page)) return; if (!list_empty(page_deferred_list(page))) return; spin_lock_irqsave(&ds_queue->split_queue_lock, flags); if (list_empty(page_deferred_list(page))) { count_vm_event(THP_DEFERRED_SPLIT_PAGE); list_add_tail(page_deferred_list(page), &ds_queue->split_queue); ds_queue->split_queue_len++; #ifdef CONFIG_MEMCG if (memcg) set_shrinker_bit(memcg, page_to_nid(page), deferred_split_shrinker.id); #endif } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); } static unsigned long deferred_split_count(struct shrinker *shrink, struct shrink_control *sc) { struct pglist_data *pgdata = NODE_DATA(sc->nid); struct deferred_split *ds_queue = &pgdata->deferred_split_queue; #ifdef CONFIG_MEMCG if (sc->memcg) ds_queue = &sc->memcg->deferred_split_queue; #endif return READ_ONCE(ds_queue->split_queue_len); } static unsigned long deferred_split_scan(struct shrinker *shrink, struct shrink_control *sc) { struct pglist_data *pgdata = NODE_DATA(sc->nid); struct deferred_split *ds_queue = &pgdata->deferred_split_queue; unsigned long flags; LIST_HEAD(list), *pos, *next; struct page *page; int split = 0; #ifdef CONFIG_MEMCG if (sc->memcg) ds_queue = &sc->memcg->deferred_split_queue; #endif spin_lock_irqsave(&ds_queue->split_queue_lock, flags); /* Take pin on all head pages to avoid freeing them under us */ list_for_each_safe(pos, next, &ds_queue->split_queue) { page = list_entry((void *)pos, struct page, deferred_list); page = compound_head(page); if (get_page_unless_zero(page)) { list_move(page_deferred_list(page), &list); } else { /* We lost race with put_compound_page() */ list_del_init(page_deferred_list(page)); ds_queue->split_queue_len--; } if (!--sc->nr_to_scan) break; } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); list_for_each_safe(pos, next, &list) { page = list_entry((void *)pos, struct page, deferred_list); if (!trylock_page(page)) goto next; /* split_huge_page() removes page from list on success */ if (!split_huge_page(page)) split++; unlock_page(page); next: put_page(page); } spin_lock_irqsave(&ds_queue->split_queue_lock, flags); list_splice_tail(&list, &ds_queue->split_queue); spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); /* * Stop shrinker if we didn't split any page, but the queue is empty. * This can happen if pages were freed under us. */ if (!split && list_empty(&ds_queue->split_queue)) return SHRINK_STOP; return split; } static struct shrinker deferred_split_shrinker = { .count_objects = deferred_split_count, .scan_objects = deferred_split_scan, .seeks = DEFAULT_SEEKS, .flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE | SHRINKER_NONSLAB, }; #ifdef CONFIG_DEBUG_FS static void split_huge_pages_all(void) { struct zone *zone; struct page *page; unsigned long pfn, max_zone_pfn; unsigned long total = 0, split = 0; pr_debug("Split all THPs\n"); for_each_zone(zone) { if (!managed_zone(zone)) continue; max_zone_pfn = zone_end_pfn(zone); for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) { int nr_pages; page = pfn_to_online_page(pfn); if (!page || !get_page_unless_zero(page)) continue; if (zone != page_zone(page)) goto next; if (!PageHead(page) || PageHuge(page) || !PageLRU(page)) goto next; total++; lock_page(page); nr_pages = thp_nr_pages(page); if (!split_huge_page(page)) split++; pfn += nr_pages - 1; unlock_page(page); next: put_page(page); cond_resched(); } } pr_debug("%lu of %lu THP split\n", split, total); } static inline bool vma_not_suitable_for_thp_split(struct vm_area_struct *vma) { return vma_is_special_huge(vma) || (vma->vm_flags & VM_IO) || is_vm_hugetlb_page(vma); } static int split_huge_pages_pid(int pid, unsigned long vaddr_start, unsigned long vaddr_end) { int ret = 0; struct task_struct *task; struct mm_struct *mm; unsigned long total = 0, split = 0; unsigned long addr; vaddr_start &= PAGE_MASK; vaddr_end &= PAGE_MASK; /* Find the task_struct from pid */ rcu_read_lock(); task = find_task_by_vpid(pid); if (!task) { rcu_read_unlock(); ret = -ESRCH; goto out; } get_task_struct(task); rcu_read_unlock(); /* Find the mm_struct */ mm = get_task_mm(task); put_task_struct(task); if (!mm) { ret = -EINVAL; goto out; } pr_debug("Split huge pages in pid: %d, vaddr: [0x%lx - 0x%lx]\n", pid, vaddr_start, vaddr_end); mmap_read_lock(mm); /* * always increase addr by PAGE_SIZE, since we could have a PTE page * table filled with PTE-mapped THPs, each of which is distinct. */ for (addr = vaddr_start; addr < vaddr_end; addr += PAGE_SIZE) { struct vm_area_struct *vma = vma_lookup(mm, addr); struct page *page; if (!vma) break; /* skip special VMA and hugetlb VMA */ if (vma_not_suitable_for_thp_split(vma)) { addr = vma->vm_end; continue; } /* FOLL_DUMP to ignore special (like zero) pages */ page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP); if (IS_ERR_OR_NULL(page)) continue; if (!is_transparent_hugepage(page)) goto next; total++; if (!can_split_folio(page_folio(page), NULL)) goto next; if (!trylock_page(page)) goto next; if (!split_huge_page(page)) split++; unlock_page(page); next: put_page(page); cond_resched(); } mmap_read_unlock(mm); mmput(mm); pr_debug("%lu of %lu THP split\n", split, total); out: return ret; } static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start, pgoff_t off_end) { struct filename *file; struct file *candidate; struct address_space *mapping; int ret = -EINVAL; pgoff_t index; int nr_pages = 1; unsigned long total = 0, split = 0; file = getname_kernel(file_path); if (IS_ERR(file)) return ret; candidate = file_open_name(file, O_RDONLY, 0); if (IS_ERR(candidate)) goto out; pr_debug("split file-backed THPs in file: %s, page offset: [0x%lx - 0x%lx]\n", file_path, off_start, off_end); mapping = candidate->f_mapping; for (index = off_start; index < off_end; index += nr_pages) { struct page *fpage = pagecache_get_page(mapping, index, FGP_ENTRY | FGP_HEAD, 0); nr_pages = 1; if (xa_is_value(fpage) || !fpage) continue; if (!is_transparent_hugepage(fpage)) goto next; total++; nr_pages = thp_nr_pages(fpage); if (!trylock_page(fpage)) goto next; if (!split_huge_page(fpage)) split++; unlock_page(fpage); next: put_page(fpage); cond_resched(); } filp_close(candidate, NULL); ret = 0; pr_debug("%lu of %lu file-backed THP split\n", split, total); out: putname(file); return ret; } #define MAX_INPUT_BUF_SZ 255 static ssize_t split_huge_pages_write(struct file *file, const char __user *buf, size_t count, loff_t *ppops) { static DEFINE_MUTEX(split_debug_mutex); ssize_t ret; /* hold pid, start_vaddr, end_vaddr or file_path, off_start, off_end */ char input_buf[MAX_INPUT_BUF_SZ]; int pid; unsigned long vaddr_start, vaddr_end; ret = mutex_lock_interruptible(&split_debug_mutex); if (ret) return ret; ret = -EFAULT; memset(input_buf, 0, MAX_INPUT_BUF_SZ); if (copy_from_user(input_buf, buf, min_t(size_t, count, MAX_INPUT_BUF_SZ))) goto out; input_buf[MAX_INPUT_BUF_SZ - 1] = '\0'; if (input_buf[0] == '/') { char *tok; char *buf = input_buf; char file_path[MAX_INPUT_BUF_SZ]; pgoff_t off_start = 0, off_end = 0; size_t input_len = strlen(input_buf); tok = strsep(&buf, ","); if (tok) { strcpy(file_path, tok); } else { ret = -EINVAL; goto out; } ret = sscanf(buf, "0x%lx,0x%lx", &off_start, &off_end); if (ret != 2) { ret = -EINVAL; goto out; } ret = split_huge_pages_in_file(file_path, off_start, off_end); if (!ret) ret = input_len; goto out; } ret = sscanf(input_buf, "%d,0x%lx,0x%lx", &pid, &vaddr_start, &vaddr_end); if (ret == 1 && pid == 1) { split_huge_pages_all(); ret = strlen(input_buf); goto out; } else if (ret != 3) { ret = -EINVAL; goto out; } ret = split_huge_pages_pid(pid, vaddr_start, vaddr_end); if (!ret) ret = strlen(input_buf); out: mutex_unlock(&split_debug_mutex); return ret; } static const struct file_operations split_huge_pages_fops = { .owner = THIS_MODULE, .write = split_huge_pages_write, .llseek = no_llseek, }; static int __init split_huge_pages_debugfs(void) { debugfs_create_file("split_huge_pages", 0200, NULL, NULL, &split_huge_pages_fops); return 0; } late_initcall(split_huge_pages_debugfs); #endif #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page) { struct vm_area_struct *vma = pvmw->vma; struct mm_struct *mm = vma->vm_mm; unsigned long address = pvmw->address; bool anon_exclusive; pmd_t pmdval; swp_entry_t entry; pmd_t pmdswp; if (!(pvmw->pmd && !pvmw->pte)) return 0; flush_cache_range(vma, address, address + HPAGE_PMD_SIZE); pmdval = pmdp_invalidate(vma, address, pvmw->pmd); /* See page_try_share_anon_rmap(): invalidate PMD first. */ anon_exclusive = PageAnon(page) && PageAnonExclusive(page); if (anon_exclusive && page_try_share_anon_rmap(page)) { set_pmd_at(mm, address, pvmw->pmd, pmdval); return -EBUSY; } if (pmd_dirty(pmdval)) set_page_dirty(page); if (pmd_write(pmdval)) entry = make_writable_migration_entry(page_to_pfn(page)); else if (anon_exclusive) entry = make_readable_exclusive_migration_entry(page_to_pfn(page)); else entry = make_readable_migration_entry(page_to_pfn(page)); if (pmd_young(pmdval)) entry = make_migration_entry_young(entry); if (pmd_dirty(pmdval)) entry = make_migration_entry_dirty(entry); pmdswp = swp_entry_to_pmd(entry); if (pmd_soft_dirty(pmdval)) pmdswp = pmd_swp_mksoft_dirty(pmdswp); if (pmd_uffd_wp(pmdval)) pmdswp = pmd_swp_mkuffd_wp(pmdswp); set_pmd_at(mm, address, pvmw->pmd, pmdswp); page_remove_rmap(page, vma, true); put_page(page); trace_set_migration_pmd(address, pmd_val(pmdswp)); return 0; } void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) { struct vm_area_struct *vma = pvmw->vma; struct mm_struct *mm = vma->vm_mm; unsigned long address = pvmw->address; unsigned long haddr = address & HPAGE_PMD_MASK; pmd_t pmde; swp_entry_t entry; if (!(pvmw->pmd && !pvmw->pte)) return; entry = pmd_to_swp_entry(*pvmw->pmd); get_page(new); pmde = mk_huge_pmd(new, READ_ONCE(vma->vm_page_prot)); if (pmd_swp_soft_dirty(*pvmw->pmd)) pmde = pmd_mksoft_dirty(pmde); if (pmd_swp_uffd_wp(*pvmw->pmd)) pmde = pmd_wrprotect(pmd_mkuffd_wp(pmde)); if (!is_migration_entry_young(entry)) pmde = pmd_mkold(pmde); /* NOTE: this may contain setting soft-dirty on some archs */ if (PageDirty(new) && is_migration_entry_dirty(entry)) pmde = pmd_mkdirty(pmde); if (is_writable_migration_entry(entry)) pmde = maybe_pmd_mkwrite(pmde, vma); else pmde = pmd_wrprotect(pmde); if (PageAnon(new)) { rmap_t rmap_flags = RMAP_COMPOUND; if (!is_readable_migration_entry(entry)) rmap_flags |= RMAP_EXCLUSIVE; page_add_anon_rmap(new, vma, haddr, rmap_flags); } else { page_add_file_rmap(new, vma, true); } VM_BUG_ON(pmd_write(pmde) && PageAnon(new) && !PageAnonExclusive(new)); set_pmd_at(mm, haddr, pvmw->pmd, pmde); /* No need to invalidate - it was non-present before */ update_mmu_cache_pmd(vma, address, pvmw->pmd); trace_remove_migration_pmd(address, pmd_val(pmde)); } #endif |
| 425 1097 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM signal #if !defined(_TRACE_SIGNAL_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SIGNAL_H #include <linux/signal.h> #include <linux/sched.h> #include <linux/tracepoint.h> #define TP_STORE_SIGINFO(__entry, info) \ do { \ if (info == SEND_SIG_NOINFO) { \ __entry->errno = 0; \ __entry->code = SI_USER; \ } else if (info == SEND_SIG_PRIV) { \ __entry->errno = 0; \ __entry->code = SI_KERNEL; \ } else { \ __entry->errno = info->si_errno; \ __entry->code = info->si_code; \ } \ } while (0) #ifndef TRACE_HEADER_MULTI_READ enum { TRACE_SIGNAL_DELIVERED, TRACE_SIGNAL_IGNORED, TRACE_SIGNAL_ALREADY_PENDING, TRACE_SIGNAL_OVERFLOW_FAIL, TRACE_SIGNAL_LOSE_INFO, }; #endif /** * signal_generate - called when a signal is generated * @sig: signal number * @info: pointer to struct siginfo * @task: pointer to struct task_struct * @group: shared or private * @result: TRACE_SIGNAL_* * * Current process sends a 'sig' signal to 'task' process with * 'info' siginfo. If 'info' is SEND_SIG_NOINFO or SEND_SIG_PRIV, * 'info' is not a pointer and you can't access its field. Instead, * SEND_SIG_NOINFO means that si_code is SI_USER, and SEND_SIG_PRIV * means that si_code is SI_KERNEL. */ TRACE_EVENT(signal_generate, TP_PROTO(int sig, struct kernel_siginfo *info, struct task_struct *task, int group, int result), TP_ARGS(sig, info, task, group, result), TP_STRUCT__entry( __field( int, sig ) __field( int, errno ) __field( int, code ) __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, group ) __field( int, result ) ), TP_fast_assign( __entry->sig = sig; TP_STORE_SIGINFO(__entry, info); memcpy(__entry->comm, task->comm, TASK_COMM_LEN); __entry->pid = task->pid; __entry->group = group; __entry->result = result; ), TP_printk("sig=%d errno=%d code=%d comm=%s pid=%d grp=%d res=%d", __entry->sig, __entry->errno, __entry->code, __entry->comm, __entry->pid, __entry->group, __entry->result) ); /** * signal_deliver - called when a signal is delivered * @sig: signal number * @info: pointer to struct siginfo * @ka: pointer to struct k_sigaction * * A 'sig' signal is delivered to current process with 'info' siginfo, * and it will be handled by 'ka'. ka->sa.sa_handler can be SIG_IGN or * SIG_DFL. * Note that some signals reported by signal_generate tracepoint can be * lost, ignored or modified (by debugger) before hitting this tracepoint. * This means, this can show which signals are actually delivered, but * matching generated signals and delivered signals may not be correct. */ TRACE_EVENT(signal_deliver, TP_PROTO(int sig, struct kernel_siginfo *info, struct k_sigaction *ka), TP_ARGS(sig, info, ka), TP_STRUCT__entry( __field( int, sig ) __field( int, errno ) __field( int, code ) __field( unsigned long, sa_handler ) __field( unsigned long, sa_flags ) ), TP_fast_assign( __entry->sig = sig; TP_STORE_SIGINFO(__entry, info); __entry->sa_handler = (unsigned long)ka->sa.sa_handler; __entry->sa_flags = ka->sa.sa_flags; ), TP_printk("sig=%d errno=%d code=%d sa_handler=%lx sa_flags=%lx", __entry->sig, __entry->errno, __entry->code, __entry->sa_handler, __entry->sa_flags) ); #endif /* _TRACE_SIGNAL_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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Stream Parser * * Copyright (c) 2016 Tom Herbert <tom@herbertland.com> */ #ifndef __NET_STRPARSER_H_ #define __NET_STRPARSER_H_ #include <linux/skbuff.h> #include <net/sock.h> #define STRP_STATS_ADD(stat, count) ((stat) += (count)) #define STRP_STATS_INCR(stat) ((stat)++) struct strp_stats { unsigned long long msgs; unsigned long long bytes; unsigned int mem_fail; unsigned int need_more_hdr; unsigned int msg_too_big; unsigned int msg_timeouts; unsigned int bad_hdr_len; }; struct strp_aggr_stats { unsigned long long msgs; unsigned long long bytes; unsigned int mem_fail; unsigned int need_more_hdr; unsigned int msg_too_big; unsigned int msg_timeouts; unsigned int bad_hdr_len; unsigned int aborts; unsigned int interrupted; unsigned int unrecov_intr; }; struct strparser; /* Callbacks are called with lock held for the attached socket */ struct strp_callbacks { int (*parse_msg)(struct strparser *strp, struct sk_buff *skb); void (*rcv_msg)(struct strparser *strp, struct sk_buff *skb); int (*read_sock)(struct strparser *strp, read_descriptor_t *desc, sk_read_actor_t recv_actor); int (*read_sock_done)(struct strparser *strp, int err); void (*abort_parser)(struct strparser *strp, int err); void (*lock)(struct strparser *strp); void (*unlock)(struct strparser *strp); }; struct strp_msg { int full_len; int offset; }; struct _strp_msg { /* Internal cb structure. struct strp_msg must be first for passing * to upper layer. */ struct strp_msg strp; int accum_len; }; struct sk_skb_cb { #define SK_SKB_CB_PRIV_LEN 20 unsigned char data[SK_SKB_CB_PRIV_LEN]; /* align strp on cache line boundary within skb->cb[] */ unsigned char pad[4]; struct _strp_msg strp; /* strp users' data follows */ struct tls_msg { u8 control; } tls; /* temp_reg is a temporary register used for bpf_convert_data_end_access * when dst_reg == src_reg. */ u64 temp_reg; }; static inline struct strp_msg *strp_msg(struct sk_buff *skb) { return (struct strp_msg *)((void *)skb->cb + offsetof(struct sk_skb_cb, strp)); } /* Structure for an attached lower socket */ struct strparser { struct sock *sk; u32 stopped : 1; u32 paused : 1; u32 aborted : 1; u32 interrupted : 1; u32 unrecov_intr : 1; struct sk_buff **skb_nextp; struct sk_buff *skb_head; unsigned int need_bytes; struct delayed_work msg_timer_work; struct work_struct work; struct strp_stats stats; struct strp_callbacks cb; }; /* Must be called with lock held for attached socket */ static inline void strp_pause(struct strparser *strp) { strp->paused = 1; } /* May be called without holding lock for attached socket */ void strp_unpause(struct strparser *strp); /* Must be called with process lock held (lock_sock) */ void __strp_unpause(struct strparser *strp); static inline void save_strp_stats(struct strparser *strp, struct strp_aggr_stats *agg_stats) { /* Save psock statistics in the mux when psock is being unattached. */ #define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat += \ strp->stats._stat) SAVE_PSOCK_STATS(msgs); SAVE_PSOCK_STATS(bytes); SAVE_PSOCK_STATS(mem_fail); SAVE_PSOCK_STATS(need_more_hdr); SAVE_PSOCK_STATS(msg_too_big); SAVE_PSOCK_STATS(msg_timeouts); SAVE_PSOCK_STATS(bad_hdr_len); #undef SAVE_PSOCK_STATS if (strp->aborted) agg_stats->aborts++; if (strp->interrupted) agg_stats->interrupted++; if (strp->unrecov_intr) agg_stats->unrecov_intr++; } static inline void aggregate_strp_stats(struct strp_aggr_stats *stats, struct strp_aggr_stats *agg_stats) { #define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat += stats->_stat) SAVE_PSOCK_STATS(msgs); SAVE_PSOCK_STATS(bytes); SAVE_PSOCK_STATS(mem_fail); SAVE_PSOCK_STATS(need_more_hdr); SAVE_PSOCK_STATS(msg_too_big); SAVE_PSOCK_STATS(msg_timeouts); SAVE_PSOCK_STATS(bad_hdr_len); SAVE_PSOCK_STATS(aborts); SAVE_PSOCK_STATS(interrupted); SAVE_PSOCK_STATS(unrecov_intr); #undef SAVE_PSOCK_STATS } void strp_done(struct strparser *strp); void strp_stop(struct strparser *strp); void strp_check_rcv(struct strparser *strp); int strp_init(struct strparser *strp, struct sock *sk, const struct strp_callbacks *cb); void strp_data_ready(struct strparser *strp); int strp_process(struct strparser *strp, struct sk_buff *orig_skb, unsigned int orig_offset, size_t orig_len, size_t max_msg_size, long timeo); #endif /* __NET_STRPARSER_H_ */ |
| 1 1 1 367 366 367 367 367 367 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 | // SPDX-License-Identifier: GPL-2.0-or-later /* * kernel/stop_machine.c * * Copyright (C) 2008, 2005 IBM Corporation. * Copyright (C) 2008, 2005 Rusty Russell rusty@rustcorp.com.au * Copyright (C) 2010 SUSE Linux Products GmbH * Copyright (C) 2010 Tejun Heo <tj@kernel.org> */ #include <linux/compiler.h> #include <linux/completion.h> #include <linux/cpu.h> #include <linux/init.h> #include <linux/kthread.h> #include <linux/export.h> #include <linux/percpu.h> #include <linux/sched.h> #include <linux/stop_machine.h> #include <linux/interrupt.h> #include <linux/kallsyms.h> #include <linux/smpboot.h> #include <linux/atomic.h> #include <linux/nmi.h> #include <linux/sched/wake_q.h> /* * Structure to determine completion condition and record errors. May * be shared by works on different cpus. */ struct cpu_stop_done { atomic_t nr_todo; /* nr left to execute */ int ret; /* collected return value */ struct completion completion; /* fired if nr_todo reaches 0 */ }; /* the actual stopper, one per every possible cpu, enabled on online cpus */ struct cpu_stopper { struct task_struct *thread; raw_spinlock_t lock; bool enabled; /* is this stopper enabled? */ struct list_head works; /* list of pending works */ struct cpu_stop_work stop_work; /* for stop_cpus */ unsigned long caller; cpu_stop_fn_t fn; }; static DEFINE_PER_CPU(struct cpu_stopper, cpu_stopper); static bool stop_machine_initialized = false; void print_stop_info(const char *log_lvl, struct task_struct *task) { /* * If @task is a stopper task, it cannot migrate and task_cpu() is * stable. */ struct cpu_stopper *stopper = per_cpu_ptr(&cpu_stopper, task_cpu(task)); if (task != stopper->thread) return; printk("%sStopper: %pS <- %pS\n", log_lvl, stopper->fn, (void *)stopper->caller); } /* static data for stop_cpus */ static DEFINE_MUTEX(stop_cpus_mutex); static bool stop_cpus_in_progress; static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo) { memset(done, 0, sizeof(*done)); atomic_set(&done->nr_todo, nr_todo); init_completion(&done->completion); } /* signal completion unless @done is NULL */ static void cpu_stop_signal_done(struct cpu_stop_done *done) { if (atomic_dec_and_test(&done->nr_todo)) complete(&done->completion); } static void __cpu_stop_queue_work(struct cpu_stopper *stopper, struct cpu_stop_work *work, struct wake_q_head *wakeq) { list_add_tail(&work->list, &stopper->works); wake_q_add(wakeq, stopper->thread); } /* queue @work to @stopper. if offline, @work is completed immediately */ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); DEFINE_WAKE_Q(wakeq); unsigned long flags; bool enabled; preempt_disable(); raw_spin_lock_irqsave(&stopper->lock, flags); enabled = stopper->enabled; if (enabled) __cpu_stop_queue_work(stopper, work, &wakeq); else if (work->done) cpu_stop_signal_done(work->done); raw_spin_unlock_irqrestore(&stopper->lock, flags); wake_up_q(&wakeq); preempt_enable(); return enabled; } /** * stop_one_cpu - stop a cpu * @cpu: cpu to stop * @fn: function to execute * @arg: argument to @fn * * Execute @fn(@arg) on @cpu. @fn is run in a process context with * the highest priority preempting any task on the cpu and * monopolizing it. This function returns after the execution is * complete. * * This function doesn't guarantee @cpu stays online till @fn * completes. If @cpu goes down in the middle, execution may happen * partially or fully on different cpus. @fn should either be ready * for that or the caller should ensure that @cpu stays online until * this function completes. * * CONTEXT: * Might sleep. * * RETURNS: * -ENOENT if @fn(@arg) was not executed because @cpu was offline; * otherwise, the return value of @fn. */ int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg) { struct cpu_stop_done done; struct cpu_stop_work work = { .fn = fn, .arg = arg, .done = &done, .caller = _RET_IP_ }; cpu_stop_init_done(&done, 1); if (!cpu_stop_queue_work(cpu, &work)) return -ENOENT; /* * In case @cpu == smp_proccessor_id() we can avoid a sleep+wakeup * cycle by doing a preemption: */ cond_resched(); wait_for_completion(&done.completion); return done.ret; } EXPORT_SYMBOL_GPL(stop_one_cpu); /* This controls the threads on each CPU. */ enum multi_stop_state { /* Dummy starting state for thread. */ MULTI_STOP_NONE, /* Awaiting everyone to be scheduled. */ MULTI_STOP_PREPARE, /* Disable interrupts. */ MULTI_STOP_DISABLE_IRQ, /* Run the function */ MULTI_STOP_RUN, /* Exit */ MULTI_STOP_EXIT, }; struct multi_stop_data { cpu_stop_fn_t fn; void *data; /* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */ unsigned int num_threads; const struct cpumask *active_cpus; enum multi_stop_state state; atomic_t thread_ack; }; static void set_state(struct multi_stop_data *msdata, enum multi_stop_state newstate) { /* Reset ack counter. */ atomic_set(&msdata->thread_ack, msdata->num_threads); smp_wmb(); WRITE_ONCE(msdata->state, newstate); } /* Last one to ack a state moves to the next state. */ static void ack_state(struct multi_stop_data *msdata) { if (atomic_dec_and_test(&msdata->thread_ack)) set_state(msdata, msdata->state + 1); } notrace void __weak stop_machine_yield(const struct cpumask *cpumask) { cpu_relax(); } /* This is the cpu_stop function which stops the CPU. */ static int multi_cpu_stop(void *data) { struct multi_stop_data *msdata = data; enum multi_stop_state newstate, curstate = MULTI_STOP_NONE; int cpu = smp_processor_id(), err = 0; const struct cpumask *cpumask; unsigned long flags; bool is_active; /* * When called from stop_machine_from_inactive_cpu(), irq might * already be disabled. Save the state and restore it on exit. */ local_save_flags(flags); if (!msdata->active_cpus) { cpumask = cpu_online_mask; is_active = cpu == cpumask_first(cpumask); } else { cpumask = msdata->active_cpus; is_active = cpumask_test_cpu(cpu, cpumask); } /* Simple state machine */ do { /* Chill out and ensure we re-read multi_stop_state. */ stop_machine_yield(cpumask); newstate = READ_ONCE(msdata->state); if (newstate != curstate) { curstate = newstate; switch (curstate) { case MULTI_STOP_DISABLE_IRQ: local_irq_disable(); hard_irq_disable(); break; case MULTI_STOP_RUN: if (is_active) err = msdata->fn(msdata->data); break; default: break; } ack_state(msdata); } else if (curstate > MULTI_STOP_PREPARE) { /* * At this stage all other CPUs we depend on must spin * in the same loop. Any reason for hard-lockup should * be detected and reported on their side. */ touch_nmi_watchdog(); } rcu_momentary_dyntick_idle(); } while (curstate != MULTI_STOP_EXIT); local_irq_restore(flags); return err; } static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1, int cpu2, struct cpu_stop_work *work2) { struct cpu_stopper *stopper1 = per_cpu_ptr(&cpu_stopper, cpu1); struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2); DEFINE_WAKE_Q(wakeq); int err; retry: /* * The waking up of stopper threads has to happen in the same * scheduling context as the queueing. Otherwise, there is a * possibility of one of the above stoppers being woken up by another * CPU, and preempting us. This will cause us to not wake up the other * stopper forever. */ preempt_disable(); raw_spin_lock_irq(&stopper1->lock); raw_spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING); if (!stopper1->enabled || !stopper2->enabled) { err = -ENOENT; goto unlock; } /* * Ensure that if we race with __stop_cpus() the stoppers won't get * queued up in reverse order leading to system deadlock. * * We can't miss stop_cpus_in_progress if queue_stop_cpus_work() has * queued a work on cpu1 but not on cpu2, we hold both locks. * * It can be falsely true but it is safe to spin until it is cleared, * queue_stop_cpus_work() does everything under preempt_disable(). */ if (unlikely(stop_cpus_in_progress)) { err = -EDEADLK; goto unlock; } err = 0; __cpu_stop_queue_work(stopper1, work1, &wakeq); __cpu_stop_queue_work(stopper2, work2, &wakeq); unlock: raw_spin_unlock(&stopper2->lock); raw_spin_unlock_irq(&stopper1->lock); if (unlikely(err == -EDEADLK)) { preempt_enable(); while (stop_cpus_in_progress) cpu_relax(); goto retry; } wake_up_q(&wakeq); preempt_enable(); return err; } /** * stop_two_cpus - stops two cpus * @cpu1: the cpu to stop * @cpu2: the other cpu to stop * @fn: function to execute * @arg: argument to @fn * * Stops both the current and specified CPU and runs @fn on one of them. * * returns when both are completed. */ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *arg) { struct cpu_stop_done done; struct cpu_stop_work work1, work2; struct multi_stop_data msdata; msdata = (struct multi_stop_data){ .fn = fn, .data = arg, .num_threads = 2, .active_cpus = cpumask_of(cpu1), }; work1 = work2 = (struct cpu_stop_work){ .fn = multi_cpu_stop, .arg = &msdata, .done = &done, .caller = _RET_IP_, }; cpu_stop_init_done(&done, 2); set_state(&msdata, MULTI_STOP_PREPARE); if (cpu1 > cpu2) swap(cpu1, cpu2); if (cpu_stop_queue_two_works(cpu1, &work1, cpu2, &work2)) return -ENOENT; wait_for_completion(&done.completion); return done.ret; } /** * stop_one_cpu_nowait - stop a cpu but don't wait for completion * @cpu: cpu to stop * @fn: function to execute * @arg: argument to @fn * @work_buf: pointer to cpu_stop_work structure * * Similar to stop_one_cpu() but doesn't wait for completion. The * caller is responsible for ensuring @work_buf is currently unused * and will remain untouched until stopper starts executing @fn. * * CONTEXT: * Don't care. * * RETURNS: * true if cpu_stop_work was queued successfully and @fn will be called, * false otherwise. */ bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, struct cpu_stop_work *work_buf) { *work_buf = (struct cpu_stop_work){ .fn = fn, .arg = arg, .caller = _RET_IP_, }; return cpu_stop_queue_work(cpu, work_buf); } EXPORT_SYMBOL_GPL(stop_one_cpu_nowait); static bool queue_stop_cpus_work(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg, struct cpu_stop_done *done) { struct cpu_stop_work *work; unsigned int cpu; bool queued = false; /* * Disable preemption while queueing to avoid getting * preempted by a stopper which might wait for other stoppers * to enter @fn which can lead to deadlock. */ preempt_disable(); stop_cpus_in_progress = true; barrier(); for_each_cpu(cpu, cpumask) { work = &per_cpu(cpu_stopper.stop_work, cpu); work->fn = fn; work->arg = arg; work->done = done; work->caller = _RET_IP_; if (cpu_stop_queue_work(cpu, work)) queued = true; } barrier(); stop_cpus_in_progress = false; preempt_enable(); return queued; } static int __stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg) { struct cpu_stop_done done; cpu_stop_init_done(&done, cpumask_weight(cpumask)); if (!queue_stop_cpus_work(cpumask, fn, arg, &done)) return -ENOENT; wait_for_completion(&done.completion); return done.ret; } /** * stop_cpus - stop multiple cpus * @cpumask: cpus to stop * @fn: function to execute * @arg: argument to @fn * * Execute @fn(@arg) on online cpus in @cpumask. On each target cpu, * @fn is run in a process context with the highest priority * preempting any task on the cpu and monopolizing it. This function * returns after all executions are complete. * * This function doesn't guarantee the cpus in @cpumask stay online * till @fn completes. If some cpus go down in the middle, execution * on the cpu may happen partially or fully on different cpus. @fn * should either be ready for that or the caller should ensure that * the cpus stay online until this function completes. * * All stop_cpus() calls are serialized making it safe for @fn to wait * for all cpus to start executing it. * * CONTEXT: * Might sleep. * * RETURNS: * -ENOENT if @fn(@arg) was not executed at all because all cpus in * @cpumask were offline; otherwise, 0 if all executions of @fn * returned 0, any non zero return value if any returned non zero. */ static int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg) { int ret; /* static works are used, process one request at a time */ mutex_lock(&stop_cpus_mutex); ret = __stop_cpus(cpumask, fn, arg); mutex_unlock(&stop_cpus_mutex); return ret; } static int cpu_stop_should_run(unsigned int cpu) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); unsigned long flags; int run; raw_spin_lock_irqsave(&stopper->lock, flags); run = !list_empty(&stopper->works); raw_spin_unlock_irqrestore(&stopper->lock, flags); return run; } static void cpu_stopper_thread(unsigned int cpu) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); struct cpu_stop_work *work; repeat: work = NULL; raw_spin_lock_irq(&stopper->lock); if (!list_empty(&stopper->works)) { work = list_first_entry(&stopper->works, struct cpu_stop_work, list); list_del_init(&work->list); } raw_spin_unlock_irq(&stopper->lock); if (work) { cpu_stop_fn_t fn = work->fn; void *arg = work->arg; struct cpu_stop_done *done = work->done; int ret; /* cpu stop callbacks must not sleep, make in_atomic() == T */ stopper->caller = work->caller; stopper->fn = fn; preempt_count_inc(); ret = fn(arg); if (done) { if (ret) done->ret = ret; cpu_stop_signal_done(done); } preempt_count_dec(); stopper->fn = NULL; stopper->caller = 0; WARN_ONCE(preempt_count(), "cpu_stop: %ps(%p) leaked preempt count\n", fn, arg); goto repeat; } } void stop_machine_park(int cpu) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); /* * Lockless. cpu_stopper_thread() will take stopper->lock and flush * the pending works before it parks, until then it is fine to queue * the new works. */ stopper->enabled = false; kthread_park(stopper->thread); } static void cpu_stop_create(unsigned int cpu) { sched_set_stop_task(cpu, per_cpu(cpu_stopper.thread, cpu)); } static void cpu_stop_park(unsigned int cpu) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); WARN_ON(!list_empty(&stopper->works)); } void stop_machine_unpark(int cpu) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); stopper->enabled = true; kthread_unpark(stopper->thread); } static struct smp_hotplug_thread cpu_stop_threads = { .store = &cpu_stopper.thread, .thread_should_run = cpu_stop_should_run, .thread_fn = cpu_stopper_thread, .thread_comm = "migration/%u", .create = cpu_stop_create, .park = cpu_stop_park, .selfparking = true, }; static int __init cpu_stop_init(void) { unsigned int cpu; for_each_possible_cpu(cpu) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); raw_spin_lock_init(&stopper->lock); INIT_LIST_HEAD(&stopper->works); } BUG_ON(smpboot_register_percpu_thread(&cpu_stop_threads)); stop_machine_unpark(raw_smp_processor_id()); stop_machine_initialized = true; return 0; } early_initcall(cpu_stop_init); int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) { struct multi_stop_data msdata = { .fn = fn, .data = data, .num_threads = num_online_cpus(), .active_cpus = cpus, }; lockdep_assert_cpus_held(); if (!stop_machine_initialized) { /* * Handle the case where stop_machine() is called * early in boot before stop_machine() has been * initialized. */ unsigned long flags; int ret; WARN_ON_ONCE(msdata.num_threads != 1); local_irq_save(flags); hard_irq_disable(); ret = (*fn)(data); local_irq_restore(flags); return ret; } /* Set the initial state and stop all online cpus. */ set_state(&msdata, MULTI_STOP_PREPARE); return stop_cpus(cpu_online_mask, multi_cpu_stop, &msdata); } int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) { int ret; /* No CPUs can come up or down during this. */ cpus_read_lock(); ret = stop_machine_cpuslocked(fn, data, cpus); cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(stop_machine); #ifdef CONFIG_SCHED_SMT int stop_core_cpuslocked(unsigned int cpu, cpu_stop_fn_t fn, void *data) { const struct cpumask *smt_mask = cpu_smt_mask(cpu); struct multi_stop_data msdata = { .fn = fn, .data = data, .num_threads = cpumask_weight(smt_mask), .active_cpus = smt_mask, }; lockdep_assert_cpus_held(); /* Set the initial state and stop all online cpus. */ set_state(&msdata, MULTI_STOP_PREPARE); return stop_cpus(smt_mask, multi_cpu_stop, &msdata); } EXPORT_SYMBOL_GPL(stop_core_cpuslocked); #endif /** * stop_machine_from_inactive_cpu - stop_machine() from inactive CPU * @fn: the function to run * @data: the data ptr for the @fn() * @cpus: the cpus to run the @fn() on (NULL = any online cpu) * * This is identical to stop_machine() but can be called from a CPU which * is not active. The local CPU is in the process of hotplug (so no other * CPU hotplug can start) and not marked active and doesn't have enough * context to sleep. * * This function provides stop_machine() functionality for such state by * using busy-wait for synchronization and executing @fn directly for local * CPU. * * CONTEXT: * Local CPU is inactive. Temporarily stops all active CPUs. * * RETURNS: * 0 if all executions of @fn returned 0, any non zero return value if any * returned non zero. */ int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) { struct multi_stop_data msdata = { .fn = fn, .data = data, .active_cpus = cpus }; struct cpu_stop_done done; int ret; /* Local CPU must be inactive and CPU hotplug in progress. */ BUG_ON(cpu_active(raw_smp_processor_id())); msdata.num_threads = num_active_cpus() + 1; /* +1 for local */ /* No proper task established and can't sleep - busy wait for lock. */ while (!mutex_trylock(&stop_cpus_mutex)) cpu_relax(); /* Schedule work on other CPUs and execute directly for local CPU */ set_state(&msdata, MULTI_STOP_PREPARE); cpu_stop_init_done(&done, num_active_cpus()); queue_stop_cpus_work(cpu_active_mask, multi_cpu_stop, &msdata, &done); ret = multi_cpu_stop(&msdata); /* Busy wait for completion. */ while (!completion_done(&done.completion)) cpu_relax(); mutex_unlock(&stop_cpus_mutex); return ret ?: done.ret; } |
| 6 6 218 6 417 2 6 324 119 36 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 | /* 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*/ |
| 43 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_WAIT_BIT_H #define _LINUX_WAIT_BIT_H /* * Linux wait-bit related types and methods: */ #include <linux/wait.h> struct wait_bit_key { void *flags; int bit_nr; unsigned long timeout; }; struct wait_bit_queue_entry { struct wait_bit_key key; struct wait_queue_entry wq_entry; }; #define __WAIT_BIT_KEY_INITIALIZER(word, bit) \ { .flags = word, .bit_nr = bit, } typedef int wait_bit_action_f(struct wait_bit_key *key, int mode); void __wake_up_bit(struct wait_queue_head *wq_head, void *word, int bit); int __wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode); int __wait_on_bit_lock(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry, wait_bit_action_f *action, unsigned int mode); void wake_up_bit(void *word, int bit); int out_of_line_wait_on_bit(void *word, int, wait_bit_action_f *action, unsigned int mode); int out_of_line_wait_on_bit_timeout(void *word, int, wait_bit_action_f *action, unsigned int mode, unsigned long timeout); int out_of_line_wait_on_bit_lock(void *word, int, wait_bit_action_f *action, unsigned int mode); struct wait_queue_head *bit_waitqueue(void *word, int bit); extern void __init wait_bit_init(void); int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key); #define DEFINE_WAIT_BIT(name, word, bit) \ struct wait_bit_queue_entry name = { \ .key = __WAIT_BIT_KEY_INITIALIZER(word, bit), \ .wq_entry = { \ .private = current, \ .func = wake_bit_function, \ .entry = \ LIST_HEAD_INIT((name).wq_entry.entry), \ }, \ } extern int bit_wait(struct wait_bit_key *key, int mode); extern int bit_wait_io(struct wait_bit_key *key, int mode); extern int bit_wait_timeout(struct wait_bit_key *key, int mode); extern int bit_wait_io_timeout(struct wait_bit_key *key, int mode); /** * wait_on_bit - wait for a bit to be cleared * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * * There is a standard hashed waitqueue table for generic use. This * is the part of the hashtable's accessor API that waits on a bit. * For instance, if one were to have waiters on a bitflag, one would * call wait_on_bit() in threads waiting for the bit to clear. * One uses wait_on_bit() where one is waiting for the bit to clear, * but has no intention of setting it. * Returned value will be zero if the bit was cleared, or non-zero * if the process received a signal and the mode permitted wakeup * on that signal. */ static inline int wait_on_bit(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, bit_wait, mode); } /** * wait_on_bit_io - wait for a bit to be cleared * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * * Use the standard hashed waitqueue table to wait for a bit * to be cleared. This is similar to wait_on_bit(), but calls * io_schedule() instead of schedule() for the actual waiting. * * Returned value will be zero if the bit was cleared, or non-zero * if the process received a signal and the mode permitted wakeup * on that signal. */ static inline int wait_on_bit_io(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, bit_wait_io, mode); } /** * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * @timeout: timeout, in jiffies * * Use the standard hashed waitqueue table to wait for a bit * to be cleared. This is similar to wait_on_bit(), except also takes a * timeout parameter. * * Returned value will be zero if the bit was cleared before the * @timeout elapsed, or non-zero if the @timeout elapsed or process * received a signal and the mode permitted wakeup on that signal. */ static inline int wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode, unsigned long timeout) { might_sleep(); if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit_timeout(word, bit, bit_wait_timeout, mode, timeout); } /** * wait_on_bit_action - wait for a bit to be cleared * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @action: the function used to sleep, which may take special actions * @mode: the task state to sleep in * * Use the standard hashed waitqueue table to wait for a bit * to be cleared, and allow the waiting action to be specified. * This is like wait_on_bit() but allows fine control of how the waiting * is done. * * Returned value will be zero if the bit was cleared, or non-zero * if the process received a signal and the mode permitted wakeup * on that signal. */ static inline int wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action, unsigned mode) { might_sleep(); if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, action, mode); } /** * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * * There is a standard hashed waitqueue table for generic use. This * is the part of the hashtable's accessor API that waits on a bit * when one intends to set it, for instance, trying to lock bitflags. * For instance, if one were to have waiters trying to set bitflag * and waiting for it to clear before setting it, one would call * wait_on_bit() in threads waiting to be able to set the bit. * One uses wait_on_bit_lock() where one is waiting for the bit to * clear with the intention of setting it, and when done, clearing it. * * Returns zero if the bit was (eventually) found to be clear and was * set. Returns non-zero if a signal was delivered to the process and * the @mode allows that signal to wake the process. */ static inline int wait_on_bit_lock(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_and_set_bit(bit, word)) return 0; return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode); } /** * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @mode: the task state to sleep in * * Use the standard hashed waitqueue table to wait for a bit * to be cleared and then to atomically set it. This is similar * to wait_on_bit(), but calls io_schedule() instead of schedule() * for the actual waiting. * * Returns zero if the bit was (eventually) found to be clear and was * set. Returns non-zero if a signal was delivered to the process and * the @mode allows that signal to wake the process. */ static inline int wait_on_bit_lock_io(unsigned long *word, int bit, unsigned mode) { might_sleep(); if (!test_and_set_bit(bit, word)) return 0; return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode); } /** * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it * @word: the word being waited on, a kernel virtual address * @bit: the bit of the word being waited on * @action: the function used to sleep, which may take special actions * @mode: the task state to sleep in * * Use the standard hashed waitqueue table to wait for a bit * to be cleared and then to set it, and allow the waiting action * to be specified. * This is like wait_on_bit() but allows fine control of how the waiting * is done. * * Returns zero if the bit was (eventually) found to be clear and was * set. Returns non-zero if a signal was delivered to the process and * the @mode allows that signal to wake the process. */ static inline int wait_on_bit_lock_action(unsigned long *word, int bit, wait_bit_action_f *action, unsigned mode) { might_sleep(); if (!test_and_set_bit(bit, word)) return 0; return out_of_line_wait_on_bit_lock(word, bit, action, mode); } extern void init_wait_var_entry(struct wait_bit_queue_entry *wbq_entry, void *var, int flags); extern void wake_up_var(void *var); extern wait_queue_head_t *__var_waitqueue(void *p); #define ___wait_var_event(var, condition, state, exclusive, ret, cmd) \ ({ \ __label__ __out; \ struct wait_queue_head *__wq_head = __var_waitqueue(var); \ struct wait_bit_queue_entry __wbq_entry; \ long __ret = ret; /* explicit shadow */ \ \ init_wait_var_entry(&__wbq_entry, var, \ exclusive ? WQ_FLAG_EXCLUSIVE : 0); \ for (;;) { \ long __int = prepare_to_wait_event(__wq_head, \ &__wbq_entry.wq_entry, \ state); \ if (condition) \ break; \ \ if (___wait_is_interruptible(state) && __int) { \ __ret = __int; \ goto __out; \ } \ \ cmd; \ } \ finish_wait(__wq_head, &__wbq_entry.wq_entry); \ __out: __ret; \ }) #define __wait_var_event(var, condition) \ ___wait_var_event(var, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ schedule()) #define wait_var_event(var, condition) \ do { \ might_sleep(); \ if (condition) \ break; \ __wait_var_event(var, condition); \ } while (0) #define __wait_var_event_killable(var, condition) \ ___wait_var_event(var, condition, TASK_KILLABLE, 0, 0, \ schedule()) #define wait_var_event_killable(var, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_var_event_killable(var, condition); \ __ret; \ }) #define __wait_var_event_timeout(var, condition, timeout) \ ___wait_var_event(var, ___wait_cond_timeout(condition), \ TASK_UNINTERRUPTIBLE, 0, timeout, \ __ret = schedule_timeout(__ret)) #define wait_var_event_timeout(var, condition, timeout) \ ({ \ long __ret = timeout; \ might_sleep(); \ if (!___wait_cond_timeout(condition)) \ __ret = __wait_var_event_timeout(var, condition, timeout); \ __ret; \ }) #define __wait_var_event_interruptible(var, condition) \ ___wait_var_event(var, condition, TASK_INTERRUPTIBLE, 0, 0, \ schedule()) #define wait_var_event_interruptible(var, condition) \ ({ \ int __ret = 0; \ might_sleep(); \ if (!(condition)) \ __ret = __wait_var_event_interruptible(var, condition); \ __ret; \ }) /** * clear_and_wake_up_bit - clear a bit and wake up anyone waiting on that bit * * @bit: the bit of the word being waited on * @word: the word being waited on, a kernel virtual address * * You can use this helper if bitflags are manipulated atomically rather than * non-atomically under a lock. */ static inline void clear_and_wake_up_bit(int bit, void *word) { clear_bit_unlock(bit, word); /* See wake_up_bit() for which memory barrier you need to use. */ smp_mb__after_atomic(); wake_up_bit(word, bit); } #endif /* _LINUX_WAIT_BIT_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 | /* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* * linux/can/skb.h * * Definitions for the CAN network socket buffer * * Copyright (C) 2012 Oliver Hartkopp <socketcan@hartkopp.net> * */ #ifndef _CAN_SKB_H #define _CAN_SKB_H #include <linux/types.h> #include <linux/skbuff.h> #include <linux/can.h> #include <net/sock.h> void can_flush_echo_skb(struct net_device *dev); int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, unsigned int idx, unsigned int frame_len); struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, unsigned int *len_ptr, unsigned int *frame_len_ptr); unsigned int __must_check can_get_echo_skb(struct net_device *dev, unsigned int idx, unsigned int *frame_len_ptr); void can_free_echo_skb(struct net_device *dev, unsigned int idx, unsigned int *frame_len_ptr); struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf); struct sk_buff *alloc_canfd_skb(struct net_device *dev, struct canfd_frame **cfd); struct sk_buff *alloc_canxl_skb(struct net_device *dev, struct canxl_frame **cxl, unsigned int data_len); struct sk_buff *alloc_can_err_skb(struct net_device *dev, struct can_frame **cf); bool can_dropped_invalid_skb(struct net_device *dev, struct sk_buff *skb); /* * The struct can_skb_priv is used to transport additional information along * with the stored struct can(fd)_frame that can not be contained in existing * struct sk_buff elements. * N.B. that this information must not be modified in cloned CAN sk_buffs. * To modify the CAN frame content or the struct can_skb_priv content * skb_copy() needs to be used instead of skb_clone(). */ /** * struct can_skb_priv - private additional data inside CAN sk_buffs * @ifindex: ifindex of the first interface the CAN frame appeared on * @skbcnt: atomic counter to have an unique id together with skb pointer * @frame_len: length of CAN frame in data link layer * @cf: align to the following CAN frame at skb->data */ struct can_skb_priv { int ifindex; int skbcnt; unsigned int frame_len; struct can_frame cf[]; }; static inline struct can_skb_priv *can_skb_prv(struct sk_buff *skb) { return (struct can_skb_priv *)(skb->head); } static inline void can_skb_reserve(struct sk_buff *skb) { skb_reserve(skb, sizeof(struct can_skb_priv)); } static inline void can_skb_set_owner(struct sk_buff *skb, struct sock *sk) { /* If the socket has already been closed by user space, the * refcount may already be 0 (and the socket will be freed * after the last TX skb has been freed). So only increase * socket refcount if the refcount is > 0. */ if (sk && refcount_inc_not_zero(&sk->sk_refcnt)) { skb->destructor = sock_efree; skb->sk = sk; } } /* * returns an unshared skb owned by the original sock to be echo'ed back */ static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb) { struct sk_buff *nskb; nskb = skb_clone(skb, GFP_ATOMIC); if (unlikely(!nskb)) { kfree_skb(skb); return NULL; } can_skb_set_owner(nskb, skb->sk); consume_skb(skb); return nskb; } static inline bool can_is_can_skb(const struct sk_buff *skb) { struct can_frame *cf = (struct can_frame *)skb->data; /* the CAN specific type of skb is identified by its data length */ return (skb->len == CAN_MTU && cf->len <= CAN_MAX_DLEN); } static inline bool can_is_canfd_skb(const struct sk_buff *skb) { struct canfd_frame *cfd = (struct canfd_frame *)skb->data; /* the CAN specific type of skb is identified by its data length */ return (skb->len == CANFD_MTU && cfd->len <= CANFD_MAX_DLEN); } static inline bool can_is_canxl_skb(const struct sk_buff *skb) { const struct canxl_frame *cxl = (struct canxl_frame *)skb->data; if (skb->len < CANXL_HDR_SIZE + CANXL_MIN_DLEN || skb->len > CANXL_MTU) return false; /* this also checks valid CAN XL data length boundaries */ if (skb->len != CANXL_HDR_SIZE + cxl->len) return false; return cxl->flags & CANXL_XLF; } /* get length element value from can[|fd|xl]_frame structure */ static inline unsigned int can_skb_get_len_val(struct sk_buff *skb) { const struct canxl_frame *cxl = (struct canxl_frame *)skb->data; const struct canfd_frame *cfd = (struct canfd_frame *)skb->data; if (can_is_canxl_skb(skb)) return cxl->len; return cfd->len; } /* get needed data length inside CAN frame for all frame types (RTR aware) */ static inline unsigned int can_skb_get_data_len(struct sk_buff *skb) { unsigned int len = can_skb_get_len_val(skb); const struct can_frame *cf = (struct can_frame *)skb->data; /* RTR frames have an actual length of zero */ if (can_is_can_skb(skb) && cf->can_id & CAN_RTR_FLAG) return 0; return len; } #endif /* !_CAN_SKB_H */ |
| 788 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_UIDGID_H #define _LINUX_UIDGID_H /* * A set of types for the internal kernel types representing uids and gids. * * The types defined in this header allow distinguishing which uids and gids in * the kernel are values used by userspace and which uid and gid values are * the internal kernel values. With the addition of user namespaces the values * can be different. Using the type system makes it possible for the compiler * to detect when we overlook these differences. * */ #include <linux/types.h> #include <linux/highuid.h> struct user_namespace; extern struct user_namespace init_user_ns; typedef struct { uid_t val; } kuid_t; typedef struct { gid_t val; } kgid_t; #define KUIDT_INIT(value) (kuid_t){ value } #define KGIDT_INIT(value) (kgid_t){ value } #ifdef CONFIG_MULTIUSER static inline uid_t __kuid_val(kuid_t uid) { return uid.val; } static inline gid_t __kgid_val(kgid_t gid) { return gid.val; } #else static inline uid_t __kuid_val(kuid_t uid) { return 0; } static inline gid_t __kgid_val(kgid_t gid) { return 0; } #endif #define GLOBAL_ROOT_UID KUIDT_INIT(0) #define GLOBAL_ROOT_GID KGIDT_INIT(0) #define INVALID_UID KUIDT_INIT(-1) #define INVALID_GID KGIDT_INIT(-1) static inline bool uid_eq(kuid_t left, kuid_t right) { return __kuid_val(left) == __kuid_val(right); } static inline bool gid_eq(kgid_t left, kgid_t right) { return __kgid_val(left) == __kgid_val(right); } static inline bool uid_gt(kuid_t left, kuid_t right) { return __kuid_val(left) > __kuid_val(right); } static inline bool gid_gt(kgid_t left, kgid_t right) { return __kgid_val(left) > __kgid_val(right); } static inline bool uid_gte(kuid_t left, kuid_t right) { return __kuid_val(left) >= __kuid_val(right); } static inline bool gid_gte(kgid_t left, kgid_t right) { return __kgid_val(left) >= __kgid_val(right); } static inline bool uid_lt(kuid_t left, kuid_t right) { return __kuid_val(left) < __kuid_val(right); } static inline bool gid_lt(kgid_t left, kgid_t right) { return __kgid_val(left) < __kgid_val(right); } static inline bool uid_lte(kuid_t left, kuid_t right) { return __kuid_val(left) <= __kuid_val(right); } static inline bool gid_lte(kgid_t left, kgid_t right) { return __kgid_val(left) <= __kgid_val(right); } static inline bool uid_valid(kuid_t uid) { return __kuid_val(uid) != (uid_t) -1; } static inline bool gid_valid(kgid_t gid) { return __kgid_val(gid) != (gid_t) -1; } #ifdef CONFIG_USER_NS extern kuid_t make_kuid(struct user_namespace *from, uid_t uid); extern kgid_t make_kgid(struct user_namespace *from, gid_t gid); extern uid_t from_kuid(struct user_namespace *to, kuid_t uid); extern gid_t from_kgid(struct user_namespace *to, kgid_t gid); extern uid_t from_kuid_munged(struct user_namespace *to, kuid_t uid); extern gid_t from_kgid_munged(struct user_namespace *to, kgid_t gid); static inline bool kuid_has_mapping(struct user_namespace *ns, kuid_t uid) { return from_kuid(ns, uid) != (uid_t) -1; } static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid) { return from_kgid(ns, gid) != (gid_t) -1; } #else static inline kuid_t make_kuid(struct user_namespace *from, uid_t uid) { return KUIDT_INIT(uid); } static inline kgid_t make_kgid(struct user_namespace *from, gid_t gid) { return KGIDT_INIT(gid); } static inline uid_t from_kuid(struct user_namespace *to, kuid_t kuid) { return __kuid_val(kuid); } static inline gid_t from_kgid(struct user_namespace *to, kgid_t kgid) { return __kgid_val(kgid); } static inline uid_t from_kuid_munged(struct user_namespace *to, kuid_t kuid) { uid_t uid = from_kuid(to, kuid); if (uid == (uid_t)-1) uid = overflowuid; return uid; } static inline gid_t from_kgid_munged(struct user_namespace *to, kgid_t kgid) { gid_t gid = from_kgid(to, kgid); if (gid == (gid_t)-1) gid = overflowgid; return gid; } static inline bool kuid_has_mapping(struct user_namespace *ns, kuid_t uid) { return uid_valid(uid); } static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid) { return gid_valid(gid); } #endif /* CONFIG_USER_NS */ #endif /* _LINUX_UIDGID_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * xfrm6_input.c: based on net/ipv4/xfrm4_input.c * * Authors: * Mitsuru KANDA @USAGI * Kazunori MIYAZAWA @USAGI * Kunihiro Ishiguro <kunihiro@ipinfusion.com> * YOSHIFUJI Hideaki @USAGI * IPv6 support */ #include <linux/module.h> #include <linux/string.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <net/ipv6.h> #include <net/xfrm.h> int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi, struct ip6_tnl *t) { XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t; XFRM_SPI_SKB_CB(skb)->family = AF_INET6; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); return xfrm_input(skb, nexthdr, spi, 0); } EXPORT_SYMBOL(xfrm6_rcv_spi); static int xfrm6_transport_finish2(struct net *net, struct sock *sk, struct sk_buff *skb) { if (xfrm_trans_queue(skb, ip6_rcv_finish)) { kfree_skb(skb); return NET_RX_DROP; } return 0; } int xfrm6_transport_finish(struct sk_buff *skb, int async) { struct xfrm_offload *xo = xfrm_offload(skb); int nhlen = skb->data - skb_network_header(skb); skb_network_header(skb)[IP6CB(skb)->nhoff] = XFRM_MODE_SKB_CB(skb)->protocol; #ifndef CONFIG_NETFILTER if (!async) return 1; #endif __skb_push(skb, nhlen); ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_postpush_rcsum(skb, skb_network_header(skb), nhlen); if (xo && (xo->flags & XFRM_GRO)) { /* The full l2 header needs to be preserved so that re-injecting the packet at l2 * works correctly in the presence of vlan tags. */ skb_mac_header_rebuild_full(skb, xo->orig_mac_len); skb_reset_network_header(skb); skb_reset_transport_header(skb); return 0; } NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, dev_net(skb->dev), NULL, skb, skb->dev, NULL, xfrm6_transport_finish2); return 0; } /* If it's a keepalive packet, then just eat it. * If it's an encapsulated packet, then pass it to the * IPsec xfrm input. * Returns 0 if skb passed to xfrm or was dropped. * Returns >0 if skb should be passed to UDP. * Returns <0 if skb should be resubmitted (-ret is protocol) */ int xfrm6_udp_encap_rcv(struct sock *sk, struct sk_buff *skb) { struct udp_sock *up = udp_sk(sk); struct udphdr *uh; struct ipv6hdr *ip6h; int len; int ip6hlen = sizeof(struct ipv6hdr); __u8 *udpdata; __be32 *udpdata32; __u16 encap_type = up->encap_type; if (skb->protocol == htons(ETH_P_IP)) return xfrm4_udp_encap_rcv(sk, skb); /* if this is not encapsulated socket, then just return now */ if (!encap_type) return 1; /* If this is a paged skb, make sure we pull up * whatever data we need to look at. */ len = skb->len - sizeof(struct udphdr); if (!pskb_may_pull(skb, sizeof(struct udphdr) + min(len, 8))) return 1; /* Now we can get the pointers */ uh = udp_hdr(skb); udpdata = (__u8 *)uh + sizeof(struct udphdr); udpdata32 = (__be32 *)udpdata; switch (encap_type) { default: case UDP_ENCAP_ESPINUDP: /* Check if this is a keepalive packet. If so, eat it. */ if (len == 1 && udpdata[0] == 0xff) { goto drop; } else if (len > sizeof(struct ip_esp_hdr) && udpdata32[0] != 0) { /* ESP Packet without Non-ESP header */ len = sizeof(struct udphdr); } else /* Must be an IKE packet.. pass it through */ return 1; break; case UDP_ENCAP_ESPINUDP_NON_IKE: /* Check if this is a keepalive packet. If so, eat it. */ if (len == 1 && udpdata[0] == 0xff) { goto drop; } else if (len > 2 * sizeof(u32) + sizeof(struct ip_esp_hdr) && udpdata32[0] == 0 && udpdata32[1] == 0) { /* ESP Packet with Non-IKE marker */ len = sizeof(struct udphdr) + 2 * sizeof(u32); } else /* Must be an IKE packet.. pass it through */ return 1; break; } /* At this point we are sure that this is an ESPinUDP packet, * so we need to remove 'len' bytes from the packet (the UDP * header and optional ESP marker bytes) and then modify the * protocol to ESP, and then call into the transform receiver. */ if (skb_unclone(skb, GFP_ATOMIC)) goto drop; /* Now we can update and verify the packet length... */ ip6h = ipv6_hdr(skb); ip6h->payload_len = htons(ntohs(ip6h->payload_len) - len); if (skb->len < ip6hlen + len) { /* packet is too small!?! */ goto drop; } /* pull the data buffer up to the ESP header and set the * transport header to point to ESP. Keep UDP on the stack * for later. */ __skb_pull(skb, len); skb_reset_transport_header(skb); /* process ESP */ return xfrm6_rcv_encap(skb, IPPROTO_ESP, 0, encap_type); drop: kfree_skb(skb); return 0; } int xfrm6_rcv_tnl(struct sk_buff *skb, struct ip6_tnl *t) { return xfrm6_rcv_spi(skb, skb_network_header(skb)[IP6CB(skb)->nhoff], 0, t); } EXPORT_SYMBOL(xfrm6_rcv_tnl); int xfrm6_rcv(struct sk_buff *skb) { return xfrm6_rcv_tnl(skb, NULL); } EXPORT_SYMBOL(xfrm6_rcv); int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, xfrm_address_t *saddr, u8 proto) { struct net *net = dev_net(skb->dev); struct xfrm_state *x = NULL; struct sec_path *sp; int i = 0; sp = secpath_set(skb); if (!sp) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINERROR); goto drop; } if (1 + sp->len == XFRM_MAX_DEPTH) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); goto drop; } for (i = 0; i < 3; i++) { xfrm_address_t *dst, *src; switch (i) { case 0: dst = daddr; src = saddr; break; case 1: /* lookup state with wild-card source address */ dst = daddr; src = (xfrm_address_t *)&in6addr_any; break; default: /* lookup state with wild-card addresses */ dst = (xfrm_address_t *)&in6addr_any; src = (xfrm_address_t *)&in6addr_any; break; } x = xfrm_state_lookup_byaddr(net, skb->mark, dst, src, proto, AF_INET6); if (!x) continue; spin_lock(&x->lock); if ((!i || (x->props.flags & XFRM_STATE_WILDRECV)) && likely(x->km.state == XFRM_STATE_VALID) && !xfrm_state_check_expire(x)) { spin_unlock(&x->lock); if (x->type->input(x, skb) > 0) { /* found a valid state */ break; } } else spin_unlock(&x->lock); xfrm_state_put(x); x = NULL; } if (!x) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES); xfrm_audit_state_notfound_simple(skb, AF_INET6); goto drop; } sp->xvec[sp->len++] = x; spin_lock(&x->lock); x->curlft.bytes += skb->len; x->curlft.packets++; spin_unlock(&x->lock); return 1; drop: return -1; } EXPORT_SYMBOL(xfrm6_input_addr); |
| 5031 1581 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM maple_tree #if !defined(_TRACE_MM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_MM_H #include <linux/tracepoint.h> struct ma_state; TRACE_EVENT(ma_op, TP_PROTO(const char *fn, struct ma_state *mas), TP_ARGS(fn, mas), TP_STRUCT__entry( __field(const char *, fn) __field(unsigned long, min) __field(unsigned long, max) __field(unsigned long, index) __field(unsigned long, last) __field(void *, node) ), TP_fast_assign( __entry->fn = fn; __entry->min = mas->min; __entry->max = mas->max; __entry->index = mas->index; __entry->last = mas->last; __entry->node = mas->node; ), TP_printk("%s\tNode: %p (%lu %lu) range: %lu-%lu", __entry->fn, (void *) __entry->node, (unsigned long) __entry->min, (unsigned long) __entry->max, (unsigned long) __entry->index, (unsigned long) __entry->last ) ) TRACE_EVENT(ma_read, TP_PROTO(const char *fn, struct ma_state *mas), TP_ARGS(fn, mas), TP_STRUCT__entry( __field(const char *, fn) __field(unsigned long, min) __field(unsigned long, max) __field(unsigned long, index) __field(unsigned long, last) __field(void *, node) ), TP_fast_assign( __entry->fn = fn; __entry->min = mas->min; __entry->max = mas->max; __entry->index = mas->index; __entry->last = mas->last; __entry->node = mas->node; ), TP_printk("%s\tNode: %p (%lu %lu) range: %lu-%lu", __entry->fn, (void *) __entry->node, (unsigned long) __entry->min, (unsigned long) __entry->max, (unsigned long) __entry->index, (unsigned long) __entry->last ) ) TRACE_EVENT(ma_write, TP_PROTO(const char *fn, struct ma_state *mas, unsigned long piv, void *val), TP_ARGS(fn, mas, piv, val), TP_STRUCT__entry( __field(const char *, fn) __field(unsigned long, min) __field(unsigned long, max) __field(unsigned long, index) __field(unsigned long, last) __field(unsigned long, piv) __field(void *, val) __field(void *, node) ), TP_fast_assign( __entry->fn = fn; __entry->min = mas->min; __entry->max = mas->max; __entry->index = mas->index; __entry->last = mas->last; __entry->piv = piv; __entry->val = val; __entry->node = mas->node; ), TP_printk("%s\tNode %p (%lu %lu) range:%lu-%lu piv (%lu) val %p", __entry->fn, (void *) __entry->node, (unsigned long) __entry->min, (unsigned long) __entry->max, (unsigned long) __entry->index, (unsigned long) __entry->last, (unsigned long) __entry->piv, (void *) __entry->val ) ) #endif /* _TRACE_MM_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 481 39 523 483 39 520 522 163 163 163 163 163 163 163 77 165 3 163 162 162 163 162 163 163 163 163 163 163 163 163 163 163 163 163 163 163 162 163 163 163 163 162 163 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/attr.c * * Copyright (C) 1991, 1992 Linus Torvalds * changes by Thomas Schoebel-Theuer */ #include <linux/export.h> #include <linux/time.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/sched/signal.h> #include <linux/capability.h> #include <linux/fsnotify.h> #include <linux/fcntl.h> #include <linux/security.h> #include <linux/evm.h> #include <linux/ima.h> #include "internal.h" /** * setattr_should_drop_sgid - determine whether the setgid bit needs to be * removed * @mnt_userns: user namespace of the mount @inode was found from * @inode: inode to check * * This function determines whether the setgid bit needs to be removed. * We retain backwards compatibility and require setgid bit to be removed * unconditionally if S_IXGRP is set. Otherwise we have the exact same * requirements as setattr_prepare() and setattr_copy(). * * Return: ATTR_KILL_SGID if setgid bit needs to be removed, 0 otherwise. */ int setattr_should_drop_sgid(struct user_namespace *mnt_userns, const struct inode *inode) { umode_t mode = inode->i_mode; if (!(mode & S_ISGID)) return 0; if (mode & S_IXGRP) return ATTR_KILL_SGID; if (!in_group_or_capable(mnt_userns, inode, i_gid_into_vfsgid(mnt_userns, inode))) return ATTR_KILL_SGID; return 0; } EXPORT_SYMBOL(setattr_should_drop_sgid); /** * setattr_should_drop_suidgid - determine whether the set{g,u}id bit needs to * be dropped * @mnt_userns: user namespace of the mount @inode was found from * @inode: inode to check * * This function determines whether the set{g,u}id bits need to be removed. * If the setuid bit needs to be removed ATTR_KILL_SUID is returned. If the * setgid bit needs to be removed ATTR_KILL_SGID is returned. If both * set{g,u}id bits need to be removed the corresponding mask of both flags is * returned. * * Return: A mask of ATTR_KILL_S{G,U}ID indicating which - if any - setid bits * to remove, 0 otherwise. */ int setattr_should_drop_suidgid(struct user_namespace *mnt_userns, struct inode *inode) { umode_t mode = inode->i_mode; int kill = 0; /* suid always must be killed */ if (unlikely(mode & S_ISUID)) kill = ATTR_KILL_SUID; kill |= setattr_should_drop_sgid(mnt_userns, inode); if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode))) return kill; return 0; } EXPORT_SYMBOL(setattr_should_drop_suidgid); /** * chown_ok - verify permissions to chown inode * @mnt_userns: user namespace of the mount @inode was found from * @inode: inode to check permissions on * @ia_vfsuid: uid to chown @inode to * * 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 bool chown_ok(struct user_namespace *mnt_userns, const struct inode *inode, vfsuid_t ia_vfsuid) { vfsuid_t vfsuid = i_uid_into_vfsuid(mnt_userns, inode); if (vfsuid_eq_kuid(vfsuid, current_fsuid()) && vfsuid_eq(ia_vfsuid, vfsuid)) return true; if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN)) return true; if (!vfsuid_valid(vfsuid) && ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN)) return true; return false; } /** * chgrp_ok - verify permissions to chgrp inode * @mnt_userns: user namespace of the mount @inode was found from * @inode: inode to check permissions on * @ia_vfsgid: gid to chown @inode to * * 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 bool chgrp_ok(struct user_namespace *mnt_userns, const struct inode *inode, vfsgid_t ia_vfsgid) { vfsgid_t vfsgid = i_gid_into_vfsgid(mnt_userns, inode); vfsuid_t vfsuid = i_uid_into_vfsuid(mnt_userns, inode); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) { if (vfsgid_eq(ia_vfsgid, vfsgid)) return true; if (vfsgid_in_group_p(ia_vfsgid)) return true; } if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN)) return true; if (!vfsgid_valid(vfsgid) && ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN)) return true; return false; } /** * setattr_prepare - check if attribute changes to a dentry are allowed * @mnt_userns: user namespace of the mount the inode was found from * @dentry: dentry to check * @attr: attributes to change * * Check if we are allowed to change the attributes contained in @attr * in the given dentry. This includes the normal unix access permission * checks, as well as checks for rlimits and others. The function also clears * SGID bit from mode if user is not allowed to set it. Also file capabilities * and IMA extended attributes are cleared if ATTR_KILL_PRIV is set. * * 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. * * Should be called as the first thing in ->setattr implementations, * possibly after taking additional locks. */ int setattr_prepare(struct user_namespace *mnt_userns, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); unsigned int ia_valid = attr->ia_valid; /* * First check size constraints. These can't be overriden using * ATTR_FORCE. */ if (ia_valid & ATTR_SIZE) { int error = inode_newsize_ok(inode, attr->ia_size); if (error) return error; } /* If force is set do it anyway. */ if (ia_valid & ATTR_FORCE) goto kill_priv; /* Make sure a caller can chown. */ if ((ia_valid & ATTR_UID) && !chown_ok(mnt_userns, inode, attr->ia_vfsuid)) return -EPERM; /* Make sure caller can chgrp. */ if ((ia_valid & ATTR_GID) && !chgrp_ok(mnt_userns, inode, attr->ia_vfsgid)) return -EPERM; /* Make sure a caller can chmod. */ if (ia_valid & ATTR_MODE) { vfsgid_t vfsgid; if (!inode_owner_or_capable(mnt_userns, inode)) return -EPERM; if (ia_valid & ATTR_GID) vfsgid = attr->ia_vfsgid; else vfsgid = i_gid_into_vfsgid(mnt_userns, inode); /* Also check the setgid bit! */ if (!in_group_or_capable(mnt_userns, inode, vfsgid)) attr->ia_mode &= ~S_ISGID; } /* Check for setting the inode time. */ if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)) { if (!inode_owner_or_capable(mnt_userns, inode)) return -EPERM; } kill_priv: /* User has permission for the change */ if (ia_valid & ATTR_KILL_PRIV) { int error; error = security_inode_killpriv(mnt_userns, dentry); if (error) return error; } return 0; } EXPORT_SYMBOL(setattr_prepare); /** * inode_newsize_ok - may this inode be truncated to a given size * @inode: the inode to be truncated * @offset: the new size to assign to the inode * * inode_newsize_ok must be called with i_mutex held. * * inode_newsize_ok will check filesystem limits and ulimits to check that the * new inode size is within limits. inode_newsize_ok will also send SIGXFSZ * when necessary. Caller must not proceed with inode size change if failure is * returned. @inode must be a file (not directory), with appropriate * permissions to allow truncate (inode_newsize_ok does NOT check these * conditions). * * Return: 0 on success, -ve errno on failure */ int inode_newsize_ok(const struct inode *inode, loff_t offset) { if (offset < 0) return -EINVAL; if (inode->i_size < offset) { unsigned long limit; limit = rlimit(RLIMIT_FSIZE); if (limit != RLIM_INFINITY && offset > limit) goto out_sig; if (offset > inode->i_sb->s_maxbytes) goto out_big; } else { /* * truncation of in-use swapfiles is disallowed - it would * cause subsequent swapout to scribble on the now-freed * blocks. */ if (IS_SWAPFILE(inode)) return -ETXTBSY; } return 0; out_sig: send_sig(SIGXFSZ, current, 0); out_big: return -EFBIG; } EXPORT_SYMBOL(inode_newsize_ok); /** * setattr_copy - copy simple metadata updates into the generic inode * @mnt_userns: user namespace of the mount the inode was found from * @inode: the inode to be updated * @attr: the new attributes * * setattr_copy must be called with i_mutex held. * * setattr_copy updates the inode's metadata with that specified * in attr on idmapped mounts. Necessary permission checks to determine * whether or not the S_ISGID property needs to be removed are performed with * the correct idmapped mount permission helpers. * Noticeably missing is inode size update, which is more complex * as it requires pagecache updates. * * 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. * * The inode is not marked as dirty after this operation. The rationale is * that for "simple" filesystems, the struct inode is the inode storage. * The caller is free to mark the inode dirty afterwards if needed. */ void setattr_copy(struct user_namespace *mnt_userns, struct inode *inode, const struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; i_uid_update(mnt_userns, attr, inode); i_gid_update(mnt_userns, attr, inode); if (ia_valid & ATTR_ATIME) inode->i_atime = attr->ia_atime; if (ia_valid & ATTR_MTIME) inode->i_mtime = attr->ia_mtime; if (ia_valid & ATTR_CTIME) inode->i_ctime = attr->ia_ctime; if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; if (!in_group_or_capable(mnt_userns, inode, i_gid_into_vfsgid(mnt_userns, inode))) mode &= ~S_ISGID; inode->i_mode = mode; } } EXPORT_SYMBOL(setattr_copy); int may_setattr(struct user_namespace *mnt_userns, struct inode *inode, unsigned int ia_valid) { int error; if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) { if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) return -EPERM; } /* * If utimes(2) and friends are called with times == NULL (or both * times are UTIME_NOW), then we need to check for write permission */ if (ia_valid & ATTR_TOUCH) { if (IS_IMMUTABLE(inode)) return -EPERM; if (!inode_owner_or_capable(mnt_userns, inode)) { error = inode_permission(mnt_userns, inode, MAY_WRITE); if (error) return error; } } return 0; } EXPORT_SYMBOL(may_setattr); /** * notify_change - modify attributes of a filesytem object * @mnt_userns: user namespace of the mount the inode was found from * @dentry: object affected * @attr: new attributes * @delegated_inode: returns inode, if the inode is delegated * * The caller must hold the i_mutex on the affected object. * * If notify_change discovers a delegation in need of breaking, * it will return -EWOULDBLOCK and return a reference to the inode in * delegated_inode. The caller should then break the delegation and * retry. Because breaking a delegation may take a long time, the * caller should drop the i_mutex before doing so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. Also, passing NULL is fine for callers holding * the file open for write, as there can be no conflicting delegation in * that case. * * 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 notify_change(struct user_namespace *mnt_userns, struct dentry *dentry, struct iattr *attr, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; umode_t mode = inode->i_mode; int error; struct timespec64 now; unsigned int ia_valid = attr->ia_valid; WARN_ON_ONCE(!inode_is_locked(inode)); error = may_setattr(mnt_userns, inode, ia_valid); if (error) return error; if ((ia_valid & ATTR_MODE)) { /* * Don't allow changing the mode of symlinks: * * (1) The vfs doesn't take the mode of symlinks into account * during permission checking. * (2) This has never worked correctly. Most major filesystems * did return EOPNOTSUPP due to interactions with POSIX ACLs * but did still updated the mode of the symlink. * This inconsistency led system call wrapper providers such * as libc to block changing the mode of symlinks with * EOPNOTSUPP already. * (3) To even do this in the first place one would have to use * specific file descriptors and quite some effort. */ if (S_ISLNK(inode->i_mode)) return -EOPNOTSUPP; /* Flag setting protected by i_mutex */ if (is_sxid(attr->ia_mode)) inode->i_flags &= ~S_NOSEC; } now = current_time(inode); attr->ia_ctime = now; if (!(ia_valid & ATTR_ATIME_SET)) attr->ia_atime = now; else attr->ia_atime = timestamp_truncate(attr->ia_atime, inode); if (!(ia_valid & ATTR_MTIME_SET)) attr->ia_mtime = now; else attr->ia_mtime = timestamp_truncate(attr->ia_mtime, inode); if (ia_valid & ATTR_KILL_PRIV) { error = security_inode_need_killpriv(dentry); if (error < 0) return error; if (error == 0) ia_valid = attr->ia_valid &= ~ATTR_KILL_PRIV; } /* * We now pass ATTR_KILL_S*ID to the lower level setattr function so * that the function has the ability to reinterpret a mode change * that's due to these bits. This adds an implicit restriction that * no function will ever call notify_change with both ATTR_MODE and * ATTR_KILL_S*ID set. */ if ((ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) && (ia_valid & ATTR_MODE)) BUG(); if (ia_valid & ATTR_KILL_SUID) { if (mode & S_ISUID) { ia_valid = attr->ia_valid |= ATTR_MODE; attr->ia_mode = (inode->i_mode & ~S_ISUID); } } if (ia_valid & ATTR_KILL_SGID) { if (mode & S_ISGID) { if (!(ia_valid & ATTR_MODE)) { ia_valid = attr->ia_valid |= ATTR_MODE; attr->ia_mode = inode->i_mode; } attr->ia_mode &= ~S_ISGID; } } if (!(attr->ia_valid & ~(ATTR_KILL_SUID | ATTR_KILL_SGID))) return 0; /* * Verify that uid/gid changes are valid in the target * namespace of the superblock. */ if (ia_valid & ATTR_UID && !vfsuid_has_fsmapping(mnt_userns, inode->i_sb->s_user_ns, attr->ia_vfsuid)) return -EOVERFLOW; if (ia_valid & ATTR_GID && !vfsgid_has_fsmapping(mnt_userns, inode->i_sb->s_user_ns, attr->ia_vfsgid)) return -EOVERFLOW; /* Don't allow modifications of files with invalid uids or * gids unless those uids & gids are being made valid. */ if (!(ia_valid & ATTR_UID) && !vfsuid_valid(i_uid_into_vfsuid(mnt_userns, inode))) return -EOVERFLOW; if (!(ia_valid & ATTR_GID) && !vfsgid_valid(i_gid_into_vfsgid(mnt_userns, inode))) return -EOVERFLOW; error = security_inode_setattr(mnt_userns, dentry, attr); if (error) return error; error = try_break_deleg(inode, delegated_inode); if (error) return error; if (inode->i_op->setattr) error = inode->i_op->setattr(mnt_userns, dentry, attr); else error = simple_setattr(mnt_userns, dentry, attr); if (!error) { fsnotify_change(dentry, ia_valid); ima_inode_post_setattr(mnt_userns, dentry); evm_inode_post_setattr(dentry, ia_valid); } return error; } EXPORT_SYMBOL(notify_change); |
| 2106 2106 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/pm_qos.h> static inline void device_pm_init_common(struct device *dev) { if (!dev->power.early_init) { spin_lock_init(&dev->power.lock); dev->power.qos = NULL; dev->power.early_init = true; } } #ifdef CONFIG_PM static inline void pm_runtime_early_init(struct device *dev) { dev->power.disable_depth = 1; device_pm_init_common(dev); } extern void pm_runtime_init(struct device *dev); extern void pm_runtime_reinit(struct device *dev); extern void pm_runtime_remove(struct device *dev); extern u64 pm_runtime_active_time(struct device *dev); #define WAKE_IRQ_DEDICATED_ALLOCATED BIT(0) #define WAKE_IRQ_DEDICATED_MANAGED BIT(1) #define WAKE_IRQ_DEDICATED_REVERSE BIT(2) #define WAKE_IRQ_DEDICATED_MASK (WAKE_IRQ_DEDICATED_ALLOCATED | \ WAKE_IRQ_DEDICATED_MANAGED | \ WAKE_IRQ_DEDICATED_REVERSE) #define WAKE_IRQ_DEDICATED_ENABLED BIT(3) struct wake_irq { struct device *dev; unsigned int status; int irq; const char *name; }; extern void dev_pm_arm_wake_irq(struct wake_irq *wirq); extern void dev_pm_disarm_wake_irq(struct wake_irq *wirq); extern void dev_pm_enable_wake_irq_check(struct device *dev, bool can_change_status); extern void dev_pm_disable_wake_irq_check(struct device *dev, bool cond_disable); extern void dev_pm_enable_wake_irq_complete(struct device *dev); #ifdef CONFIG_PM_SLEEP extern void device_wakeup_attach_irq(struct device *dev, struct wake_irq *wakeirq); extern void device_wakeup_detach_irq(struct device *dev); extern void device_wakeup_arm_wake_irqs(void); extern void device_wakeup_disarm_wake_irqs(void); #else static inline void device_wakeup_attach_irq(struct device *dev, struct wake_irq *wakeirq) {} static inline void device_wakeup_detach_irq(struct device *dev) { } #endif /* CONFIG_PM_SLEEP */ /* * sysfs.c */ extern int dpm_sysfs_add(struct device *dev); extern void dpm_sysfs_remove(struct device *dev); extern void rpm_sysfs_remove(struct device *dev); extern int wakeup_sysfs_add(struct device *dev); extern void wakeup_sysfs_remove(struct device *dev); extern int pm_qos_sysfs_add_resume_latency(struct device *dev); extern void pm_qos_sysfs_remove_resume_latency(struct device *dev); extern int pm_qos_sysfs_add_flags(struct device *dev); extern void pm_qos_sysfs_remove_flags(struct device *dev); extern int pm_qos_sysfs_add_latency_tolerance(struct device *dev); extern void pm_qos_sysfs_remove_latency_tolerance(struct device *dev); extern int dpm_sysfs_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid); #else /* CONFIG_PM */ static inline void pm_runtime_early_init(struct device *dev) { device_pm_init_common(dev); } static inline void pm_runtime_init(struct device *dev) {} static inline void pm_runtime_reinit(struct device *dev) {} static inline void pm_runtime_remove(struct device *dev) {} static inline int dpm_sysfs_add(struct device *dev) { return 0; } static inline void dpm_sysfs_remove(struct device *dev) {} static inline int dpm_sysfs_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) { return 0; } #endif #ifdef CONFIG_PM_SLEEP /* kernel/power/main.c */ extern int pm_async_enabled; /* drivers/base/power/main.c */ extern struct list_head dpm_list; /* The active device list */ static inline struct device *to_device(struct list_head *entry) { return container_of(entry, struct device, power.entry); } extern void device_pm_sleep_init(struct device *dev); extern void device_pm_add(struct device *); extern void device_pm_remove(struct device *); extern void device_pm_move_before(struct device *, struct device *); extern void device_pm_move_after(struct device *, struct device *); extern void device_pm_move_last(struct device *); extern void device_pm_check_callbacks(struct device *dev); static inline bool device_pm_initialized(struct device *dev) { return dev->power.in_dpm_list; } /* drivers/base/power/wakeup_stats.c */ extern int wakeup_source_sysfs_add(struct device *parent, struct wakeup_source *ws); extern void wakeup_source_sysfs_remove(struct wakeup_source *ws); extern int pm_wakeup_source_sysfs_add(struct device *parent); #else /* !CONFIG_PM_SLEEP */ static inline void device_pm_sleep_init(struct device *dev) {} static inline void device_pm_add(struct device *dev) {} static inline void device_pm_remove(struct device *dev) { pm_runtime_remove(dev); } static inline void device_pm_move_before(struct device *deva, struct device *devb) {} static inline void device_pm_move_after(struct device *deva, struct device *devb) {} static inline void device_pm_move_last(struct device *dev) {} static inline void device_pm_check_callbacks(struct device *dev) {} static inline bool device_pm_initialized(struct device *dev) { return device_is_registered(dev); } static inline int pm_wakeup_source_sysfs_add(struct device *parent) { return 0; } #endif /* !CONFIG_PM_SLEEP */ static inline void device_pm_init(struct device *dev) { device_pm_init_common(dev); device_pm_sleep_init(dev); pm_runtime_init(dev); } |
| 2257 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_UNWIND_H #define _ASM_X86_UNWIND_H #include <linux/sched.h> #include <linux/ftrace.h> #include <linux/rethook.h> #include <asm/ptrace.h> #include <asm/stacktrace.h> #define IRET_FRAME_OFFSET (offsetof(struct pt_regs, ip)) #define IRET_FRAME_SIZE (sizeof(struct pt_regs) - IRET_FRAME_OFFSET) struct unwind_state { struct stack_info stack_info; unsigned long stack_mask; struct task_struct *task; int graph_idx; #if defined(CONFIG_RETHOOK) struct llist_node *kr_cur; #endif bool error; #if defined(CONFIG_UNWINDER_ORC) bool signal, full_regs; unsigned long sp, bp, ip; struct pt_regs *regs, *prev_regs; #elif defined(CONFIG_UNWINDER_FRAME_POINTER) bool got_irq; unsigned long *bp, *orig_sp, ip; /* * If non-NULL: The current frame is incomplete and doesn't contain a * valid BP. When looking for the next frame, use this instead of the * non-existent saved BP. */ unsigned long *next_bp; struct pt_regs *regs; #else unsigned long *sp; #endif }; void __unwind_start(struct unwind_state *state, struct task_struct *task, struct pt_regs *regs, unsigned long *first_frame); bool unwind_next_frame(struct unwind_state *state); unsigned long unwind_get_return_address(struct unwind_state *state); unsigned long *unwind_get_return_address_ptr(struct unwind_state *state); static inline bool unwind_done(struct unwind_state *state) { return state->stack_info.type == STACK_TYPE_UNKNOWN; } static inline bool unwind_error(struct unwind_state *state) { return state->error; } static inline void unwind_start(struct unwind_state *state, struct task_struct *task, struct pt_regs *regs, unsigned long *first_frame) { first_frame = first_frame ? : get_stack_pointer(task, regs); __unwind_start(state, task, regs, first_frame); } #if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER) /* * If 'partial' returns true, only the iret frame registers are valid. */ static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state, bool *partial) { if (unwind_done(state)) return NULL; if (partial) { #ifdef CONFIG_UNWINDER_ORC *partial = !state->full_regs; #else *partial = false; #endif } return state->regs; } #else static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state, bool *partial) { return NULL; } #endif #ifdef CONFIG_UNWINDER_ORC void unwind_init(void); void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, void *orc, size_t orc_size); #else static inline void unwind_init(void) {} static inline void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, void *orc, size_t orc_size) {} #endif static inline unsigned long unwind_recover_rethook(struct unwind_state *state, unsigned long addr, unsigned long *addr_p) { #ifdef CONFIG_RETHOOK if (is_rethook_trampoline(addr)) return rethook_find_ret_addr(state->task, (unsigned long)addr_p, &state->kr_cur); #endif return addr; } /* Recover the return address modified by rethook and ftrace_graph. */ static inline unsigned long unwind_recover_ret_addr(struct unwind_state *state, unsigned long addr, unsigned long *addr_p) { unsigned long ret; ret = ftrace_graph_ret_addr(state->task, &state->graph_idx, addr, addr_p); return unwind_recover_rethook(state, ret, addr_p); } /* * This disables KASAN checking when reading a value from another task's stack, * since the other task could be running on another CPU and could have poisoned * the stack in the meantime. */ #define READ_ONCE_TASK_STACK(task, x) \ ({ \ unsigned long val; \ if (task == current) \ val = READ_ONCE(x); \ else \ val = READ_ONCE_NOCHECK(x); \ val; \ }) static inline bool task_on_another_cpu(struct task_struct *task) { #ifdef CONFIG_SMP return task != current && task->on_cpu; #else return false; #endif } #endif /* _ASM_X86_UNWIND_H */ |
| 498 498 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 | // SPDX-License-Identifier: GPL-2.0-only /* * async.c: Asynchronous function calls for boot performance * * (C) Copyright 2009 Intel Corporation * Author: Arjan van de Ven <arjan@linux.intel.com> */ /* Goals and Theory of Operation The primary goal of this feature is to reduce the kernel boot time, by doing various independent hardware delays and discovery operations decoupled and not strictly serialized. More specifically, the asynchronous function call concept allows certain operations (primarily during system boot) to happen asynchronously, out of order, while these operations still have their externally visible parts happen sequentially and in-order. (not unlike how out-of-order CPUs retire their instructions in order) Key to the asynchronous function call implementation is the concept of a "sequence cookie" (which, although it has an abstracted type, can be thought of as a monotonically incrementing number). The async core will assign each scheduled event such a sequence cookie and pass this to the called functions. The asynchronously called function should before doing a globally visible operation, such as registering device numbers, call the async_synchronize_cookie() function and pass in its own cookie. The async_synchronize_cookie() function will make sure that all asynchronous operations that were scheduled prior to the operation corresponding with the cookie have completed. Subsystem/driver initialization code that scheduled asynchronous probe functions, but which shares global resources with other drivers/subsystems that do not use the asynchronous call feature, need to do a full synchronization with the async_synchronize_full() function, before returning from their init function. This is to maintain strict ordering between the asynchronous and synchronous parts of the kernel. */ #include <linux/async.h> #include <linux/atomic.h> #include <linux/ktime.h> #include <linux/export.h> #include <linux/wait.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/workqueue.h> #include "workqueue_internal.h" static async_cookie_t next_cookie = 1; #define MAX_WORK 32768 #define ASYNC_COOKIE_MAX ULLONG_MAX /* infinity cookie */ static LIST_HEAD(async_global_pending); /* pending from all registered doms */ static ASYNC_DOMAIN(async_dfl_domain); static DEFINE_SPINLOCK(async_lock); struct async_entry { struct list_head domain_list; struct list_head global_list; struct work_struct work; async_cookie_t cookie; async_func_t func; void *data; struct async_domain *domain; }; static DECLARE_WAIT_QUEUE_HEAD(async_done); static atomic_t entry_count; static long long microseconds_since(ktime_t start) { ktime_t now = ktime_get(); return ktime_to_ns(ktime_sub(now, start)) >> 10; } static async_cookie_t lowest_in_progress(struct async_domain *domain) { struct async_entry *first = NULL; async_cookie_t ret = ASYNC_COOKIE_MAX; unsigned long flags; spin_lock_irqsave(&async_lock, flags); if (domain) { if (!list_empty(&domain->pending)) first = list_first_entry(&domain->pending, struct async_entry, domain_list); } else { if (!list_empty(&async_global_pending)) first = list_first_entry(&async_global_pending, struct async_entry, global_list); } if (first) ret = first->cookie; spin_unlock_irqrestore(&async_lock, flags); return ret; } /* * pick the first pending entry and run it */ static void async_run_entry_fn(struct work_struct *work) { struct async_entry *entry = container_of(work, struct async_entry, work); unsigned long flags; ktime_t calltime; /* 1) run (and print duration) */ pr_debug("calling %lli_%pS @ %i\n", (long long)entry->cookie, entry->func, task_pid_nr(current)); calltime = ktime_get(); entry->func(entry->data, entry->cookie); pr_debug("initcall %lli_%pS returned after %lld usecs\n", (long long)entry->cookie, entry->func, microseconds_since(calltime)); /* 2) remove self from the pending queues */ spin_lock_irqsave(&async_lock, flags); list_del_init(&entry->domain_list); list_del_init(&entry->global_list); /* 3) free the entry */ kfree(entry); atomic_dec(&entry_count); spin_unlock_irqrestore(&async_lock, flags); /* 4) wake up any waiters */ wake_up(&async_done); } static async_cookie_t __async_schedule_node_domain(async_func_t func, void *data, int node, struct async_domain *domain, struct async_entry *entry) { async_cookie_t newcookie; unsigned long flags; INIT_LIST_HEAD(&entry->domain_list); INIT_LIST_HEAD(&entry->global_list); INIT_WORK(&entry->work, async_run_entry_fn); entry->func = func; entry->data = data; entry->domain = domain; spin_lock_irqsave(&async_lock, flags); /* allocate cookie and queue */ newcookie = entry->cookie = next_cookie++; list_add_tail(&entry->domain_list, &domain->pending); if (domain->registered) list_add_tail(&entry->global_list, &async_global_pending); atomic_inc(&entry_count); spin_unlock_irqrestore(&async_lock, flags); /* schedule for execution */ queue_work_node(node, system_unbound_wq, &entry->work); return newcookie; } /** * async_schedule_node_domain - NUMA specific version of async_schedule_domain * @func: function to execute asynchronously * @data: data pointer to pass to the function * @node: NUMA node that we want to schedule this on or close to * @domain: the domain * * Returns an async_cookie_t that may be used for checkpointing later. * @domain may be used in the async_synchronize_*_domain() functions to * wait within a certain synchronization domain rather than globally. * * Note: This function may be called from atomic or non-atomic contexts. * * The node requested will be honored on a best effort basis. If the node * has no CPUs associated with it then the work is distributed among all * available CPUs. */ async_cookie_t async_schedule_node_domain(async_func_t func, void *data, int node, struct async_domain *domain) { struct async_entry *entry; unsigned long flags; async_cookie_t newcookie; /* allow irq-off callers */ entry = kzalloc(sizeof(struct async_entry), GFP_ATOMIC); /* * If we're out of memory or if there's too much work * pending already, we execute synchronously. */ if (!entry || atomic_read(&entry_count) > MAX_WORK) { kfree(entry); spin_lock_irqsave(&async_lock, flags); newcookie = next_cookie++; spin_unlock_irqrestore(&async_lock, flags); /* low on memory.. run synchronously */ func(data, newcookie); return newcookie; } return __async_schedule_node_domain(func, data, node, domain, entry); } EXPORT_SYMBOL_GPL(async_schedule_node_domain); /** * async_schedule_node |